JP7149063B2 - Monitoring system - Google Patents

Description

TECHNICAL FIELD The present invention relates to technology for monitoring a target person on a station platform.

Techniques have been proposed to prevent a visually impaired person from falling from a station platform.

In Patent Document 1, identification means provided at the ticket gate of a station identifies a person to be monitored who satisfies a predetermined monitoring target condition from among those who enter the ticket gate, A home monitoring system is described that tracks the movement of a person, detects the danger of a person to be monitored from the tracking information, and outputs an alarm signal.

In Patent Document 2, based on three-dimensional distance information obtained from a stereo camera, image processing is performed only on color images of areas around pedestrians detected in a surveillance area where there is a possibility that a white cane may be present. A white cane user detection system for detecting a white cane is described.

In Patent Document 3, a pedestrian position on a platform is detected, and when the detected position draws a walking trajectory along a block for guiding a visually impaired person, this pedestrian is determined to be a visually impaired person, and this walking trajectory is determined. Based on this, a specific monitoring zone corresponding to the position of the visually impaired person is specified from among the multiple monitoring zones that have been prepared by dividing the platform in advance, and a drop detector installed in this specific monitoring zone is used to guide the person to the track. A pedestrian fall monitoring system is described that starts a falling object detection process and, when a falling object is detected, notifies a preset notification destination of an alarm indicating that a pedestrian has fallen.

JP 2003-224844 A JP 2007-274234 A JP 2012-243177 A

In order to prevent a visually handicapped person from falling, there is a need for a station attendant to know the location of a visually handicapped person who has entered the station premises.

An object of the present invention is to enable a user such as a station attendant to easily know the location of a target person such as a visually impaired person within a predetermined area such as a station premises.

In order to solve the above-mentioned problems, the present invention selects a visually impaired person or a walking disabled person who is a target person by a predetermined possession recognized from a first image that captures a position in a predetermined area, Identifying the characteristic information of the subject in the first image, and capturing the identified characteristic information in a second image obtained by capturing a position different from the position at which the first image within the predetermined area was captured determining that a person having the same feature information as the feature information is the same person as the subject, synthesizing an image showing an area occupied by the image of the person in the second image, and synthesizing the synthesized image; Provided as a first aspect is a monitoring system that displays a screen for notifying the whereabouts of the subject within the predetermined area .

According to the monitoring system of the first aspect, the user can easily know the whereabouts of the selected target person based on the belongings.

In the monitoring system of the first aspect, the second configuration is provided with a camera that faces and images passers-by passing through the ticket gate of the station, and a camera that faces and images the platform from the opposite side of the station platform across the railroad track. It may be adopted as an aspect of.

According to the monitoring system of the second aspect, since an image of a passerby entering the station from outside the station can be obtained at a desired angle, the target person can be selected with high accuracy. In addition, according to the monitoring system of the second aspect, an image of passengers waiting for a train on a station platform can be obtained from the front, so that a target person near the edge of the platform can be recognized with high accuracy.

In the monitoring system according to the second aspect, a configuration is adopted as a third aspect, in which a plurality of cameras are arranged along the railroad track on the opposite side of the station platform and the railroad track, and the camera faces the platform and captures images. may be

According to the monitoring system of the third aspect, when the characteristic information of the subject is specified from the image captured by any one of the plurality of cameras spaced apart along the railroad track, the image of the camera that captured the image You can see that the target is in the corner.

The surveillance system according to the first aspect comprises storage means for storing the feature information, and a plurality of discretely arranged cameras, wherein the feature information is finally identified from an image captured by any one of the plurality of cameras. A fourth aspect may employ a configuration in which the characteristic information is deleted from the storage means when the subsequent elapsed time reaches a threshold value.

According to the monitoring system of the fourth aspect, passers-by who are expected to have left the monitored area are excluded from the target persons.

In addition, the present invention selects a visually impaired person or a walking handicapped person as a target person based on a predetermined possession recognized from an image captured by one of a plurality of cameras discretely arranged in a predetermined area, The feature information of the subject in the image is specified, and a person having the same feature information as the feature information in the image captured by a camera different from the camera that captured the image among the plurality of cameras is identified as the subject. is determined to be the same person, and an image indicating the area occupied by the image of the person in the image is synthesized with the image in which the person is determined to be the same person as the subject, and displayed on the screen and a storage means for storing the feature information, wherein the elapsed time after the last feature information is identified from an image captured by one of the plurality of cameras other than the specific camera is set as a threshold. If the feature information has been reached, the feature information is deleted from the storage means, and if the feature information was last specified from the image captured by the specific camera, the elapsed time after the last feature information was specified As a fifth aspect, a monitoring system is provided in which the feature information is not deleted from the storage means even if the threshold value is reached.

According to the monitoring system of the fifth aspect, a subject temporarily enters an area not to be monitored such as a toilet from an area to be monitored, and then returns to the area to be monitored. not excluded.

The figure which shows the main structures of the monitoring system which concerns on one Embodiment. The figure which showed the structure of the database which the monitoring system which concerns on one Embodiment uses. The figure which showed the structure of the database which the monitoring system which concerns on one Embodiment uses. The figure which showed the structure of the database which the monitoring system which concerns on one Embodiment uses. The figure which showed the example of arrangement|positioning of the camera with which the monitoring system which concerns on one Embodiment is provided. The figure which expanded a part of FIG. FIG. 4 is a diagram for explaining an example of a method of specifying feature information of a passerby from an image by the monitoring system according to one embodiment; 1 is a diagram showing a functional configuration of an information processing apparatus according to one embodiment; FIG. The figure which showed the flow of the process which the information processing apparatus which concerns on one Embodiment performs. The figure which showed the flow of the process which the information processing apparatus which concerns on one Embodiment performs. The figure which showed the flow of the process which the information processing apparatus which concerns on one Embodiment performs. The figure which illustrated the screen displayed by the information processing apparatus which concerns on one Embodiment. The figure which showed the flow of the process which the information processing apparatus which concerns on one Embodiment performs.

<Embodiment>
<Overall configuration of monitoring system>
A monitoring system 1 according to an embodiment of the present invention will be described below. The monitoring system 1 is a system for notifying a station attendant of the whereabouts of a visually impaired person (an example of a target person) who has entered a station in the station premises.

FIG. 1 is a diagram showing the main configuration of a monitoring system 1. As shown in FIG. A monitoring system 1 includes an information processing device 11 and a plurality of cameras 12 .

A plurality of cameras 12 are discretely arranged at various locations in the station premises. The information processing device 11 acquires images captured by the cameras 12 from each of the cameras 12 . The information processing device 11 selects a person to be monitored from the image acquired from the camera 12, identifies the location of the person in the station premises using the characteristic information of the selected person, and notifies the station staff of the identified location. .

<Configuration of information processing device>
The information processing device 11 includes a control unit 111 , a storage unit 112 , a display unit 113 , an operation unit 114 and an interface 115 .

The control unit 111 has a CPU (Central Processing Unit), ROM (Read Only Memory), and RAM (Random Access Memory), and the CPU is a computer program stored in the ROM and the storage unit 112 (hereinafter simply referred to as a program). is read and executed to control each part of the information processing apparatus 11 .

The control unit 111 also includes a vibrator using crystal, ceramic, silicon, MEMS (Micro Electro Mechanical Systems), or the like, and a clock signal generated by the vibrator is used to control the operation of the CPU.

The storage unit 112 is a secondary storage device such as a hard disk drive or solid state drive, and stores various programs read by the CPU of the control unit 111 . In addition, the storage unit 112 includes a property DB 1121 that is a database that stores property information of property used for selection of a target person, a target person DB 1122 that is a database that stores property information of a selected target person, and a plurality of A camera DB 1123, which is a database for storing position information of each camera 12, is stored.

In the present application, feature information means information indicating features specified from an image. As the feature information, for example, feature information obtained by statistically processing HOG (Histograms of Oriented Gradients) feature amounts can be used. Either may be adopted.

FIG. 2 is a diagram showing the structure of the belongings DB 1121. As shown in FIG. The belongings DB 1121 stores each of a plurality of types of belongings (hereinafter collectively referred to as "belongings J") that are normally carried by a visually impaired person while walking, but are not usually possessed by a passerby who is not visually impaired. is a collection of data records according to The belonging J is, for example, a white cane, a guide dog, a handle attached to a harness for the guide dog, or the like. In addition, although the number of belongings J is assumed to be plural in the present embodiment, only a white cane may be handled as belongings J, for example.

Each data record of the property DB 1121 has a column of “possession ID” and a column of “feature information”. The identification information of the property J is stored in the “possession ID” column. The feature information specified from the sample image of the item J is stored in the "feature information" column.

FIG. 3 is a diagram showing the configuration of the target person DB 1122. As shown in FIG. The subject DB 1122 is a collection of data records corresponding to each selected subject. In this embodiment, the selected target person is a person who possesses any of the belongings J among the persons who have moved from outside the station to inside the station.

Each data record of the target person DB 1122 has a "subject ID" column, a "feature information" column, a "camera ID" column, a "final recognition time" column, and an "image area" column. The "subject ID" column stores the identification information of the subject. The feature information of the subject is stored in the "feature information" column. The "camera ID" column stores the identification information of the camera 12 that captured the last image in which the subject was recognized. The "final recognition time" column stores the imaging time of the image in which the target person was last recognized. Information indicating the area occupied by the image of the subject in the image captured by the camera 12 is stored in the "image area" column.

The feature information stored in the "feature information" column of the subject DB 1122 includes feature information related to the subject's body itself (face, hairstyle, body shape, etc.), as well as accessories attached to the subject's body (clothing, possession, etc.). object, etc.).

FIG. 4 is a diagram showing the configuration of the camera DB 1123. As shown in FIG. The camera DB 1123 is a collection of data records corresponding to each of the plurality of cameras 12, and each data record has a "camera ID" column, a "position" column, and an "imaging direction" column.

Identification information for identifying the camera 12 is stored in the “camera ID” column. Information indicating the position of the camera 12 is stored in the "Position" column. Information indicating the imaging direction of the camera 12 is stored in the "imaging direction" column.

The description of the configuration of the monitoring system 1 will be continued with reference to FIG. The display unit 113 has a display device such as a liquid crystal display, and displays various information such as images acquired from the camera 12 under the control of the control unit 111 .

The operation unit 114 has an operator that receives an operation from the user, and supplies the control unit 111 with a signal according to the operation performed by the user. Note that the operation unit 114 has a touch panel that detects contact (or proximity) of an operation tool such as a user's finger or a stylus, and the liquid crystal display included in the display unit 113 and the touch panel included in the operation unit 114 are stacked to form a touch screen. may be configured.

The interface 115 is connected to each of the cameras 12 by wire or wirelessly, and acquires images from the cameras 12 .

<Example of camera arrangement>
FIG. 5 is a diagram showing an arrangement example of a plurality of cameras 12. As shown in FIG. The space shown in FIG. 5 is roughly divided into a station outside space R0, which is a space outside the ticket gate E1, and a station inside space R1, which is a space inside the ticket gate E1. Further, the station premises R1 shown in FIG. 5 is divided into a plaza R11, a platform R12, and a commercial facility R13.

The square R11 is a space arranged between the ticket gate E1 and the platform R12, and passers-by can freely pass through the square R11. The platform R12 is a space for passengers to get on and off the train V running along the track L. The track L is a danger zone where passengers may fall onto it and risk being hit by the train V. Platform R12 is adjacent to a dangerous area, and passengers there may fall into the dangerous area. Therefore, if there is a visually impaired person on platform R12, a station attendant needs to know exactly where he/she is.

The commercial facility R13 is a facility that provides services incidental to railway use, such as a restaurant, an article store, a restroom, a smoking area, a rest room, a nursing room, and a diaper changing space. In the example of FIG. 5, commercial facility R13 is separated from plaza R11 by gate E2, but passers-by can freely pass through gate E2 without ticket gates. Since the commercial facility R13 is away from the danger zone, it is sufficient for the station attendant to be notified that the subject is within the commercial facility R13, and the station staff is notified of the subject's location within the commercial facility R13. you don't have to.

In the arrangement example shown in FIG. 5, the plurality of cameras 12 are classified into camera 12a, camera 12b, camera 12c, camera 12d, camera 12e, and camera 12f. The camera 12a is a camera that captures an image of a passerby who passes through the ticket gate E1 and enters from the outside of the station R0 to the inside of the station R1. The camera 12b is a camera that takes an image of a passerby who passes through the ticket gate E1 and exits from the inside of the station R1 to the outside of the station R0.

FIG. 6 is an enlarged view of the vicinity of the ticket gate E1 in FIG. In the example of FIG. 6, one camera 12a or one camera 12b is arranged for one ticket gate E1. The number and imaging direction of the cameras 12a and 12b are not limited to this. For example, regarding one ticket gate E1, a plurality of cameras 12a or cameras 12b are arranged to capture images of the passerby in different directions, such as the front, right side, and left side of the passerby passing through the ticket gate E1. good too.

The camera 12c is a camera that faces the platform R12 from the opposite side across the railroad track L from the platform R12 and takes an image. A plurality of cameras 12c are spaced along the track L. The intervals between the plurality of cameras 12c are adjusted according to the angle of view of the cameras 12c and the distance from the camera 12c to the edge of the platform R12 so that a person on the edge of the platform R12 can be imaged by one of the cameras 12c. interval. When the target person is recognized in the image captured by any of the cameras 12c, the station attendant can specify the location of the target person on the platform R12 based on the position of the camera 12c that captured the image.

The camera 12d is a camera for capturing an image of a passerby entering the commercial facility R13 from the platform R12, and the camera 12e is a camera for capturing an image of a passerby exiting from the commercial facility R13 to the platform R12. The numbers and imaging directions of the cameras 12d and 12e are not limited to those shown in FIG.

<Functional Configuration of Information Processing Device>
FIG. 7 is a diagram for explaining an example of a technique for specifying feature information of a passerby from an image. 8 is a diagram showing the functional configuration of the information processing device 11. As shown in FIG.

The control unit 111 of the information processing device 11 reads out and executes the programs stored in the storage unit 112 to obtain the acquisition unit 1111, the identification unit 1112, the selection unit 1113, the registration unit 1114, the determination unit 1115, and the synthesis unit 1117. , a timer 1119 , and a deletion unit 1118 . Note that the operation unit 114 and the interface 115 are omitted in FIG.

The acquisition unit 1111 acquires an image captured by each of the cameras 12 from each of the cameras 12 . The specifying unit 1112 specifies the feature information of the person appearing in the image acquired by the acquiring unit 1111 . Specifically, the identifying unit 1112 divides the image acquired by the acquiring unit 1111 from the camera 12 into, for example, a plurality of cells (12×7=12×7 in the example of FIG. 7B) as shown in FIG. 84 cells). In the example of FIG. 7B, one cell consists of 5×5=25 pixels.

The specifying unit 1112 calculates the gradient direction and intensity of luminance of each pixel, creates a histogram of the calculated gradient direction and intensity, and calculates the feature amount of each cell. Subsequently, the specifying unit 1112 totals and normalizes the feature amounts for each block composed of a plurality of adjacent cells (for example, a block composed of 3×3=9 cells). The normalized feature amount is used to detect a person included in an image and to distinguish the detected person from other persons.

When the feature information specified by the specifying unit 1112 from the image acquired by the acquiring unit 1111 from the camera 12a includes the feature information of the item J, the selecting unit 1113 selects the person appearing in the image as the target person. Note that the image acquired by the acquisition unit 1111 from the camera 12a is an image captured in a predetermined area (the ticket gate E1 through which passersby entering the station R1 and its surrounding area).

Specifically, when the same feature information as the feature information specified by the specifying unit 1112 from the image acquired from the camera 12a is registered in the belongings DB 1121, the selection unit 1113 selects the belongings shown in the image. is a property J (a white cane, etc.), and since the person holding the property J in the image is a visually impaired person, that person is selected as the target person. In the present application, that two pieces of feature information are the same means that when the degree of similarity between two pieces of feature information is calculated according to a predetermined rule, the degree of similarity is higher than a predetermined threshold. Exact matching is not required.

The registration unit 1114 registers the feature information specified by the specifying unit 1112 regarding the person selected as the target by the selection unit 1113 in the target person DB 1122 .

If the feature information specified by the specifying unit 1112 from the image acquired by the acquiring unit 1111 from the cameras 12 (cameras 12b to 12f) other than the camera 12a includes the feature information of the subject, the determination unit 1115 determines whether the image contains the feature information of the subject. is determined to be in the image. Specifically, when the same feature information as the feature information specified by the specifying unit 1112 from the images acquired from the cameras 12b to 12f is registered in the target person DB 1122, the determination unit 1115 determines that the target person is included in the image. Judge that it is in the picture.

When the determining unit 1115 determines that the target person is shown in the images acquired from the cameras 12b to 12f, the updating unit 1116 updates the data stored in the belongings DB 1121 according to the result of the determination. do.

The synthesizing unit 1117 adds an image indicating the area occupied by the image of the target person to the image determined by the determining unit 1115 to include the target person, among the images acquired by the acquisition unit 1111 from the camera 12 . Synthesize. Examples of the image showing the area occupied by the image of the subject include, for example, an image showing the outer edge of the area with a line, and a red image with a transmittance of about 50% arranged to cover the area. It is not limited to these. That is, as long as the station attendant who sees the image generated by the synthesizing unit 1117 can distinguish which person in the image is the target person, any form of image may be synthesized. .

The deletion unit 1118 deletes data records in which the elapsed time from the last recognition time to the current time exceeds a predetermined threshold among the data records in the subject DB 1122 .

The clock unit 1119 specifies the current time based on the clock signal output from the vibrator provided in the control unit 111 . The current time specified by the timer 1119 is used by the registration unit 1114 , update unit 1116 and deletion unit 1118 .

<Operation of Information Processing Device>
<Registration accompanying the entrance of the target person>
FIG. 9 is a diagram showing the flow of processing performed by the information processing device 11 to register a new target person who enters the station premises R1 from the outside of the station R0 in the target person DB 1122. As shown in FIG. The processing in FIG. 9 is executed each time the acquisition unit 1111 acquires an image from the camera 12a.

When the acquiring unit 1111 acquires an image from the camera 12a, the specifying unit 1112 specifies feature information of a person (including belongings) included in the image from the image acquired by the acquiring unit 1111 (step S101).

Subsequently, the selecting unit 1113 determines whether or not the same feature information as the feature information specified by the specifying unit 1112 is registered in the belongings DB 1121 (step S102). If the same feature information as the feature information specified by the specifying unit 1112 is not registered in the belongings DB 1121 (step S102; NO), the information processing device 11 ends the processing related to the registration of the information associated with the entrance of the target person. .

On the other hand, if the same feature information as the feature information specified by the specifying unit 1112 is registered in the possession DB 1121 (step S102; YES), the selecting unit 1113 selects the person appearing in the image acquired by the acquiring unit 1111. The person is selected as a subject (step S103). Subsequently, the registration unit 1114 registers information about the target person selected by the selection unit 1113 in the target person DB 1122 .

Specifically, in step S103, the registration unit 1114 adds a new data record to the subject DB 1122, and puts any unique identification information in the "subject ID" column, and the subject's The identification information of the camera 12a that captured the image acquired by the acquisition unit 1111 is entered in the "camera ID" column, the information indicating the current time is entered in the "final recognition time" column, and the acquisition unit 1111 stores information indicating the area occupied by the image of the subject in the acquired image. After that, the information processing device 11 ends the processing related to the registration of information associated with the entrance of the subject (step S104).

<Deleted due to the exit of the target person>
FIG. 10 is a diagram showing the flow of processing performed by the information processing apparatus 11 in order to delete from the target person DB 1122 the information of the target person leaving the station premises R1 to the outside of the station R0. The processing in FIG. 10 is executed each time the acquisition unit 1111 acquires an image from the camera 12b.

When the acquiring unit 1111 acquires an image from the camera 12b, the specifying unit 1112 specifies the feature information of the person (including the person's belongings) included in the image from the image acquired by the acquiring unit 1111 (step S201).

Subsequently, the determining unit 1115 determines whether or not the same feature information as the feature information specified by the specifying unit 1112 is registered in the subject DB 1122 (step S202). If the same feature information as the feature information specified by the specifying unit 1112 is not registered in the target person DB 1122 (step S202; NO), the information processing apparatus 11 ends the processing related to deletion of information accompanying the leaving of the target person. .

On the other hand, when the same feature information as the feature information specified by the specifying unit 1112 is registered in the target person DB 1122 (step S202; YES), the target person according to the feature information has exited outside the station R0. After that, no supervision is required. Therefore, the deletion unit 1118 deletes from the subject DB 1122 the data record storing the same feature information as the feature information specified by the specifying unit 1112 (step S203). After that, the information processing device 11 terminates the processing related to the deletion of the information accompanying the exit of the target person.

<Updates upon target detection>
FIG. 11 shows the processing performed by the information processing apparatus 11 to update the information of the target person stored in the target person DB 1122 when the target person is detected in the plaza R11, the home R12, or the commercial facility R13. It is the figure which showed the flow. The processing in FIG. 11 is executed each time the acquisition unit 1111 acquires an image from the camera 12c, 12d, 12e, or 12f.

When the acquiring unit 1111 acquires an image from the camera 12c, 12d, 12e, or 12f, the specifying unit 1112 specifies feature information of a person (including belongings) included in the image from the image acquired by the acquiring unit 1111 (step S301).

Subsequently, the determining unit 1115 determines whether or not the same feature information as the feature information specified by the specifying unit 1112 is registered in the subject DB 1122 (step S302). If the same feature information as the feature information specified by the specifying unit 1112 is not registered in the target person DB 1122 (step S302; NO), the information processing apparatus 11 ends the processing related to updating the information accompanying detection of the target person. .

On the other hand, if the same feature information as the feature information specified by the specifying unit 1112 is registered in the target person DB 1122 (step S302; YES), it means that the target person corresponding to the feature information has been detected in the station premises R1. become. Therefore, the updating unit 1116 updates the information in the "camera ID" column, the "final recognition time" column, and the "image area" column of the data record that stores the same feature information as the feature information specified by the specifying unit 1112. is updated (step S303).

Specifically, the updating unit 1116 stores the identification information of the camera 12 that captured the image acquired by the acquiring unit 1111 in the “camera ID” column of the data record to be updated, and stores the identification information in the “final recognition time” column by the clock unit 1119. Information indicating the specified current time is overwritten with information indicating the area occupied by the image of the subject in the image acquired by the acquisition unit 1111 in the "area in image" column.

Subsequently, the synthesizing unit 1117 combines the latest image acquired by the acquiring unit 1111 from the camera 12 indicated by the information in the “camera ID” column of the data record updated in step S303 with the information indicated by the “intra-image region” column. An image for displaying the area is synthesized (step S304). The display unit 113 uses the image synthesized by the synthesizing unit 1117 to display a screen for notifying the station attendant of the target person's whereabouts (hereinafter referred to as "whereabouts notification screen") (step S305).

FIG. 12 is a diagram exemplifying a whereabouts notification screen displayed by the display unit 113. As shown in FIG. For example, by looking at the whereabouts notification screen illustrated in FIG. It is possible to intuitively know that the target person C is present.

<Deletion due to non-detection of the target person for a long time>
FIG. 13 shows that when the target person is not detected for a long time exceeding a predetermined threshold in the station premises R1, it is assumed that the target person has already left the station premises R0, and the target person's information is processed as a target. FIG. 11 is a diagram showing a flow of processing performed by the information processing apparatus 11 to delete from the person DB 1122; The process of FIG. 13 is executed, for example, every time a predetermined time elapses.

The deletion unit 1118 sequentially reads one data record from the subject DB 1122 (step S401). Subsequently, the deletion unit 1118 determines whether the information in the "camera ID" column of the read data record is the camera ID of the camera 12d that captures an image of a passerby entering the commercial facility R13 (step S402).

If the information in the "camera ID" column of the read data record is the camera ID of the camera 12d (step S402; YES), the subject is currently in the commercial facility R13. For example, if the commercial facility R13 is a restaurant or the like, the target person corresponding to this data record often stays at the commercial facility R13 for a long time. Therefore, the deletion unit 1118 does not delete this data record regardless of the length of the elapsed time from the time indicated by the information in the "final recognition time" column of this data record to the current time. In this case, the information processing apparatus 11 shifts the process to step S405.

On the other hand, if the information in the "camera ID" column of the read data record is not the camera ID of the camera 12d (step S402; NO), the deletion unit 1118 deletes data from the time indicated by the information in the "last recognition time" column of this data record. It is determined whether or not the elapsed time until the time exceeds a predetermined threshold (step S403).

If the elapsed time from the time indicated by the information in the "final recognition time" column to the current time does not exceed the predetermined threshold (step S403; NO), the target person corresponding to this data record is the station R1 (commercial facility R13 other than). Therefore, the deletion unit 1118 does not delete this data record. Also in this case, the information processing apparatus 11 shifts the process to step S405.

On the other hand, if the elapsed time from the time indicated by the information in the "last recognition time" column to the current time exceeds the predetermined threshold (step S403; YES), the target person corresponding to this data record has already moved to outside the station R0. likely to have left. Therefore, the deletion unit 1118 deletes this data record (step S404).

Subsequently, the deletion unit 1118 determines whether or not the data record read in the previous step S401 is the last data record of the subject DB 1122 (step S405). If the data record read in step S401 immediately before is not the last data record of the subject DB 1122 (step S405; NO), the information processing apparatus 11 returns the process to step S401, and the deletion unit 1118 reads in step S401. Read the next data record after the data record. After that, the processing after step S402 is repeated.

On the other hand, if the data record read in immediately preceding step S401 is the last data record in the subject DB 1122 (step S405; YES), the information processing apparatus 11 terminates the process of deleting information associated with non-detection of the subject. .

As described above, the monitoring system 1 selects a target person based on the possession recognized from the image captured in the predetermined area, and specifies and registers the feature information of the target person in this image.

Specifically, the monitoring system 1 uses the camera 12a to capture an image of a passerby who passes through the ticket gate E1 and moves from the outside of the station R0 to the inside of the station R1. A visually impaired person, who is a target person, often possesses a property J such as a white cane or a guide dog. Since two or more passers-by do not pass through one ticket gate E1 at the same time, when the visually impaired pass through the ticket gate E1, the belonging J should not be hidden behind something when viewed from the camera 12a. not much. Therefore, when a visually impaired person enters the station premises R1, the visually impaired person is selected with high accuracy as a target person, and then becomes an object of monitoring.

In addition, the monitoring system 1 determines that a person having the same feature information as the specified feature information in the image different from the image captured in the predetermined area is the same person as the subject.

Specifically, the monitoring system 1 determines whether or not the person in the images captured by the cameras 12c to 12f is the target person, not only the feature information of the person's belongings, but also the face, etc. Determination is made based on the feature information of the entire person. Therefore, even if the subject's belongings J are hidden behind something and are not captured in the image captured in the station premises R1, the subject's belongings J can be captured with high accuracy based on the feature information of the portion not hidden by the subject. location is identified.

In addition, the monitoring system 1 deletes the information of the target person from the target person DB 1122 when the target person is not detected for a long time exceeding a predetermined threshold. Therefore, the information of the subject who is expected to leave the area to be monitored is not wastefully stored.

<Modification>
The above-described embodiments can be variously modified. Examples of these modifications are shown below. Note that two or more modified examples shown below may be appropriately combined.

<Modification 1>
The program executed by the control unit 111 of the information processing device 11 is stored in a computer-readable record such as a magnetic recording medium such as a magnetic tape or magnetic disk, an optical recording medium such as an optical disk, a magneto-optical recording medium, or a semiconductor memory. It may be provided stored on a medium. It is also possible to download this program via a communication line such as the Internet. Various devices other than the CPU may be applied as the control means, and for example, a dedicated processor may be used.

<Modification 2>
In the above-described embodiment, the target person is a visually impaired person, but passersby other than the visually impaired person, such as an elderly person with a cane, a walking disabled person in a wheelchair, and a person pushing a stroller, can be used. It may be a target person. For example, when a disabled person in a wheelchair is targeted, characteristic information such as a wheelchair and characteristic parts of the wheelchair is registered and used in the belongings DB 1121 .

<Modification 3>
The position and imaging direction of the camera 12 may change. For example, the camera 12 may be reciprocally transported along a rail provided on the ceiling of the station premises R1, or the camera 12 may be mounted on a drone or the like that patrols the station premises R1. In this case, the position and imaging direction of the camera 12 are measured in real time, and the "position" column and the "imaging direction" column of the camera DB 1123 are continuously updated with the measured information.

It should be noted that the specific arrangement, processing flow, data configuration, and the like shown in the above-described embodiment are merely examples, and may be changed in various ways. For example, although the home R12 and the commercial facility R13 shown in FIG. 5 are each one in number, they may be plural. Also, the layout of the platform R12, the commercial facility R13, the ticket gate E11, etc. is not limited to the layout shown in FIG.

Reference Signs List 1 surveillance system 11 information processing device 12 camera 111 control unit 112 storage unit 113 display unit 114 operation unit 115 interface 1111 acquisition unit 1112 identification unit 1113 Selection unit 1114 Registration unit 1115 Determination unit 1116 Update unit 1117 Synthesis unit 1118 Deletion unit 1119 Timing unit

Claims (5)

A visually impaired person or a walking handicapped person is selected from a first image obtained by imaging a position within a predetermined area, and features of the subject in the first image. Information is specified, and a person having the same feature information as the specified feature information in a second image captured at a position different from the position at which the first image in the predetermined area is captured is identified as the person. determining that the subject is the same person, synthesizing an image showing the area occupied by the image of the person in the second image, and using the synthesized image to determine the subject within the predetermined area; A monitoring system that displays a screen for notifying the whereabouts . 2. The monitoring system according to claim 1, further comprising: a camera for capturing an image of a passerby passing through a ticket gate of a station; 3. The monitoring system according to claim 2, further comprising a plurality of cameras spaced apart along the railroad track on the opposite side of the station platform and the railroad track, and configured to capture images facing the platform. Storage means for storing the feature information, and a plurality of discretely arranged cameras, wherein the elapsed time after the last feature information is identified from an image captured by any one of the plurality of cameras reaches a threshold. 2. The monitoring system according to claim 1, wherein the feature information is deleted from the storage means if A visually handicapped person or a walking-impaired person who is a target person is selected from an image captured by one of a plurality of cameras discretely arranged in a predetermined area, and the target person in the image is selected from a predetermined possession recognized from the image. and determining that a person having the same feature information as the feature information in an image captured by a camera different from the camera that captured the image among the plurality of cameras is the same person as the subject. A monitoring system that synthesizes an image showing the area occupied by the image of the person in the image in which the person is determined to be the same person as the subject and displays the image on a screen,
A storage unit for storing the feature information is provided, and the elapsed time after the last feature information is identified from an image captured by any one of the plurality of cameras other than the specific camera reaches a threshold. , when the feature information is deleted from the storage means and the feature information is specified last from the image captured by the specific camera, the elapsed time after the feature information was last specified is the threshold value; a monitoring system that does not delete said feature information from said storage means even if the time reaches .

Images