JP3942606B2 - Change detection device - Google Patents

Description

  This description relates to a change detection technique for detecting and reporting the occurrence of a video change, and in particular, monitoring information generated by detecting the occurrence of a video change in a monitoring system is connected to a PC (Personal Computer) connected via a network or the like. The present invention relates to a change detection device that transmits to a mobile terminal or the like.

  In recent years, video intrusion and video distribution technologies using network technologies such as the Internet and LAN have been developed for intruder monitoring using a surveillance camera. Furthermore, a technique for storing video as digital data in a storage device such as a hard disk or a DVD (Digital Versatile Disc) has been developed.

  In addition, a technique (for example, see Patent Document 1) that detects a change in video acquired by a monitoring camera using an image recognition technique and transmits the change as monitoring information to a network-connected PC or portable terminal, and further, time. There is known a monitoring information transmission technique that can specify a monitoring schedule and a monitoring area by providing a table for holding parameters related to the area (see, for example, Patent Document 2).

Furthermore, as an image recognition technique, there is a technique for detecting the change of the image, calculating the size and center of gravity of the moving object, and processing the moving object continuously over a plurality of frames to track the moving direction of the moving object. It is known (for example, refer to Patent Document 3).
Japanese Patent Application No. 2002-347202 (page 5-6, Fig. 1) Japanese Patent Application No. 2004-146698 Japanese Unexamined Patent Publication No. 2000-105835 (pages 7-9, 1, 7, 9, 10-12, 14-16)

  In the conventional monitoring information transmission technology, the notification destination of the monitoring information when an abnormality is detected is determined in advance, and there is no means for automatically changing the notification destination based on the detected monitoring information, and the notification destination is changed. In order to do this, there is no other way but to manually rewrite the report destination of the monitoring information in the monitoring information transmission technology.

  However, there is a request for transmitting the monitoring information to different report destinations depending on the location where the moving object is detected, the size of the moving object, a combination thereof, and the like for the image of one monitoring camera.

  An object of the present invention is to provide a change detection device capable of transmitting monitoring information to different report destinations according to the location where the moving object is detected, the size of the moving object, and the like.

  In order to achieve the above object, a change detection device according to the present invention includes a monitor image input unit obtained by an imaging device, and a region designation that designates N (N is a positive integer) regions on the monitor image. A notification destination designating unit for designating a notification destination of an image change in the monitoring image according to a feature of the image change, a change detection unit for detecting an image change in the N areas, and the change detection unit. A feature extraction unit that extracts at least one feature of each image change, a monitoring information generation unit that generates monitoring information related to each detected image change, and a transmission unit for the monitoring information, the transmission unit Is configured to transmit the monitoring information to a predetermined report destination set in the report destination designation unit based on the detected feature of the image change.

  In this specification, the term “monitoring information” is used for explanation. For example, the terms “warning information” and “detection information” are similar terms and are included in the present invention. The “monitoring information” is not limited to the meaning of the term “monitoring”.

  In the change detection apparatus according to the present invention, the feature extracted by the feature extraction unit includes identification information of a region where an image change is detected, and monitoring information related to the image change is predetermined based on the identification information. It is configured to be sent to the report destination.

  In the change detection device according to the present invention, the feature extracted by the feature extraction unit further includes size information of the image change area, and the image change is determined based on the area identification information and the size information. The related monitoring information is configured to be transmitted to a predetermined report destination.

  In the change detection apparatus according to the present invention, the feature extracted by the feature extraction unit further includes the occurrence time of the image change, and monitoring information related to the image change based on the identification information and the occurrence time Is configured to be transmitted to a predetermined report destination.

  In the change detection apparatus according to the present invention, the feature extracted by the feature extraction unit includes a moving direction of the image change in the monitoring image, and the monitoring related to the image change based on the moving direction of the image change. The information is configured to be transmitted to a predetermined report destination.

  In the change detection apparatus according to the present invention, the feature extracted by the feature extraction unit relates to an order of whether or not an image change is detected in a predetermined order in two predetermined areas of the N areas. It includes a feature, and monitoring information related to the image change is transmitted to a predetermined report destination based on the feature.

  Further, in the change detection device according to the present invention, the feature extracted by the feature extraction unit further includes a feature related to time whether or not the image change is detected in the two predetermined regions within a predetermined time, Based on the feature relating to the order and the feature relating to the time, monitoring information relating to the image change is configured to be transmitted to a predetermined report destination.

  In order to achieve the above object, a monitoring system according to the present invention includes a video signal input unit, an encoder unit that converts a video signal from the video signal input unit into digital image data, and a digital image from the encoder unit. A video storage device having a function of storing data, a notification device for reading a stored video of the video storage device and detecting a change in the video, a video signal input unit, an encoder unit, a video storage device, and a notification The notification device includes a monitoring information generation unit that generates monitoring information related to a detected video change, and a feature of the detected video change. And a report destination determination unit that determines a transmission destination of the monitoring information.

  In this specification, the term “monitoring system” is used for explanation. For example, the term “report system” and “object detection system” are similar terms and are included in the present invention. .

  In the monitoring system according to the present invention, the video change feature includes at least a position of the video change on the digital image data, and the notification device is configured to monitor the monitoring information based on the position of the video change. Is configured to determine a report destination to which to transmit.

  In the monitoring system according to the present invention, the video change feature further includes a size of the video change area, and the report destination to which the monitoring information should be transmitted based on the video change position and the size. Is configured to determine.

  In the monitoring system according to the present invention, the video change feature further includes the video change occurrence time, and the notification device is based on the video change occurrence time and the video change position. The report destination to which the monitoring information is to be transmitted is determined.

  In order to achieve the above object, according to the change detection method of the present invention, N monitoring areas (N is a positive integer) are set in advance in the imaging range of the camera, and the image in the video from the camera is set in advance. Create a report destination table in which change report destinations are set according to image change characteristics, read video from a video storage device that stores video from the camera, detect image changes in the read video, The feature of the detected image change is extracted, monitoring information related to the detected image change is created, and the monitoring information is transmitted to a predetermined report destination based on the extracted feature.

  In the change detection method according to the present invention, the extracted image change feature includes a monitoring region where the image change has occurred, and the monitoring information is predetermined based on the monitoring region in which the image change has occurred. Sent to

  In the change detection method according to the present invention, the extracted image change feature further includes a size of the image change area, and the monitoring information is sent to a predetermined report destination based on the monitoring area and the size. Sent.

  In the change detection method according to the present invention, the feature of the image change thus extracted further includes an occurrence time of the image change, and the monitoring information is based on the occurrence time and the monitoring area. Sent first.

  In the change detection method according to the present invention, the extracted image change feature includes a moving direction of the image change, and monitoring information related to the image change is notified based on the moving direction of the image change. Sent first.

  In the change detection method according to the present invention, the extracted image change feature is a feature related to an order of whether or not an image change is detected in a predetermined order in two predetermined regions of the N regions. And the monitoring information transmits the monitoring information to a predetermined report destination based on the characteristics relating to the order.

  Further, in the change detection method according to the present invention, the extracted image change feature further includes a feature related to a time whether or not the image change is detected in the two predetermined regions within a predetermined time, The monitoring information is transmitted to a predetermined report destination based on the characteristics relating to the order and the characteristics relating to time.

  In order to achieve the above object, the notification device according to the present invention is configured such that the notification device according to the present invention includes an input unit for a monitoring image obtained by an imaging device and N (N is a positive integer) from the monitoring images. An area designating unit for designating an area of the N regions, a change detecting unit for detecting image changes in the N regions, a report destination designating unit for designating the report destinations of the N regions, and a monitoring information generating unit. The monitoring information generation unit is configured to transmit monitoring information to a report destination set in the report destination designation unit based on a detection result of the change detection unit.

  Further, in the notification device according to the present invention, the change detection unit detects a moving direction of the object in the monitoring image based on an image change, and sends monitoring information to a predetermined reporting destination based on the moving direction of the object. Configured to transmit.

  Further, in the notification device according to the present invention, the change detection unit detects a feature of the object in the monitoring area based on an image change, and the notification set in the report destination designation unit based on the feature of the object The monitoring information is configured to be transmitted first.

  In order to achieve the above object, a notification device according to the present invention includes a monitoring image input unit obtained by an imaging device, and an area designation that designates N (N is a positive integer) area from the monitoring image. A change detection unit that detects an image change in the N areas, a report destination designation unit that designates a report destination of the N areas, and a monitoring information generation unit, and the monitoring information generation unit includes: When the image change is detected in at least one of the N areas and the image change is detected in at least one of the other N areas, the notification destination designation is performed. The monitoring information is configured to be transmitted to the report destination set in the department.

  In order to achieve the above object, a notification device according to the present invention includes a monitoring image input unit obtained by an imaging device, and an area designation that designates N (N is a positive integer) area from the monitoring image. A change detection unit that detects an image change in the N areas, a report destination designation unit that designates a report destination of the N areas, and a monitoring information generation unit, and the monitoring information generation unit includes: When an image change is detected in at least one of the N areas, and an image change is detected in at least one of the other N areas after a predetermined time, The monitoring information is configured to be transmitted to the report destination set in the report destination designation unit.

  In order to achieve the above object, the notification device according to the present invention includes an input unit for a monitoring image obtained by an imaging device, an area specifying unit for specifying at least one monitoring region from the monitoring image, and the monitoring region. A detection unit for detecting a target object, a report destination designation unit for designating a report destination according to the characteristics of the target object, and a monitoring information generation unit, wherein the monitoring information generation unit is configured to detect the detected target object. The monitoring information is configured to be transmitted to a predetermined reporting destination set in the reporting destination designating unit based on the above characteristics.

  In order to achieve the above object, a monitoring system according to the present invention includes a video signal input unit, an encoder unit that converts a video signal from the video signal input unit into digital image data, and a digital image from the encoder unit. A video storage device having a function of storing data, and a notification device that reads out the stored video of the video storage device and detects a change in the video, wherein the notification device is the digital image in which the change in the video is detected. The monitoring information is transmitted to a predetermined report destination based on the position on the data.

  In order to achieve the above object, a monitoring system according to the present invention includes a video signal input unit, an encoder unit that converts a video signal from the video signal input unit into digital image data, and a digital image from the encoder unit. A video storage device having a function of storing data, and a notification device that reads out the stored video of the video storage device and detects characteristics of the object from the image data. The monitoring information is configured to be transmitted to a predetermined report destination based on the characteristics.

  According to the change detection device of the present invention, the monitoring image input unit obtained by the imaging device, the region designating unit for designating N regions on the monitoring image, and the notification of image change in the monitoring image A notification destination designating unit that designates each of the image changes in advance, a change detection unit that detects an image change in the N areas, and a feature that extracts at least one feature of each image change from the change detection unit In the configuration including an extraction unit, a monitoring information generation unit that generates monitoring information related to each detected image change, and a transmission unit for the monitoring information, the transmission unit is characterized by the detected image change. Since the monitoring information is transmitted to the predetermined reporting destination set in the reporting destination designation unit based on the monitoring information, for example, the monitoring information is sent to different reporting destinations depending on the location where the moving object is detected, the size of the moving object, etc. Send Can.

Embodiments of the present invention will be described below with reference to the drawings. Like members are given like reference numerals.
First, a network monitoring system according to an embodiment of the present invention will be described with reference to FIG.

FIG. 10 is a diagram showing a configuration of a network monitoring system used in the present invention.
10, 1001-1, 1001-2,..., 1001-n (n = 1, 2,...) Represent a plurality of surveillance cameras (imaging devices). In addition, when generically referring to surveillance cameras, it is represented by 1001. The same applies to the other devices in FIG.

  1002 is, for example, a transmission path for video signals such as a LAN (Local Area Network), and 1003-1, 1003-2,..., 1003-n (n = 1, 2,...) Are Web encoders. is there. Reference numeral 1004 denotes a video storage device, which has a function of storing video from the surveillance camera.

  1005-1, 1005-2,..., 1005-m (m = 1, 2,...) Are browser PCs and have a function of managing the entire monitoring system. 1006 is a hub, 1007 is a notification device, 1008 is a modem, 1009 is a transmission line using a public line, 1010 is a WAN (Wide Area Network) network such as the Internet, 1011 is a switching system of a mobile phone company, 1012-1 and 1012-2 ,..., 1012-l (l = 1, 2,...) Are portable terminals, 1013-1, 1013-2,..., 1013-p (p = 1, 2,...) It is a client PC.

  Note that there may be one surveillance camera, web encoder, or the like, or a plurality of surveillance cameras may be connected to one web encoder. It is also possible to use a device in which functions such as a monitoring camera, a Web encoder, a video storage device, and a notification device are integrated. Further, the system described with reference to FIG. 10 can be realized by using, for example, an in-body LAN of a robot, an in-vehicle LAN of a car, a network constructed in an apparatus of equipment, or the like.

  The monitoring camera 1001, the Web encoder 1003, the video storage device 1004, the hub 1006, the notification device 1007, the modem 1008, and the client PC 1013 are connected to each other via a transmission line 1002 such as a LAN. An exchange system 1011 of a cellular phone company is connected to a modem 1008 via a transmission line 1009 and a network 1010. The exchange system 1011 of the mobile phone company is connected to the mobile terminal 1012 by wireless or the like.

  FIG. 11 is a block diagram showing an embodiment of a schematic configuration of the video storage device 1004, browser PC 1005, notification device 1007, portable terminal 1012, and client PC 1013 used in the present invention. Of course, the installed software (operation program) is different depending on the functional difference, but the hardware configurations are similar, so an example is shown here. Reference numeral 1101 denotes a CPU (Central Processing Unit), 1102 denotes a memory for storing operation programs, and 1103 denotes a network interface.

  Reference numeral 1104 denotes a storage device. The storage device 1104 uses a recording medium having a large storage capacity, for example, a VTR or the like, as a storage device of the video storage device 1004, but uses a random access magnetic disk (HD: hard disk). And DVD are also suitable. Reference numeral 1105 denotes an input interface, 1108 denotes an input device such as a keyboard, 1109 denotes a pointing device such as a mouse, 1106 denotes a video interface, 1107 denotes a monitor, and 1110 denotes a bus.

  The CPU 1101 to the video interface 1106 are connected to each other via the bus 1110, the monitor 1107 is connected to the bus 1110 via the video interface 1106, and the input device 1108 and the pointing device 1109 are connected via the input interface 1105. A bus 1110 is connected. The network interface 1103 is connected to a LAN transmission line 1002. Furthermore, it may be connected to the transmission line 1009 of the public line as necessary. When the configuration of FIG. 11 is applied to the notification device 1007, the network interface 1103 and the transmission path 1002 connected thereto constitute an image input unit of the notification device and receive video from the video storage device 1004.

  Here, for example, it is assumed that the monitoring camera 1001 is installed at a predetermined monitoring position. This surveillance camera continuously captures images continuously, and the captured images are stored in the image storage device 1004 via the LAN transmission path 1002, the Web encoder 1003, and the hub 1006.

  The notification device 1007 has a function of taking out a video from the video storage device 1004, comparing the previously taken-out video with the currently taken-out video, detecting a change in the video, detecting abnormality by so-called image recognition technology, and storing it. . In addition, since the technique for detecting an abnormality by the image recognition technique is a conventionally well-known method such as a method of detecting a change in luminance component of the previous and subsequent frame screens, or a method of comparing the spectrum of a video signal, Detailed description is omitted.

  As a result of the comparison, if an abnormality is detected, such as when there is a change in the video, it is assumed that there is an abnormality. For example, the abnormal image and the date and time when the abnormality was detected are stored in the notification device 1007 together with a necessary message. At the same time, the report destination is selected according to the content of the change, and the information is distributed as monitoring information to the user's portable terminal 1012 or the client PC 1013 as the report destination. That is, the monitoring information is distributed from the reporting device 1007 to the portable terminal 1012 and the client PC 1013 via the hub 1006, the modem 1008, and the network 1010 via the modem 1008 connected to the switching system 1011 of the cellular phone company and the client PC 1013. . The message may be, for example, “An error occurred in xx month, xx day, xx hour, xx minute, and xx seconds.”

Next, the notification device (change detection device) 1007 will be described with reference to FIG.
FIG. 9 is a block diagram showing a basic configuration of a notification device 1007 of the present invention that can handle a plurality of monitoring areas and a plurality of notification destinations. The function realizing means described below may be any circuit or device as long as it can realize the function, and part or all of the function can be realized by software. is there. Furthermore, the function realizing means may be realized by a plurality of circuits, or the plurality of function realizing means may be realized by a single circuit.

  In FIG. 9, the memory unit 1201 has a plurality of memories 1201-1, 1201-2,..., 1201-q (q = 1, 2,...). An area table in which different monitoring areas are set is stored. Here, the monitoring area refers to an area in which image recognition processing is executed in the entire area of the video imaged by each monitoring camera. One memory unit 1201 may be provided for each monitoring camera, or one memory unit including a plurality of memories set for each of all the monitoring areas of all the monitoring cameras. It may be in the form.

The image input unit 1202 takes out the video of the surveillance camera from the video storage device 1004 and outputs it to the detection processing unit 1203.
The detection processing unit 1203 includes a plurality of image recognition processing units, an image recognition processing unit 1203-1, an image recognition processing unit 1203-2,..., An image recognition processing unit 1203-q (q = 1, 2,. , And the area tables stored in the memory 1201-1, the memory 1201-2,.

  Then, based on the monitoring areas defined by these area tables, the video input from the image input unit 1202 is subjected to image processing, and intruding object detection processing is performed. That is, the detection processing unit 1203 performs well-known image recognition processing only on the area defined by each area table stored in the memory unit 1201 in the area of the video captured by the surveillance camera, and detects a change in the video. To do. When there is a change in the video, the changed portion of the video that is the detection result of the detection processing unit 1203 is output to the feature extraction processing unit 1204. In the following, the detected change part of the video is handled as an object to be monitored.

  The feature extraction processing unit 1204 is based on the detection result received from the detection processing unit 1203, for example, the feature of the detected object, for example, the size of the object, the shape of the object, the color of the object, and the moving speed of the object. The moving direction of the target object, the detected region of the target object, and the like are detected and output to the conversion unit 1205 as the feature information of the target object. The feature extraction processing unit 1204 can identify whether the detected object is, for example, a person or a car, and if it is a car, its color can be specified. It goes without saying that other discrimination is possible if necessary. Note that the feature information includes the time when the change in the image is detected by the detection processing unit 1203, the date, the number of the monitoring camera, and the like. Needless to say, it is not always necessary to include all the above items as the features of the object, and only the necessary number of items may be detected according to the monitoring target and the monitoring purpose.

  The conversion unit 1205 includes a monitoring information generation unit 1206, a notification destination determination unit 1207, a transmission unit 1209, and a notification destination table A1208. Based on the output result of the feature extraction processing unit 1204, generation of monitoring information, determination of a notification destination, and monitoring Send information.

The monitoring information generation unit 1206 generates monitoring information based on the feature information of the object received from the feature extraction processing unit 1204.
The report destination determination unit 1207 searches the report destination table A1208 based on the feature information of the object received from the feature extraction processing unit 1204, and acquires the report destination that transmits the monitoring information. Here, the report destination table A1208 stores information for specifying a place to send the monitoring information, such as a mail address of the report destination. The report destination table A1208 also stores conditions for determining the report destination. That is, a report destination corresponding to the monitoring area where the object is detected, the size of the object, and the like is stored in advance.

The transmission unit 1209 transmits the generated monitoring information to the report destination determined by the report destination determination unit 1207.
It is also possible to store the detection result of the detection processing unit 1203 and the transmitted monitoring information as a log in a memory in the reporting device.

  Note that the function of the notification device 1007 shown in FIG. 9 can be realized by the processing of the CPU 1101, the memory 1102, the network interface 1103, the storage device 1104, and the like described above. The image input unit corresponds to the transmission path 1002 and the network interface 1103 (FIG. 11).

  An example of the operation of the monitoring system shown in FIG. 10 will be described with reference to the flowchart shown in FIG. FIG. 12 illustrates an operation in which the notification device 1007 detects an abnormality in a video stored in the video storage device 1004 due to, for example, a video change and transmits monitoring information to the mobile terminal 1012 or the client PC 1013. It is a flowchart figure.

  In step 201, monitoring is started, that is, monitoring of the monitoring system is started. Image compression data generated by digitally compressing a monitoring video from a predetermined monitoring camera 1001 by the Web encoder 1003 is stored in the video storage device 1004 via the hub 1006.

  Here, as the compressed image data stored in the video storage device 1004, for example, information such as the shooting date and time, the channel number of the monitoring camera 1001, and the compression format is stored together with the digital compressed image. In addition, it is conceivable that various monitoring camera images are captured by scheduling in advance under the management of the browser PC 1005 or selected based on abnormality detection information.

  In step 202, the image input unit 1202 of the notification device 1007 acquires one frame of video from the video storage device 1004. In this step, all images input from the surveillance camera 1001 to the video storage device 1004 are read in the order of input and supplied to the image input unit 1202 of the notification device 1007.

  In step 203, the detection processing unit 1203 of the notification device 1007 compares the previous video and the video currently input from the image input unit 1202, for example, by image recognition processing, and detects a change in the video. . As described above, the detection processing unit 1203 performs image recognition processing only on the monitoring area defined by the area table stored in the memory unit 1201, and detects a change in video in each monitoring area.

  In step 204, the detection processing unit 1203 determines whether or not there is a change in the video by the image recognition processing in step 203. Here, it goes without saying that whether there is a change in the image is determined for each monitoring area. Whether or not there is a change in the image, for example, a change in luminance value is detected, but in this case, a predetermined threshold is set for abnormality detection, and a change below the predetermined value is not determined to be abnormal. A method for minimizing as much as possible can be set if necessary.

As a result of the detection, if it is determined that the video has changed, the process proceeds to step 205. If not, the process returns to step 202 and the same processing is executed for the next input video.
In step 205, the feature extraction processing unit 1204, which has received the detection result of the detection processing unit 1203 in step 204, changes the image, that is, the feature of the detected object (for example, the region where the change is detected, the size of the region). And the like). The detected feature information is output to the monitoring information generation unit 1206 and the report destination determination unit 1207 included in the conversion unit 1205.

  Step 206 is a step in which the monitoring information generation unit 1206 that has received the feature information from the feature extraction processing unit 1204 generates the monitoring information. The generated monitoring information is output to the transmission unit 1209. Here, the content of the monitoring information may be, for example, a message that describes one or more of items such as the time when the change of the image is detected, the date, the number of the monitoring camera, and the feature of the detected object. Good. Furthermore, it goes without saying that the monitoring information can include a still image and / or a moving image of the video of the monitoring camera when the video changes, as necessary.

  Further, the message described above may be superimposed on a still image or the like of the video of the surveillance camera. Note that the size of the video, that is, the number of pixels of the video and the compression rate may be appropriately changed according to the data size that can be received by the client PC 1013, the communication line capacity, etc., so that the user can receive the video.

  Step 207 is a step in which the report destination determination unit 1207 selects the report destination of the monitoring information. The report destination determination unit 1207 searches the report destination table A1208 based on the feature information received from the feature extraction processing unit 1204, and selects a report destination. The selected report destination is output to the transmission unit 1209. If there is no report destination, no output to the transmission unit 1209 is performed.

  Step 208 is a step in which the transmission unit 1209 transmits the monitoring information to the mobile terminal 1012 or the client PC 1013. That is, the monitoring information generated by the monitoring information generation unit 1206 is transmitted to the notification destination selected by the notification destination determination unit 1207. The transmission method is generally e-mail, but any other e-mail method may be used as long as the mobile terminal 1012 and the client PC 1013 can receive the monitoring information. Step 209 is a monitoring end step.

  As described above, in the notification device 1007 according to the present embodiment, a plurality of monitoring areas are set in the area of the video captured by the monitoring camera, and the monitoring information transmission operation according to the detection result in each of the monitoring areas. Can do. By setting a plurality of monitoring areas in this way, more detailed detection information can be obtained for the area captured by the monitoring camera, and it is possible to transmit the monitoring information to a report destination having a need. Compared with the case where the image recognition process is performed on the entire area, the processing speed is increased, and the memory capacity required for the image recognition process can be reduced.

  In the above embodiment, a part of the entire video area is set in advance as a monitoring area, and when a change in the video, that is, an object is detected in the monitoring area, a notification is made to a predetermined notification destination. Explained when to do. However, as another method, the image recognition process is performed on the entire area of the video, the position of the target object is grasped from the center of gravity position of the detected target object, and the corresponding report destination from the report destination table based on the position. You can also select the monitoring information report destination.

  Note that the processing steps shown in FIG. 12 described above are merely examples, and it goes without saying that in an actual monitoring scene, the function of the notification device is realized by adaptively changing according to the monitoring target or the like.

Next, a reporting device according to another embodiment of the present invention will be described with reference to FIGS. The configuration of the notification device is the same as that shown in FIG.
FIG. 1 is an example of an image of a surveillance camera installed in front of the main gate when monitoring the vicinity of the main gate of a building. Reference numeral 101 denotes the entire video area of the monitoring camera, and monitoring of a place where a building named Building No. 1 is located at the end of the arrow at the top of the figure and a prohibited entry area exists at the end of the right arrow will be described. Reference numeral 102 denotes a monitoring area (1) set on the road leading from the main gate to Building No. 1, and reference numeral 103 denotes a monitoring area (2) set on the road leading from the main gate to the prohibited entry area. 104 is a person who entered from the main gate.

  In the example described here, if the person who entered from the main gate goes to Building 1 or goes to the no-entry area, the destination information is detected by image recognition processing. In this example, the monitoring information is transmitted to the reception, and the monitoring information is transmitted to the guard station when it is determined that the monitoring information is being entered.

  FIG. 2 shows an example of the monitoring area set for the video of the monitoring camera of FIG. FIG. 2 divides the video of FIG. 1 into 16 × 12 blocks. A block indicated as “1” indicates a block included in the monitoring area (1), and a block indicated as “2” indicates a monitoring area. This indicates that the block is included in (2).

  A blank block indicates that the image recognition process is not executed. In this example, when the person 104 enters the monitoring area (1) 102, the block indicated as “1” is in the detection state. Similarly, when the person 104 enters the monitoring area (2) 103, the block indicated as “2” is in the detection state.

  The monitoring area is set, for example, by an operator such as the browser PC 1005 using a pointing device 1109 such as a mouse provided in the browser PC 1005. Specifically, a desired monitoring area can be set by clicking each block with a mouse or by dragging and dropping with a mouse to specify a range. The set monitoring area (1) and monitoring area (2) are stored as area tables in the memory 1201-1 and the memory 1201-2 shown in FIG.

  FIG. 3 is a diagram showing an example of the contents of the notification destination table A1208 for designating the notification destination of the monitoring information by the monitoring area where the moving object is detected. In this table, a report destination corresponding to the monitoring area is set. In the example shown in FIG. 1, the reporting destination of the monitoring information in area 1 is reception of Building No. 1, and the reporting destination of the monitoring information in area 2 is a guard station.

  The report destination is a mail address when using e-mail as monitoring information, and a telephone number when calling such as a telephone. In addition, as long as it is information that can specifically identify the location where the monitoring information is transmitted, the reporting means and the format are not limited. As described above, in the notification destination table A1208, the notification destination of the monitoring information is set in advance when the monitoring system is installed. It is also possible to set the report destination table A1208 from the browser PC 1005, the mobile terminal 1012, and the client PC 1013 after the installation of the monitoring system.

  Next, an example of a process for detecting a moving object by image recognition and selecting a report destination of monitoring information based on the detected area will be described with reference to the flowcharts of FIGS. .

  Step 401 is a step in which the detection processing unit 1203 (FIG. 9) detects a change in video by image recognition processing and determines whether or not there has been a video change. If a video change is detected, the process proceeds to step 402; otherwise, the process of step 401 is continued.

  Step 402 is a step in which the feature extraction processing unit 1204 determines the number of the area where the video change is detected. In the example of FIG. 1, if a video change is detected in the monitoring area (1) 102, the process proceeds to step 403, and if a video change is detected in the monitoring area (2) 103, the process proceeds to step 404.

  In the feature extraction processing unit 1204, for example, when a video change is detected by the image recognition processing unit 1203-1, the region number is determined such that a video change is detected in the monitoring region (1). It is possible. Of course, the present invention is not limited to this, and it is needless to say that it is possible to determine a region where a change in the image is detected.

  Step 403 generates monitoring information when the conversion unit 1205 detects a change in the video in the monitoring area (1), and refers to the notification destination table A1208 shown in FIG. ) To obtain the reporting destination of the monitoring information and transmit the monitoring information. In this example, the monitoring information is transmitted to the first building reception.

  In step 404, as in step 403, when the change of the video is detected in the monitoring area (2) by the conversion unit 1205, the monitoring information is generated. Also, referring to the table of FIG. This is a step of acquiring a monitoring information report destination corresponding to 2) and transmitting the monitoring information. In this example, the monitoring information is transmitted to the guard station.

  Step 405 is a step of determining whether to continue or end the monitoring. Here, the determination of whether to continue or end the monitoring is made by the CPU of the reporting device based on, for example, whether there is a monitoring termination instruction from the user or a table (not shown) that stores the operation schedule of the reporting device. To do. If the monitoring is continued as a result of the determination in step 405, the process proceeds to step 401. If the monitoring is ended, the monitoring process is ended.

  Note that the determination in step 405, that is, whether to continue or end the monitoring, may be determined for each monitoring area or each report destination. For example, in the case of accepting Building No. 1, which is a report destination of the monitoring area (1), monitoring information is not transmitted or image processing for the monitoring area (1) is not performed outside the opening hours of the Building No. 1. On the other hand, the guard station, which is the reporting destination of the monitoring area (2), always has a guard station resident on a 24-hour basis, and therefore always transmits monitoring information and performs image processing on the monitoring area (2).

  Similarly, in step 403 and step 404, the time when the video change is detected may be further taken into consideration. 15A and 15B show an embodiment of a report destination table in which a time when a video change is detected and a report destination of monitoring information are associated with each other. Here, FIG. 15A is a report destination table set for the monitoring area (1), and FIG. 15B is a report destination table set for the monitoring area (2). In FIG. 15A and FIG. 15B, the time when the video change is detected and the monitoring information report destination are set.

  In the example shown in FIG. 15A, when a change in the image is detected from 9:00 to 17:00 within the opening time of the first building, the monitoring information is transmitted to the first building reception, and the change in the image is detected outside the opening time. If this happens, monitoring information is not sent. Of course, when a video change is detected outside the opening hours, the monitoring information may be transmitted to a place other than the reception of the first building.

  Further, in the example shown in FIG. 15B, the guard station where the monitoring area (2) is reported is stationed 24 hours a day, so when a video change is detected, the guard station always stands by. Send monitoring information to a location.

  By the method described above, a plurality of monitoring areas are set for the video of the monitoring camera, and when a change in the video is detected in each of the monitoring areas, the report destination of the monitoring information can be switched for each monitoring area. it can.

  Also, since multiple monitoring areas are provided in the image processing of the reporting device, it is possible to obtain the same effect as realization of multiple cameras, and to obtain more detailed monitoring information. Monitoring information can be sent to the report destination.

Next, a reporting device according to still another embodiment of the present invention will be described with reference to FIGS. 5A, 5B, 6, and 13. FIG.
In this example, the video of the surveillance camera shown in FIG. 1 is used, but in addition to the above-described embodiment, a determination on the size of the detected object is also added. Specifically, in the monitoring area (1) or the monitoring area (2), the number of blocks in which video changes have occurred is summed. For example, if the sum is a predetermined number or more or less than a predetermined number, detection is performed. The monitoring information is transmitted as the target object.

  FIG. 13 is a block diagram showing the basic configuration of the reporting device in the present embodiment. The same components as those in FIG. 9 are denoted by the same reference numerals, and are the same as those in the block diagram shown in FIG. 9 except for the report destination table B 1208 ′, and thus the description thereof is omitted here.

  5A and 5B show an embodiment of a report destination table B1208 ′ in which the total number of blocks in which video changes have occurred and the report destination of the monitoring information are associated with each other. Here, FIG. 5A is a report destination table set for the monitoring area (1), and FIG. 5B is a report destination table set for the monitoring area (2). In FIGS. 5A and 5B, the number of blocks in which a video change is detected and the monitoring information report destination are set.

  In the example shown in FIG. 5A, it is determined that the object corresponding to the size of 6 or more and less than 12 is the person 104, and the monitoring information is transmitted to the first building reception, and the object corresponding to 12 or more blocks. Determines that the vehicle is a car and sends monitoring information to the first building car organizer. In addition, when the number of blocks in which a video change has occurred is less than 6, transmission is not performed. Here, the target to be detected with less than 6 blocks is, for example, a small animal other than a human. Thus, there is an effect that the number of alarms due to false alarms can be reduced by not transmitting monitoring information when the number of blocks is less than six.

  In the example shown in FIG. 5B, all the objects corresponding to the size of 6 blocks or more transmit monitoring information to the guards' waiting area, and when the number of blocks in which the video change has occurred is less than 6, the transmission is performed. The table is configured as follows. Needless to say, the contents of the report destination table B1208 ′ are appropriately changed as necessary.

FIG. 6 is a flowchart for explaining the processing flow of this embodiment.
Step 601 is a step in which the detection processing unit 1203 determines whether there is a video change in the monitoring area (1) 102 or the monitoring area (2) 103. If there is a change in the image, the process proceeds to step 602; otherwise, the process proceeds to step 608.

  Step 602 is a step in which the feature extraction processing unit 1204 determines the number of the area where the video change is detected. If a video change is detected in the monitoring area (1), the process proceeds to step 603. If a video change is detected in the monitoring area (2), the process proceeds to step 606.

  Step 603 is a step in which the feature extraction processing unit 1204 determines the number of blocks in which a video change is detected. When the number of blocks in which a video change is detected is less than 6, the process proceeds to step 608. When the number is 6 or more and less than 12, the process proceeds to step 604. When the number is 12 or more, the process proceeds to step 605.

  In step 604, the conversion unit 1205 generates monitoring information, and the number of blocks in which a video change is detected corresponds to 6 or more and less than 12 from the notification destination table for the monitoring area (1) illustrated in FIG. 5A. Acquire the monitoring information report destination and send the monitoring information to the corresponding report destination. In this example, the monitoring information is transmitted to the first building reception.

  In step 605, the conversion unit 1205 generates monitoring information, and monitoring corresponding to a case where the number of blocks in which a video change is detected from the notification destination table for the monitoring area (1) shown in FIG. 5A is 12 or more. Acquire the information report destination and send the monitoring information to the corresponding report destination. In this example, monitoring information is transmitted to the Building No. 1 vehicle organizer.

  Step 606 is a step in which the feature extraction processing unit 1204 determines the number of blocks in which a video change has been detected, as in Step 603. If the number of blocks in which a video change is detected is less than 6, the process proceeds to step 608, and if it is 6 or more, the process proceeds to step 607.

  In step 607, the conversion unit 1205 generates monitoring information, and monitoring corresponding to a case where the number of blocks in which a video change is detected from the notification destination table for the monitoring area (2) illustrated in FIG. 5B is 6 or more. Acquire the information report destination and send the monitoring information to the corresponding report destination. In this example, the monitoring information is transmitted to the guard station.

Step 608 is a step in which the conversion unit 1205 determines whether or not to continue monitoring. When the monitoring is continued, the process proceeds to step 601.
As described above, the type of the moving object can be determined based on the number of blocks in which the video change is detected, that is, the size of the moving object, and the monitoring information report destination can be switched depending on the type of the moving object.

  In this embodiment, the case where a plurality of monitoring areas are set has been described. However, when there is only one monitoring area set for the video of the monitoring camera, or the entire area of the video of the monitoring camera Needless to say, the same processing can be applied to the case where the number of the monitoring areas is one.

  In the above-described two embodiments, the monitoring information report destination can be switched when a video change is detected in the monitoring area (1) or the monitoring area (2). However, for example, there is a problem that it is impossible to determine whether the person detected in the monitoring area (1) is heading from the main gate to the first building or vice versa.

  That is, when the person detected in the monitoring area (1) is heading from the first building to the main gate, there is no need to transmit the monitoring information to the reception of the first building, and such unnecessary transmission is eliminated. Is required. The following embodiment is for realizing such a request, and this will be described with reference to FIGS. 7, 8, and 14. FIG.

  FIG. 14 is a block diagram illustrating a detailed configuration of the notification device according to the present embodiment. The same components as those in FIG. 9 are denoted by the same reference numerals, and the components other than the feature extraction processing unit 1204 ′ are the same as those in the block diagram shown in FIG.

  Here, the feature extraction processing unit 1204 ′ includes a timer unit 1401 for measuring the passage of time. In this embodiment, the moving direction of the moving object is grasped by a simple process using the time history of the monitoring area where the moving object is detected, and unnecessary transmission is reduced. Hereinafter, the present embodiment will be described in more detail.

  FIG. 7 is the same as FIG. 1, but a monitoring area (3) 701 is newly added. In FIG. 7, a person heading from the main gate to the first building is detected in the monitoring area (1) 102 after being detected in the monitoring area (3) 701. Conversely, a person heading from the first building to the main gate is detected in the monitoring area (1) 102 and then detected in the monitoring area (3) 701. Therefore, by determining the order of the areas in which the person is detected, it is possible to determine where the detected person is heading, and more reliable transmission of monitoring information can be performed.

  Similarly, a person heading from the main gate to the prohibited area is detected in the monitoring area (2) 103 after being detected in the monitoring area (3) 701, and a person heading from the prohibited area to the main gate is detected in the monitoring area (2) 103. Is detected in the monitoring area (3) 701.

  In the example shown in FIG. 7, a person heading from the No. 1 building to the forbidden area is first detected in the monitoring area (1) 102, but then detected in the monitoring area (3) 701 and then the monitoring area (2 ) 103. In addition, a person heading from Building No. 1 to Building No. 1 is first detected in monitoring area (2) 103, but then detected in monitoring area (3) 701 and then detected in monitoring area (1) 102.

  That is, the person heading from the main gate to Building No. 1 and the person heading from Building No. 1 to Building No. 1 are detected in the monitoring area (1) 102 after being detected in the monitoring area (3) 701. The same applies to other places.

  Next, the processing flow of the present embodiment will be described using the flowchart shown in FIG. In FIG. 8, an example in which the monitoring information is transmitted only when the total number of blocks in which the video change has occurred in the above-described embodiment is 6 or more and less than 12, that is, when a person is detected will be described. Further, it is assumed that the monitoring information is transmitted only when the detected person goes to the No. 1 building or the restricted entry area, and the monitoring information is not transmitted when going to the main gate.

  Step 801 is a step in which the detection processing unit 1203 detects whether or not there is a video change. If there is a change, the process proceeds to step 802, and if not, the process proceeds to step 811.

  Step 802 is a step in which the feature extraction processing unit 1204 ′ determines whether or not the region where the change in the image is detected is the monitoring region (3) 701. If it is the monitoring area (3), the process proceeds to step 803; otherwise, the process proceeds to step 811. This is because the monitoring area (3) 701 is first detected when heading to the No. 1 building or the restricted entry area. Further, as described above, the case of going from the No. 1 building to the no-entry area, etc., can be handled as being detected by the monitoring area (3) 701 first.

  Step 803 is a step in which the feature extraction processing unit 1204 ′ performs determination on the number of blocks in which a video change is detected. If the number of detected blocks is 6 or more and less than 12, that is, if the person 104 is detected, the process proceeds to step 804. Otherwise, go to Step 811.

  Step 804 is a step of starting the measurement of the elapsed time since the person was detected in the monitoring area (3) 701. The feature extraction processing unit 1204 ′ resets the timer unit 1401 in order to determine the elapsed time, and newly starts measuring the elapsed time.

  In step 805, the feature extraction processing unit 1204 ′ determines whether or not the person 104 is detected in the monitoring area (1). If it is detected in the monitoring area (1), the process proceeds to step 807; otherwise, the process proceeds to step 806.

  Note that step 805 is a step that is executed when the detection processing unit 1203 detects a change in the video by processing (not shown for simplification) on the video from the image input unit 1202 after step 804. In addition, the description of the determination processing for the number of detected blocks that is required after step 805 and step 806 is also omitted below.

  Step 806 is a step in which the feature extraction processing unit 1204 ′ determines whether the person 104 is detected in the monitoring area (2). If detected in the monitoring area (2), the process proceeds to step 809; otherwise, the process proceeds to step 811.

  Step 807 is a step in which the feature extraction processing unit 1204 ′ determines an elapsed time from when the change in the video is detected in the monitoring area (3) until the change in the video is detected in the monitoring area (1). . The feature extraction processing unit 1204 ′ reads the current elapsed time from the timer unit 1401, and proceeds to step 808 if the elapsed time is within a predetermined set time, otherwise to step 811. move on.

  In step 808, the conversion unit 1205 generates monitoring information, and obtains a reporting destination of monitoring information when a video change is detected in the monitoring area (1) from the reporting destination table A1208 shown in FIG. It is a step of transmitting information. In this example, the monitoring information is transmitted to the reception of Building No. 1.

  Step 809 is a step in which the feature extraction processing unit 1204 ′ determines an elapsed time from when a video change is detected in the monitoring area (3) until a video change is detected in the monitoring area (2). . As in step 807, the current elapsed time is read from the timer unit 1401. If the elapsed time is within a predetermined set time, the process proceeds to step 810. Otherwise, the process proceeds to step 811.

  Note that the set time used in the determination in step 809 may be set to a time different from the set time used in step 807. For example, the time used in the determinations in step 807 and step 809 is determined in advance according to the distance from the monitoring area (3). Further, the elapsed time may be determined by recording the video change detection time in each monitoring area without measuring the elapsed time using the timer unit 1401. In that case, for example, detection history information including information such as the number of the monitoring area where the abnormality is detected and the abnormality detection time is stored in the memory of the reporting device.

  In step 810, the conversion unit 1205 generates monitoring information, and acquires a reporting destination of monitoring information when a video change is detected in the monitoring area (2) from the reporting destination table A1208 shown in FIG. It is a step of transmitting information. In this example, the monitoring information is transmitted to the guard station.

Step 811 is a step for determining whether to continue or end the monitoring. When the monitoring is continued, the process proceeds to step 801.
By the method described above, it is possible to perform advanced processing such as determining the moving direction from the time history of the monitoring area where the moving object is detected, and switching the monitoring information report destination or not transmitting according to the moving direction of the moving object. is there. That is, it is possible to predict where the moving object is going from the moving direction.

  Further, in the above-described step 807 and step 809, the detection interval is determined. For example, if you are heading straight from the main gate to the first building, the time to reach the monitoring region (1) from the monitoring area (3) will be shorter, but you will take a walk from the main gate to the first building. If it is a person who is not in business in Building No. 1, the time to reach the monitoring area (1) from the monitoring area (3) becomes longer, and the detection interval also becomes longer. Therefore, by determining the detection interval in addition to the moving direction, it is possible to transmit only the monitoring information with more needs to the report destination, and reduce unnecessary transmission.

  However, the detection interval is not determined, and the monitoring information is transmitted when the object is detected in the monitoring area (1) or the monitoring area (2) after the object is detected in the monitoring area (3). Needless to say, you can. Even in this case, the transmission frequency of the monitoring information can be reduced as compared with the case where the monitoring information is always transmitted when an object is detected in any of the monitoring areas.

  Further, in this embodiment, the moving object can be detected by a simple process using the time history of the monitoring area where the moving object is detected without using complicated image processing such as template matching or the like with a conventionally known tracking processing technique. It is possible to grasp the moving direction. Thereby, the burden on the CPU of the reporting device is reduced. However, combining the well-known image recognition technology and tracking processing technology to determine the same object, track the same object with higher accuracy, grasp the movement direction, destination, etc., further reduce unnecessary transmission, Needless to say, it is also possible to send monitoring information to a reporting destination that has more needs.

  When a moving object is detected in any one of the monitoring area (1) 102, the monitoring area (2) 103, or the monitoring area (3) 701, first, preliminary alarm information is used as a temporary alarm. May be transmitted to a predetermined report destination.

  In the above embodiment, intrusion object detection processing is performed by performing image processing in a monitoring area set to a part of the entire video area, but image processing is also performed on the entire video area, When any object is detected, preliminary monitoring information with a low alarm level may be transmitted to a predetermined report destination as a temporary alarm. In this case, image processing is also performed on the entire video area, and the burden on the reporting device such as memory capacity and CPU increases. However, because detection is separately performed in each monitoring area by image processing. As for the image processing for the entire area, a large and rough detection process of pixel blocks may be performed.

  In addition, the feature extraction processing unit can detect the color of the object, the moving speed of the object, and the like in addition to the characteristics of the object described in the above-described embodiment, and switch the monitoring information report destination. Similarly, the notification destination of the monitoring information can be switched according to the time zone when the object is detected.

As described above, in the above-described embodiment, the monitoring information can be transmitted to different report destinations according to the location where the moving object is detected, the size of the moving object, and the like.
While the above description has been made with reference to exemplary embodiments, it will be apparent to those skilled in the art that the invention is not limited thereto and that various changes and modifications can be made within the spirit of the invention and the scope of the appended claims.

  Here, the configuration of the change detection device, the monitoring system, and the like according to the present invention is not necessarily limited to the above-described configuration, and various configurations may be used. The present invention can also be provided as, for example, a method or method for executing the processing according to the present invention, a program for realizing such a method or method, or a recording medium for recording the program. It is also possible to provide various devices and systems.

  The application field of the present invention is not necessarily limited to the above-described fields, and the present invention can be applied to various fields. For example, it goes without saying that the present invention can be applied to fields other than the monitoring field.

  In addition, as various types of processing performed in the change detection device and the monitoring system according to the present invention, for example, the processor executes a control program stored in a ROM (Read Only Memory) in hardware resources including a processor and a memory. The structure controlled by doing may be used, and each function means for performing the said process may be comprised as an independent hardware circuit, for example.

  Further, the present invention can be grasped as a computer-readable recording medium such as a floppy (registered trademark) disk or a CD (Compact Disc) -ROM storing the control program, or the program (itself). The processing according to the present invention can be performed by inputting the program from the recording medium to the computer and causing the processor to execute the program.

It is a figure for demonstrating an example of the image | video of the monitoring camera for demonstrating the selection method of the report destination of the monitoring information by one Example of this invention. It is a figure which shows an example of the monitoring area | region set with respect to the image | video of the monitoring camera of FIG. It is a figure which shows an example of the report destination table used with the selection method of the report destination of the monitoring information of one Example of this invention. It is a flowchart for demonstrating the selection method of the report destination of the monitoring information of one Example of this invention. It is a figure which shows the example of the notification destination table used for selection of the notification destination of the monitoring information by another Example of this invention. It is a figure which shows the example of the notification destination table used for selection of the notification destination of the monitoring information by another Example of this invention. It is a flowchart for demonstrating the selection method of the report destination of the monitoring information using the report destination table of FIG. 5A and FIG. 5B. It is a figure for demonstrating an example of the image | video of the monitoring camera for demonstrating the selection method of the report destination of the monitoring information by another Example of this invention. It is a flowchart for demonstrating the selection method of the monitoring information of the Example of this invention demonstrated with reference to the image | video of the monitoring camera shown in FIG. It is a block diagram which shows the basic composition of the notification apparatus by one Example of this invention. It is a figure which shows the structure of the network monitoring system by one Example of this invention. It is a block diagram which shows schematic structure of each apparatus which comprises the monitoring system of FIG. 11 is a flowchart illustrating an operation of the network monitoring system of FIG. 10 according to an embodiment of the present invention. It is a block diagram which shows the basic composition of the alerting | reporting apparatus by one Example of this invention with respect to the alerting | reporting destination selection method demonstrated with reference to FIG. 5A, 5B, 6. FIG. FIG. 9 is a block diagram showing a basic configuration of a notification device according to an embodiment of the present invention directed to the notification destination selection method described with reference to FIGS. It is a figure which shows an example of the notification destination table for the monitoring area | region (1) which linked | related the time when the image change was detected, and the notification destination of monitoring information. It is a figure which shows an example of the notification destination table for the monitoring area | region (2) which linked | related the time when the image change was detected, and the notification destination of monitoring information.

Explanation of symbols

101: monitoring target image, 102: monitoring area (1), 103: monitoring area (2), 104: intruder, 701: monitoring area (3).

Claims (2)

A monitoring image input means obtained by the imaging device;
Area storage means for storing N areas (N is a positive integer greater than or equal to 3) areas on the monitoring image set so as to be able to determine the destination, each area comprising a plurality of blocks;
Change detecting means for detecting objects in the N areas;
Feature extraction means for extracting at least one feature of the object detected by the change detection means;
Monitoring information generating means for generating monitoring information related to the detected image change;
The monitoring information transmission means,
The feature extracted by the feature extraction means is an order when objects are detected in order in at least two of the N regions.
The transmission unit is a device that exists at the destination of the object based on the feature extracted by the feature extraction unit , or a device that is not at the destination of the object.
The change detection apparatus characterized by the above-mentioned. The change detection apparatus according to claim 1,
The feature extracted by the feature extraction unit further includes a feature relating to time whether or not the object is detected in two predetermined areas within a predetermined time,
Determining whether to send monitoring information based on the order and the time characteristics;
The change detection apparatus characterized by the above-mentioned.