JP2011077694A - Intercom device - Google Patents

Abstract

<P>PROBLEM TO BE SOLVED: To provide an intercom device less in processing loads required for a face detection function. <P>SOLUTION: A range where ratio that face parts of visitors are located is high in image data to be picked up with a camera 101 is specified based on position information of faces parts of the visitors in the past accumulated in a memory 208 by a priority range specification part 2072, and face detection by a face detection circuit 2071 is preferentially performed from the range. <P>COPYRIGHT: (C)2011,JPO&INPIT

Description

  The present invention relates to an intercom apparatus including a camera-equipped entrance slave unit and a living room master unit, and more particularly to an intercom apparatus having a function of detecting a face.

  2. Description of the Related Art Conventionally, an intercom device having a face detection function for detecting a face portion of a visitor among image data captured by a camera of a camera-equipped entrance slave is known. According to the intercom device having such a face detection function, based on the detection result of the face detection function, when the face is difficult to see due to backlighting, the image data is corrected to make it easier to see the visitor's face. By analyzing the visitor's human phase, it is possible to determine whether or not the visitor is a suspicious person registered in advance, and to change the ringing tone by the visitor, which is highly convenient.

Japanese Unexamined Patent Publication No. 2007-259367

  As described above, it is expected that various processes will be performed in the intercom device based on the detection result of the face detection function. For this reason, it is desired to reduce the processing load required for the face detection function in the intercom device as much as possible.

  The present invention has been made in view of the above situation, and it is an object of the present invention to provide an intercom apparatus with a small processing load required for the face detection function.

  In order to solve this problem, the present inventor proposes the following intercom apparatus.

Since the intercom unit's camera-equipped handset is used at a fixed position at the front door, when the visitor's camera is imaged with the camera's front door, the visitor's face is It is assumed that it is located at a certain fixed position in the entire imaged image data. The present invention has been made paying attention to this point, and has the following configuration.
That is, the intercom device of the present application includes a camera for capturing a visitor and a camera-equipped cordless handset having a function of calling a resident, a monitor for displaying an image captured by the camera, and the camera-based entrance cordless handset. And a living room base unit having a function of answering a call. The intercom unit's room master unit is detected by the face detection unit for detecting the face part of the visitor from the image data captured by the camera received from the camera-equipped slave unit, and the face detection unit. A memory for storing position information in the image data of the face portion of the visitor and a face portion of the visitor in image data captured by the camera based on the position information stored in the memory A range specifying unit that specifies a range in which the rate of positioning is high, and the face detecting unit preferentially detects the face portion of the visitor from the range specified by the range specifying unit. It is like that.

  In such an intercom device, based on the position information of the past visitor's face stored in the memory, the range in which the visitor's face is located in the image data captured by the camera is high. Since face detection is performed preferentially from this range, the processing load required for face detection can be reduced compared to the case where face detection is always performed from the entire image data.

When the face detection unit cannot detect the visitor's face portion from the range specified by the range specification unit, the face detection unit detects the visitor's face portion from the entire image data captured by the camera. It can be configured to perform.
As described above, when the visitor's face portion cannot be detected from within the range specified by the range specifying means, the visitor's face portion is detected from the entire image data captured by the camera. Thus, the face portion of the visitor can be reliably detected.

In the memory, position information in the image data of the visitor's face portion detected by the face detection means is stored at predetermined time intervals, and the range specifying means includes the position information On the basis of the above, a range in which the rate at which the face portion of the visitor is located in the image data picked up by the camera may be specified every predetermined time.
According to the intercom apparatus having such a configuration, the range in which the rate of the face portion of the visitor is high can be updated in real time, and the visitor can move even when the position changes as the visitor moves. It is possible to reflect the position of a new visitor by specifying the range in which the ratio of the face part of the person is high.
The timing at which the location information in the image data of the visitor's face portion stored in the memory is stored in the memory is the same as the timing at which the range specifying means specifies a range in which the visitor's face portion is located at a high rate. There may be a certain configuration or a different configuration.

The memory may be configured such that position information in the image data of the visitor's face portion detected by the face detection means is stored every time a call operation is performed.
In the memory, the location information in the image data of the face part of the visitor from when a call is received from the entrance slave unit until the response operation by the master unit is completed, and by operating the master unit, Location information etc. in the image data of the face part of the visitor when the camera of the entrance cordless handset is activated from the aircraft side may be accumulated, but it is accumulated every time a call operation is performed It may be like this.
In this way, if the configuration is such that only the initial position of the visitor when the call operation is performed is stored in the memory, the load on the memory can be reduced, so the processing load required for face detection is further increased. It can be reduced.

  ADVANTAGE OF THE INVENTION According to this invention, the intercom apparatus with little processing load required for a face detection function can be provided.

The figure which shows the whole structure of the intercom apparatus of this embodiment. The block diagram which shows the whole structure of the intercom apparatus of this embodiment. The figure which shows an example of the priority range determined by the priority range determination part.

  Hereinafter, preferred embodiments of the intercom apparatus of the present invention will be described in detail with reference to the drawings.

The intercom apparatus 1 according to this embodiment is schematically configured as shown in FIG. That is, the intercom apparatus 1 includes an entrance slave unit 10 with a camera, and a living room master unit 20 that can receive image data transmitted from the entrance slave unit 10 with a camera and display the received image data on a monitor. Contains.
The entrance slave device 10 with a camera is used for a visitor to call a resident, and is mainly installed at the entrance of a dwelling unit. The room master 20 is used for responding to calls from the camera-equipped entrance slave 10 and is installed in the dwelling unit. The camera-equipped entrance slave unit 10 and the living room master unit 20 are connected via a transmission line 30.

  Hereinafter, the configuration of the camera-equipped entrance slave unit 10 and the room master unit 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 includes a camera 101 for photographing a visitor, a call button 102 for a visitor to call a resident, a handset microphone 103 for calling a resident, and a child. A communication circuit 105 for making a call with a resident using the machine speaker 104, the child machine microphone 103, and the child machine speaker 104, a modulation circuit 106 for modulating the video taken by the camera 101, and the room master unit 20 are communicated. A slave unit IF 107 and a slave unit CPU 108 for controlling each part of the entrance slave unit 10.

  The base unit 20 includes a base unit IF 201 for communicating with the entrance slave unit 10, a base unit microphone 202 and a base unit speaker 203 for communicating with the slave unit microphone 103 and the slave unit speaker 104 of the entrance slave unit 10, a visitor A call circuit 204 for responding to a call from the phone, a call circuit 205 for making a call with a visitor using the master microphone 202 and the master speaker 203, and a video modulated by the modulation circuit 106 of the front door 10 A demodulating circuit 206 for demodulating, a video processing unit 207 for performing various processing of image data demodulated by the demodulating circuit 206 as necessary, a memory 208, a monitor 209 for outputting image data, and the room master 20 A master CPU 210 for controlling each of the circuits is provided.

The video processing unit 207 has a face detection circuit 2071 for detecting the position of the face portion of the visitor in the image data captured by the camera 101 of the front door 10.
The memory 208 is for accumulating position information in the image data of the face portion of the visitor detected by the face detection circuit 2071. In this memory 208, position information of past visitors is sequentially accumulated. In the present embodiment, the memory 208 will be described assuming that the position information in the image data of the face portion of the visitor detected by the face detection circuit 207 is accumulated every time a call operation is performed. Not limited to this, the position information in the image data of the face part of the visitor until the response operation by the living room master unit 20 is completed after the call from the entrance cordless handset 10 is operated, and the living room master unit 20 is operated. By doing so, the position information and the like in the image data of the face portion of the visitor when the camera 101 of the front door slave 10 is activated from the side of the living room master 20 and captured may be accumulated.
The video processing unit 207 is a priority range specifying unit that specifies a range in which a visitor's face portion is located at a high rate in image data captured by the camera 101 based on position information accumulated in the memory 208. 2072.

Next, the operation of the intercom apparatus 1 configured as described above will be described.
When a visitor calls the resident by pressing the call button 102, a call signal is transmitted from the child device CPU 108 to the living room parent device 20 via the child device IF 107, and the parent device CPU 210 in the living room parent device 20 receives the parent device IF 201. Is controlled to receive a call signal via the call circuit 205, and to ring a ring tone from the main unit speaker 203 via the call circuit 205, and to supply power to drive the camera 101 of the front door unit 10. Since it is the same as that of the prior art, detailed description is omitted. Here, the camera 101 of the front door slave 10 is driven, and the captured image data is modulated by the modulation circuit 106 and transmitted from the slave IF 107 to the living room master 20 via the transmission line 30 and displayed on the monitor 209. The operation until it is performed will be described.

The room master 20 receives the image data transmitted from the entrance slave 10 and imaged by the camera 101 and modulated by the modulation circuit 106 from the slave IF 107 via the master IF 201. The received modulated image data is demodulated by the demodulation circuit 206 and input to the video processing unit 207. Further, the location information of the visitor when the call operation is performed by the visitor is stored in the memory 208.
When image data is input to the video processing unit 207, the face detection circuit 2071 detects the position of the face portion of the visitor in the entire image data captured by the camera 101. Specifically, an edge (contour) of image data captured by the camera 101 is detected and compared with image data assuming a human face, a face portion is detected.
This detection is performed preferentially from a range in which the face portion of the visitor is located in the image data specified by the priority range specifying unit 2072 and captured by the camera 101 (hereinafter referred to as a priority range). Is called. FIG. 3 is a diagram showing an example of this priority range, and shows a priority range a in the entire image data A captured by the camera 101, which is a range in which the rate at which a visitor's face portion is located is high. .
As described above, the face detection circuit 2071 according to the present embodiment is configured so that the face of the visitor in the image data captured by the camera 101 based on the position information of the past visitor's face stored in the memory 208. Since face detection is performed preferentially from a range in which the ratio of the portion is high, the processing load required for face detection can be reduced compared to the case where face detection is always performed from the entire image data.

This priority range is specified based on the location information of past visitors stored in the memory 208. In the present embodiment, a predetermined area larger than the size of the human face is determined as the priority range.
Specifically, for example, each time a visitor performs a call operation, this priority range is the coordinates that determine the priority range, upper left coordinates (x1, y1), lower left coordinates (x1, y2), upper right coordinates (x2 , y1) and the lower right coordinates (x2, y2) are stored as position information in the memory 208, and the average value of the coordinate data is obtained.

  If the face portion of the visitor cannot be detected from the priority range specified by the priority range specifying unit 2072, the face detection circuit 2071 uses the entire image data input from the demodulation circuit 206, that is, the camera 101. The face portion of the visitor is detected from the entire captured image data. As described above, when the face portion of the visitor cannot be detected from within the priority range, the visitor's face portion is detected from the entire image data captured by the camera 101, so that the visitor's face portion is detected. The face portion can be detected reliably.

  When the face detection circuit 2071 detects the visitor's face in this manner, the video processing unit 207 makes the brightness of the face darker than the brightness of the entire image based on the detection result. If so, various processes are performed each time, such as a backlight correction process for brightening the face portion, and image data is output to the monitor 209.

  As described above, according to the intercom apparatus 1 of the present embodiment, the priority range specifying unit 2072 is imaged by the camera 101 based on the position information of the past visitor's face stored in the memory 208. In this image data, the range in which the face portion of the visitor is located is specified, and the face detection circuit 2071 preferentially detects the face from this range, so the face is always detected from the entire image data. The processing load required for face detection can be reduced compared to the case where detection is performed.

  Note that the face detection by the face detection circuit 2071 may be performed in any other range as long as the above range is detected preferentially, but the face detection circuit 2071 of the present embodiment may be used. When the face portion of the visitor cannot be detected from the range specified by the priority range specifying unit 2072, the face portion of the visitor is detected from the entire image data captured by the camera 101. Therefore, it is possible to reliably detect the face part of the visitor.

The memory 208 of this embodiment stores the position information in the image data of the face part of the visitor detected by the face detection circuit 2071 every time the call operation is performed. Only the initial position of the visitor at the time of being stored is stored in the memory 208, so that the load on the memory 208 can be reduced and the processing load required for face detection can be further reduced.

Although the intercom apparatus 1 of the present embodiment has been described as described above, the position information in the image data of the face portion of the visitor detected by the face detection circuit 2071 is stored in the memory 208 for a predetermined time (for example, 1 The priority range specifying unit 2072 may specify the priority range every predetermined time based on the position information. The priority range in this case is, for example, the upper left coordinates (x1, y1), the lower left coordinates (x1, y2), the upper right coordinates (x2, y1), and the lower right coordinates, which are the coordinates for determining the priority range for the past 10 minutes in the memory 208. The coordinate (x2, y2) value is accumulated, and the average value of the coordinate data is obtained.
With the intercom device configured as described above, the priority range can be updated in real time, and even when the position of the visitor changes due to the movement of the visitor, a newer visitor's It can be reflected to the position.
It should be noted that the timing at which the position information in the image data of the visitor's face portion stored in the memory 208 is stored in the memory 208 is configured to be the same as the timing at which the priority range specifying unit 2072 specifies the priority range. It is good also as a different structure.

1 .. Interphone device 10.. Entrance slave unit with camera, 20.. Base unit with room 30.. Transmission line 101, Camera 102, Call button 103, Handset microphone 104, Child・ Speaker 105, ・ Communication circuit 106 ・ ・ Modulation circuit 107 ・ Slave unit IF 108 ・ Slave unit CPU 201 ・ Base unit IF 202 ・ Base unit microphone 203 ・ Base unit speaker 204 .. Call button, 205 .. Call circuit, 206 .. Demodulator circuit, 207 .. Video processing unit, 208 .. Memory, 209 .. Monitor, 210 .. Master CPU, 2071. Detecting means), 2072... Priority range specifying unit (range specifying means).

Claims (4)

Provided with a camera for capturing a visitor and a function of calling a resident, a monitor with a camera for displaying a captured image of the camera, and a function for responding to a call from the camera with a camera In an intercom device having a living room base unit,
The living room master unit is a face detection unit that detects a face part of a visitor out of the image data captured by the camera received from the camera-equipped entrance slave unit,
A memory for storing position information in the image data of the face portion of the visitor detected by the face detection means;
Range specifying means for specifying a range in which the rate at which the face part of the visitor is located is high in the image data captured by the camera based on the position information stored in the memory; And
The face detection means is configured to preferentially detect the face portion of the visitor from the range specified by the range specification means;
Intercom device. When the face detection unit cannot detect the visitor's face portion from the range specified by the range specification unit, the face detection unit detects the visitor's face portion from the entire image data captured by the camera. Is supposed to do the
The intercom apparatus according to claim 1. In the memory, position information in the image data of the face portion of the visitor detected by the face detection means is stored every predetermined time,
The range specifying means specifies, for each predetermined time, a range in which a ratio of a visitor's face portion is high in image data captured by the camera based on the position information. Yes,
The intercom apparatus according to claim 1 or 2. In the memory, position information in the image data of the visitor's face portion detected by the face detection means is stored every time a call operation is performed.
The intercom apparatus according to claim 1 or 2.

Images