WO2012046907A1 - Apparatus for processing an image in a manner which protects privacy, image security system using same, and method therefor - Google Patents
Apparatus for processing an image in a manner which protects privacy, image security system using same, and method therefor Download PDFInfo
- Publication number
- WO2012046907A1 WO2012046907A1 PCT/KR2010/007262 KR2010007262W WO2012046907A1 WO 2012046907 A1 WO2012046907 A1 WO 2012046907A1 KR 2010007262 W KR2010007262 W KR 2010007262W WO 2012046907 A1 WO2012046907 A1 WO 2012046907A1
- Authority
- WO
- WIPO (PCT)
- Prior art keywords
- image
- protection
- video
- privacy
- protected
- Prior art date
Links
- 238000000034 method Methods 0.000 title claims abstract description 107
- 238000012545 processing Methods 0.000 title claims abstract description 59
- 238000012544 monitoring process Methods 0.000 claims abstract description 10
- 230000005540 biological transmission Effects 0.000 claims description 22
- 238000001514 detection method Methods 0.000 claims description 20
- 238000005516 engineering process Methods 0.000 claims description 12
- 230000000739 chaotic effect Effects 0.000 claims description 9
- 230000000873 masking effect Effects 0.000 claims description 4
- 230000004064 dysfunction Effects 0.000 abstract 1
- 230000001815 facial effect Effects 0.000 abstract 1
- 230000008569 process Effects 0.000 description 22
- 238000007726 management method Methods 0.000 description 20
- 230000009545 invasion Effects 0.000 description 8
- 238000010586 diagram Methods 0.000 description 6
- 238000004891 communication Methods 0.000 description 5
- 230000008901 benefit Effects 0.000 description 4
- 238000010511 deprotection reaction Methods 0.000 description 3
- 230000002265 prevention Effects 0.000 description 3
- 230000010076 replication Effects 0.000 description 3
- 241000700605 Viruses Species 0.000 description 2
- 230000006866 deterioration Effects 0.000 description 2
- 238000011161 development Methods 0.000 description 2
- 230000000694 effects Effects 0.000 description 2
- 238000000605 extraction Methods 0.000 description 2
- 230000003213 activating effect Effects 0.000 description 1
- 238000004590 computer program Methods 0.000 description 1
- 238000009795 derivation Methods 0.000 description 1
- 238000009434 installation Methods 0.000 description 1
- 230000003993 interaction Effects 0.000 description 1
- 238000012986 modification Methods 0.000 description 1
- 230000004048 modification Effects 0.000 description 1
- 238000007781 pre-processing Methods 0.000 description 1
- 238000003672 processing method Methods 0.000 description 1
- 238000003908 quality control method Methods 0.000 description 1
- 238000011160 research Methods 0.000 description 1
- 238000000926 separation method Methods 0.000 description 1
- 238000006467 substitution reaction Methods 0.000 description 1
- 238000012795 verification Methods 0.000 description 1
Images
Classifications
-
- H—ELECTRICITY
- H04—ELECTRIC COMMUNICATION TECHNIQUE
- H04N—PICTORIAL COMMUNICATION, e.g. TELEVISION
- H04N7/00—Television systems
- H04N7/18—Closed-circuit television [CCTV] systems, i.e. systems in which the video signal is not broadcast
- H04N7/181—Closed-circuit television [CCTV] systems, i.e. systems in which the video signal is not broadcast for receiving images from a plurality of remote sources
-
- H—ELECTRICITY
- H04—ELECTRIC COMMUNICATION TECHNIQUE
- H04N—PICTORIAL COMMUNICATION, e.g. TELEVISION
- H04N21/00—Selective content distribution, e.g. interactive television or video on demand [VOD]
- H04N21/20—Servers specifically adapted for the distribution of content, e.g. VOD servers; Operations thereof
- H04N21/21—Server components or server architectures
- H04N21/218—Source of audio or video content, e.g. local disk arrays
- H04N21/2187—Live feed
-
- H—ELECTRICITY
- H04—ELECTRIC COMMUNICATION TECHNIQUE
- H04N—PICTORIAL COMMUNICATION, e.g. TELEVISION
- H04N21/00—Selective content distribution, e.g. interactive television or video on demand [VOD]
- H04N21/20—Servers specifically adapted for the distribution of content, e.g. VOD servers; Operations thereof
- H04N21/23—Processing of content or additional data; Elementary server operations; Server middleware
- H04N21/231—Content storage operation, e.g. caching movies for short term storage, replicating data over plural servers, prioritizing data for deletion
-
- H—ELECTRICITY
- H04—ELECTRIC COMMUNICATION TECHNIQUE
- H04N—PICTORIAL COMMUNICATION, e.g. TELEVISION
- H04N21/00—Selective content distribution, e.g. interactive television or video on demand [VOD]
- H04N21/20—Servers specifically adapted for the distribution of content, e.g. VOD servers; Operations thereof
- H04N21/23—Processing of content or additional data; Elementary server operations; Server middleware
- H04N21/234—Processing of video elementary streams, e.g. splicing of video streams or manipulating encoded video stream scene graphs
- H04N21/23418—Processing of video elementary streams, e.g. splicing of video streams or manipulating encoded video stream scene graphs involving operations for analysing video streams, e.g. detecting features or characteristics
-
- H—ELECTRICITY
- H04—ELECTRIC COMMUNICATION TECHNIQUE
- H04N—PICTORIAL COMMUNICATION, e.g. TELEVISION
- H04N21/00—Selective content distribution, e.g. interactive television or video on demand [VOD]
- H04N21/20—Servers specifically adapted for the distribution of content, e.g. VOD servers; Operations thereof
- H04N21/23—Processing of content or additional data; Elementary server operations; Server middleware
- H04N21/234—Processing of video elementary streams, e.g. splicing of video streams or manipulating encoded video stream scene graphs
- H04N21/2343—Processing of video elementary streams, e.g. splicing of video streams or manipulating encoded video stream scene graphs involving reformatting operations of video signals for distribution or compliance with end-user requests or end-user device requirements
- H04N21/234345—Processing of video elementary streams, e.g. splicing of video streams or manipulating encoded video stream scene graphs involving reformatting operations of video signals for distribution or compliance with end-user requests or end-user device requirements the reformatting operation being performed only on part of the stream, e.g. a region of the image or a time segment
-
- H—ELECTRICITY
- H04—ELECTRIC COMMUNICATION TECHNIQUE
- H04N—PICTORIAL COMMUNICATION, e.g. TELEVISION
- H04N21/00—Selective content distribution, e.g. interactive television or video on demand [VOD]
- H04N21/20—Servers specifically adapted for the distribution of content, e.g. VOD servers; Operations thereof
- H04N21/23—Processing of content or additional data; Elementary server operations; Server middleware
- H04N21/234—Processing of video elementary streams, e.g. splicing of video streams or manipulating encoded video stream scene graphs
- H04N21/2347—Processing of video elementary streams, e.g. splicing of video streams or manipulating encoded video stream scene graphs involving video stream encryption
- H04N21/23476—Processing of video elementary streams, e.g. splicing of video streams or manipulating encoded video stream scene graphs involving video stream encryption by partially encrypting, e.g. encrypting the ending portion of a movie
-
- H—ELECTRICITY
- H04—ELECTRIC COMMUNICATION TECHNIQUE
- H04N—PICTORIAL COMMUNICATION, e.g. TELEVISION
- H04N5/00—Details of television systems
- H04N5/76—Television signal recording
Definitions
- the present invention relates to privacy protection in an image collection process, and more particularly, to partially protect and store / manage only an area (particularly, a human face area, etc.) that requires privacy protection in an image collected through a surveillance camera or the like.
- an image protection processing apparatus, an image security system using the same, and a method thereof are provided.
- the present invention is derived from the research conducted as part of the Ministry of Knowledge Economy's Information and Communication Standards Technology Enhancement Project [Task Management No .: 2009-P1-31-09J47, Task Name: Development of Next Generation Biometric Applied Technology Standard].
- CTV closed-circuit television
- Such a CCTV surveillance system generally comprises a CCTV camera 10, a video surveillance / control server 12, an authentication and access control server 14, and a client 16, as shown in FIG.
- Image data is exchanged between components through wired / wireless communication network.
- each component is briefly described as follows.
- CCTV surveillance system transmits the image information collected through the recording device (for example, camera, etc.) installed in a certain space through a closed wired / wireless transmission path so that only a specific person can receive it. Any communication equipment that makes it possible.
- CCTV surveillance system is one of the most widely used physical security technology, it is installed in a specific location (space) and is used for various purposes.
- the video surveillance / control server 12 not only stores / manages the video information obtained from the CCTV camera 10, but also monitors and monitors the video, and the authentication and access control server 14 stores the video that is stored / managed. To control the access of the client 16 for security.
- the authentication and access control server 14 may be included in the video surveillance / control server 12.
- the client 16 is a system or user to receive and use a CCTV image from the video surveillance / control server 14, and may be a desktop computer, a laptop, a personal digital assistant (PDA), a mobile phone, or the like. This may correspond.
- PDA personal digital assistant
- Security threats in security systems include: (1) privacy-related security threats that may occur in individual components, such as wired and wireless CCTVs, video surveillance / control servers, and clients; and (2) wired and wireless CCTVs and video surveillance / There is a security-related security threat that may occur during the transmission and reception of video data between the control server and the transmission and reception of video data between the video surveillance / control server and the client.
- privacy threats / infringements related to the video surveillance / control server 12 include the storage and use of personal video information through illegal or privacy infringement, illegal surveillance and attacks by administrators / internals, and unauthorized user or third party intrusions. Access / leak / invasion of personal privacy information by personal information, exposure of personal characteristic information due to use of indiscriminate identification system, invasion of personal privacy, leakage of undestructed personal information due to unsettled video storage period, and uncontrolled image quality control Personal privacy violations that occur.
- an object of the present invention is to provide an image protection processing device for privacy protection, an image security system using the same, and a method thereof, which can prevent an unintended privacy infringement (inverse function) while maintaining the net function of a surveillance system. There is this.
- the present invention partially protects and stores / manages only the area requiring privacy protection from an image collected through a surveillance camera or the like, and restores the original recognizable image according to a user's request. Protection release).
- the present invention provides an image protection processing apparatus for privacy protection, comprising: detecting means for detecting a region to be protected from a collected image; Protection processing means for generating a protected image having an unrecognized area by applying a privacy protection algorithm to the detected protected area; And management means for storing / managing the generated protected image.
- the present invention provides a video security system using privacy protection, comprising: image collecting means for collecting and encrypting an image for a specific security target; And image monitoring / control means for decoding the encrypted image received from the image collecting means, detecting a protection target region from the decrypted collected image, and applying a privacy protection algorithm.
- the image security method for privacy protection comprising: detecting a region to be protected from the image collected for the security target; Generating and storing / managing a protected image having an unrecognized area by applying a privacy protection algorithm to the detected protected area; And restoring the original image by applying a privacy protection release algorithm to the protected image according to the client's protection release request.
- the invention as described above partially protects and stores / manages only the area (in particular, the face area of the person) that requires privacy protection from the image collected through the CCTV surveillance system, and restores the original recognizable image as needed ( Since the protection system is used to achieve the original purpose or pure function of the surveillance system, it can effectively prevent unintended leakage of personal information or invasion of privacy.
- the present invention has the effect of minimizing the possibility of leakage of personal information or invasion of privacy by applying encryption / decryption techniques to images transmitted and received between CCTV cameras (video collection devices), video surveillance / control servers, and clients. have.
- the present invention has the effect of pioneering and activating a biometric-based physical security area by combining a physical security technology such as a CCTV surveillance system with a human face area detection technology, which is a kind of biometric recognition technology.
- 1 is a configuration example of a general CCTV surveillance system
- FIG. 2 is an explanatory diagram of a privacy-related security threat that may occur in a CCTV surveillance system
- FIG. 3 is a configuration diagram of an embodiment of a video security system using privacy protection according to the present invention.
- FIG. 4 is an overall explanatory diagram of a security process performed in each component of the video security system of FIG. 3 according to the present invention
- FIG. 5 is a flowchart illustrating a method for obtaining a privacy-protected image by a client according to the present invention
- FIG. 6 is a diagram illustrating an embodiment of a privacy protection framework using face region detection according to the present invention.
- FIG. 7A is a flowchart illustrating a method of generating a privacy protection processed image according to the present invention.
- FIG. 7B is a flowchart illustrating a method of generating a privacy deprotection image according to the present invention.
- FIG. 8A is a flowchart of an image scrambling method applied to the present invention.
- 8B is a flowchart illustrating an image descrambling method applied to the present invention.
- the present invention relates to an image protection processing device for privacy protection.
- Detection means for detecting a region to be protected from the collected image
- Protection processing means for generating a protected image having an unrecognized area by applying a privacy protection algorithm to the detected protected area
- Management means for storing / managing the generated protected image
- It provides an image protection processing device comprising a.
- FIG. 3 is a configuration diagram of an image security system using privacy protection according to an embodiment of the present invention, which illustrates a process of detecting and protecting a specific area of a collected image (privacy protection processing).
- FIG. 3 illustrates a process of protecting privacy by using face area detection in a CCTV surveillance system.
- the present invention obtains the user's face information obtained from the CCTV surveillance system through the detection of the face area as part of the bio-recognition, and performs a protection process such as mosaic, scrambling and so on so as not to recognize who is stored so that personal information is not exposed If necessary, it is characterized by reconstructing the original image through a reverse scrambling process.
- a protection process such as mosaic, scrambling and so on so as not to recognize who is stored so that personal information is not exposed If necessary, it is characterized by reconstructing the original image through a reverse scrambling process.
- the video security system (“broad video security system”) for performing this function, as shown in the drawing, one or more video collection device 300, video surveillance / control server 310, And a client 320.
- video security system (“video security system in consultation”).
- each component will be described.
- the image collection device 300 collects (acquires) an image of a surveillance object and transmits the image to the image surveillance / control server 310 safely, and in particular, encrypts and transmits the collected (acquired) image for privacy protection. do.
- the image acquisition apparatus 300 corresponds to a CCTV camera, and the CCTV camera may include an encryption module itself, and in some embodiments, may download and use an encryption application from the video surveillance / control server 310.
- a CCTV camera may be a USB (Universal Serial Bus) camera or an IP (Internet Protocol) camera.
- USB Universal Serial Bus
- IP Internet Protocol
- a wireless Wi-Fi camera it is very easy to install and can be easily installed at any location at low cost. There is this.
- the analog camera may also be used as a CCTV camera, and in this case, the digitalization module and the encryption module may be included in the image acquisition device 300.
- the video surveillance / control server 310 processes and stores / manages the images received from the image capturing apparatus 300 in a form suitable for a specific purpose (“privacy protection processing”), and stores the images according to a client's request.
- the level of privacy protection is performed and the processed image is encrypted and transmitted to the client 320 through the wired / wireless communication network.
- the video surveillance / control server 310 may be referred to as an image receiving processing unit 311 and an image protection processing device 312 (“image protection processing unit”), which is merely a difference in name. , And there is no difference in the functions performed by them), and the image transmission processing unit 313, which will be described in detail below.
- image protection processing unit an image protection processing device 312
- the video surveillance / control server 310 may include a monitoring unit, a display unit, an authentication and access control unit, and the like.
- the image receiving processor 311 receives an image from the image collecting apparatus 300 through a wired / wireless network, and performs a decryption process when the received image is encrypted. That is, the image receiving processor 311 includes a receiver 3111 for receiving an image through a wired / wireless network and a decoder 3112 for decoding the received image.
- the image receiving processing unit 311 is a CCTV camera that is authenticated through verification of an X.509v3-based CCTV device certificate (CCTV certificate) in relation to the image collecting device 300 in receiving an image through the receiving unit 3111. Check whether or not.
- the conventional CCTV surveillance system did not consider the CCTV-only certificate, and thus, general users, including administrators, could not verify whether the corresponding CCTV camera is a legal / illegal / sneaky camera. Therefore, in the present invention, by mounting a dedicated certificate having a format suitable for the CCTV environment in the CCTV camera, the image receiving processing unit 311 in receiving the collected image from the CCTV camera corresponding to the embodiment of the image collecting device 300 CCTV Device authentication can be performed through a dedicated certificate.
- An image protection processing device (image protection processing unit) 312 includes a face area detection unit 3121, a protection processing unit 3122, and a storage / management unit 3123, which will be described below.
- the face area detector 3121 detects a face area from the collected image (decoded image), where the face area is an example of the “protected area”, and may be a part (area) other than the face according to an embodiment.
- the protection target region will be described as being limited to the "face region”.
- the face area detection technique is a process to be performed before the face recognition process and is a technique of finding out where the face is in the image.
- face area detection up to the step of finding the main parts of the face such as eyes, nose, mouth, etc. in face recognition is called “face area detection”, and the pre-processing and feature extraction step after detecting the face area are called “feature extraction step”.
- feature extraction step up to the step of finding the main parts of the face such as eyes, nose, mouth, etc. in face recognition is called “face area detection”, and the pre-processing and feature extraction step after detecting the face area are called “feature extraction step”.
- bio-recognition techniques which include knowledge-based methods, feature-based methods, template-based methods, and appearance-based methods. -Based Mthods).
- the protection processing unit 3122 applies an appropriate privacy protection algorithm (privacy protection application algorithm) to the protection target area (face area) detected by the face area detection unit 3121, and " protection image having unrecognized area " For example, an image in which a face region is changed to an unrecognized state (hereinafter, in some cases, simply referred to as “privacy protection image”, “protected image”, and “protection image”) is generated and stored safely.
- the privacy protection algorithm includes an algorithm of an encryption method, a scrambling method, or a masking method.
- the protection processing unit 3122 restores (generates) the original image by applying an appropriate privacy protection release algorithm to the image (protected image). That is, the original image is reconstructed (generated) by applying a privacy protection release algorithm to an unrecognized region (eg, a face region in an unrecognized state) of the protected image.
- an appropriate privacy protection release algorithm to the image (protected image). That is, the original image is reconstructed (generated) by applying a privacy protection release algorithm to an unrecognized region (eg, a face region in an unrecognized state) of the protected image.
- the storage / management unit 3123 safely stores / manages an image (protection processing image) that has been subjected to privacy protection processing in the protection processing unit 3122, and in particular, controls access to the stored image.
- the storage / management unit 3123 may store an image through a separate DVR (Digital Video Recorder) server.
- DVR Digital Video Recorder
- the storage / management unit 3123 when the storage / management unit 3123 receives a request for a specific image from the client 320, the storage / management unit 3123 finds a corresponding protected processing image (an image in the state where privacy protection processing is applied) that is safely stored / managed, and then the image transmission processor 313. ) To the client 320. Accordingly, when a protection release (privacy protection release) for the face image is requested from the client 320, the storage / management unit 3123 obtains a reconstruction image (privacy protection release image) through interworking with the protection processing unit 3122. Thereafter, the image transmission processor 313 transmits the data to the client 320.
- a protection release for the face image
- the storage / management unit 3123 obtains a reconstruction image (privacy protection release image) through interworking with the protection processing unit 3122. Thereafter, the image transmission processor 313 transmits the data to the client 320.
- the client 320 may request the protection release only for a part of the protection areas among the plurality of protection areas existing in the protected image.
- a specific processing method in this case will be described. If the client 320 requests protection release (privacy protection) only for face images of k ( ⁇ n) persons who need privacy removal (unprotection) among the n privacy-protected persons present in the image,
- the management unit 3123 acquires the reconstructed image (the privacy protection release image for k persons) through the interworking with the protection processor 3122, and transmits the reconstructed image to the client 320 through the image transmission processor 313. In this way, privacy protection is maintained for the n-k names that were not subject to protection.
- the storage / management unit 3123 when the storage / management unit 3123 receives a request for a "unprotected specific image" from the client 320, the storage / management unit 3123 immediately acquires a reconstructed image (privacy protection release image) through interworking with the protection processing unit 3122. After that, the image transmission processor 313 transmits the data to the client 320.
- the image transmission processor 313 transmits an image to the client 320 through a wired / wireless network, and encrypts and transmits an image to be transmitted. That is, the image transmission processor 313 includes an encryption unit 3131 for encrypting a transmission target image, and a receiver 3132 for transmitting an encrypted image to a client through a wired / wireless network.
- the client 320 corresponds to a user terminal, the image received from the video surveillance / control server 310 for a variety of purposes, such as authentication, identification (ID) management, crime prevention, evidence collection, terrorism prevention, access management Use it accordingly.
- ID identification
- the interaction between the video surveillance / control server 310 and the client 320 will be described in detail with reference to FIG. 5.
- FIG 4 is a general description of the security process performed in each component of the video security system of Figure 3 according to the present invention, each component (ie CCTV camera, video surveillance / control server, client) of the video security system Shows the privacy-related security functions performed by and the privacy-related security functions performed by the components.
- each component ie CCTV camera, video surveillance / control server, client
- the CCTV camera 300 performs video encryption 400, device authentication through a CCTV-only certificate (401), and (2) video surveillance.
- image encryption / decryption 410, image storage / management and access control / authentication 411, face region detection 412, privacy protection application / release image generation 413, etc. are performed.
- the client performs image decoding 420 or the like.
- FIG. 5 is a flowchart illustrating a method of obtaining a privacy-protected image by a client according to the present invention, and illustrates a processing performed between the video surveillance / control server and the client through a wired / wireless communication network.
- the video surveillance / control server 310 When the video surveillance / control server 310 receives a request for a specific video from the client 320 (500), it searches for and reads the corresponding protected video (video in which privacy protection processing is applied) that is securely stored / managed. After on (502), it is encrypted (504) and sent to the client (320) (506).
- protected video video in which privacy protection processing is applied
- the client 320 decodes the received protection process image (508) and then retrieves the face image needed by the client (510), and monitors / unblocks the protection of the detected face image (privacy protection). Request to the control server 310 (512). As described above in detail with reference to FIG. 3, the client 320 may request a privacy protection release request for only a face image (ie, a face image of a plurality of protected face images) required by the client 320.
- the video surveillance / control server 310 restores the face image information using the privacy protection algorithm (514), encrypts the restored image information (516), and securely transmits it to the client (320). 518).
- the client 320 When the client 320 receives the requested video from the video surveillance / control server 310, the client 320 decodes the received video (520) and utilizes the received video (522).
- the data transmission / reception between the video surveillance / control server 310 and the client 320 should be performed safely, the video surveillance / control server 310 It is preferable to perform encryption on the image (regardless of whether privacy protection processing) is transmitted to the client 320.
- the protection cancellation algorithm is immediately applied to the video without the process "506" to "510".
- the original image can be restored and transmitted.
- FIG. 6 is an exemplary diagram illustrating a privacy protection framework using face region detection according to the present invention, and illustrates a security framework for protecting personal information using face region detection in a CCTV environment.
- the framework includes a security technology to be applied for each security function, and also shows a privacy protection method performed in the process of capturing and storing / using CCTV images, which will be described in detail below.
- the video surveillance / control server 310 After the CCTV camera 300 captures the image of the surveillance / security target and encrypts the image and transmits the image to the video surveillance / control server 310 safely, the video surveillance / control server 310 receives the received encrypted image. After decoding, the image is stored through an appropriate processing procedure (for example, privacy protection processing).
- the client 320 when the client 320 requests an image from the video surveillance / control server 310, the client 320 undergoes an encryption / decryption process. At this time, encryption based on a certificate, a public key, and a symmetric key is applied.
- the video surveillance / control server 310 decrypts the encrypted image received from the CCTV camera 300 and protects privacy by performing a face region detection process based on a suitable face region detection algorithm.
- a protected image is generated using a privacy protection algorithm (privacy level adjustment) suitable for a face image detected through a face region detection technique.
- the privacy protection processing techniques include encryption techniques, scrambling techniques, masking techniques, and the like, and in particular, chaotic based scrambling techniques will be described in detail with reference to FIG. 8A.
- the video surveillance / control server 310 decodes an image stored and managed in a storage medium, and then applies an appropriate privacy protection algorithm to thereby detect (recognize) a face region (privacy protection). Release image).
- the privacy protection technique includes a decryption technique, a reverse scrambling technique, a reverse masking technique, and the like. In particular, the reverse scrambling technique will be described in detail with reference to FIG. 8B.
- the video surveillance / control server 310 stores / manages the video information generated through the privacy protection algorithm by applying safe video storage / management methods. At this time, access control, watermarking encoding technique, steganography encoding technique, encryption technique, face image separation storage technique, intentional deterioration encoding technique, image storage technique using speech modulation, etc. may be applied.
- the video monitoring / control server 310 When the video surveillance / control server 310 receives a request for a specific video from the client 320, the video monitoring / control server 310 applies a secure video reading algorithm to decode the video.
- a secure video reading algorithm In this case, techniques such as access control, watermark decoding, steganography decoding, decoding, separate face image restoration, intentional deterioration image decoding, and image restoration using speech modulation restoration may be applied.
- X.509v3 device authentication techniques that provide device identification and authentication can be applied for CCTV device authentication.
- FIG. 7A is a flowchart illustrating a method of generating a privacy protection processing image according to an exemplary embodiment of the present invention, and illustrates a process in which the video surveillance / control server 310 performs privacy protection processing through face detection and scrambling.
- the image surveillance / control server 310 captures image information transmitted by the CCTV camera corresponding to the image acquisition apparatus 300 (700), and detects a face region from the captured image information (702).
- the video surveillance / control server 310 applies a scrambling technique to the detected face (704), and stores the resulting “scrambled video” (protected video) in the storage / management unit 3123 or the DVR.
- the image data is stored in the server (when the image is stored in a separate external storage server) (706).
- FIG. 7B is a flowchart illustrating a method of generating a privacy deprotection image according to an exemplary embodiment of the present invention, and illustrates a process in which the image monitoring / control server 310 performs privacy deprotection through reverse scrambling.
- the video surveillance / control server 310 is a video stored in a storage / management unit 3123 or a DVR server (a case where an image is stored in a separate external storage server, which is not shown in the figure) (protected video).
- the stored face position information is read (712) when the scrambling is applied.
- the video surveillance / control server 310 applies descrambling using the face position information (714) and stores the resulting image (descrambled image, that is, unprotected image) (716). ).
- FIG. 8A is a flowchart illustrating an image scrambling method applied to the present invention, and illustrates a chaotic based scrambling process 800 performed by the video surveillance / control server 310.
- Image scrambling is an input key and an original image as inputs, which makes the original image unrecognizable by complicating the image position or pixel color. However, if necessary, it should be possible to reproduce the original image by a specific algorithm (inverse algorithm).
- image scrambling techniques include various methods such as a method based on a chaotic map system and an Arnold transform.
- the video surveillance / control server 310 When the video surveillance / control server 310 receives an input key and an image (original image) to be scrambling, the video surveillance / control server 310 obtains a chaotic sequence using a logistic map function (801), and obtains the chaotic sequence. Arrange 802 to obtain a scrambling table.
- the image monitoring / control server 310 outputs (generates) the scrambling image (privacy protection image) by changing the position of the pixels of the original image using the scrambling table (803).
- FIG. 8B is a flowchart illustrating a video descrambling method applied to the present invention, and illustrates a chaotic-based descrambling process 810 performed by the video surveillance / control server 310.
- the video surveillance / control server 310 When the video surveillance / control server 310 receives an input key and an image (protected image) to be descrambling, the video surveillance / control server 310 obtains a chaotic sequence using a logistic map function (811). The descrambling table is obtained by sorting the chaotic order (812).
- the image monitoring / control server 310 outputs (generates) a descrambling image (privacy protection release image) by changing the position of pixels of the descrambling target image using the descrambling table (813).
- the method of the present invention as described above can be written in a computer program. And the code and code segments constituting the program can be easily inferred by a computer programmer in the art.
- the written program is stored in a computer-readable recording medium (information storage medium), and read and executed by a computer to implement the method of the present invention.
- the recording medium may include any type of computer readable recording medium.
- the present invention partially protects and stores / manages only the areas requiring privacy protection (especially human face areas, etc.) from images collected through a CCTV surveillance system, and restores the original recognizable image as necessary (unprotection). Because it is used to maintain and maintain the original purpose or pure function of the surveillance system, the image protection processing device for privacy protection and the image using the same can effectively prevent unintended leakage of personal information or invasion of privacy. It can be employed as a security system and method.
Landscapes
- Engineering & Computer Science (AREA)
- Multimedia (AREA)
- Signal Processing (AREA)
- Databases & Information Systems (AREA)
- Closed-Circuit Television Systems (AREA)
- Studio Devices (AREA)
Abstract
The present invention relates to an apparatus for processing an image in a manner which protects privacy, to an image security system using same, and to a method therefor. By processing only the area (particularly the facial area) in an image collected by a surveillance camera required for the protection of privacy, storing/managing the image, and restoring (protection canceling) the image to the original perceptible image at the request of the user, accidental infringement of privacy (dysfunction) can be prevented while maintaining the proper function of a monitoring system. To this end, the image security system using privacy protection according to the present invention is characterized in that it comprises: an image-collecting means which collects and encrypts images for specific security objects; and an image-monitoring/controlling means which decrypts encrypted images received from the image-collecting means, detects a security object area in the decrypted collection image, and applies a privacy protection algorithm thereto.
Description
본 발명은 영상 수집 과정에서의 프라이버시 보호에 관한 것으로, 더욱 상세하게는 감시 카메라 등을 통하여 수집된 영상에서 프라이버시 보호가 필요한 영역(특히, 사람의 얼굴 영역 등)만을 부분적으로 보호 처리하여 저장/관리하고, 사용자의 요청에 따라 원래의 인식 가능한 영상으로 복원(보호 해제)할 수 있게 함으로써, 감시 시스템의 순기능을 유지하면서도 비의도적으로 발생하는 프라이버시 침해(역기능)를 방지할 수 있는, 프라이버시 보호를 위한 영상 보호처리 장치와, 그를 이용한 영상 보안 시스템 및 그 방법에 관한 것이다.The present invention relates to privacy protection in an image collection process, and more particularly, to partially protect and store / manage only an area (particularly, a human face area, etc.) that requires privacy protection in an image collected through a surveillance camera or the like. By reconstructing (unprotecting) the original recognizable image at the request of the user, it is possible to prevent unintentional invasion of privacy (reverse function) while maintaining the net function of the surveillance system. An image protection processing apparatus, an image security system using the same, and a method thereof are provided.
본 발명은 지식경제부의 정보통신표준기술력향상사업의 일환으로 수행한 연구로부터 도출된 것이다[과제관리번호: 2009-P1-31-09J47, 과제명: 차세대 바이오인식 응용기술 표준개발].The present invention is derived from the research conducted as part of the Ministry of Knowledge Economy's Information and Communication Standards Technology Enhancement Project [Task Management No .: 2009-P1-31-09J47, Task Name: Development of Next Generation Biometric Applied Technology Standard].
인터넷 기술의 발전과 함께 폐쇄회로 텔레비젼(CCTV: Closed-Circuit television)은 사회의 전반적인 분야에 널리 사용되고 있다. 특히, 범죄 예방을 위한 목적으로 널리 사용되며 그 활용도가 점차 확대되고 있다.With the development of internet technology, closed-circuit television (CCTV) has become widely used in the general field of society. In particular, it is widely used for the purpose of crime prevention and its use is gradually expanding.
이러한 CCTV 감시 시스템은 일반적으로 도 1에 도시된 바와 같이, CCTV 카메라(10), 영상 감시/관제 서버(12), 인증 및 접근 제어 서버(14), 및 클라이언트(16)를 포함하여 이루어지며, 유/무선 통신망을 통하여 구성요소 상호 간에 영상 데이터를 주고 받는다. 이하, 각각의 구성요소를 간단히 설명하면 다음과 같다.Such a CCTV surveillance system generally comprises a CCTV camera 10, a video surveillance / control server 12, an authentication and access control server 14, and a client 16, as shown in FIG. Image data is exchanged between components through wired / wireless communication network. Hereinafter, each component is briefly described as follows.
CCTV 감시 시스템(CCTV 보안 시스템, 또는 CCTV 시스템)은 일정한 공간에 설치된 촬영기기(예를 들어, 카메라 등)를 통해 수집한 화상정보를 폐쇄적인 유/무선 전송로를 통하여 전송함으로써 특정인만이 수신할 수 있게 하는 통신장비 일체를 말한다. 즉, CCTV 감시 시스템은 현재 가장 널리 사용되는 물리보안 기술 중 하나로서, 특정 위치(공간)에 설치되어 다양한 목적으로 활용되고 있다.CCTV surveillance system (CCTV security system, or CCTV system) transmits the image information collected through the recording device (for example, camera, etc.) installed in a certain space through a closed wired / wireless transmission path so that only a specific person can receive it. Any communication equipment that makes it possible. In other words, CCTV surveillance system is one of the most widely used physical security technology, it is installed in a specific location (space) and is used for various purposes.
영상 감시/관제 서버(12)는 CCTV 카메라(10)로부터 얻은 영상 정보를 저장/관리할 뿐만 아니라 모니터링하고 영상을 감시하는 기능을 수행하며, 인증 및 접근 제어 서버(14)는 저장/관리되는 영상의 보안을 위하여 클라이언트(16)의 접근 등을 제어하는 기능을 수행한다. 실시예에 따라 인증 및 접근 제어 서버(14)는 영상 감시/관제 서버(12)에 포함될 수 있다.The video surveillance / control server 12 not only stores / manages the video information obtained from the CCTV camera 10, but also monitors and monitors the video, and the authentication and access control server 14 stores the video that is stored / managed. To control the access of the client 16 for security. According to an embodiment, the authentication and access control server 14 may be included in the video surveillance / control server 12.
그리고, 클라이언트(16)는 영상 감시/관제 서버(14)로부터 CCTV 영상을 전달받아 사용하고자 하는 시스템(System) 혹은 사용자(User)로서, 데스크탑 컴퓨터, 랩탑, PDA(Personal Digital Assistant), 모바일 폰 등이 해당할 수 있다.In addition, the client 16 is a system or user to receive and use a CCTV image from the video surveillance / control server 14, and may be a desktop computer, a laptop, a personal digital assistant (PDA), a mobile phone, or the like. This may correspond.
한편, 최근 CCTV의 성능이 개선됨에 따라, CCTV 영상으로부터 획득된 사람의 얼굴 정보를 바탕으로 하는 얼굴 인식 등을 통해 다양한 업무(예를 들어, 범인 검거 등)를 자동 처리하는 기술들이 개발되고 있다.Meanwhile, as the performance of CCTV has been recently improved, technologies for automatically processing various tasks (eg, criminal arrest, etc.) have been developed through face recognition based on face information obtained from CCTV images.
하지만, 이러한 기술들이 악용될 경우, 개인들에 대한 중대한 프라이버시(privacy) 침해가 발생할 우려가 있는데, CCTV 감시 시스템 등과 같은 보안 시스템에서 발생할 수 있는 프라이버시 위협/침해의 유형을 도 2를 참조하여 살펴보면, 다음과 같다.However, if these technologies are exploited, there is a risk of serious privacy breach to individuals. Looking at the types of privacy threats / infringements that can occur in security systems such as CCTV surveillance systems, referring to FIG. As follows.
CCTV 감시 시스템 등과 같은 보안 시스템의 보안 위협에는, (1)유무선 CCTV, 영상 감시/관제 서버, 및 클라이언트 등과 같은 각각의 구성요소에서 발생할 수 있는 프라이버시 관련 보안 위협, (2)유무선 CCTV와 영상 감시/관제 서버 간의 영상 데이터 송수신과, 영상 감시/관제 서버와 클라이언트 간의 영상 데이터 송/수신 과정에서 발생할 수 있는 프라이버시 관련 보안 위협이 있다.Security threats in security systems such as CCTV surveillance systems include: (1) privacy-related security threats that may occur in individual components, such as wired and wireless CCTVs, video surveillance / control servers, and clients; and (2) wired and wireless CCTVs and video surveillance / There is a security-related security threat that may occur during the transmission and reception of video data between the control server and the transmission and reception of video data between the video surveillance / control server and the client.
먼저, CCTV 감시 시스템과 관련된 일반적인 위협을 살펴보기로 한다.First, let's look at general threats related to CCTV surveillance systems.
일반적인 위협은 (1) CCTV 카메라(10)와 관련해서는 무단 접속, 물리적 공격, 서비스 거부(DoS: Denial of Service)/분간 서비스 거부(DDoS:Distributed Denial of Service) 공격 등이 있고, (2) 영상 감시/관제 서버(12)와 관련해서는 공격자의 서버 무단 침입, 데이터베이스 합의(Database Compromise), DoS/DDoS 공격, 데이터 처리 중 공격자의 방해 등이 있으며, (3) 클라이언트(16)와 관련해서는 데이터 처리 중 공격자의 방해가 있다. 특히, 클라이언트(16)가 "휴대폰"인 경우에는 USIM(Universal Subscriber Identity Module) 복제, 휴대폰 복제, 모바일 악성코드를 통한 영상 취득 및 훼손 등과 같은 위협이 있고, 클라이언트(16)가 "데스크탑 컴퓨터"인 경우에는 IP 조작(원격제어, 무단접속), 바이러스 및 악성코드, 스파이웨어 강제 설치 등의 위협이 있으며, 클라이언트(16)가 "모바일 장비"인 경우에는 모바일 바이러스 및 악성코드, IP 복제(Wi-Fi), 단말기 복제 등의 위협이 있다.Common threats include (1) unauthorized access, physical attacks, Denial of Service (DoS) / Distributed Denial of Service (DDoS) attacks in relation to CCTV cameras, and (2) video. Regarding the monitoring / control server 12, an attacker's server intrusion, database agreement, DoS / DDoS attack, attacker's interruption during data processing, etc. (3) Data processing with respect to the client 16 There is interference of the attacker. In particular, if the client 16 is a "mobile phone," there are threats such as Universal Subscriber Identity Module (USIM) replication, mobile phone replication, image acquisition and corruption through mobile malware, and the client 16 is a "desktop computer." In this case, there are threats such as IP manipulation (remote control, unauthorized access), viruses and malware, and spyware forced installation. In the case where the client 16 is a "mobile device," it is a mobile virus and malware, IP replication (Wi- Fi) and terminal duplication.
한편, CCTV 카메라(10)에서 영상 감시/관제 서버(14)로 영상을 전송하는 경우에는 도청, 재전송 공격, 중간자 공격, 의안화 공격 등이 있고, 영상 감시/관제 서버(12)와 클라이언트(16)가 영상정보를 포함한 데이터를 송수신하는 경우에는 도청, 재전송 공격, 중간자 공격, 의안화 공격, IP(Internet Protocol) 교란, DoS/DDoS 공격 등이 있다.On the other hand, when transmitting the video from the CCTV camera 10 to the video surveillance / control server 14, there are eavesdropping, retransmission attack, man-in-the-middle attack, bill of fire attack, video surveillance / control server 12 and client 16 ) Transmits and receives data including image information, there are eavesdropping, retransmission attacks, man-in-the-middle attacks, bill-of-fire attacks, IP (Internet Protocol) disturbances, and DoS / DDoS attacks.
다음은, 프라이버시 관련 위협/침해에 대하여 설명하기로 한다.Next, privacy threats / infringements will be described.
첫째, CCTV 카메라(10)와 관련해서는 위치정보/영상정보/신체정보 등의 미인지 개인정보를 실시간으로 수집하는 경우, 몰래카메라/불법 감청 장치 등의 불법 수단으로 개인 정보를 수집하는 경우, 불법 위치에서 개인 영상정보를 무단으로 수집 및 촬영(예를 들어, 목욕탕 등)하는 경우 등의 프라이버시 위협/침해가 있다.First, in the case of collecting unrecognized personal information such as location information, video information, and physical information in real time with respect to the CCTV camera 10, when collecting personal information by illegal means such as a sneak camera / illegal interception device, illegal There is a privacy threat / invasion, such as when the personal image information is collected and photographed (for example, a bathhouse) without permission.
둘째, 영상 감시/관제 서버(12)와 관련된 프라이버시 위협/침해에는, 불법 또는 프라이버시 침해를 통한 개인 영상 정보 저장 및 이용, 관리자/내부자에 의한 불법 감시 및 공격, 비인가된 사용자 또는 제3자 침입에 의한 개인 프라이버시 정보 접근/유출/침해, 무분별한 식별시스템의 사용에 따른 개인특징정보 노출 및 개인 프라이버시 침해, 영상 저장 기간 미설정 등으로 인한 파기되지 않은 개인 정보 유출, 저장된 영상의 화질 제어 기능 미탑재로 인하여 발생하는 개인 프라이버시 침해 등이 있다.Second, privacy threats / infringements related to the video surveillance / control server 12 include the storage and use of personal video information through illegal or privacy infringement, illegal surveillance and attacks by administrators / internals, and unauthorized user or third party intrusions. Access / leak / invasion of personal privacy information by personal information, exposure of personal characteristic information due to use of indiscriminate identification system, invasion of personal privacy, leakage of undestructed personal information due to unsettled video storage period, and uncontrolled image quality control Personal privacy violations that occur.
셋째, 클라이언트(16)와 관련해서는, 본인 동의가 없는 개인 정보의 무단 이용 및 상업적/정치적 활용, 유사 바이오 정보로 인한 개인 프라이버시 침해, 개인 프라이버시 정보의 불법 유출, 이종 서비스 간의 개인정보 공유/활용, 개인정보 미파기 및 삭제 요구 불이행, 서비스 이용과 관련 없는 과도한 개인정보 요청/수집/활용 등과 같은 프라이버시 위협/침해가 있다.Third, with respect to the client 16, unauthorized use and commercial / political use of personal information without your consent, invasion of personal privacy due to similar bio information, illegal leakage of personal privacy information, sharing / utilization of personal information between heterogeneous services, There are privacy threats / infringements, such as failure to destroy and delete personal information, excessive request / collection / use of personal information not related to service use.
넷째, 영상 정보를 포함한 데이터를 송수신하는 경우(예를 들어, CCTV와 영상 감시/관제 서버 사이의 송수신, 또는 영상 감시/관제 서버와 클라이언트 사이의 송수신)에 발생할 수 있는 프라이버시 위협/침해에는, 개인 프라이버시 정보의 도청 및 노출, 위조된 개인 프라이버시 정보의 송수신 등이 있다.Fourth, privacy threats / infringements that may occur in the case of transmitting / receiving data including video information (e.g., sending / receiving between CCTV and video surveillance / control server or between video surveillance / control server and client), Eavesdropping and exposure of privacy information, transmission and reception of forged personal privacy information, and the like.
요컨대, 오늘날 CCTV를 이용하여 다양한 목적을 달성할 수 있는 장점(순기능)이 있어 그 활용 분야가 증가하고 있는데, 이러한 긍정적인 모습의 이면에는 개인 영상정보의 수집, 저장(보관), 전송, 활용 등과 관련하여 위에서 살펴본 바와 같은 다양한 형태의 프라이버시 위협/침해가 발생하고 있거나 발생할 우려가 있다는 문제가 있으며, 이러한 프라이버시 침해는 일단 발생하면 사후적으로 회복시키는 것이 극히 곤란하거나 불가능하여 사전에 적극적으로 프라이버시 침해를 방지하는 것이 중요하다.In short, there is an advantage (net function) that can achieve various purposes by using CCTV today, and its field of use is increasing. Behind this positive aspect, the collection, storage (archive), transmission, utilization of personal video information, etc. In relation to this, there is a problem that various types of privacy threats / infringements are occurring or are likely to occur as described above. Such infringement of privacy is extremely difficult or impossible to recover once it has occurred. It is important to prevent.
따라서 본 발명은 감시 시스템의 순기능을 유지하면서도 비의도적으로 발생하는 프라이버시 침해(역기능)를 방지할 수 있는, 프라이버시 보호를 위한 영상 보호처리 장치와, 그를 이용한 영상 보안 시스템 및 그 방법을 제공하는데 그 목적이 있다.Accordingly, an object of the present invention is to provide an image protection processing device for privacy protection, an image security system using the same, and a method thereof, which can prevent an unintended privacy infringement (inverse function) while maintaining the net function of a surveillance system. There is this.
본 발명의 목적들은 이상에서 언급한 목적으로 제한되지 않으며, 언급되지 않은 본 발명의 다른 목적 및 장점들은 하기의 설명에 의해서 이해될 수 있으며, 본 발명의 실시예에 의해 보다 분명하게 알게 될 것이다. 또한, 본 발명의 목적 및 장점들은 특허 청구 범위에 나타낸 수단 및 그 조합에 의해 실현될 수 있음을 쉽게 알 수 있을 것이다.The objects of the present invention are not limited to the above-mentioned objects, and other objects and advantages of the present invention which are not mentioned above can be understood by the following description, and will be more clearly understood by the embodiments of the present invention. Also, it will be readily appreciated that the objects and advantages of the present invention may be realized by the means and combinations thereof indicated in the claims.
본 발명은 상기와 같은 목적을 달성하기 위하여, 감시 카메라 등을 통하여 수집된 영상에서 프라이버시 보호가 필요한 영역만을 부분적으로 보호 처리하여 저장/관리하고, 사용자의 요청에 따라 원래의 인식 가능한 영상으로 복원(보호 해제)하는 것을 특징으로 한다.In order to achieve the above object, the present invention partially protects and stores / manages only the area requiring privacy protection from an image collected through a surveillance camera or the like, and restores the original recognizable image according to a user's request. Protection release).
더욱 구체적으로, 본 발명은, 프라이버시 보호를 위한 영상 보호처리 장치에 있어서, 수집 영상으로부터 보호대상 영역을 검출하기 위한 검출 수단; 상기 검출된 보호대상 영역에 프라이버시 보호 알고리즘을 적용하여 인식불능 영역을 갖는 보호처리 영상을 생성하기 위한 보호 처리 수단; 및 상기 생성된 보호처리 영상을 저장/관리하기 위한 관리 수단을 포함한다.More specifically, the present invention provides an image protection processing apparatus for privacy protection, comprising: detecting means for detecting a region to be protected from a collected image; Protection processing means for generating a protected image having an unrecognized area by applying a privacy protection algorithm to the detected protected area; And management means for storing / managing the generated protected image.
또한, 본 발명은, 프라이버시 보호를 이용한 영상 보안 시스템에 있어서, 특정 보안대상에 대한 영상을 수집하여 암호화하기 위한 영상 수집 수단; 및 상기 영상 수집 수단으로부터 수신된 암호화 영상을 복호화하고, 상기 복호화된 수집 영상에서 보호대상 영역을 검출하여 프라이버시 보호 알고리즘을 적용하기 위한 영상 감시/관제 수단을 포함한다.In addition, the present invention provides a video security system using privacy protection, comprising: image collecting means for collecting and encrypting an image for a specific security target; And image monitoring / control means for decoding the encrypted image received from the image collecting means, detecting a protection target region from the decrypted collected image, and applying a privacy protection algorithm.
또한, 본 발명은, 프라이버시 보호를 위한 영상 보안 방법에 있어서, 보안 대상에 대하여 수집된 영상으로부터 보호대상 영역을 검출하는 단계; 상기 검출된 보호대상 영역에 프라이버시 보호 알고리즘을 적용하여 인식불능 영역을 갖는 보호처리 영상을 생성하여 저장/관리하는 단계; 및 클라이언트의 보호해제 요청에 따라, 해당 보호처리 영상에 대하여 프라이버시 보호 해제 알고리즘을 적용하여 원본 영상을 복원하는 단계를 포함한다.In addition, the present invention, the image security method for privacy protection, comprising: detecting a region to be protected from the image collected for the security target; Generating and storing / managing a protected image having an unrecognized area by applying a privacy protection algorithm to the detected protected area; And restoring the original image by applying a privacy protection release algorithm to the protected image according to the client's protection release request.
상기와 같은 발명은 CCTV 감시 시스템을 통하여 수집된 영상에서 프라이버시 보호가 필요한 영역(특히, 사람의 얼굴 영역 등)만을 부분적으로 보호 처리하여 저장/관리하고, 필요에 따라 원래의 인식 가능한 영상으로 복원(보호 해제)하여 활용하기 때문에, 감시 시스템의 본래 목적이나 순기능을 그대로 달성/유지하면서도 의도하지 않은 개인 정보의 유출이나 프라이버시 침해를 효율적으로 방지할 수 있는 효과가 있다.The invention as described above partially protects and stores / manages only the area (in particular, the face area of the person) that requires privacy protection from the image collected through the CCTV surveillance system, and restores the original recognizable image as needed ( Since the protection system is used to achieve the original purpose or pure function of the surveillance system, it can effectively prevent unintended leakage of personal information or invasion of privacy.
또한, 본 발명은 CCTV 카메라(영상 수집 장치), 영상 감시/관제 서버, 및 클라이언트 상호 간에 주고 받는 영상에 대하여 암/복호화 기술을 적용함으로써, 개인 정보의 유출이나 프라이버시 침해의 가능성을 최소화하는 효과가 있다.In addition, the present invention has the effect of minimizing the possibility of leakage of personal information or invasion of privacy by applying encryption / decryption techniques to images transmitted and received between CCTV cameras (video collection devices), video surveillance / control servers, and clients. have.
또한, 본 발명은 CCTV 감시 시스템과 같은 물리 보안 기술에 바이오 인식 기술의 일종인 사람 얼굴영역 검출 기술을 결합함으로써, 바이오 인식 기반의 물리보안 영역을 개척하고 이를 활성화하는 효과가 있다.In addition, the present invention has the effect of pioneering and activating a biometric-based physical security area by combining a physical security technology such as a CCTV surveillance system with a human face area detection technology, which is a kind of biometric recognition technology.
도 1은 일반적인 CCTV 감시 시스템의 구성예시도,1 is a configuration example of a general CCTV surveillance system,
도 2는 CCTV 감시 시스템에서 발생 가능한 프라이버시 관련 보안 위협에 대한 설명도,2 is an explanatory diagram of a privacy-related security threat that may occur in a CCTV surveillance system;
도 3은 본 발명에 따른 프라이버시 보호를 이용한 영상 보안 시스템의 일실시예 구성도,3 is a configuration diagram of an embodiment of a video security system using privacy protection according to the present invention;
도 4는 본 발명에 따른 도 3의 영상 보안 시스템의 각 구성요소에서 수행되는 보안 과정에 대한 전반적인 설명도,4 is an overall explanatory diagram of a security process performed in each component of the video security system of FIG. 3 according to the present invention;
도 5는 본 발명에 따른 클라이언트가 프라이버시 보호해제된 영상을 획득하는 방법에 대한 일실시예 흐름도,5 is a flowchart illustrating a method for obtaining a privacy-protected image by a client according to the present invention;
도 6은 본 발명에 따른 얼굴 영역 검출을 이용한 프라이버시 보호 프레임워크에 대한 일실시예 설명도,6 is a diagram illustrating an embodiment of a privacy protection framework using face region detection according to the present invention;
도 7a는 본 발명에 따른 프라이버시 보호처리 영상을 생성하는 방법에 대한 일실시예 흐름도,7A is a flowchart illustrating a method of generating a privacy protection processed image according to the present invention;
도 7b는 본 발명에 따른 프라이버시 보호해제 영상을 생성하는 방법에 대한 일실시예 흐름도,7B is a flowchart illustrating a method of generating a privacy deprotection image according to the present invention;
도 8a는 본 발명에 적용되는 영상 스크램블링 방법에 대한 흐름도,8A is a flowchart of an image scrambling method applied to the present invention;
도 8b는 본 발명에 적용되는 영상 역스크램블링 방법에 대한 흐름도이다.8B is a flowchart illustrating an image descrambling method applied to the present invention.
본 발명은 프라이버시 보호를 위한 영상 보호처리 장치에 있어서,The present invention relates to an image protection processing device for privacy protection.
수집 영상으로부터 보호대상 영역을 검출하기 위한 검출 수단;Detection means for detecting a region to be protected from the collected image;
상기 검출된 보호대상 영역에 프라이버시 보호 알고리즘을 적용하여 인식불능 영역을 갖는 보호처리 영상을 생성하기 위한 보호 처리 수단; 및Protection processing means for generating a protected image having an unrecognized area by applying a privacy protection algorithm to the detected protected area; And
상기 생성된 보호처리 영상을 저장/관리하기 위한 관리 수단Management means for storing / managing the generated protected image
을 포함하는 영상 보호처리 장치를 제공한다.It provides an image protection processing device comprising a.
상술한 목적, 특징 및 장점은 첨부된 도면과 관련한 다음의 상세한 설명을 통하여 보다 분명해 질 것이며, 그에 따라 본 발명이 속하는 기술분야에서 통상의 지식을 가진 자가 본 발명의 기술적 사상을 용이하게 실시할 수 있을 것이다. 또한, 본 발명을 설명함에 있어서 본 발명과 관련된 공지 기술에 대한 구체적인 설명이 본 발명의 요지를 불필요하게 흐릴 수 있다고 판단되는 경우에 그 상세한 설명을 생략하기로 한다. 이하, 첨부된 도면을 참조하여 본 발명에 따른 바람직한 일실시예를 상세히 설명하기로 한다.The above objects, features and advantages will become more apparent from the following detailed description taken in conjunction with the accompanying drawings, whereby those skilled in the art may easily implement the technical idea of the present invention. There will be. In addition, in describing the present invention, when it is determined that the detailed description of the known technology related to the present invention may unnecessarily obscure the gist of the present invention, the detailed description thereof will be omitted. Hereinafter, exemplary embodiments of the present invention will be described in detail with reference to the accompanying drawings.
도 3은 본 발명에 따른 프라이버시 보호를 이용한 영상 보안 시스템의 일실시예 구성도로서, 수집 영상의 특정 영역을 검출하여 보호 처리(프라이버시 보호 처리)하는 과정을 나타낸다. 특히, 도 3은 CCTV 감시 시스템에서 얼굴 영역 검출을 이용하여 프라이버시를 보호하는 과정을 나타낸다. 이하, 본 발명에 따른 영상 보안 시스템을 설명하면서, 그 시스템에서 수행되는 영상 보안 방법도 함께 설명하기로 한다.3 is a configuration diagram of an image security system using privacy protection according to an embodiment of the present invention, which illustrates a process of detecting and protecting a specific area of a collected image (privacy protection processing). In particular, FIG. 3 illustrates a process of protecting privacy by using face area detection in a CCTV surveillance system. Hereinafter, while describing the video security system according to the present invention, a video security method performed in the system will be described together.
본 발명은 CCTV 감시 시스템에서 얻어지는 사용자 얼굴 정보를 바이오 인식의 일환인 얼굴 영역 검출을 통해 획득하여, 누군지 알아볼 수 없게 모자이크, 스크램블링(scrambling) 등의 보호 처리를 수행하여 개인정보가 노출되지 않도록 저장하고, 필요시에는 역스크램블링 처리를 통해 원래 영상으로 복원하는 것을 특징으로 한다.The present invention obtains the user's face information obtained from the CCTV surveillance system through the detection of the face area as part of the bio-recognition, and performs a protection process such as mosaic, scrambling and so on so as not to recognize who is stored so that personal information is not exposed If necessary, it is characterized by reconstructing the original image through a reverse scrambling process.
이러한 기능을 수행하는 본 발명에 따른 영상 보안 시스템("광의의 영상 보안 시스템")은, 도면에 도시된 바와 같이, 하나 또는 2 이상의 영상 수집 장치(300), 영상 감시/관제 서버(310), 및 클라이언트(320)를 포함하여 이루어진다. 여기서, 영상 수집 장치(300)와 영상 감시/관제 서버(310)만을 지칭해서 영상 보안 시스템("협의의 영상 보안 시스템")이라 할 수 있다. 이하, 각각의 구성 요소에 대하여 설명하기로 한다.The video security system ("broad video security system") according to the present invention for performing this function, as shown in the drawing, one or more video collection device 300, video surveillance / control server 310, And a client 320. Here, only the image acquisition apparatus 300 and the image surveillance / control server 310 may be referred to as a video security system (“video security system in consultation”). Hereinafter, each component will be described.
먼저, 영상 수집 장치(300)는 감시 대상에 대한 영상을 수집(획득)하여 영상 감시/관제 서버(310)에 안전하게 전송하는 것으로서, 특히 프라이버시 보호를 위해서 상기 수집(획득)된 영상을 암호화하여 전송한다.First, the image collection device 300 collects (acquires) an image of a surveillance object and transmits the image to the image surveillance / control server 310 safely, and in particular, encrypts and transmits the collected (acquired) image for privacy protection. do.
영상 수집 장치(300)는 CCTV 카메라에 해당하는 것으로서, CCTV 카메라는 암호화 모듈을 자체적으로 포함할 수 있고, 실시예에 따라서는 영상 감시/관제 서버(310)로부터 암호화 어플리케이션을 다운받아 사용할 수도 있다. 여기서, CCTV 카메라로는 USB(Universal Serial Bus) 카메라 또는 IP(Internet Protocol) 카메라가 사용될 수도 있는데, 무선 Wi-Fi 카메라의 경우에는 설치가 매우 용이하고, 저비용으로 임의의 위치에 쉽게 설치할 수 있는 장점이 있다. 아날로그 카메라 또한 CCTV 카메라로 사용 가능하며, 이때에는 디지털화 모듈과 암호화 모듈이 영상 수집 장치(300)에 포함될 수 있다.The image acquisition apparatus 300 corresponds to a CCTV camera, and the CCTV camera may include an encryption module itself, and in some embodiments, may download and use an encryption application from the video surveillance / control server 310. Here, a CCTV camera may be a USB (Universal Serial Bus) camera or an IP (Internet Protocol) camera. In the case of a wireless Wi-Fi camera, it is very easy to install and can be easily installed at any location at low cost. There is this. The analog camera may also be used as a CCTV camera, and in this case, the digitalization module and the encryption module may be included in the image acquisition device 300.
다음은, 영상 감시/관제 서버(310)에 대하여 설명하기로 한다. Next, the video surveillance / control server 310 will be described.
영상 감시/관제 서버(310)는 영상 수집 장치(300)로부터 전송받은 영상을 특정 목적에 맞는 형태로 처리("프라이버시 보호 처리")하여 저장/관리하고, 클라이언트의 요청에 따라, 저장된 영상에서 적절한 수준의 프라이버시 보호 해제를 수행하고 그 처리결과 영상을 암호화하여 유무선 통신망을 통해 클라이언트(320)에 전송한다. The video surveillance / control server 310 processes and stores / manages the images received from the image capturing apparatus 300 in a form suitable for a specific purpose (“privacy protection processing”), and stores the images according to a client's request. The level of privacy protection is performed and the processed image is encrypted and transmitted to the client 320 through the wired / wireless communication network.
이러한 영상 감시/관제 서버(310)는 도면에 도시된 바와 같이, 영상 수신처리부(311), 영상 보호처리 장치(312)("영상 보호처리부"라고도 할 수 있으며, 이는 단순한 명칭의 차이에 불과하고, 이들에 의해 수행되는 기능에는 차이가 없음), 및 영상 송신처리부(313)를 포함하여 이루어지는데, 이하 각각의 구성요소에 대하여 상세히 설명하기로 한다. 참고로, 도면에는 도시하지 않았으나, 실시예에 따라서는 영상 감시/관제 서버(310)는 모니터링부, 디스플레이부, 인증 및 접근 제어부 등이 포함될 수 있다.As shown in the figure, the video surveillance / control server 310 may be referred to as an image receiving processing unit 311 and an image protection processing device 312 (“image protection processing unit”), which is merely a difference in name. , And there is no difference in the functions performed by them), and the image transmission processing unit 313, which will be described in detail below. For reference, although not shown in the drawings, the video surveillance / control server 310 may include a monitoring unit, a display unit, an authentication and access control unit, and the like.
영상 수신처리부(311)는 유/무선 네트워크를 통하여 영상 수집 장치(300)로부터 영상을 수신하는 것으로서, 수신된 영상이 암호화된 경우에는 복호화 과정을 수행한다. 즉, 영상 수신처리부(311)는 유/무선 네트워크를 통하여 영상을 수신하는 수신부(3111)와, 수신된 영상을 복호화하는 복호화부(3112)를 포함하여 이루어진다. 영상 수신처리부(311)는 수신부(3111)를 통하여 영상을 수신함에 있어서, 영상 수집 장치(300)와의 관계에서, X.509v3 기반의 CCTV 기기인증서(CCTV 전용인증서) 검증을 통해 인증된 CCTV 카메라인지 여부를 확인한다. 이를 상세히 설명하면, 종래의 CCTV 감시 시스템에서는 CCTV 전용 인증서를 고려하지 않았는데, 이로 인하여 해당 CCTV 카메라가 합법/불법/몰래 카메라인지 여부를 관리자를 포함한 일반 사용자들은 검증할 수 없었다. 따라서, 본 발명에서는 CCTV 환경에 적합한 포맷을 가지는 전용 인증서를 CCTV 카메라에 탑재함으로써, 영상 수신처리부(311)가 영상 수집 장치(300)의 실시예에 해당하는 CCTV 카메라로부터 수집 영상을 수신함에 있어서 CCTV 전용 인증서를 통하여 기기 인증을 수행할 수 있게 한다.The image receiving processor 311 receives an image from the image collecting apparatus 300 through a wired / wireless network, and performs a decryption process when the received image is encrypted. That is, the image receiving processor 311 includes a receiver 3111 for receiving an image through a wired / wireless network and a decoder 3112 for decoding the received image. The image receiving processing unit 311 is a CCTV camera that is authenticated through verification of an X.509v3-based CCTV device certificate (CCTV certificate) in relation to the image collecting device 300 in receiving an image through the receiving unit 3111. Check whether or not. In detail, the conventional CCTV surveillance system did not consider the CCTV-only certificate, and thus, general users, including administrators, could not verify whether the corresponding CCTV camera is a legal / illegal / sneaky camera. Therefore, in the present invention, by mounting a dedicated certificate having a format suitable for the CCTV environment in the CCTV camera, the image receiving processing unit 311 in receiving the collected image from the CCTV camera corresponding to the embodiment of the image collecting device 300 CCTV Device authentication can be performed through a dedicated certificate.
영상 보호처리 장치(영상 보호처리부)(312)는 얼굴영역 검출부(3121), 보호 처리부(3122), 및 저장/관리부(3123)를 포함하여 이루어지는데, 이하 각각에 대하여 설명하기로 한다.An image protection processing device (image protection processing unit) 312 includes a face area detection unit 3121, a protection processing unit 3122, and a storage / management unit 3123, which will be described below.
얼굴영역 검출부(3121)는 수집된 영상(복호화된 영상)으로부터 얼굴 영역을 검출하는데, 여기서 얼굴 영역은 "보호대상 영역"의 예로서, 실시예에 따라 얼굴 이외의 부분(영역)일 수도 있다. 이하, 보호대상 영역은 "얼굴 영역"으로 한정하여 설명하기로 한다.The face area detector 3121 detects a face area from the collected image (decoded image), where the face area is an example of the “protected area”, and may be a part (area) other than the face according to an embodiment. Hereinafter, the protection target region will be described as being limited to the "face region".
얼굴 영역 검출 기법은 얼굴 인식 과정 이전에 실행되어야 하는 과정으로서, 영상에서 얼굴이 있는 곳을 찾아내는 기술이다. 일반적으로 얼굴 인식에 있어 눈, 코, 입 등 얼굴의 주요부위를 찾아내는 단계까지를 "얼굴 영역 검출"이라고 하고, 얼굴 영역을 검출한 후의 전처리 및 특칭 추출 단계를 일컬어 "특징 추출 단계"라 한다. 이러한 얼굴 영역 검출 기법은 바이오 인식 기술을 이용하는 것으로서, 이에는 지식기반 방법(Knowledge-Based Methods), 특징기반 방법(Feature-Based Methods), 탬플릿 매칭 방법(Template-Based Methods), 외형기반 방법(Appearance-Based Mthods) 등이 있다.The face area detection technique is a process to be performed before the face recognition process and is a technique of finding out where the face is in the image. In general, up to the step of finding the main parts of the face such as eyes, nose, mouth, etc. in face recognition is called "face area detection", and the pre-processing and feature extraction step after detecting the face area are called "feature extraction step". The face detection technique uses bio-recognition techniques, which include knowledge-based methods, feature-based methods, template-based methods, and appearance-based methods. -Based Mthods).
보호 처리부(3122)는 얼굴영역 검출부(3121)에서 검출된 보호대상 영역(얼굴 영역)에 대하여 적합한 프라이버시 보호 알고리즘(프라이버시 보호 적용 알고리즘)을 적용하여 "인식불능 영역을 갖는 보호처리 영상"(예를 들어, 얼굴 영역이 인식불능 상태로 변경된 영상)(이하, 경우에 따라, 간단히 "프라이버시 보호적용 영상", "보호처리된 영상", "보호처리 영상"이라 하기로 한다)을 생성하여 안전하게 저장/관리한다. 여기서, 프라이버시 보호 알고리즘(프라이버시 보호 적용 알고리즘)에는 암호화 방식, 스크램블링 방식 또는 마스킹 방식의 알고리즘이 포함된다. 또한, 보호 처리부(3122)는 저장/관리부(3123)가 클라이언트로부터 영상 요청을 받은 경우, 해당 영상(보호처리된 영상)에 대하여 적합한 프라이버시 보호 해제 알고리즘을 적용하여 원본 영상을 복원(생성)한다. 즉, 보호처리 영상의 인식불능 영역(예를 들어, 인식불능 상태에 있는 얼굴 영역)에 프라이버시 보호 해제 알고리즘을 적용하여 원본 영상을 복원(생성)한다.The protection processing unit 3122 applies an appropriate privacy protection algorithm (privacy protection application algorithm) to the protection target area (face area) detected by the face area detection unit 3121, and " protection image having unrecognized area " For example, an image in which a face region is changed to an unrecognized state (hereinafter, in some cases, simply referred to as "privacy protection image", "protected image", and "protection image") is generated and stored safely. Manage. Here, the privacy protection algorithm (privacy protection application algorithm) includes an algorithm of an encryption method, a scrambling method, or a masking method. In addition, when the storage / management unit 3123 receives an image request from the client, the protection processing unit 3122 restores (generates) the original image by applying an appropriate privacy protection release algorithm to the image (protected image). That is, the original image is reconstructed (generated) by applying a privacy protection release algorithm to an unrecognized region (eg, a face region in an unrecognized state) of the protected image.
저장/관리부(3123)는 보호 처리부(3122)에서 프라이버시 보호처리가 이루어진 영상(보호처리 영상)을 안전하게 저장/관리하며, 특히 이 저장된 영상에 대한 접근을 제어한다. 저장/관리부(3123)는 별도의 DVR(Digital Video Recorder) 서버를 통하여 영상을 저장할 수도 있다. The storage / management unit 3123 safely stores / manages an image (protection processing image) that has been subjected to privacy protection processing in the protection processing unit 3122, and in particular, controls access to the stored image. The storage / management unit 3123 may store an image through a separate DVR (Digital Video Recorder) server.
또한, 저장/관리부(3123)는 클라이언트(320)로부터 특정 영상에 대한 요청을 받으면, 안전하게 저장/관리되고 있는 해당 보호처리 영상(프라이버시 보호 처리가 적용된 상태에 있는 영상)을 찾아 영상 송신처리부(313)를 통하여 클라이언트(320)에 전송한다. 이에 따라, 클라이언트(320)로부터 얼굴 영상에 대한 보호 해제(프라이버시 보호 해제)를 요청받으면, 저장/관리부(3123)는 보호 처리부(3122)와의 연동을 통하여 복원 영상(프라이버시 보호 해제 영상)을 획득한 후 영상 송신처리부(313)를 통하여 클라이언트(320)에 전송한다. In addition, when the storage / management unit 3123 receives a request for a specific image from the client 320, the storage / management unit 3123 finds a corresponding protected processing image (an image in the state where privacy protection processing is applied) that is safely stored / managed, and then the image transmission processor 313. ) To the client 320. Accordingly, when a protection release (privacy protection release) for the face image is requested from the client 320, the storage / management unit 3123 obtains a reconstruction image (privacy protection release image) through interworking with the protection processing unit 3122. Thereafter, the image transmission processor 313 transmits the data to the client 320.
보호 해제와 관련하여 클라이언트(320)는 보호처리 영상 내에 존재하는 복수의 보호 영역 중에서 일부의 보호 영역에 대해서만 보호 해제 요청을 할 수 있는데, 이 경우의 구체적인 처리 방법에 대하여 설명하기로 한다. 클라이언트(320)가 해당 영상 내에 존재하는 프라이버시 보호된 n명의 사람들 중에서 프라이버시 제거(보호 해제)가 필요한 k(<n)명의 사람에 대한 얼굴 영상에 대해서만 보호 해제(프라이버시 보호 해제)를 요청한 경우, 저장/관리부(3123)는 보호 처리부(3122)와의 연동을 통하여 복원 영상(k명의 사람에 대한 프라이버시 보호 해제 영상)을 획득한 후 영상 송신처리부(313)를 통하여 클라이언트(320)에 전송한다. 이렇게 함으로써, 보호 해제의 대상이 되지 않았던 n-k명에 대해서는 프라이버시 보호가 유지되게 된다.In relation to the protection release, the client 320 may request the protection release only for a part of the protection areas among the plurality of protection areas existing in the protected image. A specific processing method in this case will be described. If the client 320 requests protection release (privacy protection) only for face images of k (<n) persons who need privacy removal (unprotection) among the n privacy-protected persons present in the image, The management unit 3123 acquires the reconstructed image (the privacy protection release image for k persons) through the interworking with the protection processor 3122, and transmits the reconstructed image to the client 320 through the image transmission processor 313. In this way, privacy protection is maintained for the n-k names that were not subject to protection.
실시예에 따라서는 저장/관리부(3123)가 클라이언트(320)로부터 "보호해제된 특정 영상"에 대한 요청을 받으면, 즉시 보호 처리부(3122)와의 연동을 통하여 복원 영상(프라이버시 보호 해제 영상)을 획득한 후 영상 송신처리부(313)를 통하여 클라이언트(320)에 전송한다.According to an exemplary embodiment, when the storage / management unit 3123 receives a request for a "unprotected specific image" from the client 320, the storage / management unit 3123 immediately acquires a reconstructed image (privacy protection release image) through interworking with the protection processing unit 3122. After that, the image transmission processor 313 transmits the data to the client 320.
한편, 영상 송신처리부(313)는 유/무선 네트워크를 통하여 클라이언트(320)에 영상을 송신하는 것으로서, 송신대상이 되는 영상을 암호화하여 전송한다. 즉, 영상 송신처리부(313)는 송신대상 영상을 암호화하는 암호화부(3131)와, 유/무선 네트워크를 통하여 클라이언트에 암호화된 영상을 송신하는 수신부(3132)를 포함하여 이루어진다.Meanwhile, the image transmission processor 313 transmits an image to the client 320 through a wired / wireless network, and encrypts and transmits an image to be transmitted. That is, the image transmission processor 313 includes an encryption unit 3131 for encrypting a transmission target image, and a receiver 3132 for transmitting an encrypted image to a client through a wired / wireless network.
한편, 클라이언트(320)는 사용자 단말에 해당하는 것으로서, 영상 감시/관제 서버(310)로부터 수신한 영상을 인증, ID(Identification) 관리, 범죄 예방, 증거 수집, 테러 예방, 접근 관리 등 다양한 목적에 맞게 활용한다. 영상 감시/관제 서버(310)와 클라이언트(320)의 상호 작용은 도 5에서 상세히 설명하기로 한다.On the other hand, the client 320 corresponds to a user terminal, the image received from the video surveillance / control server 310 for a variety of purposes, such as authentication, identification (ID) management, crime prevention, evidence collection, terrorism prevention, access management Use it accordingly. The interaction between the video surveillance / control server 310 and the client 320 will be described in detail with reference to FIG. 5.
도 4는 본 발명에 따른 도 3의 영상 보안 시스템의 각 구성요소에서 수행되는 보안 과정에 대한 전반적인 설명도로서, 영상 보안 시스템의 각 구성요소(즉, CCTV 카메라, 영상 감시/관제 서버, 클라이언트)에서 수행되는 프라이버시 관련 보안 기능과, 구성요소 상호 간에 수행되는 프라이버시 관련 보안 기능을 나타낸다.Figure 4 is a general description of the security process performed in each component of the video security system of Figure 3 according to the present invention, each component (ie CCTV camera, video surveillance / control server, client) of the video security system Shows the privacy-related security functions performed by and the privacy-related security functions performed by the components.
영상 보안 시스템의 각 구성요소에서의 보안 기능과 관련하여, (1)CCTV 카메라(300)에서는 영상 암호화(400), CCTV 전용인증서를 통한 기기 인증(401) 등이 수행되고, (2)영상 감시/관제 서버(310)에서는 영상 암/복호화(410), 영상 저장/관리 및 접근제어/인증(411), 얼굴영역 검출(412), 프라이버시 보호 적용/해제 영상 생성(413) 등이 수행되며, (3)클라이언트에서는 영상 복호화(420) 등이 수행된다.Regarding the security function in each component of the video security system, (1) the CCTV camera 300 performs video encryption 400, device authentication through a CCTV-only certificate (401), and (2) video surveillance. In the control server 310, image encryption / decryption 410, image storage / management and access control / authentication 411, face region detection 412, privacy protection application / release image generation 413, etc. are performed. (3) The client performs image decoding 420 or the like.
한편, 구성요소 상호 간에 수행되는 프라이버시 관련 보안 기능과 관련해서는 CCTV 카메라(300)와 영상 감시/관제 서버(310) 사이, 및 영상 감시/관제 서버(310)와 클라이언트(320) 사이에서는 암호화된 영상의 안전한 송/수신이 이루어진다(430, 440).On the other hand, in relation to the privacy-related security functions performed between the components between the CCTV camera 300 and the video surveillance / control server 310, and between the video surveillance / control server 310 and the client 320 encrypted image Secure transmission / reception of the connection is made (430, 440).
도 5는 본 발명에 따른 클라이언트가 프라이버시 보호해제된 영상을 획득하는 방법에 대한 일실시예 흐름도로서, 유/무선 통신망을 통하여 영상 감시/관제 서버와 클라이언트 사이에서 수행되는 처리 과정을 나타낸다.FIG. 5 is a flowchart illustrating a method of obtaining a privacy-protected image by a client according to the present invention, and illustrates a processing performed between the video surveillance / control server and the client through a wired / wireless communication network.
영상 감시/관제 서버(310)가 클라이언트(320)로부터 특정 영상에 대한 요청을 받으면(500), 안전하게 저장/관리되고 있는 해당 보호처리 영상(프라이버시 보호 처리가 적용된 상태에 있는 영상)을 검색하여 읽어 온 후(502), 이를 암호화하여(504) 클라이언트(320)에게 전송한다(506). When the video surveillance / control server 310 receives a request for a specific video from the client 320 (500), it searches for and reads the corresponding protected video (video in which privacy protection processing is applied) that is securely stored / managed. After on (502), it is encrypted (504) and sent to the client (320) (506).
그러면, 클라이언트(320)는 수신한 보호처리 영상을 복호화한 후(508) 자신이 필요로 하는 얼굴 영상을 검색하고(510), 그 검색된 얼굴 영상에 대한 보호 해제(프라이버시 보호 해제)를 영상 감시/관제 서버(310)에게 요청한다(512). 이미 도 3에서 상세히 설명한 바와 같이, 클라이언트(320)는 자신이 필요로 하는 얼굴 영상(즉, 보호처리된 복수의 얼굴 영상 중에서 일부의 얼굴 영상)에 대해서만 프라이버시 보호 해제 요청을 할 수 있다.Then, the client 320 decodes the received protection process image (508) and then retrieves the face image needed by the client (510), and monitors / unblocks the protection of the detected face image (privacy protection). Request to the control server 310 (512). As described above in detail with reference to FIG. 3, the client 320 may request a privacy protection release request for only a face image (ie, a face image of a plurality of protected face images) required by the client 320.
그에 따라, 영상 감시/관제 서버(310)는 프라이버시 보호해제 알고리즘을 이용하여 해당 얼굴 영상 정보를 복원한 후(514) 그 복원된 영상 정보를 암호화하여(516) 클라이언트(320)에게 안전하게 전송한다(518). Accordingly, the video surveillance / control server 310 restores the face image information using the privacy protection algorithm (514), encrypts the restored image information (516), and securely transmits it to the client (320). 518).
클라이언트(320)는 영상 감시/관제 서버(310)로부터 상기 요청한 영상을 수신하면, 그 수신된 영상을 복호화하여(520) 활용한다(522). When the client 320 receives the requested video from the video surveillance / control server 310, the client 320 decodes the received video (520) and utilizes the received video (522).
위의 "504" 및 "516" 과정을 통해서도 알 수 있듯이, 영상 감시/관제 서버(310)와 클라이언트(320) 사이의 데이터 송/수신은 안전하게 수행되어야 하는 바, 영상 감시/관제 서버(310)가 클라이언트(320)에게 전송하는 영상(프라이버시 보호처리 여부에 관계없이)에 대해서는 암호화를 수행하는 것이 바람직하다.As can be seen through the above "504" and "516" process, the data transmission / reception between the video surveillance / control server 310 and the client 320 should be performed safely, the video surveillance / control server 310 It is preferable to perform encryption on the image (regardless of whether privacy protection processing) is transmitted to the client 320.
한편, 실시예에 따라서는 영상 감시/관제 서버(310)가 클라이언트(320)로부터 "보호해제된 특정 영상"에 대한 요청을 받으면, "506" 내지 "510" 과정 없이 바로 해당 영상에 보호 해제 알고리즘(프라이버시 보호 해제 알고리즘)을 적용하여 원본 영상으로 복원하여 전송할 수도 있다.Meanwhile, according to the exemplary embodiment, when the video surveillance / control server 310 receives a request for the "unprotected specific video" from the client 320, the protection cancellation algorithm is immediately applied to the video without the process "506" to "510". By applying (Privacy Protection Release Algorithm), the original image can be restored and transmitted.
도 6은 본 발명에 따른 얼굴 영역 검출을 이용한 프라이버시 보호 프레임워크에 대한 일실시예 설명도로서, CCTV 환경에서 얼굴 영역 검출을 이용하여 개인정보를 보호하기 위한 보안 프레임워크를 나타낸다. 특히, 본 프레임워크는 보안기능별로 적용해야 할 보안 기술을 포함하고 있으며, 또한 CCTV 영상의 촬영부터 저장/활용까지의 과정에서 수행되는 프라이버시 보호 방안을 나타내는 바, 이하 이에 대하여 상세히 설명하기로 한다.FIG. 6 is an exemplary diagram illustrating a privacy protection framework using face region detection according to the present invention, and illustrates a security framework for protecting personal information using face region detection in a CCTV environment. In particular, the framework includes a security technology to be applied for each security function, and also shows a privacy protection method performed in the process of capturing and storing / using CCTV images, which will be described in detail below.
먼저, 데이터(영상정보를 포함함)의 암호화 및 복호화 방안에 대하여 설명하기로 한다.First, a method of encrypting and decrypting data (including image information) will be described.
CCTV 카메라(300)가 감시/보안 대상에 대한 영상을 촬영한 후 그 영상을 암호화하여 영상 감시/관제 서버(310)로 안전하게 전송하면, 영상 감시/관제 서버(310)는 수신한 암호화된 영상을 복호화한 후 적절한 처리절차(예를 들어, 프라이버시 보호 처리 등)를 거쳐 해당 영상을 저장한다.After the CCTV camera 300 captures the image of the surveillance / security target and encrypts the image and transmits the image to the video surveillance / control server 310 safely, the video surveillance / control server 310 receives the received encrypted image. After decoding, the image is stored through an appropriate processing procedure (for example, privacy protection processing).
또한, 클라이언트(320)가 영상 감시/관제 서버(310)에 영상을 요청하는 경우도 이와 마찬가지로 암호화/복호화 과정을 거치게 된다. 이때, 공인인증서, 공개키, 대칭키 기반의 암호화가 적용된다.In addition, when the client 320 requests an image from the video surveillance / control server 310, the client 320 undergoes an encryption / decryption process. At this time, encryption based on a certificate, a public key, and a symmetric key is applied.
다음은, 구성요소 간의 데이터(영상정보를 포함함) 송/수신 과정에서의 보안 방안에 대하여 설명하기로 한다.Next, a description will be given of the security method in the transmission / reception of data (including image information) between the components.
CCTV 카메라(300)와 영상 감시/관제 서버(310), 및 영상 감시/관제 서버(310)와 클라이언트(영상 요청자)(320) 간의 안전한 데이터 송수신을 위해서는 공인인증서/공개키/대칭키를 기반으로 한 SSL(Secure Socket Layer)/TLS(Transport Layer Security) 등과 같은 세션키 유도 및 안전한 채널 설정이나, X.509v3 기반의 기기인증 등을 통하여, 공격자로부터 도청, 위변조 등을 막을 수 있어야 한다.In order to securely transmit and receive data between the CCTV camera 300 and the video surveillance / control server 310 and the video surveillance / control server 310 and the client (video requestor) 320 based on the public certificate / public key / symmetric key. It should be able to prevent eavesdropping and forgery from attackers through derivation of session key such as Secure Socket Layer (SSL) / Transport Layer Security (TLS), secure channel setting, and X.509v3-based device authentication.
다음은, 영상 감시/관제 서버(310)에서의 얼굴 영역 검출 관련 방안을 설명하기로 한다.Next, a method of detecting a face region in the video surveillance / control server 310 will be described.
영상 감시/관제 서버(310)는 CCTV 카메라(300)로부터 수신한 암호화된 영상을 복호화한 후, 적합한 얼굴 영역 검출 알고리즘을 기반으로 얼굴 영역 검출 과정을 수행함으로써 프라이버시를 보호하는데, 얼굴 영역 검출 알고리즘에는 지식기반 방법, 특징기반 방법, 탬플릿 매칭 방법, 외형기반 방법 등이 있다.The video surveillance / control server 310 decrypts the encrypted image received from the CCTV camera 300 and protects privacy by performing a face region detection process based on a suitable face region detection algorithm. Knowledge-based, feature-based, template matching, and appearance-based methods.
다음은, 영상 감시/관제 서버(310)에서의 프라이버시 보호 처리 및 보호 해제 방안에 대하여 설명하기로 한다.Next, a privacy protection process and a protection releasing method in the video surveillance / control server 310 will be described.
개인 영상 정보에 대한 프라이버시 보호를 제공하기 위해서는 얼굴 영역 검출 기법을 통해서 검출된 얼굴 영상에 적합한 프라이버시 보호 알고리즘(프라이버시 레벨(강도) 조절 가능)을 사용하여 보호처리 영상(프라이버시 보호처리 영상)을 생성한다. 여기서, 프라이버시 보호 처리 기법에는 암호화 기법, 스크램블링 기법, 마스킹 기법 등이 있으며, 특히, 카오틱 기반의 스크램블링 기법에 대해서는 도 8a에서 상세히 설명하기로 한다.In order to provide privacy protection for personal image information, a protected image (privacy protection image) is generated using a privacy protection algorithm (privacy level adjustment) suitable for a face image detected through a face region detection technique. . Here, the privacy protection processing techniques include encryption techniques, scrambling techniques, masking techniques, and the like, and in particular, chaotic based scrambling techniques will be described in detail with reference to FIG. 8A.
영상 감시/관제 서버(310)는 저장 매체에 저장되어 관리되는 영상에 대해 복호화를 수행한 후, 적합한 프라이버시 보호해제 알고리즘을 적용함으로써, 얼굴 영역을 인지(인식)할 수 있는 보호해제 영상(프라이버시 보호해제 영상)을 생성한다. 여기서, 프라이버시 보호해제 기법에는 복호화 기법, 역스크램블링 기법, 역마스킹 기법 등이 있으며, 특히, 역스크램블링 기법에 대해서는 도 8b에서 상세히 설명하기로 한다.The video surveillance / control server 310 decodes an image stored and managed in a storage medium, and then applies an appropriate privacy protection algorithm to thereby detect (recognize) a face region (privacy protection). Release image). Here, the privacy protection technique includes a decryption technique, a reverse scrambling technique, a reverse masking technique, and the like. In particular, the reverse scrambling technique will be described in detail with reference to FIG. 8B.
다음은, 영상 감시/관제 서버(310)에서의 영상 저장/관리 및 접근제어 방안에 대하여 설명하기로 한다.Next, an image storage / management and access control method in the video surveillance / control server 310 will be described.
영상 감시/관제 서버(310)는 프라이버시 보호 알고리즘을 통해 생성된 영상 정보에 대해서는 안전한 영상 저장/관리 방법들을 적용하여 저장/관리한다. 이때, 접근 제어, 워터마킹 인코딩 기법, 스테가노그래피 인코딩 기법, 암호화 기법, 얼굴 영상 분리저장 기법, 의도적 화질 저하 인코딩 기법, 음성 변조를 적용한 영상 저장 기법 등을 적용할 수 있다.The video surveillance / control server 310 stores / manages the video information generated through the privacy protection algorithm by applying safe video storage / management methods. At this time, access control, watermarking encoding technique, steganography encoding technique, encryption technique, face image separation storage technique, intentional deterioration encoding technique, image storage technique using speech modulation, etc. may be applied.
영상 감시/관제 서버(310)가 클라이언트(320)로부터 특정 영상에 대한 요청을 받으면, 안전한 영상 읽기 알고리즘을 적용하여 해당 영상을 디코딩한다. 이때에도 접근 제어, 워터마킹 디코딩, 스테가노그래피 디코딩, 복호화, 분리된 얼굴 영상 복원, 의도적 화질 저하 영상 디코딩, 음성 변조 복원을 적용한 영상 복원 등의 기법이 적용될 수 있다. 특히, CCTV 기기 인증을 위해서는 기기 식별 및 인증 등을 제공하는 X.509v3 기기인증 기법을 적용할 수 있다. When the video surveillance / control server 310 receives a request for a specific video from the client 320, the video monitoring / control server 310 applies a secure video reading algorithm to decode the video. In this case, techniques such as access control, watermark decoding, steganography decoding, decoding, separate face image restoration, intentional deterioration image decoding, and image restoration using speech modulation restoration may be applied. In particular, X.509v3 device authentication techniques that provide device identification and authentication can be applied for CCTV device authentication.
도 7a는 본 발명에 따른 프라이버시 보호처리 영상을 생성하는 방법에 대한 일실시예 흐름도로서, 영상 감시/관제 서버(310)가 얼굴 검출과 스크램블링을 통하여 프라이버시 보호 처리를 수행하는 과정을 나타낸다.FIG. 7A is a flowchart illustrating a method of generating a privacy protection processing image according to an exemplary embodiment of the present invention, and illustrates a process in which the video surveillance / control server 310 performs privacy protection processing through face detection and scrambling.
영상 감시/관제 서버(310)는 영상 수집 장치(300)에 해당하는 CCTV 카메라가 송신하는 영상 정보를 캡쳐(capture) 하고(700), 그 캡쳐된 영상 정보에서 얼굴 영역을 검출한다(702).The image surveillance / control server 310 captures image information transmitted by the CCTV camera corresponding to the image acquisition apparatus 300 (700), and detects a face region from the captured image information (702).
이후, 영상 감시/관제 서버(310)는 검출된 얼굴에서 대하여 스크램블링 기법을 적용하고(704), 그 결과로 생성된 "스크램블링된 영상"(보호처리된 영상)을 저장/관리부(3123) 또는 DVR 서버(별도의 외부 저장 서버에 영상을 저장한 경우)에 저장한다(706).Thereafter, the video surveillance / control server 310 applies a scrambling technique to the detected face (704), and stores the resulting “scrambled video” (protected video) in the storage / management unit 3123 or the DVR. The image data is stored in the server (when the image is stored in a separate external storage server) (706).
도 7b는 본 발명에 따른 프라이버시 보호해제 영상을 생성하는 방법에 대한 일실시예 흐름도로서, 영상 감시/관제 서버(310)가 역스크램블링을 통하여 프라이버시 보호 해제를 수행하는 과정을 나타낸다.FIG. 7B is a flowchart illustrating a method of generating a privacy deprotection image according to an exemplary embodiment of the present invention, and illustrates a process in which the image monitoring / control server 310 performs privacy deprotection through reverse scrambling.
영상 감시/관제 서버(310)는 저장/관리부(3123) 또는 DVR 서버(별도의 외부 저장 서버에 영상을 저장한 경우로서, 도면에는 도시되지 않았음)에 저장되어 있는 해당 영상(보호처리된 영상)을 불러와(710), 스크램블링을 적용할 때 저장한 얼굴 위치 정보를 읽는다(712).The video surveillance / control server 310 is a video stored in a storage / management unit 3123 or a DVR server (a case where an image is stored in a separate external storage server, which is not shown in the figure) (protected video). In step 710, the stored face position information is read (712) when the scrambling is applied.
다음으로, 영상 감시/관제 서버(310)는 얼굴 위치 정보를 이용하여 역스크램블링을 적용하고(714), 그 결과로 생성된 영상(역스크램블링된 영상, 즉 보호해제된 영상)을 저장한다(716).Next, the video surveillance / control server 310 applies descrambling using the face position information (714) and stores the resulting image (descrambled image, that is, unprotected image) (716). ).
도 8a는 본 발명에 적용되는 영상 스크램블링 방법에 대한 흐름도로서, 영상 감시/관제 서버(310)가 수행하는 카오틱 기반의 스크램블링 과정(800)을 나타낸다.FIG. 8A is a flowchart illustrating an image scrambling method applied to the present invention, and illustrates a chaotic based scrambling process 800 performed by the video surveillance / control server 310.
영상 스크램블링은 입력 키와 원본 영상을 입력으로 하여, 영상 위치 또는 픽셀의 색상을 복잡하게 함으로써 원본 영상이 인식될 수 없게 하는 것이다. 그러나, 필요에 따라, 특정한 알고리즘(역 알고리즘)에 의하여 원본 영상을 재생성할 수 있어야 한다. 이러한 영상 스크램블링 기법에는 카오틱 맵 시스템을 기반한 방법과 아놀드 트랜스폼 등 다양한 기법들이 있다.Image scrambling is an input key and an original image as inputs, which makes the original image unrecognizable by complicating the image position or pixel color. However, if necessary, it should be possible to reproduce the original image by a specific algorithm (inverse algorithm). Such image scrambling techniques include various methods such as a method based on a chaotic map system and an Arnold transform.
영상 감시/관제 서버(310)는 입력 키(Key)와 스크램블링 대상이 되는 영상(원본 영상)을 입력받으면, 로지스틱스 맵 함수를 사용하여 카오틱 순서를 획득하고(801), 상기 획득된 카오틱 순서를 정렬하여 스크램블링 테이블을 획득한다(802).When the video surveillance / control server 310 receives an input key and an image (original image) to be scrambling, the video surveillance / control server 310 obtains a chaotic sequence using a logistic map function (801), and obtains the chaotic sequence. Arrange 802 to obtain a scrambling table.
그리고 나서, 영상 감시/관제 서버(310)는 스크램블링 테이블을 이용하여 원본 영상의 픽셀들의 위치를 변경함으로써 스크램블링 영상(프라이버시 보호 영상)을 출력(생성)한다(803).Then, the image monitoring / control server 310 outputs (generates) the scrambling image (privacy protection image) by changing the position of the pixels of the original image using the scrambling table (803).
도 8b는 본 발명에 적용되는 영상 역스크램블링 방법에 대한 흐름도로서, 영상 감시/관제 서버(310)가 수행하는 카오틱 기반의 역스크램블링 과정(810)을 나타낸다.FIG. 8B is a flowchart illustrating a video descrambling method applied to the present invention, and illustrates a chaotic-based descrambling process 810 performed by the video surveillance / control server 310.
영상 감시/관제 서버(310)는 입력 키(Key)와 역스크램블링 대상이 되는 영상(보호처리된 영상)을 입력받으면, 로지스틱스 맵 함수를 사용하여 카오틱 순서를 획득하고(811), 상기 획득된 카오틱 순서를 정렬하여 역스크램블링 테이블을 획득한다(812).When the video surveillance / control server 310 receives an input key and an image (protected image) to be descrambling, the video surveillance / control server 310 obtains a chaotic sequence using a logistic map function (811). The descrambling table is obtained by sorting the chaotic order (812).
그리고 나서, 영상 감시/관제 서버(310)는 역스크램블링 테이블을 이용하여 역스크램블링 대상 영상의 픽셀들의 위치를 변경함으로써 역스크램블링 영상(프라이버시 보호 해제 영상)을 출력(생성)한다(813).Then, the image monitoring / control server 310 outputs (generates) a descrambling image (privacy protection release image) by changing the position of pixels of the descrambling target image using the descrambling table (813).
한편, 전술한 바와 같은 본 발명의 방법은 컴퓨터 프로그램으로 작성이 가능하다. 그리고 상기 프로그램을 구성하는 코드 및 코드 세그먼트는 당해 분야의 컴퓨터 프로그래머에 의하여 용이하게 추론될 수 있다. 또한, 상기 작성된 프로그램은 컴퓨터가 읽을 수 있는 기록매체(정보저장매체)에 저장되고, 컴퓨터에 의하여 판독되고 실행됨으로써 본 발명의 방법을 구현한다. 그리고 상기 기록매체는 컴퓨터가 판독할 수 있는 모든 형태의 기록매체를 포함한다.On the other hand, the method of the present invention as described above can be written in a computer program. And the code and code segments constituting the program can be easily inferred by a computer programmer in the art. In addition, the written program is stored in a computer-readable recording medium (information storage medium), and read and executed by a computer to implement the method of the present invention. The recording medium may include any type of computer readable recording medium.
이상에서 설명한 본 발명은, 본 발명이 속하는 기술 분야에서 통상의 지식을 가진 자에게 있어 본 발명의 기술적 사상을 벗어나지 않는 범위 내에서 여러 가지 치환, 변형 및 변경이 가능하므로 전술한 실시예 및 첨부된 도면에 의해 한정되는 것이 아니다.The present invention described above is capable of various substitutions, modifications, and changes without departing from the technical spirit of the present invention for those skilled in the art to which the present invention pertains. It is not limited by the drawings.
발명은 CCTV 감시 시스템을 통하여 수집된 영상에서 프라이버시 보호가 필요한 영역(특히, 사람의 얼굴 영역 등)만을 부분적으로 보호 처리하여 저장/관리하고, 필요에 따라 원래의 인식 가능한 영상으로 복원(보호 해제)하여 활용하기 때문에, 감시 시스템의 본래 목적이나 순기능을 그대로 달성/유지하면서도 의도하지 않은 개인 정보의 유출이나 프라이버시 침해를 효율적으로 방지할 수 있는 효과를 갖는 프라이버시 보호를 위한 영상 보호처리 장치와 이를 이용한 영상 보안 시스템 및 방법으로 채용될 수 있다.The present invention partially protects and stores / manages only the areas requiring privacy protection (especially human face areas, etc.) from images collected through a CCTV surveillance system, and restores the original recognizable image as necessary (unprotection). Because it is used to maintain and maintain the original purpose or pure function of the surveillance system, the image protection processing device for privacy protection and the image using the same can effectively prevent unintended leakage of personal information or invasion of privacy. It can be employed as a security system and method.
Claims (17)
- 프라이버시 보호를 위한 영상 보호처리 장치에 있어서,In the image protection processing device for privacy protection,수집 영상으로부터 보호대상 영역을 검출하기 위한 검출 수단;Detection means for detecting a region to be protected from the collected image;상기 검출된 보호대상 영역에 프라이버시 보호 알고리즘을 적용하여 인식불능 영역을 갖는 보호처리 영상을 생성하기 위한 보호 처리 수단; 및Protection processing means for generating a protected image having an unrecognized area by applying a privacy protection algorithm to the detected protected area; And상기 생성된 보호처리 영상을 저장/관리하기 위한 관리 수단Management means for storing / managing the generated protected image을 포함하는 영상 보호처리 장치.Image protection processing device comprising a.
- 제 1 항에 있어서,The method of claim 1,상기 보호 처리 수단은,The protection processing means,클라이언트로부터 보호해제 요청된 해당 보호처리 영상에 대하여 프라이버시 보호 해제 알고리즘을 적용하여 원본 영상을 복원하는 기능을 더 수행하되, 일부의 보호대상 영역에 대한 보호해제 요청에 대해서는 해당 일부 영역에 한정하여 상기 프라이버시 보호 해제 알고리즘을 적용하는 것을 특징으로 하는 영상 보호처리 장치.The method further restores the original image by applying a privacy protection algorithm to the corresponding protected image requested to be released from the client. An image protection processing device, characterized by applying a protection release algorithm.
- 제 2 항에 있어서,The method of claim 2,상기 저장/관리 수단은,The storage / management means,저장된 영상에 대한 접근 제어를 수행하고, 상기 클라이언트의 보호해제 요청에 따라 프라이버시 보호 해제를 위하여 상기 보호처리 수단과 연동하는 것을 특징으로 하는 영상 보호처리 장치.And controlling the access to the stored image and interworking with the protection processing means for releasing privacy protection according to the client's protection release request.
- 제 3 항에 있어서,The method of claim 3, wherein상기 저장/관리 수단은,The storage / management means,상기 클라이언트로부터의 특정 영상의 요청에 따라 해당 보호처리 영상을 검색하여 영상 송신처리부를 통해 상기 클라이언트에 전송하고, 상기 클라이언트로부터 영상의 특정 영역에 대한 보호해제를 요청받음에 따라 상기 보호처리 수단에 의하여 복원된 원본 영상을 상기 영상 송신처리부를 통해 상기 클라이언트에 전송하는 것을 특징으로 하는 영상 보호처리 장치.In response to a request for a specific image from the client, the protected processing image is searched for and transmitted to the client through an image transmission processor, and the protection processing means is requested by the client to release the protection of a specific region of the image. And a restored original image is transmitted to the client through the image transmission processor.
- 제 1 항 내지 제 4 항 중 어느 한 항에 있어서,The method according to any one of claims 1 to 4,상기 검출 수단은,The detection means,바이오 인식 기술을 이용하여 상기 수집 영상으로부터 사람 얼굴영역을 검출하는 것을 특징으로 하는 영상 보호처리 장치.And a human face region is detected from the collected image by using biometric technology.
- 제 5 항에 있어서,The method of claim 5,상기 검출 수단은,The detection means,지식기반 방식, 특징기반 방식, 탬플릿 매칭 방식, 및 외형기반 방식 중 어느 하나의 검출 방식을 적용하여 상기 사람 얼굴영역을 검출하는 것을 특징으로 하는 영상 보호처리 장치.And a human face region is detected by applying any one of a knowledge-based method, a feature-based method, a template matching method, and an appearance-based method.
- 제 1 항 내지 제 4 항 중 어느 한 항에 있어서,The method according to any one of claims 1 to 4,상기 프라이버시 보호 알고리즘은,The privacy protection algorithm,암호화 방식, 카오틱 기반 스크램블링 방식 또는 마스킹 방식 중 어느 하나의 방식에 해당하는 것을 특징으로 하는 영상 보호처리 장치.The image protection processing device, characterized in that any one of an encryption method, chaotic based scrambling method or a masking method.
- 프라이버시 보호를 이용한 영상 보안 시스템에 있어서,In the video security system using privacy protection,특정 보안대상에 대한 영상을 수집하여 암호화하기 위한 영상 수집 수단; 및Image collection means for collecting and encrypting an image for a specific security target; And상기 영상 수집 수단으로부터 수신된 암호화 영상을 복호화하고, 상기 복호화된 수집 영상에서 보호대상 영역을 검출하여 프라이버시 보호 알고리즘을 적용하기 위한 영상 감시/관제 수단Image monitoring / control means for decoding the encrypted image received from the image collecting means, detecting a protected area from the decoded collected image and applying a privacy protection algorithm.을 포함하는 영상 보안 시스템.Image security system comprising a.
- 제 8 항에 있어서,The method of claim 8,상기 영상 수집 수단은,The image collecting means,폐쇄회로 텔레비젼(CCTV) 카메라인 것을 특징으로 하는 영상 보안 시스템.A video security system, characterized in that it is a closed circuit television (CCTV) camera.
- 제 8 항에 있어서,The method of claim 8,상기 보호대상 영역은,The protected area,사람의 얼굴 영역인 것을 특징으로 하는 영상 보안 시스템.A video security system, characterized in that the human face area.
- 제 8 항 내지 제 10 항 중 어느 한 항에 있어서,The method according to any one of claims 8 to 10,상기 영상 감시/관제 수단은,The video surveillance / control means,상기 영상 수집 수단으로부터 암호화 영상을 수신하여 복호화하기 위한 영상 수신처리 수단; 및Image receiving processing means for receiving and decoding an encrypted image from the image collecting means; And상기 복호화된 영상에서 보호대상 영역을 검출하고, 상기 검출된 보호대상 영역에 프라이버시 보호 알고리즘을 적용하여 인식불능 영역을 갖는 보호처리 영상을 생성하여 저장/관리하기 위한 영상 보호처리 수단Image protection processing means for detecting a protected area from the decoded image, and generating and storing / managing a protected image having an unrecognized area by applying a privacy protection algorithm to the detected protected area.을 포함하는 영상 보안 시스템.Image security system comprising a.
- 제 11 항에 있어서,The method of claim 11,상기 영상 수신처리 수단은,The video receiving processing means,상기 영상 수집 수단이 보유한 전용 인증서를 통하여 기기 인증을 수행하는 것을 특징으로 하는 영상 보안 시스템.And a device authentication through a dedicated certificate held by the video collecting means.
- 제 11 항에 있어서,The method of claim 11,상기 영상 보호처리 수단은,The image protection processing means,클라이언트로부터 보호해제 요청된 해당 보호처리 영상에 대하여 프라이버시 보호 해제 알고리즘을 적용하여 원본 영상을 복원하는 기능을 더 수행하되, 일부의 보호대상 영역에 대한 보호해제 요청에 대해서는 해당 일부 영역에 한정하여 상기 프라이버시 보호 해제 알고리즘을 적용하는 것을 특징으로 하는 영상 보안 시스템.The method further restores the original image by applying a privacy protection release algorithm to the corresponding protected image requested to be released from the client. A video security system, characterized by applying a protection release algorithm.
- 제 13 항에 있어서,The method of claim 13,상기 복원된 원본 영상을 암호화하여 상기 클라이언트에게 전송하기 위한 영상 송신처리 수단Image transmission processing means for encrypting the restored original image and transmitting it to the client을 더 포함하는 영상 보안 시스템.Video security system further comprising.
- 제 14 항에 있어서,The method of claim 14,상기 영상 보호처리 수단은,The image protection processing means,상기 클라이언트로부터의 특정 영상의 요청에 따라 해당 보호처리 영상을 검색하여 상기 영상 송신처리 수단으로 전달하고, 상기 클라이언트로부터 영상의 특정 영역에 대한 보호해제를 요청받음에 따라 상기 복원된 원본 영상을 상기 영상 송신처리 수단으로 전달하는 것을 특징으로 하는 영상 보안 시스템.In response to a request for a specific video from the client, the corresponding protected video is searched and transmitted to the video transmission processing means, and the restored original video is transmitted to the video when the client is requested to release protection for a specific area of the video. Video security system, characterized in that the transmission to the transmission processing means.
- 프라이버시 보호를 위한 영상 보안 방법에 있어서,In the video security method for privacy protection,보안 대상에 대하여 수집된 영상으로부터 보호대상 영역을 검출하는 단계;Detecting a region to be protected from an image collected for the security object;상기 검출된 보호대상 영역에 프라이버시 보호 알고리즘을 적용하여 인식불능 영역을 갖는 보호처리 영상을 생성하여 저장/관리하는 단계; 및Generating and storing / managing a protected image having an unrecognized area by applying a privacy protection algorithm to the detected protected area; And클라이언트의 보호해제 요청에 따라, 해당 보호처리 영상에 대하여 프라이버시 보호 해제 알고리즘을 적용하여 원본 영상을 복원하는 단계Restoring the original image by applying a privacy protection algorithm to the protected image according to the client's request to release protection;를 포함하는 영상 보안 방법.Image security method comprising a.
- 제 16 항에 있어서,The method of claim 16,상기 원본 영상을 복원하는 단계는,Restoring the original image,일부의 보호대상 영역에 대한 보호해제 요청에 대해서는 해당 일부 영역에 한정하여 상기 프라이버시 보호 해제 알고리즘을 적용하는 것을 특징으로 하는 영상 보안 방법.The method of claim 1, wherein the privacy protection algorithm is applied to the protection release request for a portion of the protected area.
Applications Claiming Priority (2)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
KR10-2010-0096708 | 2010-10-05 | ||
KR1020100096708A KR20120035299A (en) | 2010-10-05 | 2010-10-05 | Image protection processing apparatus for privacy protection, and image security system and method using the same |
Publications (1)
Publication Number | Publication Date |
---|---|
WO2012046907A1 true WO2012046907A1 (en) | 2012-04-12 |
Family
ID=45927885
Family Applications (1)
Application Number | Title | Priority Date | Filing Date |
---|---|---|---|
PCT/KR2010/007262 WO2012046907A1 (en) | 2010-10-05 | 2010-10-22 | Apparatus for processing an image in a manner which protects privacy, image security system using same, and method therefor |
Country Status (2)
Country | Link |
---|---|
KR (1) | KR20120035299A (en) |
WO (1) | WO2012046907A1 (en) |
Cited By (13)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN105141922A (en) * | 2015-09-02 | 2015-12-09 | 广东美的制冷设备有限公司 | Security monitoring method based on air conditioner and air conditioner |
CN108540742A (en) * | 2018-04-13 | 2018-09-14 | 广州卫软信息科技有限公司 | A kind of medical image audio and video recording system |
EP3461100A1 (en) * | 2017-09-21 | 2019-03-27 | Hanwha Techwin Co., Ltd. | Authenticating a networked camera using a certificate having device binding information |
CN109753921A (en) * | 2018-12-29 | 2019-05-14 | 上海交通大学 | A Face Feature Vector Privacy-Preserving Recognition Method |
CN110941806A (en) * | 2019-11-29 | 2020-03-31 | 徐州科睿安防科技有限公司 | Privacy protection security system for office area |
CN111429330A (en) * | 2020-03-31 | 2020-07-17 | 上海兑观信息科技技术有限公司 | Method and system for protecting privacy of monitoring video |
CN113160348A (en) * | 2021-05-20 | 2021-07-23 | 深圳文达智通技术有限公司 | Recoverable face image privacy protection method, device, equipment and storage medium |
CN113312660A (en) * | 2021-05-06 | 2021-08-27 | 北京航空航天大学 | Remote monitoring privacy protection method and system based on computer vision |
CN113705485A (en) * | 2021-08-31 | 2021-11-26 | 贵州东冠科技有限公司 | System and method for recognizing life hygiene image of user |
CN114727071A (en) * | 2022-06-08 | 2022-07-08 | 中航智能建设(深圳)有限公司 | Smart park data transmission method and system |
CN115376542A (en) * | 2022-08-22 | 2022-11-22 | 西南科技大学 | Low-invasiveness audio-visual voice separation method and system |
CN117672026A (en) * | 2024-01-31 | 2024-03-08 | 安徽渔之蓝教育软件技术有限公司 | Educational service question-answering dialogue system with privacy protection |
CN119854426A (en) * | 2025-03-17 | 2025-04-18 | 长安大学 | Blind extraction method, device and equipment for privacy information of thumbnail-maintained encrypted image |
Families Citing this family (18)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
KR101460552B1 (en) * | 2013-09-04 | 2014-11-11 | 엠엠피씨 주식회사 | Masking and Recovering Method of Privacy Region |
WO2016010328A1 (en) * | 2014-07-14 | 2016-01-21 | 넥시스 주식회사 | Information processing system and method using wearable device |
KR101639258B1 (en) | 2015-01-19 | 2016-07-14 | 주식회사 아이디스 | Apparatus and method for protecting personal information of recorded image, and computer-readable recording medium having thereon computer program for performing the same |
US9454675B2 (en) | 2015-01-26 | 2016-09-27 | Idis Co., Ltd. | Apparatus and method for protecting personal information of recorded image, and computer-readable recording medium having computer program recorded therein |
KR101538064B1 (en) * | 2015-02-05 | 2015-07-22 | (주)씨앤에스아이 | System for controling image and method for sharing and transmitting of video using the same |
KR101695655B1 (en) | 2016-02-23 | 2017-01-12 | 이정선 | Method and apparatus for analyzing video and image |
KR101677111B1 (en) * | 2016-03-14 | 2016-11-17 | 주식회사우경정보기술 | Dynamic image object privacy protection device and the method of detecting the face of the pedestrian based |
KR102561306B1 (en) | 2016-12-01 | 2023-07-31 | 한화비전 주식회사 | Apparatus and method for processing image |
KR101952623B1 (en) * | 2017-09-14 | 2019-02-27 | (주)글루버 | Method and apparatus for video service with privacy protection |
KR102066778B1 (en) * | 2017-12-29 | 2020-01-15 | 경일대학교산학협력단 | Image processing system comprising image transmitter and image receiver based on internet of things, and image processing method using the same |
KR102078265B1 (en) * | 2018-01-10 | 2020-02-19 | 주식회사 티제이원 | Aapparatus of processing image and method of providing image thereof |
KR102524220B1 (en) * | 2018-04-26 | 2023-04-24 | 한국전자통신연구원 | Layered protecting apparatus and system for multiple video objects based on neural network learning and method thereof |
KR102200865B1 (en) * | 2018-12-26 | 2021-01-11 | 인하대학교 산학협력단 | System and method for the privacy protection of image data |
KR102281601B1 (en) * | 2019-08-09 | 2021-07-23 | 엘지전자 주식회사 | System on chip, method and apparatus for protecting information using the same |
KR102129031B1 (en) * | 2020-02-27 | 2020-07-02 | 주식회사 지란지교데이터 | Method and device for de-identifying security information in video |
KR102454677B1 (en) * | 2021-01-25 | 2022-10-17 | 주식회사 노타 | Encryption key-based video personal information de-identification and restoration technology |
KR102371391B1 (en) * | 2021-04-07 | 2022-03-08 | (주)아이엠시티 | License platae recognition system using ai and operation method thereof |
KR102814068B1 (en) * | 2024-07-19 | 2025-05-30 | 주식회사 포커스에이아이 | AI-based resident safety management system and controlling method for the same |
Citations (3)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
KR20000056643A (en) * | 1999-02-24 | 2000-09-15 | 윤종용 | Screen hiding apparatus and method for particular part of digital still camera |
KR20060093242A (en) * | 2005-02-21 | 2006-08-24 | 삼성전자주식회사 | Surveillance system to mask privacy area and mask area setting method |
KR20070048841A (en) * | 2005-11-07 | 2007-05-10 | 엘지전자 주식회사 | Control method of privacy mask display of surveillance camera |
-
2010
- 2010-10-05 KR KR1020100096708A patent/KR20120035299A/en not_active Ceased
- 2010-10-22 WO PCT/KR2010/007262 patent/WO2012046907A1/en active Application Filing
Patent Citations (3)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
KR20000056643A (en) * | 1999-02-24 | 2000-09-15 | 윤종용 | Screen hiding apparatus and method for particular part of digital still camera |
KR20060093242A (en) * | 2005-02-21 | 2006-08-24 | 삼성전자주식회사 | Surveillance system to mask privacy area and mask area setting method |
KR20070048841A (en) * | 2005-11-07 | 2007-05-10 | 엘지전자 주식회사 | Control method of privacy mask display of surveillance camera |
Cited By (17)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN105141922A (en) * | 2015-09-02 | 2015-12-09 | 广东美的制冷设备有限公司 | Security monitoring method based on air conditioner and air conditioner |
CN105141922B (en) * | 2015-09-02 | 2018-10-02 | 广东美的制冷设备有限公司 | Security-protecting and monitoring method based on air-conditioning and air conditioner |
EP3461100A1 (en) * | 2017-09-21 | 2019-03-27 | Hanwha Techwin Co., Ltd. | Authenticating a networked camera using a certificate having device binding information |
CN108540742A (en) * | 2018-04-13 | 2018-09-14 | 广州卫软信息科技有限公司 | A kind of medical image audio and video recording system |
CN109753921A (en) * | 2018-12-29 | 2019-05-14 | 上海交通大学 | A Face Feature Vector Privacy-Preserving Recognition Method |
CN110941806A (en) * | 2019-11-29 | 2020-03-31 | 徐州科睿安防科技有限公司 | Privacy protection security system for office area |
CN111429330A (en) * | 2020-03-31 | 2020-07-17 | 上海兑观信息科技技术有限公司 | Method and system for protecting privacy of monitoring video |
CN113312660A (en) * | 2021-05-06 | 2021-08-27 | 北京航空航天大学 | Remote monitoring privacy protection method and system based on computer vision |
CN113160348A (en) * | 2021-05-20 | 2021-07-23 | 深圳文达智通技术有限公司 | Recoverable face image privacy protection method, device, equipment and storage medium |
CN113705485A (en) * | 2021-08-31 | 2021-11-26 | 贵州东冠科技有限公司 | System and method for recognizing life hygiene image of user |
CN113705485B (en) * | 2021-08-31 | 2024-04-05 | 贵州东冠科技有限公司 | System and method for identifying life hygiene image of user |
CN114727071A (en) * | 2022-06-08 | 2022-07-08 | 中航智能建设(深圳)有限公司 | Smart park data transmission method and system |
CN114727071B (en) * | 2022-06-08 | 2022-08-09 | 中航智能建设(深圳)有限公司 | Smart park data transmission method and system |
CN115376542A (en) * | 2022-08-22 | 2022-11-22 | 西南科技大学 | Low-invasiveness audio-visual voice separation method and system |
CN117672026A (en) * | 2024-01-31 | 2024-03-08 | 安徽渔之蓝教育软件技术有限公司 | Educational service question-answering dialogue system with privacy protection |
CN117672026B (en) * | 2024-01-31 | 2024-04-19 | 安徽渔之蓝教育软件技术有限公司 | Educational service question-answering dialogue system with privacy protection |
CN119854426A (en) * | 2025-03-17 | 2025-04-18 | 长安大学 | Blind extraction method, device and equipment for privacy information of thumbnail-maintained encrypted image |
Also Published As
Publication number | Publication date |
---|---|
KR20120035299A (en) | 2012-04-16 |
Similar Documents
Publication | Publication Date | Title |
---|---|---|
WO2012046907A1 (en) | Apparatus for processing an image in a manner which protects privacy, image security system using same, and method therefor | |
KR101320350B1 (en) | Secure management server and video data managing method of secure management server | |
CN111274578B (en) | Data safety protection system and method for video monitoring system | |
US8677132B1 (en) | Document security | |
US7792296B2 (en) | Access-controlled encrypted recording method for site, interaction and process monitoring | |
WO2018101727A1 (en) | Personal information infringement prevention method and system, in which biometric authentication and phase division of authentication process are combined | |
WO2013048111A2 (en) | Method and apparatus for detecting an intrusion on a cloud computing service | |
US7774023B2 (en) | System and method for associating device information with digital images | |
WO2014193058A1 (en) | Device and method for providing security in remote digital forensic environment | |
KR100917453B1 (en) | Image information processing apparatus and method | |
KR101951605B1 (en) | Cctv image security system to prevent image leakage | |
WO2020067734A1 (en) | Non-address network equipment and communication security system using same | |
WO2017105049A1 (en) | Digital forensic image verification system | |
CN107947937A (en) | A kind of safe audio-video encryption system and terminal authentication implementation method | |
WO2017052240A1 (en) | Duplicate image evidence management system for verifying authenticity and integrity | |
CN115499844A (en) | Mobile terminal information safety protection system and method | |
Han et al. | The privacy protection framework for biometric information in network based CCTV environment | |
KR101847618B1 (en) | Method for privacy object masking and key management for user authentication in video surveillance system and video surveillance system using the same | |
KR102530406B1 (en) | System and method for processing video data to protect personal information based on blockchain | |
WO2016125974A1 (en) | Integrated image control system, and image transmitting and sharing method using same | |
WO2019103443A1 (en) | Method, apparatus and system for managing electronic fingerprint of electronic file | |
CN107315974A (en) | A kind of image-forming media protection device based on Internet of Things | |
WO2021025185A1 (en) | Apparatus and method for encoding whitebox cryptography by using anti-inversion function | |
WO2015026183A1 (en) | Offline log-in method using sw token and mobile device employing said method | |
KR101803963B1 (en) | Image Recording Apparatus for Securing Admissibility of Evidence about Picked-up Image |
Legal Events
Date | Code | Title | Description |
---|---|---|---|
121 | Ep: the epo has been informed by wipo that ep was designated in this application |
Ref document number: 10858183 Country of ref document: EP Kind code of ref document: A1 |
|
NENP | Non-entry into the national phase |
Ref country code: DE |
|
122 | Ep: pct application non-entry in european phase |
Ref document number: 10858183 Country of ref document: EP Kind code of ref document: A1 |