JP2013042357A - Intercom system - Google Patents

Abstract

PROBLEM TO BE SOLVED: To provide an intercom system capable of notifying who a visitor is even if a user does not move to a place of an indoor unit.SOLUTION: An intercom system includes: an entrance slave unit 10 having image input means 101 for producing image data of a visitor; and an indoor master unit 20 having face detecting means 212 for detecting a face image from the image data, memory means 213 for storing registered face image data and voice data, a master unit speaker 203, and master unit control means 214. The master unit control means 214 extracts the feature amount of a face from the fage image data of the detected visitor and the registered face image data, and determines whether the registered data matching or closely resemble to the visitor exists or not from the extracted feature amount. The master unit control means 214 reads out the voice data corresponding to the registered face image data from the memory means 213 and reproduces that from the master unit speaker 203, when the visitor has been registered.

Description

  The present invention relates to an intercom system.

  Conventionally, when the call button of a camera-equipped cordless handset is pressed and a visitor is imaged by the camera, the visitor must directly view the image captured by the camera displayed on the display unit of the interphone master unit. The user could not confirm who the person is. In order to confirm the visitor reliably, it has been proposed to check the visitor's face by operating the indoor parent machine to zoom or pan / tilt the camera (see Patent Document 1).

JP-A-5-176213

  However, even when the visitor's face can be recognized by the display unit of the indoor parent device, there is a problem that the visitor cannot be confirmed unless the user moves to the installation location of the indoor parent device. In addition, when the user moves to the installation location of the indoor parent device, the visitor moves out of the imaging range of the camera, and when the user looks at the display means of the indoor parent device, the visitor is There was a problem that it could not be confirmed.

  An object of the present invention is to provide an intercom system capable of notifying who the visitor is even if the user does not move to the location of the indoor base unit.

In order to solve the above problem, the invention described in claim 1 is, for example, as shown in FIGS.
An entrance handset 10 having an image input means 101 for imaging a visitor and generating image data of the visitor, a handset speaker 104, and a microphone 103 for inputting the voice of the visitor;
Display means 207 for displaying an image based on the imaged image data of the visitor; a face detection means 212 for detecting a face image from the image data; a plurality of registered face image data and a plurality of audio data; Are stored in correspondence with each other, and an indoor parent device 20 having a parent device speaker 203 and a parent device control means 214 is provided.
The master control unit 214 extracts a facial feature amount from the face image data of the visitor detected by the face detection unit 212, reads the registered face image data from the storage unit 213, and reads the registered face The registered features having feature quantities that match or approximate the facial feature quantities extracted from the visitor face image data by extracting facial feature quantities from the image data and collating these extracted feature quantities Determine if there is face image data,
When there is registered face image data having the matching or approximating feature value, the master control unit 214 stores voice data corresponding to the registered face image data having the matching or approximating feature value. Is read out from the master speaker 203 and is reproduced.

  According to the first aspect of the present invention, when there is registered face image data having the feature quantity that matches or approximates, the base unit control unit 214 registers the face that has the feature quantity that matches or approximates. Since voice data corresponding to the image data is read from the storage means 213 and reproduced from the parent speaker 203, the visitor can be confirmed without moving to the place where the indoor parent device 20 is installed.

The invention according to claim 2 is, for example, as shown in FIGS.
The intercom system 100 according to claim 1,
When there is no registered face image data having the matching or approximate feature quantity, the base unit control means determines whether or not to register the visitor's face image data in association with arbitrary audio data. The display unit 213 displays the image data in such a manner that the face image data of the visitor is registered in the storage unit 213 in association with arbitrary audio data in accordance with a user registration operation.

  According to the second aspect of the present invention, when there is no registered face image data having the matching or approximate feature amount, the base unit control unit 214 associates the visitor's face image data with any audio data. Whether or not to register is displayed on the display unit 207 so as to be selectable, and the face image data of the visitor is registered in the storage unit 213 in association with arbitrary audio data in accordance with the user's registration operation. A visitor who does not have registered face image data having a matching or approximate feature amount can be registered, and when the visitor visits again, even if the user does not move to the installation location of the indoor base unit 20 Can check the visitor.

The invention described in claim 3 is, for example, as shown in FIGS.
In the intercom system 100 according to claim 1 or 2,
When there is no registered face image data having the matching or approximate feature amount, the master unit control unit 214 reads out voice data from the storage unit 213 to inform the visitor of the message, Playing from the speaker 104, the voice of the visitor is detected by the microphone 103, and output from the master speaker 203.

  According to the third aspect of the present invention, when there is no registered face image data having the matching or approximate feature amount, the voice data indicating that a request is to be transmitted to the visitor is read from the storage unit 213, Since it is reproduced from the slave speaker 104, the voice of the visitor is detected by the microphone 103, and is output from the master speaker 203, it has the matching or approximate feature amount before the user directly talks to the visitor. You can check the requirements of visitors who have no registered face image data.

The invention according to claim 4 is, for example, as shown in FIGS.
In the intercom system 100 as described in any one of Claims 1-3,
If the visitor's face image cannot be detected, the master unit control unit 214 reads out voice data indicating that the visitor's face cannot be detected from the storage unit 213, and the slave unit speaker 104 and the master unit speaker are read out. It is characterized by being reproduced from 203.

  According to the fourth aspect of the present invention, when the face image of the visitor cannot be detected, the voice data indicating that the visitor's face cannot be detected is read from the storage unit 213, Since playback is performed from the master speaker 203, it is possible to prompt the visitor to look at the camera.

The invention according to claim 5 is, for example, as shown in FIGS.
In the intercom system 100 as described in any one of Claims 1-4,
When there is no registered face image data having the matching or approximate feature quantity, the master unit control unit 214 reads out voice data indicating that a visitor is not registered from the storage unit 213, and the master unit speaker 203. It is characterized by playing from.

  According to the fifth aspect of the present invention, when there is no registered face image data having the matching or approximate feature amount, voice data indicating that a visitor is not registered is read from the storage unit 213, and the parent Since the reproduction is performed from the machine speaker 203, it can be confirmed that the visitor is an unintended visitor, so that the user can confirm whether or not the visitor is a suspicious person.

The invention according to claim 6 is, for example, as shown in FIGS.
In the intercom system 100 as described in any one of Claims 1-4,
It further comprises an electronic lock 300 that can be opened and closed with an electrical signal,
The registered face image data is classified into a plurality of groups including a specific group,
When the visitor belongs to the specific group, the parent device control unit 214 unlocks the electronic lock 300 for a predetermined time.

  According to the sixth aspect of the present invention, when the visitor belongs to a specific group, the base unit control means 214 unlocks the electronic lock 300 for a predetermined time. When belonging to a specific group, the user can unlock the door without going to the entrance.

  ADVANTAGE OF THE INVENTION According to this invention, even if a user does not move to the place of indoor parent machine, the intercom system which can notify who is a visitor can be provided.

It is a figure which shows an example of the intercom system which concerns on this invention, and is a figure which shows the whole structure. It is a figure which shows a functional block diagram equally. 4 is a flowchart showing an operation example of the intercom system. It is a figure which shows an example of the table memorize | stored in a memory | storage means similarly.

  Hereinafter, a preferred embodiment of an intercom system of the present invention will be described in detail with reference to the drawings.

<Embodiment>
As shown in FIG. 1, the intercom system 100 can receive an entrance slave unit 10 with a camera and image data transmitted from the entrance slave unit 10 with a camera, and display the received image data on a display unit 207. And an electronic lock 300 that can be opened and closed by an electrical signal, which is installed at the entrance connected to the indoor parent device 20.

  The entrance unit 10 with a camera is used by a visitor to call a user (resident) and is mainly installed at the entrance of a house. The indoor parent device 20 is used to respond to a call from the camera-equipped entrance child device 10 and is installed in the house. The camera-equipped entrance child device 10 and the indoor parent device 20 are connected via a transmission line 30. The indoor parent device 20 and the electronic lock 300 are connected via a transmission line 40.

  Hereinafter, the configuration of the camera-equipped entrance child device 10 and the indoor parent device 20 will be described. First, the configuration of the camera-equipped entrance slave unit 10 will be described.

  As shown in FIG. 2, the front door 10 has a camera (image input means) 101 for imaging a visitor and generating visitor image data, a call button 102 for a visitor to call a user, With a camera 101 and a call circuit 105 for making a call with a user using a handset microphone 103 and handset speaker 104, a handset microphone 103 and handset speaker 104 for inputting a visitor's voice and talking with the user A modulation circuit 106 for modulating the captured video, a slave unit IF 107 for communicating with the indoor master unit 20, and a slave unit control means 108 for controlling each part of the entrance slave unit 10 are provided.

  The camera 101 is for photographing a visitor, and can be photographed with a wide angle of view of 180 °, for example.

  The indoor master unit 20 includes a master unit IF 201 for communicating with the entrance slave unit 10, a master unit microphone 202 and a master unit speaker 203 for communicating with the slave unit microphone 103 and the slave unit speaker 104 of the entrance slave unit 10, and a visitor. The call button 204 for responding to a call from the phone, the caller circuit 205 for making a call with a visitor using the parent device microphone 202 and the parent device speaker 203, and the imaging modulated by the modulation circuit 106 of the front door device 10. Demodulating circuit 206 for demodulating the visitor's image data (video), display means 207 for displaying an image based on the image data demodulated by demodulating circuit 206, and video processing unit for performing various processes 211, the position of the face portion of the visitor in the image data captured by the camera 101 of the front door 10 is detected, and the face portion is detected from the image data. Includes a face detection unit 212 for detecting the image data, storage means 213 for storing in correspondence a registered face image data and audio data, the master unit controlling means 214 for controlling the respective circuits of the indoor base unit 20.

Next, the operation of the intercom system 100 configured as described above will be described with reference to FIG.
When a visitor calls the user by pressing the call button 102 (YES in step S1), a call signal is transmitted from the child device control means 108 to the indoor parent device 20 via the child device IF 107, and the indoor parent device 20 The base unit control means 214 receives a call signal via the base unit IF 201, performs control to ring a ringing tone from the base unit speaker 203 via the call circuit 205, and drives the camera 101 of the front door unit 10. Control to supply power. Here, the camera 101 of the entrance slave unit 10 is driven, and the captured image data is modulated by the modulation circuit 106 and transmitted to the indoor master unit 20 via the slave unit IF 107.

  The indoor parent device 20 receives the image data transmitted from the entrance child device 10 and imaged by the camera 101 and modulated by the modulation circuit 106 from the child device IF 107 via the parent device IF 201. The received modulated image data is demodulated by the demodulation circuit 206 and displayed on the display means 207 via the video processing unit 211 (step S2).

The image data demodulated by the demodulation circuit 206 is also transmitted to the face detection circuit 212.
The face detection circuit 212 detects a visitor's face part (face image) in the entire image data captured by the camera 101 (step S3). When the face part of the visitor is detected (YES in step S3), the face image data of the visitor's face part detected by the face detection circuit 212 is extracted, and the face image data is transmitted to the parent device control means 214. On the other hand, the parent device control unit 214 records the visitor's face image data in the storage unit 213. If the visitor's face image cannot be detected (NO in step S3), the master unit control unit 214 reads out voice data indicating that the visitor's face cannot be detected from the storage unit 213, and the slave unit speaker 104 and the master speaker 203 are reproduced (step S4).

  The master control unit 214 extracts the facial feature amount from the visitor's face image data detected by the face detection unit 212, while reading the registered face image data from the storage unit 213, and the registration It is determined whether or not there is registered face image data having the matching or approximate feature amount by extracting facial feature amounts from the completed face image data and collating these extracted feature amounts (step S5). ).

  If there is registered face image data having the matching or approximate feature amount (if it can be recognized: YES in step S6), the base unit control means 214 determines whether the visitor belongs to a specific group. If the visitor belongs to a specific group, the electronic lock 300 is unlocked for a predetermined time (steps S7 and S8). The registered face image data is classified into a plurality of groups including a specific group. For example, as shown in FIG. 4, in the case where the visitor is Mr. A who belongs to the group 1, the electronic lock 300 is unlocked for a predetermined time (for example, 5 seconds), while corresponding to the registered face image data. Audio data is read from the storage means 213 and reproduced from the parent speaker 203 (step S9). For example, when the registered visitor is “Mr. A”, “the visitor is Mr. A” is reproduced from the parent speaker 203.

  When there is no registered face image data having the matching or approximate feature amount (when it cannot be recognized: NO in step S6), the base unit control unit 214 sends a request to the visitor. The voice data to be transmitted is read from the storage means 213 and reproduced from the slave unit speaker 104. The voice of the visitor is detected by the microphone 103 and output from the master unit speaker 203, while the visitor Audio data indicating that it is not registered is read from the storage means 213 and reproduced from the parent speaker 203 (steps S10 and S11).

  Further, when there is no registered face image data having the matching or approximate feature amount, the base unit control means 214 determines whether or not to register the visitor's face image data in association with any audio data. The display unit 207 displays the image so as to be selectable, and registers the visitor's face image data in the storage unit 213 in association with arbitrary audio data according to the user's registration operation (steps S12 and S13). For example, when the selection button shown in FIG. 1 is pressed, a plurality of standard sentences are displayed on the display means 207. When the selection button is pressed again using the upper button 216 and the lower button 217, the face image data and The audio data is stored in the storage means 213 correspondingly. In addition, a touch panel may be adopted as the display unit 207 so that characters can be input and an arbitrary message can be recorded as voice data.

  According to the present embodiment, when there is registered face image data having the matching or approximate feature quantity, the base unit control means 214 stores voice data corresponding to the registered face image data. Since the data is read out from the main unit speaker 203 and reproduced from the main unit speaker 203, the visitor can be confirmed without moving to the place where the indoor main unit 20 is installed.

  Further, when there is no registered face image data having the matching or approximate feature amount, the base unit control means 214 determines whether or not to register the visitor's face image data in association with any audio data. Since the display means 207 displays selectably, it is possible to register a visitor having no registered face image data having the matching or approximate feature amount, and when the visitor visits again, the user The visitor can be confirmed without moving to the place where the base unit 20 is installed.

  If there is no registered face image data having the matching or approximate feature amount, the voice data indicating that the visitor needs to be informed is read from the storage means 213 and reproduced from the slave unit speaker 104. Since the voice of the visitor is detected by the microphone 103 and output from the master speaker 203, the visitor who does not have registered face image data having the matching or approximate feature amount before the user directly talks to the visitor. You can check the requirements.

  If the visitor's face image cannot be detected, voice data indicating that the visitor's face cannot be detected is read from the storage unit 213 and reproduced from the slave speaker 104 and the master speaker 203. A visitor can be prompted to look at the camera.

  In addition, when there is no registered face image data having the matching or approximate feature amount, the voice data indicating that the visitor is not registered is read from the storage unit 213 and is reproduced from the parent speaker 203. Since it can be confirmed that the visitor is an unintended visitor, the user can confirm whether or not the visitor is a suspicious person.

  Further, when the visitor belongs to a specific group, the base unit control means 214 unlocks the electronic lock 300 for a predetermined time. For example, when the visitor belongs to a specific group such as a family, the user It can be unlocked without going to the entrance.

(Modification)
In the above embodiment, when the call button 102 is pressed (step S1 in FIG. 6), an image is displayed on the display means 207 (step S6 in FIG. 6), and automatic visitor authentication is started. However, the present invention is not limited to this, and a visitor may be detected using a human sensor, or a video may be always taken from a camera, and a visitor may be detected from the video and authentication may be automatically started. In this case, the image may not be displayed on the display unit 207.
In addition, in a modification, the same code | symbol is attached | subjected to the same member as the said embodiment, and description is abbreviate | omitted.

DESCRIPTION OF SYMBOLS 10 Entrance cordless handset 20 Indoor base phone 100 Intercom system 101 Image input means (camera)
102 Call button 103 Microphone 104 Handset speaker 105 Summing circuit 106 Modulation circuit 107 Handset IF
108 Child machine control circuit 214 Parent machine control means 201 Parent machine IF
202 Master microphone 203 Master speaker 204 Call button 205 Call circuit 206 Demodulation circuit 207 Display means 211 Video processing means 212 Face detection means 213 Storage means 214 Master control means 300 Electronic lock

Claims (6)

An entrance cordless handset having an image input means for capturing an image of the visitor and generating image data of the visitor, a handset speaker, and a microphone for inputting the voice of the visitor;
Display means for displaying an image based on the captured visitor image data, a face detection means for detecting a face image from the image data, and a plurality of registered image data and a plurality of audio data respectively A storage means for storing the information, a parent machine speaker, and an indoor parent device having a parent device control means,
The master control unit extracts a facial feature amount from a visitor's face image data detected by the face detection unit 212, reads the registered face image data from the storage unit, and stores the registered face image data. Determining whether or not there is registered face image data having the matching or approximating feature amount by extracting the feature amount of the face from, and comparing these extracted feature amounts;
When there is registered face image data having the matching or approximate feature amount, the base unit control unit reads out audio data corresponding to the registered face image data from the storage unit and reproduces it from the base unit speaker. Interphone system characterized by. The intercom system according to claim 1, wherein
When there is no registered face image data having the matching or approximate feature amount, the control means can select whether or not to register the visitor face image data in association with arbitrary audio data on the display means The intercom system is characterized in that the face image data of the visitor is associated with arbitrary audio data and registered in the storage means in accordance with a user registration operation. The intercom system according to claim 1 or 2,
When there is no registered face image data having the matching or approximate feature amount, the control means reads out voice data from the storage means to request a visitor from the storage device and reproduces it from the slave unit speaker. An interphone system, wherein a voice of a visitor is detected by the microphone and output from the master speaker. In the intercom system according to any one of claims 1 to 3,
When the face image of the visitor cannot be detected, the base unit control means reads out voice data indicating that the visitor's face cannot be detected from the storage means and reproduces it from the handset speaker and the base unit speaker. Characteristic intercom system. In the intercom system according to any one of claims 1 to 4,
When there is no registered face image data having the matching or approximate feature amount, the master unit control unit reads out voice data indicating that a visitor is not registered from the storage unit and reproduces it from the master unit speaker. Interphone system characterized by that. In the intercom system according to any one of claims 1 to 4,
It further includes an electronic lock that can be opened and closed with an electrical signal.
The registered face image data is classified into a plurality of groups including a specific group,
The intercom system, wherein the control means unlocks the electronic lock for a predetermined time when a visitor belongs to the specific group.

Images