JP2017062594A - Nuisance estimation system, and control method and control program for nuisance estimation system - Google Patents

Abstract

PROBLEM TO BE SOLVED: To provide a nuisance estimation system capable of estimating a nuisance in the space where many and unspecified persons come and go.SOLUTION: In a nuisance estimation system 500, a first imaging part 501 images a person who enters the space. A second imaging part 502 is provided within the space and images the periphery of a corresponding position in accordance with a notification signal from a notification terminal 503. An image analysis part 504 extracts face data from the images which are captured by the first imaging part 501 and the second imaging part 502, and stores the face data in a first database part 505 and a second database part 506. A face data analysis part 508 analyzes the face data in the first database part 505 and the second database part 506, selects face data to be stored in a third database part 507 and calculates a frequency score. A discrimination part 509 estimates a person of face data of which the corresponding frequency score exceeds a threshold value after the lapse of a specific period, as a nuisance.SELECTED DRAWING: Figure 1

Description

  The present invention relates to a nuisance agent estimation system, a control method for a nuisance agent estimation system, and a control program.

  A technique for detecting a suspicious person using a security camera is known. In Patent Document 1, a plurality of cameras are installed in a monitoring area, the position of the monitoring target is acquired by the GPS function of the terminal held by the monitoring target, and a camera within a predetermined distance from the position is photographed. A technique is described in which face images other than those to be monitored are extracted from the captured images, and a suspicious person is estimated from these face images.

JP 2010-191620 A JP 2006-146323 A

  However, in a space where an unspecified number of people enter and exit such as in a train, it is assumed that the person to be monitored has been specified in advance because the person who has received the nuisance (nuisance) is not specified in advance. In the technique described in Patent Document 1, it is difficult to narrow down nuisance persons. In addition, there are many cases where such a space where an unspecified number of people come and go is crowded, but in such a case, the face image extracted from the image taken by the camera installed in the space is incomplete. There was also a risk that the person could not be identified.

  The present invention has been made in view of the above background, a nuisance person estimation system capable of estimating a nuisance person in a space where an unspecified number of people go in and out, a control method for a nuisance person estimation system, and An object is to provide a control program.

  The present invention is a nuisance person estimation system for estimating nuisance persons in a space with an entrance where an unspecified number of people enter and exit, and is a first system for photographing a person who is provided near the entrance and enters the space. An imaging unit; a second imaging unit that identifies a position where the notification signal is transmitted when receiving a notification signal from the notification terminal provided in the space; and images the periphery of the position; and the first imaging unit An image analysis unit that analyzes an image captured by the second image capturing unit and an image captured by the second image capturing unit to extract face data, and a first database unit that stores face data extracted from the image captured by the first image capturing unit A second database unit that stores face data extracted from an image captured by the second imaging unit, a third database unit that stores face data that is a candidate for a nuisance agent, and the third database unit. A face data analysis unit for selecting face data to be stored in a storage unit and calculating a frequency score; and a determination unit for determining a person estimated based on the frequency score, wherein the face data analysis unit includes: The first face data stored in the first database part and the second face data stored in the second database part are collated, and the one closest to the second face data is selected from the first face data. When there is no stored face data stored in the third database unit that is extracted as stored candidate face data and substantially matches the stored candidate face data, the face data analyzing unit extracts the stored candidate face data. An initial value is given as the frequency score corresponding to the stored candidate face data newly stored and stored in the third database unit, and substantially matches the stored candidate face data When there is stored face data stored in three database parts, the face data analysis part matches the stored candidate face data without storing the candidate storage face data in the third database part. The frequency score corresponding to the face data is increased by a predetermined value, and the judgment unit determines that the frequency score corresponding to the face data stored in the third database unit after the elapse of a predetermined time period. A person whose face data exceeds a predetermined threshold is determined to be a person estimated to be a nuisance.

  In addition, the present invention provides a first imaging unit that is provided in the vicinity of an entrance / exit of a space with an entrance / exit for an unspecified number of people to / from the entrance, and a report from a report terminal provided in the space. A second imaging unit that identifies a position from which the notification signal is transmitted when a signal is received and images the vicinity of the position, an image captured by the first imaging unit, and an image captured by the second imaging unit. An image analysis unit that analyzes and extracts face data, a first database unit that stores face data extracted from an image captured by the first imaging unit, and an image captured by the second imaging unit A second database unit for storing face data, a third database unit for storing face data as candidates for nuisance, and selection of face data stored in the third database unit and calculation of a frequency score. A method for controlling a nuisance agent estimation system for estimating a nuisance agent in the space, comprising: a data analysis unit; and a determination unit for determining a person estimated based on the frequency score, wherein the face data analysis A unit compares the first face data stored in the first database unit with the second face data stored in the second database unit, and converts the first face data into the second face data. When there is no stored face data stored in the third database section that substantially matches the stored candidate face data, the face data analyzing section Storing the candidate storage face data newly in the third database unit and giving an initial value as the frequency score corresponding to the stored candidate face data stored; When there is stored face data stored in the third database unit that substantially matches the stored candidate face data, the face data analysis unit stores the storage candidate face data in the third database unit. Without increasing the frequency score corresponding to the stored face data that matches the stored candidate face data by a predetermined value, and after the predetermined time period has elapsed, the determination unit stores in the third database unit And determining a person whose face data has a corresponding frequency score exceeding a predetermined threshold among the stored face data as a person who is estimated to be a nuisance person.

  Furthermore, the present invention provides a first imaging unit that is provided in the vicinity of an entrance / exit of a space with an entrance / exit for an unspecified number of people, and a report from a notification terminal provided in the space. A second imaging unit that identifies a position from which the notification signal is transmitted when a signal is received and images the vicinity of the position, an image captured by the first imaging unit, and an image captured by the second imaging unit. An image analysis unit that analyzes and extracts face data, a first database unit that stores face data extracted from an image captured by the first imaging unit, and an image captured by the second imaging unit A second database unit for storing face data; a third database unit for storing face data as candidates for nuisance performers; and selection of face data stored in the third database unit and calculation of a frequency score. A control program for a nuisance agent estimation system for estimating a nuisance agent in the space, comprising: a face data analysis unit; and a determination unit for determining a person estimated based on the frequency score, wherein the face data The analysis unit compares the first face data stored in the first database unit with the second face data stored in the second database unit, and the second face data is selected from the first face data. When there is no stored face data stored in the third database section substantially matching the stored candidate face data, the face data analyzing section The storage candidate face data is newly stored in the third database unit and the initial value is given as the frequency score corresponding to the stored candidate face data. And when there is stored face data already stored in the third database unit that substantially matches the stored candidate face data, the face data analysis unit stores the stored candidate face data in the third database. A step of increasing the frequency score corresponding to the stored face data that matches the stored candidate face data without being stored in a predetermined part by a predetermined value; and after the elapse of a predetermined period, the determination unit (3) causing a computer to execute a step of determining a person whose face data has a corresponding frequency score exceeding a predetermined threshold among face data stored in the database unit as a person estimated to be a nuisance Is.

  According to the present invention, it is possible to estimate a nuisance person in a space where an unspecified number of people come in and out.

It is a figure explaining the outline | summary of this invention. It is a block diagram which shows schematic structure of the nuisance person estimation system 100 concerning this Embodiment. It is a figure explaining the boarding situation of the 1st day. It is a figure which shows an example of the data stored in the camera database part in a station on the 1st day. It is a figure explaining the condition in a train at the time of the 1st report. It is a figure which shows an example of the data stored in the vehicle camera database part on the 1st day. It is a figure which shows an example of the data stored in the integrated data database part on the 1st day. It is a figure explaining the boarding situation of the 2nd day. It is a figure which shows an example of the data stored in the camera database part in a station on the 2nd day. It is a figure explaining the condition in a train at the time of the report on the 2nd day. It is a figure which shows an example of the data stored in the vehicle camera database part on the 2nd day. It is a figure which shows an example of the data stored in the integrated data database part on the 2nd day. It is a flowchart which shows the flow of the process which acquires the face data of the person who gets on a train, and stores the said face data in the camera database part in a station. It is a flowchart which shows the flow of a process which acquires the face data of the person around a troubled person in a train, and stores the said face data in a vehicle camera database part. It is a flowchart which shows the flow of the process which estimates a nuisance person using the frequency score corresponding to the face data stored in the integrated data database part.

[Features of the present invention]
Prior to the description of the embodiments of the present invention, an outline of the features of the present invention will be described first.

  The nuisance person estimation system according to the present invention estimates a nuisance person in a space where an unspecified number of people enter and exit. FIG. 1 is a diagram for explaining the outline of the present invention. FIG. 1 is a block diagram showing a schematic configuration of an annoying person estimation system 500 according to the present invention. As shown in FIG. 1, the nuisance person estimation system 500 includes a first photographing unit 501, a second photographing unit 502, a reporting terminal 503, an image analyzing unit 504, a first database unit 505, and a second database. A unit 506, a third database unit 507, a face data analysis unit 508, and a determination unit 509.

  The first photographing unit 501 is provided near the entrance of a space where an unspecified number of people enter and exit, and photographs a person entering the space. The second imaging unit 502 is provided in the space, and when receiving a notification signal from the notification terminal 503, identifies the position where the notification signal is transmitted and images the vicinity of the position. The image analysis unit 504 analyzes the image captured by the first imaging unit 501 and the image captured by the second imaging unit 502, and extracts face data.

  The first database unit 505 stores face data extracted from the image photographed by the first photographing unit 501. The second database unit 506 stores face data extracted from the image captured by the second imaging unit 502. The third database unit 507 stores face data that is a nuisance candidate. The face data analysis unit 508 selects face data stored in the third database unit 507 and calculates a frequency score. The determination unit 509 determines a person estimated to be a nuisance based on the frequency score.

  The face data analysis unit 508 collates the first face data stored in the first database unit 505 with the second face data stored in the second database unit 506, and selects the second face from the first face data. The data closest to the data is extracted as the stored candidate face data. When there is no stored face data stored in the third database unit 507 that substantially matches the stored candidate face data, the face data analysis unit 508 newly adds the stored candidate face data to the third database unit 507. And the initial value is given as a frequency score corresponding to the stored candidate face data.

  When there is stored face data stored in the third database unit 507 that substantially matches the stored candidate face data, the face data analysis unit 508 stores the stored candidate face data in the third database unit 507. Instead, the frequency score corresponding to the stored face data that matches the stored candidate face data is increased by a predetermined value.

  After the elapse of a predetermined time period, the determination unit 509 detects a person whose face data has a corresponding frequency score that exceeds a predetermined threshold from among the face data stored in the third database unit 507. It is determined that the person is estimated.

  As described above, according to the present invention, it is possible to estimate a nuisance person in a space where a large number of unspecified persons enter and exit.

Embodiments of the present invention will be described below with reference to the drawings.
FIG. 2 is a block diagram showing a schematic configuration of the nuisance person estimation system 100 according to the present embodiment. As shown in FIG. 2, the nuisance person estimation system 100 includes an in-station camera system 101 as a first imaging unit, an in-vehicle camera system 102 as a second imaging unit, an analysis unit 103, a database unit 104, A person estimation report unit 105 as a determination unit and a reporting terminal 106 are provided.

  The in-station camera system 101 is installed in the vicinity of each boarding position on the platform of the station (near the entrance / exit of the train stopped in the platform for getting on and off), and the in-station camera 1, the camera identification information unit 2, and the control unit 3 and a communication unit 4. The in-station camera 1 receives a shooting instruction from the control unit 3 and takes a picture. The image captured by the in-station camera 1 may be either a moving image or a still image. When taking a still image, a plurality of images are taken. The camera identification information unit 2 receives the acquisition instruction from the control unit 3 and acquires the boarding position and boarding time. The control unit 3 sends an acquisition instruction to the in-station camera 1 and the camera identification information unit 2 while the train door is opened and closed for getting on and off at the platform of the station. The communication unit 4 sends the image acquired by the in-station camera 1 and the boarding position and boarding time acquired by the camera identification information unit 2 to the image analysis unit 9 wirelessly or by wire.

  A plurality of in-vehicle camera systems 102 are installed in a train, and include an in-vehicle camera 5, a camera identification information unit 6, a control unit 7, and a communication unit 8. The in-vehicle camera 5 captures an image in response to a capturing instruction from the control unit 7 that has received the notification signal from the notification terminal 106. The in-vehicle camera 5 is installed at a position where a person's face can be easily captured, for example, above the entrance door of a train. For communication between the reporting terminal 106 and the control unit 7, short-distance communication such as Bluetooth (registered trademark) that can easily identify the position is used. The image captured by the in-vehicle camera 5 may be either a moving image or a still image. When taking a still image, a plurality of images are taken. The camera identification information unit 6 receives the acquisition instruction from the control unit 7 and acquires information on the time when the notification signal is transmitted (time information) and information on the position where the notification signal is transmitted (position information). The location information is detected by a notification signal transmitted from the notification terminal 106. When receiving a notification signal from the notification terminal 106, the control unit 7 sends an acquisition instruction to the in-vehicle camera 5 and the camera identification information unit 6. The communication unit 8 wirelessly transmits the image acquired by the in-vehicle camera 5 and the time information and position information acquired by the camera identification information unit 6 to the image analysis unit 9.

  The analysis unit 103 includes an image analysis unit 9 and a face data matching frequency score calculation unit 10 as a face data analysis unit. The image analysis unit 9 extracts a human face from the image transmitted from the in-station camera system 101 and the image transmitted from the in-vehicle camera system 102, and analyzes the extracted feature points of each person's face. To create face data. A known technique can be used as a technique for extracting a human face from an image taken by a camera. The face data matching frequency score calculation unit 10 extracts face data closest to the face data stored in the in-vehicle camera database unit 12 from the face data stored in the in-station camera database unit 11, and this closest face data Is stored in the integrated data database unit 13 as a person present at the time of occurrence of the nuisance, and the detection frequency (frequency score) of the face data is calculated. The calculation of the detection score will be described later.

  The database unit 104 includes an in-station camera database unit 11 as a first database unit, an in-vehicle camera database unit 12 as a second database unit, and an integrated data database unit 13 as a third database unit. The in-station camera database unit 11 stores face data corresponding to each person's face extracted from an image taken by the in-station camera 1. The in-vehicle camera database unit 12 stores face data corresponding to each person's face extracted from an image taken by the in-vehicle camera 5. The integrated data database unit 13 stores human face data, frequency scores, and the like that were present when the nuisance occurred, as person data. The person estimation report unit 105 estimates that the person data stored in the integrated data database unit 13 has a frequency score that exceeds a predetermined threshold within a specified period as a nuisance agent, Provide the updated information to the system administrator. The reporting terminal 106 is a mobile communication terminal for an annoying person who has received a nuisance to transmit a reporting signal. For example, the reporting terminal 106 is a smartphone installed with a dedicated application for transmitting a reporting signal. A dedicated app may be available for free to anyone via the Internet.

A specific operation of the nuisance person estimation system 100 will be described below.
FIG. 3 is a diagram for explaining a boarding situation on the first day. As shown in FIG. 3, on the first day, assume that seven people get on the train that has arrived at the platform of the station. In the vicinity of each boarding position on the platform of the station, an in-station camera system 101 (No. 001 in-station camera system 101_1, No. 002 in-station camera system 101_2, No. 003 in-station camera system 101_3 and No. 004 in-station camera system 101_4) is installed. The in-station camera 1 of these in-station camera systems 101 is installed at such a height that a face image of a person on board can be taken clearly.

  The in-station camera system 101 captures a person who gets on the train and transmits the image to the analysis unit 103. Assume that each station camera system 101 takes a picture of a person who gets on the train at 8:00 on the first day. No. The face data C and D are extracted from the image captured by the 001 in-station camera system 101_1. The face data A, B, G are extracted from the image taken by the 002 station camera system 101_2. The face data F is extracted from the image taken by the 003 station camera system 101_3. Assume that face data E is extracted from an image taken by the 004 station camera system 101_4.

  FIG. 4 is a diagram illustrating an example of data stored in the in-station camera database unit 11 on the first day. As shown in FIG. 4, the in-station camera database unit 11 records the boarding position and boarding time corresponding to the face data together with the face data extracted from the image taken by the in-station camera system 101.

  FIG. 5 is a diagram for explaining the situation in the train at the time of reporting on the first day. As shown in FIG. 5, in-car camera systems 102 (No. 001 in-vehicle camera system 102_1, No. 002 in-vehicle camera system 102_2, No. 003 in-vehicle camera system 102_3, No. 004 in-vehicle camera are located near the entrances and exits of the train. System 102_4, No. 005 in-vehicle camera system 102_5, No. 006 in-vehicle camera system 102_6, No. 007 in-vehicle camera system 102_7 and No. 008 in-vehicle camera system 102_8) are installed.

  The notification signal transmitted from the notification terminal 106 by the disturbed person is received and detected by the control unit 7 of the in-vehicle camera system 102. In the control unit 7 of the in-vehicle camera system 102, the position where the notification signal is transmitted is specified by the reception angle of the notification signal. Then, photographing is performed by the in-vehicle camera system 102 closest to the position where the notification signal is transmitted.

  In FIG. 5, it is assumed that the person corresponding to the face data G (the nuisance activist) makes a report by the report terminal 106 when receiving the nuisance act. At this time, it is assumed that there are persons corresponding to the face data A, B, C, and D around the person corresponding to the face data G. The in-vehicle camera system 102 closest to the transmission position of the notification signal is No. No. 004 In-vehicle camera system 102_4, no. The 004 in-vehicle camera system 102_4 performs photographing. No. Assume that face data a, b, c, d, and g are extracted from an image captured by the 004 in-vehicle camera system 102_4.

  FIG. 6 is a diagram illustrating an example of data stored in the in-vehicle camera database unit 12 on the first day. As shown in FIG. 6, time information and position information corresponding to the face data are recorded in the vehicle camera database unit 12 together with the face data extracted from the image captured by the vehicle camera system 102. Here, the time information means information on the time when the notification signal is transmitted, and the position information means information on the position where the notification signal is transmitted by the notification terminal 106. When the nuisance occurs, any of the persons present around the nuisance (the sender of the notification signal) is considered to be the nuisance. In other words, any of the persons corresponding to the face data a, b, c, d, and g stored in the in-vehicle camera database unit 12 is considered to be an annoying person.

  In general, since passengers face the front and board the train from the doorway, the face of the person reflected in the image taken by the in-station camera system 101 often faces almost the front. On the other hand, the face of a person reflected in an image taken by the in-vehicle camera system 102 is often not facing the front because the train is crowded. For this reason, the face data extracted from the image captured by the in-vehicle camera system 102 tends to have insufficient facial feature points compared to the face data extracted from the image captured by the in-station camera system 101. For this reason, it is conceivable that a person cannot be sufficiently specified only by face data extracted from an image photographed by the in-vehicle camera system 102.

  The person corresponding to the face data stored in the in-vehicle camera database unit 12 is always stored in the in-station camera database unit 11. For this reason, the face data closest to the face data stored in the in-vehicle camera database unit 12 among the face data stored in the in-vehicle camera database unit 11 and the face data stored in the in-vehicle camera database unit 11 It can be assumed that the person corresponding to is the same person. Therefore, the face data matching frequency score calculation unit 10 compares the face data extracted from the image captured by the in-vehicle camera system 102 with the face data extracted from the image captured by the in-station camera system 101. The face data closest to the face data stored in the in-vehicle camera database unit 12 is extracted from the face data stored in the in-station camera database unit 11. Then, the face data matching frequency score calculation unit 10 stores the closest face data in the integrated data database unit 13 as a person present at the time of occurrence of the nuisance. A known method (for example, a method described in Patent Document 2) can be used as a method for extracting face data from a captured image and a method for collating face data.

  FIG. 7 is a diagram illustrating an example of data stored in the integrated data database unit 13 on the first day. As a result of collation between the face data stored in the in-vehicle camera database unit 12 shown in FIG. 6 and the face data stored in the in-station camera database unit 11 shown in FIG. 4, the face data a (see FIG. 6) is a face. In the data A (see FIG. 4), the face data b (see FIG. 6) is the face data B (see FIG. 4), the face data c (see FIG. 6) is the face data C (see FIG. 4), and the face data d. Assume that (see FIG. 6) is closest to face data D (see FIG. 4), and face data g (see FIG. 6) is closest to face data G (see FIG. 4). As shown in FIG. 7, face data A, B, C, D, and G are stored in the integrated data database unit 13. For the data relating to the boarding time and boarding position corresponding to the face data A, B, C, D, G stored in the in-station camera database unit 11, the face data A, B, stored in the integrated data database unit 13 are also stored. C, D, and G are associated with each other and stored in the integrated data database unit 13.

  Further, the time data and the data related to the position information corresponding to the face data a, b, c, d, and g stored in the in-vehicle camera database unit 12 are the face data a, b, c, d, and g, respectively. Corresponding to A, B, C, D, and G, the face data A, B, C, D, and G stored in the integrated data database unit 13 are stored in the integrated data database unit 13 in association with each other. When face data is newly stored in the integrated data database unit 13, an initial value of 1 is recorded in the frequency score of the face data.

  FIG. 8 is a diagram illustrating the boarding situation on the second day. As shown in FIG. 8, assume that each station camera system 101 takes a picture of a person on the train at 8:00 on the second day. No. The face data R and Q are extracted from the image captured by the 001 in-station camera system 101_1. The face data O, P, U are extracted from the image taken by the 002 station camera system 101_2. The face data T is extracted from the image taken by the 003 station camera system 101_3. It is assumed that the face data S is extracted from the image captured by the 004 station camera system 101_4.

  FIG. 9 is a diagram illustrating an example of data stored in the in-station camera database unit 11 on the second day. As shown in FIG. 9, the in-station camera database unit 11 records the boarding time and boarding position corresponding to the face data together with the face data extracted from the image taken by the in-station camera system 101. In order to avoid an enormous amount of data, the in-station camera database unit 11 starts data recording from the first day of the day and resets the data after the last train. That is, in the in-station camera database unit 11, the data stored on the first day (see FIG. 4) is deleted on the second day.

  FIG. 10 is a diagram for explaining the situation in the train at the time of notification on the second day. As shown in FIG. 10, it is assumed that a person corresponding to the face data U (an annoying person) makes a report using the reporting terminal 106 when receiving the annoying action. At this time, it is assumed that there are persons corresponding to the face data O, P, Q, and R around the person corresponding to the face data U. The in-vehicle camera system 102 closest to the transmission position of the notification signal is No. No. 004 In-vehicle camera system 102_4, no. The 004 in-vehicle camera system 102_4 performs photographing. No. Assume that face data o, p, q, r, u are extracted from an image taken by the 004 in-vehicle camera system 102_4.

  FIG. 11 is a diagram illustrating an example of data stored in the in-vehicle camera database unit 12 on the second day. As shown in FIG. 11, time information and position information corresponding to the face data are recorded in the in-vehicle camera database unit 12 together with the face data extracted from the image captured by the in-vehicle camera system 102. Here, the time information means information on the time when the notification signal is transmitted, and the position information means information on the position where the notification signal is transmitted by the notification terminal 106. The in-vehicle camera database unit 12 starts data recording from the first day of the day in order to avoid an enormous amount of data, and resets the data after the last train. That is, in the in-vehicle camera database unit 12, the data stored on the first day (see FIG. 6) is deleted on the second day.

  The face data matching frequency score calculation unit 10 collates the face data stored in the in-vehicle camera database unit 12 shown in FIG. 11 with the face data stored in the in-station camera database unit 11 shown in FIG. As a result, the face data o (see FIG. 11) is the face data O (see FIG. 9), the face data p (see FIG. 11) is the face data P (see FIG. 9), and the face data q (see FIG. 11) is the face. In the data Q (see FIG. 9), the face data r (see FIG. 11) is closest to the face data R (see FIG. 9), and the face data u (see FIG. 11) is closest to the face data U (see FIG. 9). Suppose. The face data O, P, Q, R, and U are candidates to be stored in the integrated data database unit 13. The time information and position information of the face data o, p, q, r, u are associated with the face data O, P, Q, R, U, respectively.

  Subsequently, the face data matching frequency score calculation unit 10 includes face data O, which are candidates to be stored in the integrated data database unit 13 among the face data already stored in the integrated data database unit 13 (see FIG. 7). A search is made to see if there is a substantial match with P, Q, R, U. As a result of the search, it is assumed that the face data A already stored in the integrated data database unit 13 and the face data O that is a candidate stored in the integrated data database unit 13 substantially match. It is assumed that the face data P, Q, R, and U that are candidates to be stored in the integrated data database unit 13 do not substantially match the face data already stored in the integrated data database unit 13.

FIG. 12 is a diagram illustrating an example of data stored in the integrated data database unit 13 on the second day.
As shown in FIG. 12, among the candidates stored in the integrated data database unit 13, face data P, Q, R and U are newly stored in the integrated data database unit 13. Position information, time information, boarding position and boarding time corresponding to the face data P, Q, R, U are also recorded in the integrated data database unit 13 together with the face data P, Q, R, U. When face data is newly stored in the integrated data database unit 13, the initial value 1 is recorded as the frequency score of the face data.

  Among the candidates to be stored in the integrated data database unit 13, face data O that has been found to substantially match the face data already stored in the integrated data database unit 13 is newly added to the integrated data database unit 13. The position information corresponding to the face data O, the time information, the boarding position, and the boarding time data are additionally recorded in the face data A column. Further, 1 which is a predetermined value is added to the frequency score of the face data A already stored in the integrated data database unit 13. That is, the frequency score corresponding to the face data A is 2.

  When the nuisance person estimation system 100 repeats the processing on the first day and the second day described above, data of a person who is a nuisance person candidate is accumulated in the integrated data database unit 13 every day. When a specified period (for example, one month) has elapsed, the integrated data database unit 13 estimates that the person corresponding to the face data whose frequency score exceeds a predetermined threshold (for example, 4) is a nuisance acter. The

  In general, since a nuisance person has a strong tendency to repeat the nuisance action, the nuisance action person can be accurately estimated from the frequency score described above. From the above, it is possible to estimate nuisance agents in a space where an unspecified number of people enter and exit from the nuisance agent estimation system 100 according to the present embodiment.

  Next, the flow of processing in which the nuisance person estimation system 100 estimates the nuisance person will be described below. FIG. 13, FIG. 14 and FIG. 15 are flowcharts showing the flow of processing in which the nuisance person estimation system 100 estimates the nuisance person. In the following description, FIG. 2 is also referred to as appropriate.

  FIG. 13 is a flowchart showing a flow of processing for acquiring face data of a person getting on a train and storing the face data in the in-station camera database unit 11. As shown in FIG. 13, first, the control unit 3 of the in-station camera system 101 issues an instruction to capture an image, a boarding time, and a boarding position to the in-station camera 1 and camera identification information, respectively (steps). S1). The in-station camera 1 captures an image, and the camera identification information acquires the boarding time and boarding position (step S2).

  Next, the communication unit 4 transmits the image taken by the camera identification information unit 2 and the boarding time and boarding position acquired by the camera identification information to the image analysis unit 9 (step S3). Subsequent to step S3, the image analysis unit 9 extracts face data from the image taken by the in-station camera 1 (step S4), and associates the extracted face data with the boarding time and boarding position in the station. Store in the camera database unit 11 (step S5).

  FIG. 14 is a flowchart showing a flow of processing for acquiring face data of persons around the nuisance performer in a train and storing the face data in the in-vehicle camera database unit 12. As shown in FIG. 14, first, the control unit 7 of the in-vehicle camera system 102 receives a report signal transmitted from the report terminal 106 of the nuisance person (step S101). Next, the control part 7 which received the report signal specifies the position where the report signal was transmitted from the angle etc. of the report signal (step S102).

  Subsequent to step S102, in the in-vehicle camera system 102 installed at the closest distance from the notification position, the in-vehicle camera 5 captures an image around the transmission position of the notification signal, and the camera identification information section 6 displays time information / position information. Is acquired (step S103). Here, the time information means information on the time when the notification signal is transmitted, and the position information means information on the position where the notification signal is transmitted by the notification terminal 106. Then, the communication unit 8 transmits the image taken by the in-vehicle camera and the position information / time information acquired by the camera identification information unit 6 to the image analysis unit 9 (step S104).

  Subsequent to step S104, the image analysis unit 9 extracts face data from the image captured by the in-vehicle camera 5 (step S105), and associates the extracted face data with the position information / time information in the in-vehicle camera database. Store in the unit 12 (step S106).

  FIG. 15 is a flowchart showing a flow of processing for estimating a nuisance person from a frequency score corresponding to face data stored in the integrated data database unit 13. As shown in FIG. 15, first, the face data matching frequency score calculation unit 10 compares the face data stored in the in-vehicle camera database unit 12 with the face data stored in the in-station camera database unit 11, Out of the face data stored in the in-station camera database unit 11, the face data closest to the face data stored in the in-vehicle camera database unit 12 is extracted as a candidate to be stored in the integrated data database unit 13 (step S201).

  Subsequent to step S201, the face data matching frequency score calculation unit 10 substantially matches the face data extracted as candidates to be stored in the integrated data database unit 13 among the face data already stored in the integrated data database unit 13. Whether there is a match is searched (step S202).

  If there is a match in step S202, the face data matching frequency score calculation unit 10 does not newly store the matching face data in the integrated data database unit 13, but only newly sets the matching face data. The data is stored in the integrated data database unit 13 (step S203). When storing face data, the corresponding position information and time information are also stored.

  If there is no match in step S202, all the face data extracted as candidates to be stored in the integrated data database unit 13 are newly stored in the integrated data database unit 13 (step S204). When storing face data, the corresponding position information and time information are also stored.

  Following step S203 and step S204, the frequency score of the integrated data database unit 13 is updated (step S205). Specifically, the initial value 1 is recorded in the frequency score of the face data newly stored in the integrated data database unit 13 among the candidates, and is not newly stored in the integrated data database unit 13 among the candidates. For face data, a predetermined value of 1 is added to the corresponding frequency score of face data already stored in the integrated data database unit 13.

  Following step S205, it is determined whether the specified period has elapsed (step S206). When it is determined in step S206 that the specified period has elapsed, the face data stored in the integrated data database unit 13 is estimated to be a nuisance person with face data whose frequency score exceeds a predetermined threshold. The person is determined to be a person who reports to the administrator (step S207). If it is not determined in step S206 that the specified period has elapsed, the process returns to step S201.

  In the above-described embodiments, the present invention has been described as a hardware configuration, but the present invention is not limited to this. The present invention can also be realized by causing a CPU (Central Processing Unit) to execute a computer program for each process.

  In the above example, the program can be stored and provided to a computer using various types of non-transitory computer readable media. Non-transitory computer readable media include various types of tangible storage media. Examples of non-transitory computer-readable media include magnetic recording media (for example, flexible disks, magnetic tapes, hard disk drives), magneto-optical recording media (for example, magneto-optical disks), CD-ROMs (Read Only Memory), CD-Rs, CD-R / W, semiconductor memory (for example, mask ROM, PROM (Programmable ROM), EPROM (Erasable PROM), flash ROM, RAM (Random Access Memory), and various types of temporary programs. Computer-readable media may be provided to a computer by way of example, such as electrical signals, optical signals, and electromagnetic waves. The temporary computer-readable medium can supply the program to the computer via a wired communication path such as an electric wire and an optical fiber, or a wireless communication path.

  Although the present invention has been described with reference to the above embodiment, the present invention is not limited only to the configuration of the above embodiment, and within the scope of the invention of the claims of the present application. It goes without saying that various modifications, corrections, and combinations that can be made by those skilled in the art are included.

  For example, in the above-described embodiment, the location information at which the reporting terminal has transmitted a reporting signal may be taken into account in calculating the frequency score. Specifically, in the calculation of the frequency score, a predetermined value to be added is made larger than the reference value for a person who has been detected again after receiving a notification signal transmitted at the same position. For example, if the reference value of the predetermined value is 1, the predetermined value to be added is 2 for the person who is detected again at the same position. Since the addict of the nuisance often performs the nuisance again at the position where the nuisance is once performed, the accuracy of the estimation of the nuisance can be improved by calculating the frequency score in this way.

  The in-vehicle camera 5 of the in-vehicle camera system 102 may be a movable type that can move along a guide such as a rail disposed in the train. Thereby, it is possible to more easily capture the faces of persons around the nuisance performer. The movable in-vehicle camera moves to an optimal position in order to capture the face of the person around the nuisance agent according to the position of the nuisance agent specified by the notification signal transmitted from the notification terminal.

  When a notification signal is transmitted from the notification terminal 106, a plurality of in-vehicle camera systems 102 may take an image. In this way, it is possible to avoid a face data acquisition error.

  The in-vehicle camera system 102 installed at a position closest to the position where the notification terminal 106 has transmitted the notification signal, and the in-vehicle camera system 102 disposed opposite to the in-vehicle camera system 102, take an image. It may be. For example, in FIG. 5, the in-vehicle camera system 102 installed at the closest position is No. If it is 004 in-vehicle camera system 102_4, No. 004 in-vehicle camera system 102_4, The No. 003 in-vehicle camera system 102_3 disposed opposite to the 004 in-vehicle camera system 102_4 captures an image. In this way, it is possible to avoid a face data acquisition error.

  An image may be taken in the in-vehicle camera system 102 installed within a predetermined distance from the position where the notification terminal 106 transmits the notification signal. In this way, it is possible to avoid a face data acquisition error.

500 nuisance estimation system 501 first imaging unit 502 second imaging unit 503 reporting terminal 504 image analysis unit 505 first database unit 506 second database unit 507 third database unit 508 face data analysis unit 509 determination unit

Claims (8)

A nuisance person estimation system that estimates nuisance persons in a space where an unspecified number of people enter and exit,
A first photographing unit provided near the entrance and photographing a person entering the space;
A second imaging unit which is provided in the space and identifies a position where the notification signal is transmitted when receiving a notification signal from the notification terminal, and images the periphery of the position;
An image analysis unit that analyzes an image captured by the first imaging unit and an image captured by the second imaging unit and extracts face data;
A first database unit for storing face data extracted from an image captured by the first imaging unit;
A second database unit for storing face data extracted from an image captured by the second imaging unit;
A third database unit for storing facial data that are candidates for nuisances;
A face data analysis unit for selecting face data to be stored in the third database unit and calculating a frequency score;
A determination unit that determines a person estimated to be a nuisance based on the frequency score,
The face data analysis unit compares the first face data stored in the first database unit with the second face data stored in the second database unit, and the first face data is compared with the first face data. The one closest to the two face data is extracted as the storage candidate face data,
When there is no stored face data stored in the third database part that substantially matches the candidate storage face data, the face data analysis part newly adds the stored candidate face data to the third database part. Storing and giving an initial value as the frequency score corresponding to the stored candidate face data stored;
When there is stored face data stored in the third database unit that substantially matches the stored candidate face data, the face data analysis unit stores the storage candidate face data in the third database unit. Without increasing the frequency score corresponding to the stored face data that matches the stored candidate face data by a predetermined value,
The determination unit nuisances a person whose face data has a corresponding frequency score that exceeds a predetermined threshold among the face data stored in the third database unit after a predetermined period of time has elapsed. System for estimating a nuisance person who determines that the person is estimated to be a person.   The nuisance person estimation system according to claim 1, wherein in calculating the frequency score corresponding to the face data stored in the third database unit, information on a position where the notification terminal transmits a notification signal is considered.   The nuisance person estimation system according to claim 1 or 2, wherein a plurality of the second photographing units are installed in the space.   When a notification signal is transmitted from the notification terminal, among the plurality of second imaging units, at least the one closest to the position where the notification signal is transmitted is photographed around the transmitted position. The nuisance person estimation system according to claim 3.   When a notification signal is transmitted from the notification terminal, the transmission position is a distance from a position where the notification signal is transmitted within a predetermined distance among the plurality of second imaging units. The nuisance person estimation system according to claim 4, wherein the surrounding area is photographed.   The said 2nd imaging | photography part is movable along the guide arrange | positioned in the said space, and moves according to the transmission position of the notification signal by the said notification terminal. Nuisance estimation system. When receiving a notification signal from a notification terminal provided in the space provided in the space near the entrance and exit of a space with an entrance where an unspecified number of people enter and exit, and a person entering the space The second image capturing unit that identifies the position where the notification signal is transmitted and captures the periphery of the position, the image captured by the first image capturing unit, and the image captured by the second image capturing unit are analyzed and face data is analyzed. An image analysis unit to extract; a first database unit that stores face data extracted from an image captured by the first imaging unit; and a first database unit that stores face data extracted from an image captured by the second imaging unit. 2 database units, a third database unit for storing face data as candidates for nuisances, a face data analysis unit for selecting face data stored in the third database unit and calculating a frequency score A method of controlling a nuisance who estimation system for estimating a nuisance who within the space provided and determining section, the determining a person suspected of nuisance person based on the frequency score,
The face data analysis unit compares the first face data stored in the first database unit with the second face data stored in the second database unit, and the first face data is compared with the first face data. Extracting the closest face data to the face candidate face data;
When there is no stored face data stored in the third database part that substantially matches the candidate storage face data, the face data analysis part newly adds the stored candidate face data to the third database part. Storing and giving an initial value as the frequency score corresponding to the stored candidate face data stored;
When there is stored face data stored in the third database unit that substantially matches the stored candidate face data, the face data analysis unit stores the storage candidate face data in the third database unit. Without increasing the frequency score corresponding to the stored face data that matches the stored candidate face data by a predetermined value;
The determination unit nuisances a person whose face data has a corresponding frequency score that exceeds a predetermined threshold among the face data stored in the third database unit after a predetermined period of time has elapsed. A method of controlling a nuisance person estimation system comprising: determining a person estimated to be a person. When receiving a notification signal from a notification terminal provided in the space provided in the space near the entrance and exit of a space with an entrance where an unspecified number of people enter and exit, and a person entering the space The second image capturing unit that identifies the position where the notification signal is transmitted and captures the periphery of the position, the image captured by the first image capturing unit, and the image captured by the second image capturing unit are analyzed and face data is analyzed. An image analysis unit to extract; a first database unit that stores face data extracted from an image captured by the first imaging unit; and a first database unit that stores face data extracted from an image captured by the second imaging unit. 2 database units, a third database unit for storing face data as candidates for nuisances, a face data analysis unit for selecting face data stored in the third database unit and calculating a frequency score A control program of the nuisance's estimation system for estimating a nuisance people in the space provided a determination unit, a determining a person is estimated based on the frequency score,
The face data analysis unit compares the first face data stored in the first database unit with the second face data stored in the second database unit, and the first face data is compared with the first face data. Extracting the closest face data to the face candidate face data;
When there is no stored face data stored in the third database part that substantially matches the candidate storage face data, the face data analysis part newly adds the stored candidate face data to the third database part. Storing and giving an initial value as the frequency score corresponding to the stored candidate face data stored;
When there is stored face data stored in the third database unit that substantially matches the stored candidate face data, the face data analysis unit stores the storage candidate face data in the third database unit. Without increasing the frequency score corresponding to the stored face data that matches the stored candidate face data by a predetermined value;
The determination unit nuisances a person whose face data has a corresponding frequency score that exceeds a predetermined threshold among the face data stored in the third database unit after a predetermined period of time has elapsed. Determining that the person is estimated to be a person,
A control program that causes a computer to execute.

Images