CN109309808A - A kind of monitoring system and method based on recognition of face - Google Patents
A kind of monitoring system and method based on recognition of face Download PDFInfo
- Publication number
- CN109309808A CN109309808A CN201710619875.3A CN201710619875A CN109309808A CN 109309808 A CN109309808 A CN 109309808A CN 201710619875 A CN201710619875 A CN 201710619875A CN 109309808 A CN109309808 A CN 109309808A
- Authority
- CN
- China
- Prior art keywords
- face
- monitoring
- recognition
- data
- monitoring management
- Prior art date
- Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
- Pending
Links
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
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06V—IMAGE OR VIDEO RECOGNITION OR UNDERSTANDING
- G06V40/00—Recognition of biometric, human-related or animal-related patterns in image or video data
- G06V40/10—Human or animal bodies, e.g. vehicle occupants or pedestrians; Body parts, e.g. hands
- G06V40/16—Human faces, e.g. facial parts, sketches or expressions
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06V—IMAGE OR VIDEO RECOGNITION OR UNDERSTANDING
- G06V40/00—Recognition of biometric, human-related or animal-related patterns in image or video data
- G06V40/10—Human or animal bodies, e.g. vehicle occupants or pedestrians; Body parts, e.g. hands
- G06V40/16—Human faces, e.g. facial parts, sketches or expressions
- G06V40/168—Feature extraction; Face representation
-
- G—PHYSICS
- G08—SIGNALLING
- G08B—SIGNALLING OR CALLING SYSTEMS; ORDER TELEGRAPHS; ALARM SYSTEMS
- G08B13/00—Burglar, theft or intruder alarms
- G08B13/18—Actuation by interference with heat, light, or radiation of shorter wavelength; Actuation by intruding sources of heat, light, or radiation of shorter wavelength
- G08B13/189—Actuation by interference with heat, light, or radiation of shorter wavelength; Actuation by intruding sources of heat, light, or radiation of shorter wavelength using passive radiation detection systems
- G08B13/194—Actuation by interference with heat, light, or radiation of shorter wavelength; Actuation by intruding sources of heat, light, or radiation of shorter wavelength using passive radiation detection systems using image scanning and comparing systems
- G08B13/196—Actuation by interference with heat, light, or radiation of shorter wavelength; Actuation by intruding sources of heat, light, or radiation of shorter wavelength using passive radiation detection systems using image scanning and comparing systems using television cameras
Landscapes
- Engineering & Computer Science (AREA)
- Multimedia (AREA)
- Oral & Maxillofacial Surgery (AREA)
- Physics & Mathematics (AREA)
- General Physics & Mathematics (AREA)
- Health & Medical Sciences (AREA)
- General Health & Medical Sciences (AREA)
- Human Computer Interaction (AREA)
- Theoretical Computer Science (AREA)
- Signal Processing (AREA)
- Computer Vision & Pattern Recognition (AREA)
- Image Analysis (AREA)
- Image Processing (AREA)
- Alarm Systems (AREA)
Abstract
The invention discloses a kind of monitoring system and method based on recognition of face, the system comprises: monitoring management apparatus and one or more pattern recognition devices；Described image identification device includes the camera and processing module of the real-time video pictures for obtaining monitoring area；The processing module automatically extracts the facial feature data of the face when recognizing and face occur in the video pictures that the camera obtains, and analysed and compared according to the face features data recognized with the object data in storage inside data, triggering alarm is judged whether according to the result of the analyses and comparison；Operation has monitoring management application and the corresponding display received data on the interface of monitoring management application on the monitoring management apparatus.Compared to existing face identification system, cost be can be greatly reduced, and meet the application demand of individual consumer, and the accuracy and reliability of recognition of face is effectively increased by way of deep learning.
Description
Technical field
The present invention relates to security monitoring technology more particularly to a kind of monitoring system and methods based on recognition of face.
Background technique
It usually needs to be monitored protection to the personal effects of oneself in the place of densely populated place, if arranging specific people
Not only to expend a large amount of manpower and material resources to be supervised, and its supervision reliability also because peopleware is fluctuated, because
This, existing monitoring system is mostly completed by face recognition technology.Face recognition technology is the face feature letter based on people
Breath carries out a kind of biological identification technology of identification.Image or video flowing containing face are acquired with video camera or camera,
And automatic detection and tracking face in the picture, and then a series of the relevant technologies of face are carried out to the face detected, usually
Also referred to as Identification of Images, face recognition
In realizing process of the present invention, at least there are the following problems in the prior art for inventor's discovery: existing face is known
Other safety monitoring equipment framework is complicated, at high price, is generally supplied to mega project, and the security protection of individual consumer's grade is supervised
It is then difficult to bear so high cost in control demand, and fixation faceform and algorithm dependent on non-deep learning, carry out
The comparison of database human face photo black and white lists, recognition accuracy is low, and recognition speed is slow, identifies unstable, poor user experience.
Summary of the invention
In order to overcome the shortcomings of Related product in the prior art, the present invention proposes a kind of monitoring system based on recognition of face
And method, solve the problems, such as that current face identifies that the high primary characterization rate of safety monitoring equipment cost is low.
The present invention provides a kind of monitoring systems based on recognition of face, comprising: including monitoring management apparatus and with institute
State one or more pattern recognition devices of monitoring management apparatus communication connection；Described image identification device includes camera and place
Manage module；The camera obtains the video pictures of monitoring area in real time；The processing module is obtained recognizing the camera
Occur automatically extracting the facial feature data of the face when face in the video pictures taken, and according to the face recognized
Facial feature data is analysed and compared with the object data in storage inside data, wherein each object data pair
Triggering alarm should be judged whether according to the result of the analyses and comparison in only one personnel objects, and by the analyses and comparison
Result and it is described it is real-time obtain monitoring area video pictures be sent to the monitoring management apparatus；The monitoring management dress
Setting operation has monitoring management application and the corresponding display received data on the interface of monitoring management application.
As a further improvement of the present invention, the processing module is specifically used for: to the video pictures obtained in real time
Face datection is carried out, and obtains the frame image when detecting face and cuts out corresponding facial image；To the face figure
As carrying out critical point detection and executing image conversion；Facial image progress image procossing is obtained into corresponding facial characteristics number
According to.
As a further improvement of the present invention, the monitoring management apparatus is used for: applying upper input in the monitoring management
Corresponding URL Selection and call or the corresponding camera of switching.
As a further improvement of the present invention, the monitoring management apparatus is used for: to same a pair in internal storing data
Deep learning is carried out as the facial image of input preset quantity, and by adding or deleting operation to the storage inside number
Object data in is updated.
As a further improvement of the present invention, the system also includes triggering the alarm dress to send a warning when alarm
It sets, the alarm device is integrated on described image identification device or monitoring management apparatus, what the system sent a warning
Mode includes following at least one: mail reminder, information pop-up, alarm device vibration and light flash.
The present invention provides a kind of monitoring methods based on recognition of face, applied to any of the above-described based on recognition of face
Monitoring system, comprising: the video pictures for obtaining monitoring area in real time by camera occur recognizing in the video pictures
The facial feature data of the face is automatically extracted when face, and according to the face features data recognized and inside
Object data in storing data is analysed and compared, wherein each object data corresponds to only one personnel couple
As；According to the result of the analyses and comparison judge whether triggering alarm, and by the result of the analyses and comparison and it is described in real time
The video pictures for obtaining monitoring area are sent to monitoring management apparatus；Monitoring management application is run on the monitoring management apparatus
And the corresponding display received data on the interface of monitoring management application.
As a further improvement of the present invention, described that institute is automatically extracted when recognizing and face occur in the video pictures
The facial feature data for stating face includes: to carry out Face datection to the video pictures obtained in real time, and detecting face
When obtain the frame image and cut out corresponding facial image；Critical point detection is carried out to the facial image and executes image turn
It changes；Facial image progress image procossing is obtained into corresponding facial feature data.
As a further improvement of the present invention, the method also includes: the monitoring management using it is upper input it is corresponding
URL Selection and call or the corresponding camera of switching.
As a further improvement of the present invention, the method also includes: in internal storing data same target input
The facial image of preset quantity operates to carry out deep learning, and by adding or deleting in the storage inside data
Object data is updated.
As a further improvement of the present invention, the mode to send a warning when the triggering alarm includes following at least one
Kind: mail reminder, information pop-up, vibration and light flash.
Compared with prior art, the present invention has the following advantages:
The monitoring system and method based on recognition of face passes through the processing module of embedded images visual processing program
Come handle camera acquisition video pictures, corresponding monitoring programme is run on PC computer to show that each camera obtains in real time
The video pictures that take and corresponding recognition of face as a result, and triggering alarm is judged whether according to the result of the recognition of face,
Compared to existing face identification system, cost be can be greatly reduced, and meet the application demand of individual consumer, and be passed through
The mode of deep learning effectively increases the accuracy and reliability of recognition of face, and user is made to obtain better usage experience.
Detailed description of the invention
It to describe the technical solutions in the embodiments of the present invention more clearly, below will be to needed in the embodiment
Attached drawing is briefly described, it should be apparent that, drawings in the following description are only some embodiments of the invention, for ability
For the those of ordinary skill of domain, without creative efforts, it can also be obtained according to these attached drawings other attached
Figure.
Fig. 1 is the theory structure schematic diagram of the monitoring system of the present invention based on recognition of face；
Fig. 2 is the schematic diagram that the present invention carries out recognition of face；
Fig. 3 is the flow diagram of the monitoring method of the present invention based on recognition of face.
Specific embodiment
In order to enable those skilled in the art to better understand the solution of the present invention, below in conjunction in the embodiment of the present invention
Attached drawing, technical scheme in the embodiment of the invention is clearly and completely described.Obviously, described embodiment is only
A part of the embodiment of the present invention gives presently preferred embodiments of the present invention instead of all the embodiments in attached drawing.The present invention can
To realize in many different forms, however it is not limited to embodiment described herein, on the contrary, provide the mesh of these embodiments
Be to make the disclosure of the present invention more thorough and comprehensive.Based on the embodiments of the present invention, the common skill in this field
Art personnel every other embodiment obtained without creative efforts belongs to the model that the present invention protects
It encloses.
Unless otherwise defined, all technical and scientific terms used herein and belong to technical field of the invention
The normally understood meaning of technical staff is identical.Term as used herein in the specification of the present invention is intended merely to description tool
The purpose of the embodiment of body, it is not intended that in the limitation present invention.In description and claims of this specification and above-mentioned attached drawing
Term " includes " and " having " and their any deformations, it is intended that cover and non-exclusive include.Such as contain a system
The process, method, system, product or equipment of column step or unit are not limited to listed step or unit, but optional
Ground further includes the steps that not listing or unit, or optionally further comprising intrinsic for these process, methods, product or equipment
Other step or units.
Referenced herein " embodiment " is it is meant that a particular feature, structure, or characteristic described can wrap in conjunction with the embodiments
Containing at least one embodiment of the present invention.Each position in the description occur the phrase might not each mean it is identical
Embodiment, nor the independent or alternative embodiment with other embodiments mutual exclusion.Those skilled in the art explicitly and
Implicitly understand, embodiment described herein can be combined with other embodiments.
As shown in fig.1, the monitoring system based on recognition of face include communication connection monitoring management apparatus 2 and
One or more pattern recognition devices 1.
Described image identification device 1 includes the camera 11 and processing module 12 of electric connection, in embodiments of the present invention,
The camera 11 and processing module 12, which can integrate, works as described image in other embodiments of the invention for entirety
When identification device 1 is applied under the security protection scene of such as cell or public place, its ready-made camera 11 can also be directly utilized,
Need to only be equipped at this time the corresponding processing module 12 it is connected with the ready-made camera 11 may achieve it is described
The equivalent function of pattern recognition device 1.
The camera 11 obtains the video pictures of monitoring area in real time, when described image identification device 1 includes multiple,
Its corresponding multiple camera 11 can be separately positioned on each corner in region for needing to monitor, and will respectively obtain respectively
Video pictures are transmitted to the processing module 12 being attached thereto and are handled.
The processing module 12 is automatically extracted when recognizing and face occur in the video pictures that the camera 11 obtains
The facial feature data of the face, and according to pair in the face features data recognized and storage inside data
Image data is analysed and compared, wherein each object data corresponds to only one personnel objects, according to the analysis
The result of comparison judge whether triggering alarm, and by the result of the analyses and comparison and it is described it is real-time obtain monitoring area view
Frequency picture is sent to the monitoring management apparatus 2；When in the face features data recognized and storage inside data
Object data matching when, i.e., artificial " acquaintance " in current video picture, the embodiment of the present invention will not trigger alarm, accordingly
, when the object data in the face features data recognized and storage inside data mismatches, that is, work as forward sight
Artificial " stranger " in frequency picture, the embodiment of the present invention will trigger alarm and alert.
The processing module 12 carries out Face datection to the video pictures obtained in real time, and obtains when detecting face
It takes the frame image and cuts out corresponding facial image, critical point detection is carried out to the facial image and execute image conversion,
Facial image progress image procossing is obtained into corresponding facial feature data；In embodiments of the present invention, the processing mould
Block 12 detects the video pictures obtained in real time frame by frame, by detecting with recognizers such as dlib, OpenCV
Face in video pictures, the processing module 12 automatically extract the frame image detecting when there is face in a certain frame picture
And facial image is cut out, critical point detection is carried out to the facial image cut out later and executes image conversion, described image
Conversion refers to that the angle position of its face location of the original image of acquisition is inclination or stands upside down, in order to keep its position upright, institute
Processing module 12 is stated by identifying that the original image obtains the profile key point of face in described image, the position including canthus
Set, the position of nose, face totally 68 points such as profile point, will be after whole image radiation transformation on the basis of these profile key points
It is in its each profile key point position rationally, is aligned the face " " on the whole.
Facial image after the conversion is carried out what HOG (histograms of oriented gradients) processing obtained by the processing module 12
Characteristic value data, the described HOG processing, which refers to, is converted into black white image for the facial image, every on the black white image
The depth of a pixel and its surrounding pixel, and the direction of the depth of each pixel from high to low, i.e. pattern are indicated with arrow direction
By bright dimmed direction；Successively the above-mentioned arrow of each pixel is replaced and generates a gradient relation figure, the gradient relation
Figure can be expressed as a convolution vector, and the vector is 128 dimensional vectors based on VGG16 model, and the VGG16 is depth
The characteristic value data of image is calculated after algorithm process by inputting original image in a basic model in habit, right
Should include 128 characteristic value datas, the characteristic value data be that above-mentioned vector indicates, between the vector expression away from
From the similarity that can directly reflect face, as shown in Fig. 2, respectively HOG treated facial feature data and
Storage inside data, for the facial image of the same person, the Euclidean distance of corresponding vector is smaller, correspondingly, for
The facial image of different people, the Euclidean distance between corresponding vector is larger, therefore, processing described in the embodiment of the present invention
Module 12 obtains corresponding face spy in progress image procossing by carrying out Face datection to the video pictures obtained in real time
Data are levied, and analysis ratio is carried out according to the object data in the face features data recognized and storage inside data
To i.e. can recognize present image in artificial " acquaintance " still " stranger " and judge whether triggering alarm；The face is known
Other result is the likelihood ratio, i.e., the object data in face features data and storage inside data obtains after being analysed and compared
The similarity of the two arrived, for example, be 100% when identical, other such as 90%, 30%, in embodiments of the present invention, when
When similarity is more than certain threshold value, when such as 70%, artificial " acquaintance " in present image can be assert, when being lower than the threshold value,
It can then assert artificial " stranger " in present image, certainly, the threshold value of setting will affect recognition of face when too high or too low
Accuracy, therefore, the threshold value of the similarity can self-setting according to the actual situation, the embodiment of the present invention to this and it is unlimited
System.
Operation has monitoring management application and corresponds on the interface of monitoring management application on the monitoring management apparatus 2
Showing received data, the monitoring management, which is applied, carries out data interaction by route network and the processing module 12,
In the monitoring management using corresponding URL (the Uniform Resource Locator uniform resource locator) selection of upper input
Corresponding camera 11 is called or switches, the video of monitoring area is drawn where can transmitting it with the corresponding camera 11 of unrestricted choice
Face and implementing on the interface of monitoring management application accordingly increases or delete operation manages selected camera 11
Operating status；The data of corresponding display include the view that each camera 11 obtains in real time on the interface of the monitoring management application
Frequency picture and corresponding recognition of face as a result, and current whether in triggering alarm state.
The embodiment of the present invention inputs present count by the same target in 2 pairs of the monitoring management apparatus internal storing datas
The facial image of amount operates to carry out deep learning, and by adding or deleting to the number of objects in the storage inside data
According to being updated；In order to further increase the accuracy of recognition of face, the embodiment of the present invention is right by the monitoring management apparatus 2
Same target in storage inside data inputs the facial image of preset quantity to carry out deep learning, and the facial image is
The facial image of facial image under same target different angle and environment, input is more, and the success rate of recognition of face is got over
It is high；Meanwhile user is when using the monitoring system, it is difficult to avoid adding or deleting corresponding object select " acquaintance " or
" stranger ", adding or deleting operation to the human face data execution of same target by the monitoring management apparatus 2 can be completed
The update of object data in the storage inside data.
In embodiments of the present invention, the processing module 12 is the raspberry pie component of embedded images visual processing program,
The monitoring management apparatus 2 then can be PC computer, and the PC computer expert crosses route device and the processing module 12 forms
The video of acquisition monitoring area can be realized by running corresponding monitoring management application on the PC computer in local area network, user
Picture simultaneously carries out recognition of face automatically and inspires alarm after recognizing " stranger ", compared to existing face monitoring system
Required large server, the embodiment of the present invention can be realized corresponding by the corresponding monitoring management application of PC computer operation
Function greatly reduces cost, can satisfy the usage scenario of personal consumption grade.
In embodiments of the present invention, the system also includes triggering the alarm device 3 to send a warning when alarm, institute
It states alarm device 3 to be integrated on described image identification device 1 or monitoring management apparatus 2, the side that the system sends a warning
Formula includes following at least one: mail reminder, information pop-up, the vibration of alarm device 3 and light flash, wherein the mail
It reminds and information pop-up is completed by the monitoring management apparatus 2, the method sounded an alarm can be any of the above-described kind of side
Formula is also possible to combination one or more in aforesaid way；The alarm device 3 includes buzzer and flash lamp, difference
It is integrated on described image identification device 1 or monitoring management apparatus 2 for generating vibration and light flash, the alarm device 3
When applied under different scenes respectively, for example, when user itself is located near camera 11, after triggering alarm, the place
The alarm device 3 integrated in reason module 12 is alarmed by vibration and light flash immediately；When user is located at the prison
When 2 attachment of control management device, be integrated with the monitoring management apparatus 2 of the alarm device 3 carried out when triggering alarm information pop-up,
Vibration or light flash are alarmed；When user is in other places and the warning message of the processing module 12 and monitoring management apparatus 2
When can not see, the monitoring management apparatus 2 is sent in alarm mail to preset subscriber mailbox automatically；Certainly, above-mentioned more
A scene can greatly improve the reliability of monitoring management with connected applications.
In embodiments of the present invention, the monitoring system based on recognition of face passes through embedded images visual processing program
Processing module 12 handle the video pictures of the acquisition of camera 11, it is each to show that corresponding monitoring programme is run on PC computer
Video pictures that a camera 11 obtains in real time and corresponding recognition of face as a result, and being sentenced according to the result of the recognition of face
Disconnected whether to trigger alarm, compared to existing face identification system, cost be can be greatly reduced, and meet individual consumer's
Application demand, and the accuracy and reliability of recognition of face is effectively increased by way of deep learning, obtain user
Better usage experience.
As shown in fig.3, for the flow diagram of the monitoring method based on recognition of face described in the embodiment of the present invention, packet
It includes:
S101: obtaining the video pictures of monitoring area by camera in real time, occurs recognizing in the video pictures
The facial feature data of the face is automatically extracted when face, and according to the face features data recognized and inside
Object data in storing data is analysed and compared.
In embodiments of the present invention, each object data corresponds to only one personnel objects；Optionally, this hair
Bright embodiment obtains the frame image when detecting face by carrying out Face datection to the video pictures obtained in real time
And cut out corresponding facial image, critical point detection is carried out to the facial image and execute image conversion, by the face
Image carries out image procossing and obtains corresponding facial feature data.
S102: according to the result of the analyses and comparison judge whether triggering alarm, and by the result of the analyses and comparison with
And the real-time video pictures for obtaining monitoring area are sent to monitoring management apparatus.
In embodiments of the present invention, the mode to send a warning when the triggering alarm includes following at least one: postal
Part prompting, information pop-up, vibration and light flash.
S103: monitoring management application is run on the monitoring management apparatus and on the interface of monitoring management application
Corresponding display received data.
Optionally, the embodiment of the present invention is in the monitoring management using the corresponding URL Selection and call of upper input or switching pair
The camera answered；The embodiment of the present invention carries out the facial image of the same target input preset quantity in internal storing data
Deep learning, and the object data in the storage inside data is updated by adding or deleting operation.
Monitoring method described in the embodiment of the present invention based on recognition of face is applied to be based on provided by above-described embodiment
The monitoring system of recognition of face, the monitoring method based on recognition of face have the above-mentioned monitoring system phase based on recognition of face
The functional module and beneficial effect answered, referring specifically to the embodiment of the above-mentioned monitoring system based on recognition of face, the present invention is real
Applying example, details are not described herein.
In above-described embodiment provided by the present invention, it should be understood that disclosed device and method can pass through it
Its mode is realized.For example, the apparatus embodiments described above are merely exemplary, for example, the division of the module, only
Only a kind of logical function partition, there may be another division manner in actual implementation, for example, multiple module or components can be tied
Another system is closed or is desirably integrated into, or some features can be ignored or not executed.
The module as illustrated by the separation member may or may not be physically separated, aobvious as module
The component shown may or may not be physical module, it can and it is in one place, or may be distributed over multiple
In network unit.Some or all of the modules therein can be selected to realize the mesh of this embodiment scheme according to the actual needs
's.
The above is only the embodiment of the present invention, are not intended to limit the scope of the patents of the invention, although with reference to the foregoing embodiments
Invention is explained in detail, still can be to aforementioned each specific reality for coming for those skilled in the art
It applies technical solution documented by mode to modify, or equivalence replacement is carried out to part of technical characteristic.It is all to utilize this
The equivalent structure that description of the invention and accompanying drawing content are done directly or indirectly is used in other related technical areas, similarly
Within the invention patent protection scope.
Claims (10)
1. a kind of monitoring system based on recognition of face, which is characterized in that including monitoring management apparatus and with the monitoring pipe
Manage one or more pattern recognition devices of device communication connection；
Described image identification device includes camera and processing module；
The camera obtains the video pictures of monitoring area in real time；
The processing module automatically extracts the face when recognizing and face occur in the video pictures that the camera obtains
Facial feature data, and according to the object data in the face features data recognized and storage inside data into
Row is analysed and compared, wherein each object data corresponds to only one personnel objects, according to the knot of the analyses and comparison
Fruit judges whether triggering alarm, and the result of the analyses and comparison and the real-time video pictures for obtaining monitoring area are sent out
It send to the monitoring management apparatus；
Operation has monitoring management application and the corresponding display on the interface of monitoring management application on the monitoring management apparatus
Received data.
2. the monitoring system according to claim 1 based on recognition of face, which is characterized in that the processing module is specifically used
In:
Face datection is carried out to the video pictures obtained in real time, and obtains the frame image when detecting face and cuts out
Corresponding facial image；
Critical point detection is carried out to the facial image and executes image conversion；
Facial image progress image procossing is obtained into corresponding facial feature data.
3. the monitoring system according to claim 1 based on recognition of face, which is characterized in that the monitoring management apparatus is used
In:
In the monitoring management using the corresponding URL Selection and call of upper input or the corresponding camera of switching.
4. the monitoring system according to claim 1 based on recognition of face, which is characterized in that the monitoring management apparatus is used
In:
Deep learning is carried out to the facial image of the same target input preset quantity in internal storing data, and by adding
Add or delete operation is updated the object data in the storage inside data.
5. the monitoring system according to claim 1 based on recognition of face, which is characterized in that the system also includes touching
The alarm device to send a warning when hair alarm, the alarm device are integrated in described image identification device or monitoring management dress
It sets, the mode that the system sends a warning includes following at least one: mail reminder, information pop-up, alarm device vibration
Dynamic and light flash.
6. a kind of monitoring method based on recognition of face, the prison applied to any one of the claims 1-5 based on recognition of face
Control system characterized by comprising
The video pictures for obtaining monitoring area in real time by camera, recognize there is face in the video pictures when it is automatic
The facial feature data of the face is extracted, and according in the face features data recognized and storage inside data
Object data analyse and compare, wherein the object data corresponds to only one personnel objects；
According to the result of the analyses and comparison judge whether triggering alarm, and by the result of the analyses and comparison and it is described in real time
The video pictures for obtaining monitoring area are sent to monitoring management apparatus；
Monitoring management application and the corresponding display on the interface of monitoring management application are run on the monitoring management apparatus
Received data.
7. the monitoring method according to claim 6 based on recognition of face, which is characterized in that described to recognize the view
The facial feature data for occurring automatically extracting the face in frequency picture when face includes:
Face datection is carried out to the video pictures obtained in real time, and obtains the frame image when detecting face and cuts out
Corresponding facial image；
Critical point detection is carried out to the facial image and executes image conversion；
Facial image progress image procossing is obtained into corresponding facial feature data.
8. the monitoring method according to claim 6 based on recognition of face, which is characterized in that the method also includes:
In the monitoring management using the corresponding URL Selection and call of upper input or the corresponding camera of switching.
9. the monitoring method according to claim 6 based on recognition of face, which is characterized in that the method also includes:
Deep learning is carried out to the facial image of the same target input preset quantity in internal storing data, and by adding
Add or delete operation is updated the object data in the storage inside data.
10. the monitoring method according to claim 6 based on recognition of face, which is characterized in that the triggering is sent out when alarming
The mode of warning information includes following at least one out: mail reminder, information pop-up, vibration and light flash.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201710619875.3A CN109309808A (en) | 2017-07-26 | 2017-07-26 | A kind of monitoring system and method based on recognition of face |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201710619875.3A CN109309808A (en) | 2017-07-26 | 2017-07-26 | A kind of monitoring system and method based on recognition of face |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN109309808A true CN109309808A (en) | 2019-02-05 |
Family
ID=65202337
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN201710619875.3A Pending CN109309808A (en) | 2017-07-26 | 2017-07-26 | A kind of monitoring system and method based on recognition of face |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN109309808A (en) |
Cited By (17)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN110399855A (en) * | 2019-07-31 | 2019-11-01 | 深圳市富视康实业发展有限公司 | A kind of alarm system and method based on face recognition technology |
| CN110490037A (en) * | 2019-05-30 | 2019-11-22 | 福建知鱼科技有限公司 | A kind of face recognition system |
| CN110532881A (en) * | 2019-07-30 | 2019-12-03 | 长江大学 | A kind of recognition of face security alarm method based on embedded artificial intelligent chip |
| CN110532882A (en) * | 2019-07-30 | 2019-12-03 | 长江大学 | Recognition of face safety alarm system and equipment based on embedded artificial intelligent chip |
| CN110619277A (en) * | 2019-08-15 | 2019-12-27 | 青岛文达通科技股份有限公司 | Multi-community intelligent deployment and control method and system |
| CN111028227A (en) * | 2019-12-17 | 2020-04-17 | 江西洪都航空工业集团有限责任公司 | Quick alignment method for numerical control machine tool |
| CN111131766A (en) * | 2019-11-15 | 2020-05-08 | 重庆中科云从科技有限公司 | Data processing method, system, equipment and medium based on intelligent gateway |
| CN111260869A (en) * | 2020-01-19 | 2020-06-09 | 世纪龙信息网络有限责任公司 | Method and device for extracting video frames in monitoring video and computer equipment |
| CN111614935A (en) * | 2020-04-30 | 2020-09-01 | 深圳市椰壳信息科技有限公司 | Intelligent monitoring method and device, terminal equipment and readable storage medium |
| CN111629184A (en) * | 2020-06-17 | 2020-09-04 | 内蒙古京海煤矸石发电有限责任公司 | Video monitoring alarm system and method capable of identifying personnel in monitoring area |
| CN112185043A (en) * | 2019-07-05 | 2021-01-05 | 上海市建筑通信网络有限公司 | Intelligent monitoring system and method |
| CN112288671A (en) * | 2020-11-19 | 2021-01-29 | 长江大学 | Method, system and device for judging organic matter type based on MAPS scanning technology |
| CN112653874A (en) * | 2020-12-01 | 2021-04-13 | 杭州勋誉科技有限公司 | Storage device and intelligent video monitoring system |
| CN113077470A (en) * | 2021-03-26 | 2021-07-06 | 天翼爱音乐文化科技有限公司 | Method, system, device and medium for cutting horizontal and vertical screen conversion picture |
| CN113128356A (en) * | 2021-03-29 | 2021-07-16 | 成都理工大学工程技术学院 | Smart city monitoring system based on image recognition |
| CN113569816A (en) * | 2021-09-22 | 2021-10-29 | 南通赛尔科技信息系统有限公司 | Monitoring device based on facial recognition |
| CN114827540A (en) * | 2022-04-14 | 2022-07-29 | 山西长河科技股份有限公司 | Monitoring station safe operation method and terminal based on video intelligent analysis technology |
Citations (12)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN1472691A (en) * | 2002-07-30 | 2004-02-04 | ŷķ����ʽ���� | Face comparison verifying device and method |
| CN101047848A (en) * | 2007-04-27 | 2007-10-03 | 北京大学 | Network flow media player and method for support multi-viewpoint vedio composition |
| CN101080104A (en) * | 2006-05-25 | 2007-11-28 | 株式会社日立制作所 | Control device, control method and control program |
| CN101141632A (en) * | 2006-09-06 | 2008-03-12 | 新巨企业股份有限公司 | Portable image monitoring and identifying device |
| CN104536426A (en) * | 2015-01-15 | 2015-04-22 | 山东弘生源电子科技有限公司 | Sensor signal linkage and simulation system using networks |
| CN105357473A (en) * | 2015-10-23 | 2016-02-24 | 苏州佳风网络科技有限公司 | Video monitoring method |
| CN105430347A (en) * | 2015-11-30 | 2016-03-23 | 燕山大学 | Compressed sensing based wireless sensor image capturing and transmitting system |
| CN105678250A (en) * | 2015-12-31 | 2016-06-15 | 北京小孔科技有限公司 | Face identification method in video and face identification device in video |
| CN105704453A (en) * | 2016-02-21 | 2016-06-22 | 国网江西省电力科学研究院 | Raspberry Pi-based power grid equipment video monitoring device |
| CN105812635A (en) * | 2016-05-05 | 2016-07-27 | 游佳彬 | Infrared camera |
| CN106339702A (en) * | 2016-11-03 | 2017-01-18 | 北京星宇联合投资管理有限公司 | Multi-feature fusion based face identification method |
| CN106909882A (en) * | 2017-01-16 | 2017-06-30 | 广东工业大学 | A kind of face identification system and method for being applied to security robot |
-
2017
- 2017-07-26 CN CN201710619875.3A patent/CN109309808A/en active Pending
Patent Citations (12)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN1472691A (en) * | 2002-07-30 | 2004-02-04 | ŷķ����ʽ���� | Face comparison verifying device and method |
| CN101080104A (en) * | 2006-05-25 | 2007-11-28 | 株式会社日立制作所 | Control device, control method and control program |
| CN101141632A (en) * | 2006-09-06 | 2008-03-12 | 新巨企业股份有限公司 | Portable image monitoring and identifying device |
| CN101047848A (en) * | 2007-04-27 | 2007-10-03 | 北京大学 | Network flow media player and method for support multi-viewpoint vedio composition |
| CN104536426A (en) * | 2015-01-15 | 2015-04-22 | 山东弘生源电子科技有限公司 | Sensor signal linkage and simulation system using networks |
| CN105357473A (en) * | 2015-10-23 | 2016-02-24 | 苏州佳风网络科技有限公司 | Video monitoring method |
| CN105430347A (en) * | 2015-11-30 | 2016-03-23 | 燕山大学 | Compressed sensing based wireless sensor image capturing and transmitting system |
| CN105678250A (en) * | 2015-12-31 | 2016-06-15 | 北京小孔科技有限公司 | Face identification method in video and face identification device in video |
| CN105704453A (en) * | 2016-02-21 | 2016-06-22 | 国网江西省电力科学研究院 | Raspberry Pi-based power grid equipment video monitoring device |
| CN105812635A (en) * | 2016-05-05 | 2016-07-27 | 游佳彬 | Infrared camera |
| CN106339702A (en) * | 2016-11-03 | 2017-01-18 | 北京星宇联合投资管理有限公司 | Multi-feature fusion based face identification method |
| CN106909882A (en) * | 2017-01-16 | 2017-06-30 | 广东工业大学 | A kind of face identification system and method for being applied to security robot |
Non-Patent Citations (1)
| Title |
|---|
| 慕春雷: "基于HOG特征的人脸识别系统研究", 《中国优秀硕士学位论文全文数据库 信息科技辑》 * |
Cited By (19)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN110490037A (en) * | 2019-05-30 | 2019-11-22 | 福建知鱼科技有限公司 | A kind of face recognition system |
| CN112185043A (en) * | 2019-07-05 | 2021-01-05 | 上海市建筑通信网络有限公司 | Intelligent monitoring system and method |
| CN110532881A (en) * | 2019-07-30 | 2019-12-03 | 长江大学 | A kind of recognition of face security alarm method based on embedded artificial intelligent chip |
| CN110532882A (en) * | 2019-07-30 | 2019-12-03 | 长江大学 | Recognition of face safety alarm system and equipment based on embedded artificial intelligent chip |
| CN110399855A (en) * | 2019-07-31 | 2019-11-01 | 深圳市富视康实业发展有限公司 | A kind of alarm system and method based on face recognition technology |
| CN110619277A (en) * | 2019-08-15 | 2019-12-27 | 青岛文达通科技股份有限公司 | Multi-community intelligent deployment and control method and system |
| CN111131766A (en) * | 2019-11-15 | 2020-05-08 | 重庆中科云从科技有限公司 | Data processing method, system, equipment and medium based on intelligent gateway |
| CN111028227A (en) * | 2019-12-17 | 2020-04-17 | 江西洪都航空工业集团有限责任公司 | Quick alignment method for numerical control machine tool |
| CN111260869A (en) * | 2020-01-19 | 2020-06-09 | 世纪龙信息网络有限责任公司 | Method and device for extracting video frames in monitoring video and computer equipment |
| CN111260869B (en) * | 2020-01-19 | 2022-06-10 | 天翼数字生活科技有限公司 | Method and device for extracting video frames in monitoring video and computer equipment |
| CN111614935A (en) * | 2020-04-30 | 2020-09-01 | 深圳市椰壳信息科技有限公司 | Intelligent monitoring method and device, terminal equipment and readable storage medium |
| CN111629184A (en) * | 2020-06-17 | 2020-09-04 | 内蒙古京海煤矸石发电有限责任公司 | Video monitoring alarm system and method capable of identifying personnel in monitoring area |
| CN112288671A (en) * | 2020-11-19 | 2021-01-29 | 长江大学 | Method, system and device for judging organic matter type based on MAPS scanning technology |
| CN112653874A (en) * | 2020-12-01 | 2021-04-13 | 杭州勋誉科技有限公司 | Storage device and intelligent video monitoring system |
| CN113077470A (en) * | 2021-03-26 | 2021-07-06 | 天翼爱音乐文化科技有限公司 | Method, system, device and medium for cutting horizontal and vertical screen conversion picture |
| CN113077470B (en) * | 2021-03-26 | 2022-01-18 | 天翼爱音乐文化科技有限公司 | Method, system, device and medium for cutting horizontal and vertical screen conversion picture |
| CN113128356A (en) * | 2021-03-29 | 2021-07-16 | 成都理工大学工程技术学院 | Smart city monitoring system based on image recognition |
| CN113569816A (en) * | 2021-09-22 | 2021-10-29 | 南通赛尔科技信息系统有限公司 | Monitoring device based on facial recognition |
| CN114827540A (en) * | 2022-04-14 | 2022-07-29 | 山西长河科技股份有限公司 | Monitoring station safe operation method and terminal based on video intelligent analysis technology |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN109309808A (en) | A kind of monitoring system and method based on recognition of face | |
| KR102553883B1 (en) | A method for generating alerts in a video surveillance system | |
| CN110287923A (en) | Human body attitude acquisition methods, device, computer equipment and storage medium | |
| CN113347387B (en) | Image monitoring system and image monitoring method | |
| CN109614882A (en) | A kind of act of violence detection system and method based on human body attitude estimation | |
| US10956753B2 (en) | Image processing system and image processing method | |
| CN114140746B (en) | In-box camera shielding detection method, elevator operation control method and device | |
| CN104834902A (en) | Safety check graph discrimination system including video analysis and graph discrimination method | |
| CN110442742A (en) | Retrieve method and device, processor, electronic equipment and the storage medium of image | |
| CN110674761A (en) | Regional behavior early warning method and system | |
| CN109961031A (en) | Face fusion identifies identification, target person information display method, early warning supervision method and system | |
| JP5718632B2 (en) | Part recognition device, part recognition method, and part recognition program | |
| CN114187561A (en) | Abnormal behavior identification method and device, terminal equipment and storage medium | |
| CN204926116U (en) | Picture system is declared in safety inspection containing video analysis | |
| CN109284740A (en) | Method, apparatus, equipment and the storage medium that mouse feelings are counted | |
| KR102182660B1 (en) | System and method for detecting violence using spatiotemporal features and computer readable recording media storing program for executing method thereof | |
| US20220130148A1 (en) | System and Method for Identifying Outfit on a Person | |
| CN115205581A (en) | Fishing detection method, fishing detection device and computer readable storage medium | |
| CN113955594B (en) | Elevator control method and device, computer equipment and storage medium | |
| CN110134810A (en) | Retrieve the method and device of image | |
| CN114764895A (en) | Abnormal behavior detection device and method | |
| CN107301373A (en) | Data processing method, device and storage medium | |
| CN115240277A (en) | Security check behavior monitoring method and device, electronic equipment and storage medium | |
| CN113158744A (en) | Security protection management system based on face recognition | |
| Law et al. | Smart Prison-Video Analysis for Human Action Detection |
Legal Events
| Date | Code | Title | Description |
|---|---|---|---|
| PB01 | Publication | ||
| PB01 | Publication | ||
| SE01 | Entry into force of request for substantive examination | ||
| SE01 | Entry into force of request for substantive examination | ||
| RJ01 | Rejection of invention patent application after publication |
Application publication date: 20190205 |
|
| RJ01 | Rejection of invention patent application after publication |