Person identification methods, person identification systems, and person identification procedures

Abstract

This disclosure provides a person identification method, a person identification system, and a person identification program. It provides a technique for identifying persons contained in a camera image even when the number of antennas transmitting and receiving user information is less than the total number of cameras. The process includes a first and a second identification process. In the first identification process, identification information of persons contained in an image within a first range captured by a first camera is compared with user information containing antenna information of the antenna corresponding to the first camera. If the location and time identification information matches the user information, the person contained in the image within the first range is identified as a user, and tracking support information for that user is generated. In the second identification process, identification information of persons contained in an image within a second range captured by a second camera is compared with tracking support information of the first camera corresponding to the second camera, and it is determined whether a user identical to the user identified as contained in the image within the first range is contained in the second range.

Description

Technical Field

[0001] This disclosure relates to methods, systems, and procedures for identifying a person contained in a camera image by combining camera images and communications. Background Technology

[0002] Japanese Patent Application Publication No. 2016-122300 discloses a system for identifying a person contained in a camera image by combining camera image and communication. This conventional system includes: a beacon device located near the camera to transmit a detection signal to a user's portable terminal; and an image processing unit for performing person identification processing. Upon receiving a detection signal from the beacon device, the user's portable terminal transmits the beacon device's identification information and user information to the image processing unit. This user information includes identification information assigned to the user, feature information such as the user's facial image, or a combination of these.

[0003] In the discrimination process performed by the image processing device, based on the identification information of the beacon device and the time information of the acquired user information, it is predicted that a user exists within the field of view of a camera located near the beacon device. Furthermore, in the discrimination process, a person is extracted from the camera image using the camera image acquired by the camera and the time information of the acquired user information. Moreover, by comparing the feature information of the extracted person with the feature information contained in the user information, the user contained in the camera image is determined.

[0004] Existing technical documents

[0005] Patent documents

[0006] Patent Document 1: Japanese Patent Application Publication No. 2016-122300

[0007] Patent Document 2: Japanese Patent Application Publication No. 2012-008802

[0008] Patent Document 3: Japanese Patent Application Publication No. 2020-194295 Summary of the Invention

[0009] Consider replacing the beacon device in a conventional system with an antenna capable of transmitting and receiving data. In this case, the antenna acquires user information, for example, through short-range wireless communication with a portable terminal, and transmits it to an external device (e.g., an image processing device) through long-range communication. According to a system including such an antenna, it is possible, as with conventional systems, to combine camera images and communication to identify people contained within the camera image.

[0010] Here, from the perspectives of monitoring people included in camera images and preventing crime using camera images, it is preferable to increase the number of cameras constituting the system. Furthermore, if the number of antennas increases, the accuracy of the location information of the portable terminal (i.e., the user) improves, and it is expected that the accuracy of identifying people included in camera images will improve. On the other hand, there are concerns about increased costs when the number of antennas increases. Therefore, it is desirable to develop a technology that can identify people included in camera images even when the total number of antennas is less than the total number of cameras.

[0011] One object of this disclosure is to provide a technique for identifying people contained in a camera image even when the number of antennas transmitting and receiving user information is less than the total number of cameras.

[0012] The first viewpoint is a method for identifying people contained in a camera image, which has the following characteristics.

[0013] The method includes:

[0014] The steps include obtaining user information assigned to a user terminal through short-range wireless communication using an antenna, and sending the user information to the outside through long-range communication using the same antenna.

[0015] The step of using the first camera to acquire an image of a first range that includes at least a portion of the range of short-range wireless communication utilizing the antenna;

[0016] The step of using a second camera to acquire an image of a second range that does not include the range of the near-field wireless communication;

[0017] The steps of identifying persons within the first range of images; and

[0018] The step of identifying the person in the image contained in the second range.

[0019] The steps for identifying persons within the first range of images include:

[0020] The step of generating identification information of persons contained in the image within the first range;

[0021] The step of determining whether a user associated with the user terminal is included in the first range of images based on the identification information of persons in the images contained in the first range, the identification information of the antenna, and the user information obtained by the antenna; and

[0022] The step of generating tracking support information for a user who is determined to be associated with the user terminal and whose image is included in the first range.

[0023] The steps for identifying persons within the second range of images include:

[0024] The step of generating identification information of persons within the image of the second range; and

[0025] The step of determining whether a user who is the same as the user determined to be included in the first range of images is included in the second range of images, based on the identification information of the person included in the second range of images and the tracking support information.

[0026] The second viewpoint also has the following characteristics compared to the first viewpoint.

[0027] The tracking support information includes user information of the user identified as being included in the first range of images, information about the location of the first camera that obtained the first range of images, and information about the time when the first camera obtained the first range of images.

[0028] The step of identifying persons within the second range of images further includes:

[0029] The step of reducing the tracking support information is based on the information of the time when the image of the first range was obtained, the information of the position of the first camera when the image of the first range was obtained, the information of the time when the image of the second range was obtained, and the information of the position of the second camera.

[0030] The steps to reduce the tracking support information include:

[0031] The step of extracting tracking support information generated from images of the first range obtained by a first camera located within a predetermined distance from the position of the second camera during a predetermined time period tracing back from the moment the image of the second range was obtained.

[0032] The third viewpoint also has the following characteristics compared to the first or second viewpoint.

[0033] The second camera includes at least two cameras.

[0034] The step of identifying persons within the second range of images further includes:

[0035] In the case where it is determined that a user, who is also identified as a user included in the first range of images, is included in the second range of images, the step of generating tracking confirmation information for that user is as follows: user information of the user identified as being included in the second range of images, information on the location of the second camera that captured the second range of images, and information on the time when the second camera captured the second range of images; and

[0036] The step of reducing the tracking confirmation information is based on the information of the time when the image of the second range was obtained, the information of the location of the second camera included in the tracking confirmation information, the information of the time when the image of the second range as the object of person identification was obtained, and the information of the location of the second camera that obtained the image of the second range as the object of person identification.

[0037] The steps to reduce the tracking support information include:

[0038] The step of extracting tracking confirmation information is generated based on images of the second range acquired by another second camera located within a predetermined distance from the position of the second camera that acquired the image of the second range as the object of person identification during a predetermined time period tracing back from the moment the image of the second range as the object of person identification was acquired.

[0039] The fourth viewpoint also has the following characteristics in any one of the first to third viewpoints.

[0040] The first camera includes at least two cameras.

[0041] The method further includes:

[0042] If it is determined that the same user is included in at least two images within the first range obtained by the at least two first cameras, the step of calculating the user's direction of movement is performed based on information about the positions of the first cameras that obtained the at least two images and information about the times at which the at least two images were obtained.

[0043] The step of identifying persons within the first range of images further includes:

[0044] If a user associated with the user terminal is found to be included in the image of the first range, the step of determining whether to calculate information about the user's direction of movement; and

[0045] If it is determined that the information of the direction of movement has been calculated, then, based on the information of the direction of movement, the step of adding the identification information of the second camera, which is located in front of the direction of movement from the perspective of the first camera that has obtained the image of the first range, to the tracking support information.

[0046] The step of identifying persons within the second range of images further includes:

[0047] The step of determining whether the identification information of the second camera located ahead in the direction of movement is included in the tracking support information; and

[0048] If the identification information of the second camera, which is determined to be located in front of the direction of movement, is included in the tracking support information, the step of reducing the number of people in the image included in the second range is based on the identification information of the second camera.

[0049] The fifth point is a system for identifying people contained in a camera image, which has the following characteristics.

[0050] The system includes an antenna, a first and a second camera, and a management server.

[0051] The antenna acquires user information assigned to the user terminal through short-range wireless communication and transmits the user information to the outside through long-range communication.

[0052] The first camera captures a first range that includes at least a portion of the range of short-range wireless communication using the antenna.

[0053] The second camera captures a second range that does not include the range of the near-field wireless communication.

[0054] The management server performs a first identification process to identify people in images within the first range, and a second identification process to identify people in images within the second range.

[0055] In the first identification process, the management server...

[0056] Generate identification information for the person contained in the image within the first range.

[0057] Based on the identification information of the person in the image within the first range, the identification information of the antenna, and the user information obtained by the antenna, it is determined whether the user associated with the user terminal is included in the image within the first range.

[0058] If a user is determined to be associated with the user terminal and is included in the first range of images, tracking support information for that user is generated.

[0059] In the second identification process, the management server...

[0060] Generate identification information for the person contained in the image within the second range.

[0061] Based on the identification information of the person in the image included in the second range and the tracking support information, it is determined whether the same user as the user determined to be included in the image in the first range is included in the image in the second range.

[0062] The sixth viewpoint also has the following characteristics as seen in the fifth viewpoint.

[0063] The tracking support information includes user information of the user identified as being included in the first range of images, information about the location of the first camera that obtained the first range of images, and information about the time when the first camera obtained the first range of images.

[0064] The management server also performs the following in the second identification process:

[0065] The processing of the tracking support information is reduced based on the information included in the tracking support information regarding the time when the image of the first range was acquired, the information included in the tracking support information regarding the position of the first camera when the image of the first range was acquired, the information included in the tracking support information regarding the time when the image of the second range was acquired, and the information regarding the position of the second camera.

[0066] The management server reduces the processing of the tracking support information.

[0067] Extract tracking support information generated from images of the first range obtained by a first camera located within a predetermined distance from the position of the second camera during a predetermined time period tracing back from the moment the image of the second range was obtained.

[0068] The seventh viewpoint also has the following characteristics compared to the fifth or sixth viewpoint.

[0069] The second camera includes at least two cameras.

[0070] In the second identification process, the management server, further,

[0071] If a user is determined to be the same user as the user determined to be included in the first range of images and is included in the second range of images, tracking confirmation information for that user is generated. The tracking confirmation information includes: user information of the user determined to be included in the second range of images, information on the location of the second camera that captured the second range of images, and information on the time when the second camera captured the second range of images.

[0072] In the second identification process, the management server further performs the following:

[0073] The processing of the tracking confirmation information is reduced based on the information included in the tracking confirmation information about the time when the image of the second range was obtained, the information included in the tracking confirmation information about the position of the second camera, the information about the time when the image of the second range, which is the object of the second discrimination process, was obtained, and the information about the position of the second camera that obtained the image of the second range, which is the object of the second discrimination process.

[0074] The management server reduces the processing of the tracking confirmation information.

[0075] Extract tracking confirmation information, which is generated based on images of the second range obtained by another second camera located within a predetermined distance from the position of the second camera that obtained the image of the second range as the object of the second identification process during a predetermined time period tracing back from the moment when the image of the second range as the object of the second identification process was obtained.

[0076] The eighth viewpoint also has the following characteristics among any one of the viewspoints from the fifth to the seventh.

[0077] The first camera includes at least two cameras.

[0078] The management server then,

[0079] If it is determined that the same user is included in at least two images within the first range obtained by the at least two first cameras, the user's direction of movement is calculated based on the information of the positions of the first cameras that obtained the at least two images and the information of the time when the at least two images were obtained.

[0080] In the first identification process, the management server, further,

[0081] If a user associated with the user terminal is found to be included in the image within the first range, it is determined whether information about the user's direction of movement has been calculated.

[0082] If it is determined that the information of the movement direction has been calculated, the identification information of the second camera, which is located in front of the movement direction from the perspective of the first camera that obtained the image of the first range, is added to the tracking support information based on the information of the movement direction.

[0083] In the second identification process, the management server, further,

[0084] Determine whether the identification information of the second camera located ahead in the direction of movement is included in the tracking support information.

[0085] If the identification information of the second camera, which is determined to be located in front of the direction of movement, is included in the tracking support information, the number of people in the image included in the second range is reduced based on the identification information of the second camera.

[0086] The ninth point is to enable a computer to execute a program that identifies people contained in a camera image, and it has the following characteristics.

[0087] The program causes the computer to execute:

[0088] User information assigned to a user terminal is obtained through short-range wireless communication using an antenna, and this user information is then transmitted to an external processing facility through long-range communication using the same antenna.

[0089] Processing of acquiring an image of a first range, including at least a portion of the range of short-range wireless communication utilizing the antenna, using the first camera;

[0090] Processing of acquiring images of a second range that does not include the range of the near-field wireless communication using a second camera;

[0091] Processing for identifying persons within the first range of images; and

[0092] Processing for identifying people in the images contained within the second range.

[0093] The process of identifying persons within the first range of images includes:

[0094] Processing to generate identification information of people in the image contained in the first range;

[0095] The process of determining whether a user associated with the user terminal is included in the first range of images based on the identification information of persons in the images contained in the first range, the identification information of the antenna, and the user information obtained by the antenna; and

[0096] In the case where it is determined that a user associated with the user terminal is included in the first range of images, the process of generating tracking support information for that user is performed.

[0097] The process of identifying persons within the second range of images includes:

[0098] Processing to generate identification information of persons within the image contained in the second range; and

[0099] The process of determining whether a user who is the same as the user identified as being included in the first range of images is included in the second range of images, based on the identification information of the person included in the second range of images and the tracking support information.

[0100] According to viewpoints 1, 5, or 8, in the process of identifying persons within images in the first range (first identification process), if a user associated with a user terminal is determined to be included in the images in the first range, tracking support information for that user is generated. This tracking support information is then used in the process of identifying persons within images in the second range (second identification process) to determine whether the same user as the one determined to be included in the images in the first range is also included in the images in the second range. Therefore, even when the total number of antennas is less than the total number of cameras, it is possible to identify users included in the second range. This contributes to efficient user tracking in environments with limited infrastructure resources.

[0101] Based on point 2 or 6, the tracking support information is reduced. Therefore, the processing load on the computer performing the second identification process can be reduced. This contributes to more efficient tracking for users.

[0102] According to viewpoint 3 or 7, in the second discrimination process, if it is determined that the same user as the user determined to be included in the first range of images is included in the second range of images, tracking confirmation information for that user is generated. This tracking confirmation information is used in a second discrimination process different from the first discrimination process. Therefore, by repeatedly performing the second discrimination process and other second discrimination processes, it is possible to continuously track the user.

[0103] According to viewpoint 4 or 8, based on the user's direction of movement, the identification information of the second camera located ahead in that direction is added to the tracking support information. Therefore, the processing load on the computer performing the second identification process can be reduced. This contributes to more efficient tracking for the user. Attached Figure Description

[0104] Figure 1 This is a diagram illustrating the outline of person identification performed in the system according to the embodiments of this disclosure.

[0105] Figure 2 This is a diagram illustrating the envisioned state of the implementation method.

[0106] Figure 3 This is a block diagram illustrating an example of the overall structure of the system involved in the implementation.

[0107] Figure 4 It is shown Figure 3 The diagram shows an example of the functional structure of a management server.

[0108] Figure 5 This is a diagram illustrating a reduced example of the tracking support information used in the second identification process.

[0109] Figure 6 This diagram illustrates an example of a method for determining a camera with additional identification information added to track support information.

[0110] Figure 7 This is a flowchart illustrating an example of the first discrimination process performed by the management server (processor).

[0111] Figure 8 This is a flowchart illustrating an example of the second discrimination process performed by the management server (processor).

[0112] (Symbol Explanation)

[0113] 1, 11, 12, 1X: Antenna; 2, 21, 22: User terminal; 3, 31, 32, 33, 34, 35, 36, 37, 38, 39, 3Y: Camera; 4, 41, 42, 43, 44, 45, 4Z: Camera; 5: Management server; 51: Processor; 52: Memory; U, U1, U2: User; Du: Direction of movement; CR1, CR11, CR12, CR1X: Communication range; SR3, SR31, SR32, SR3Y: Shooting range; SR4, SR41, SR42, SR4Z: Shooting range; ANT: Antenna information; CAM1, CAM2: Camera information; IDN: Identification information; TRA: Tracking support information; TRC: Tracking confirmation information; USR: User information. Detailed Implementation

[0114] Hereinafter, with reference to the accompanying drawings, the person identification method, person identification system, and person identification program according to embodiments of the present disclosure will be described. Furthermore, the person identification method according to the embodiments is implemented through computer processing performed in the person identification system according to the embodiments. The person identification program according to the embodiments is a program used to cause a computer to execute the person identification method according to the embodiments. In the various figures, the same or equivalent parts are given the same reference numerals, and their descriptions are simplified or omitted.

[0115] 1. Overview of the implementation method

[0116] 1-1. Character Identification

[0117] Figure 1 This diagram illustrates an outline of person identification performed in a system (hereinafter referred to as the "system") according to an embodiment of this disclosure. The system according to the embodiment includes at least two antennas. Figure 1In this illustration, antennas 11, 12, and 1X are depicted as an example of at least two antennas. Hereinafter, without special distinction, antennas 11, 12, and 1X will be collectively referred to as "antenna 1". Antenna 1 communicates with a terminal (hereinafter also referred to as "user terminal") carried by a user U providing services (e.g., person monitoring service, person tracking service) provided by the system involved in the embodiment.

[0118] exist Figure 1 In this illustration, user terminals 21 and 22 are depicted as examples of user terminals. User terminal 21 is a terminal carried by user U1, and user terminal 22 is a terminal carried by user U2. Hereinafter, without special distinction, user terminals 21 and 22 will be collectively referred to as "user terminal 2". For example, communication is conducted with user terminal 2 via antenna 1 using short-range wireless communication. Here, short-range wireless communication utilizes a communication method with a communication distance of several meters to tens of meters. Examples of specific communication methods include Bluetooth and Zigbee.

[0119] In short-range wireless communication with user terminal 2, antenna 1 acquires information related to user U (hereinafter also referred to as "user information"). Examples of user information include identification information assigned to user U. For instance, during the initial use of the service, identification information is set for each user terminal 2 according to the system described in this implementation. The setting of the identification information for user terminal 2 can also be reset at a certain period (e.g., every day). The user information also includes information about the distance from antenna 1 to user terminal 2 and the orientation of user terminal 2 relative to antenna 1 (i.e., information about the location of user terminal 2).

[0120] User information may also include feature information such as the user U's facial image. For example, the feature information may be set by the user U. The feature information may also be set based on the result of person identification performed by the management server (described later) during the user U's use of the service. In this case, for example, the feature information set based on the result of person identification is added to the user information held by the user terminal 2.

[0121] Antenna 1 also conducts long-distance communication with a base station (not shown) on the network. Here, long-distance communication utilizes communication methods with a communication distance of several kilometers to tens of kilometers. Specific communication methods include various LPWA (Low Power Wide Area) and LTE (Long Term Evolution) protocols. The connection destination of antenna 1 via the base station includes a management server (described later). A relay module such as Wi-Fi (trademarked) may also exist between antenna 1 and the base station. This relay module may also exist between the base station and the management server.

[0122] In long-distance communication with the base station, antenna 1 transmits its identification information. Examples of antenna 1 identification information include the location of antenna 1 and the range of short-range wireless communication using antenna 1 (CR11, CR12, and CR1X; hereinafter, without specifically distinguishing between ranges CR11, CR12, and CR1X, they are collectively referred to as "communication range CR1"). When user information is obtained from user terminal 2, antenna 1 transmits this user information and the time at which it was obtained to the base station.

[0123] The identification information of antenna 1, the user information acquired by antenna 1, and the information of the time when the user information was acquired are examples of information contained in "Antenna Information ANT" (described later).

[0124] The system described in this implementation also includes at least two cameras. Figure 1 In this illustration, cameras 31, 32, and 3Y are depicted as an example of at least two cameras. Camera 31 captures a range SR31 that includes at least a portion of the communication range CR11 utilizing antenna 11. Camera 32 captures a range SR32 that includes at least a portion of the communication range CR12 utilizing antenna 12. Camera 3Y captures a range SR3Y that includes at least a portion of the communication range CR1X utilizing antenna 1X. Hereinafter, without specifically distinguishing between cameras 31, 32, and 3Y, they will be collectively referred to as "camera 3". Furthermore, without specifically distinguishing between ranges SR31, SR32, and SR3Y, they will be collectively referred to as "capture range SR3".

[0125] Camera 3 is installed on an indoor or outdoor structure to observe its surroundings. The camera 3 can be positioned at a fixed point or can move horizontally or vertically. Camera 3 also communicates over long distances with a base station on the network. This long-distance communication utilizes the same method as that used by antenna 1. During long-distance communication with the base station, camera 3 transmits its identification information and the image information it has acquired. The identification information includes, for example, information about the location of camera 3. The image information acquired by camera 3 is typically a moving image, but it can also be a still image. The image information acquired by camera 3 also includes information about the time at which the image was acquired.

[0126] The identification information of camera 3 and the image information acquired by camera 3 are examples of information contained in "Camera Information CAM1" (described later).

[0127] In the system described in the implementation, a "discrimination process" is performed in the management server (described later) to identify people in the image within the shooting range SR3. This discrimination process includes, for example, identifying people in the image within the shooting range SR3. When a person is identified in the image within the shooting range SR3, identification information for that person is generated. Examples of this identification information include information about the location of the identified person. The identification information may also include feature information such as the face image of the identified person. Furthermore, in the discrimination process, based on the identification information of the person in the image within the shooting range SR3, the identification information of antenna 1, and the user information obtained by antenna 1, it is determined whether user U is included in the image within the shooting range SR3.

[0128] 1-2. Characteristics of the discrimination process

[0129] Here, it is considered to increase the number of cameras 3 and antennas 1. From the perspectives of monitoring people within the image range SR3 and preventing crime using image information obtained from cameras 3, it is preferable to increase the number of cameras 3. Furthermore, if the number of antennas 1 is increased, the accuracy of the location information of the user terminal 2 will improve, and it is expected that the accuracy of identifying people within the image range SR3 will increase. On the other hand, there are concerns about increased costs when increasing the number of antennas 1.

[0130] Therefore, in the implementation, we consider the case where the total number of antennas 1 is less than the number of cameras. Here, the shooting range SR3 of the camera 3 includes at least a portion of the communication range CR1 utilizing the antennas 1. Therefore, when the total number of antennas 1 is less than the number of cameras, there exists a camera that can capture a range excluding the communication range CR1.

[0131] Figure 2 This is a diagram illustrating the envisioned state of the implementation method. In Figure 2 In addition to Figure 1 In addition to antenna 1 and camera 3, cameras 41, 42, and 4Z are also depicted. Cameras 41, 42, and 4Z are examples of cameras that respectively capture images of the range SR41, 42, and 4Z excluding the communication range CR1. The basic structure of cameras 41, 42, and 4Z is the same as that of camera 3. Hereinafter, without specifically distinguishing between cameras 41, 42, and 4Z, they will be collectively referred to as "camera 4". Furthermore, without specifically distinguishing between ranges SR41, SR42, and SR4Z, they will be collectively referred to as "capture range SR4".

[0132] In long-distance communication with a base station, camera 4 transmits its identification information and image information acquired by camera 4. Examples of the identification information for camera 4 include information about its location. The image information acquired by camera 4 is typically a moving image, but it can also be a still image. The image information acquired by camera 4 also includes information about the time at which the image was acquired.

[0133] The identification information of camera 4 and the image information acquired by camera 4 are examples of information contained in "Camera Information CAM2" (described later).

[0134] In this embodiment, the identification process includes not only the identification of people in the image within the shooting range SR3, but also the identification of people in the image within the shooting range SR4. For ease of explanation, the process for identifying the former will be referred to as the "first identification process," and the process for identifying the latter will be referred to as the "second identification process." As described above, the first identification process also generates "tracking support information" for user U. This tracking support information is generated when it is determined that user U is included in the image within the shooting range SR3.

[0135] Tracking support information includes, for example, user information of the user U determined to be included in the image within the shooting range SR3 (specifically, the identification information and location information of the user terminal 2), identification information of the camera 3 that acquired the image within the shooting range SR3, and information about the time when the image was acquired. When tracking support information is generated, it is used in the second identification process.

[0136] In the second identification process, a process is performed to identify persons within the image captured by the SR4 camera. If a person is identified within the image captured by the SR4 camera, identification information for that person is generated. This identification information includes information about the location of the identified person. Feature information such as the face of the identified person may also be included in the identification information. Furthermore, in the second identification process, based on the identification information of the person within the image captured by the SR4 camera and tracking support information, it is determined whether user U is included in the image captured by the SR4 camera.

[0137] Thus, according to the system described in the embodiment, the tracking support information generated in the first identification process is used in the second identification process to identify people within the image captured by the SR4. Therefore, even when the total number of antennas 1 is less than the total number of cameras, it is possible to identify users U within the SR4. This contributes to efficient tracking of users U in environments with limited infrastructure resources.

[0138] In the system described in the embodiment, "tracking confirmation information" for user U may also be generated in the second identification process. The generation of "tracking support information" occurs when it is determined that user U is included in the image within the shooting range SR3. Conversely, the generation of "tracking confirmation information" occurs when it is determined that user U is included in the image within the shooting range SR4. The tracking confirmation information includes, for example, user information of user U determined to be included in the image within the shooting range SR4, identification information of the camera 4 that acquired the image within the shooting range SR4, and information about the time when the image was acquired. When tracking confirmation information is generated, it is used in "other second identification processes."

[0139] Other second discrimination processing refers to second discrimination processing that takes an image of the shooting range SR4, which is different from the second discrimination processing that generated tracking confirmation information, as the object, or second discrimination processing that takes an image of the shooting range SR, which is common to the second discrimination processing that generated tracking confirmation information, as the object, and is performed at a different time than the second discrimination processing that generated tracking confirmation information.

[0140] The system involved in the implementation method will be described in more detail below.

[0141] 2. Structural Example of a Person Recognition System

[0142] 2-1. Example of overall structure

[0143] Figure 3 This is a block diagram illustrating an example of the overall structure of the system involved in the implementation method. Figure 3 In the example shown, the system involved in the implementation includes an antenna 1, a camera 3 and 4, a management server 5, and a display 6.

[0144] Antenna 1 is a communication device installed in an indoor or outdoor structure. The total number of antennas 1 is at least two. Antenna 1 conducts short-range wireless communication with user terminal 2. In this short-range wireless communication, a communication distance of several meters to tens of meters is utilized. In the short-range wireless communication, antenna 1 obtains user information (USR) from user terminal 2. The USR includes, for example, identification information of user terminal 2, the distance from antenna 1 to user terminal 2, and the orientation of user terminal 2 relative to antenna 1. The USR may also include feature information such as the user's facial image.

[0145] Antenna 1 also communicates with management server 5 over a long distance via network 7. This long-distance communication utilizes a communication method with a distance ranging from several kilometers to tens of kilometers. During this long-distance communication, antenna 1 sends antenna information ANT to management server 5. This antenna information ANT includes, for example, identification information of antenna 1. When antenna 1 obtains user information USR, it appends the user information USR to the antenna information ANT.

[0146] Cameras 3 and 4 are observation devices installed on structures indoors or outdoors. The total number of cameras 3 is at least two, and the total number of cameras 4 is also at least two. The total number of cameras 3 and 4 combined is greater than the total number of antennas 1. Cameras 3 photograph a range including at least a portion of the communication range CR1 of antenna 1 (i.e., the photographing range SR3). On the other hand, cameras 4 photograph a range excluding the communication range CR1 (i.e., the photographing range SR4).

[0147] Cameras 3 and 4 communicate remotely with management server 5 via network 7. During this communication, camera 3 sends camera information CAM1 to management server 5. Camera information CAM1 includes, for example, identification information of camera 3 and image information acquired by camera 3. Conversely, camera 4 sends camera information CAM2 to management server 5. Camera information CAM2 includes, for example, identification information of camera 4 and image information acquired by camera 4.

[0148] Here, the correspondence between the implementation method and the viewpoint of this disclosure is explained. Camera 3 corresponds to the "first camera" in the viewpoint of this disclosure, and camera 4 corresponds to the "second camera" in the viewpoint of this disclosure. In addition, the shooting range SR3 corresponds to the "first range" in the viewpoint of this disclosure, and the shooting range SR4 corresponds to the "second range" in the viewpoint of this disclosure.

[0149] Management server 5 is a computer that manages the services provided by the system involved in the implementation method. Management server 5 performs information processing based on various information received from antenna 1, camera 3, and camera 4 (antenna information ANT, camera information CAM1, and CAM2). As a structure for performing information processing, management server 5 includes at least one processor 51 and at least one memory 52. ​​Processor 51 includes a CPU (Central Processing Unit). Memory 52 is volatile memory such as DDR memory, used for executing various programs used by processor 51 and temporarily storing various information. Various information received by management server 5 from antenna 1, camera 3, and camera 4 is stored in memory 52.

[0150] The processor 51 executes a person recognition program stored in the memory 52, performing various processes associated with the first and second recognition processes. Additionally, the processor 51 performs display control to output the results of the first and second recognition processes to the display 6.

[0151] Display 6 is a display device that outputs image data DIMG generated by display control. Display 6 is installed in the facilities of the operator providing the services involved in the implementation. Display 6 is a display device for the terminal of the user U, such as for monitoring the user U. In the former case, it is connected to the management server 5 via wired or wireless means. In the latter case, display 6 is connected to the management server 5 via network 7. The total number of displays 6 is not particularly limited; for example, there are at least two in the former case and at least one in the latter case.

[0152] 2-2. Example of the functional structure of a management server

[0153] Figure 4 It is shown Figure 3 The diagram shows an example of the functional structure of management server 5. Figure 4 In the example shown, the management server 5 includes an information acquisition unit 53, a first discrimination unit 54, a first display control unit 55, a second discrimination unit 56, and a second display control unit 57. Furthermore, Figure 3 The functions of each block shown are implemented by the processor 51 executing a predetermined program stored in memory 52. ​​Furthermore, in Figure 4 One of each of the first discrimination unit 54 and the first display control unit 55 is depicted, but these functions can also be set according to the total number of settings for the camera 3. This also applies to the functions of the second discrimination unit 56 and the second display control unit 57.

[0154] 2-2-1. Information Acquisition Department

[0155] The information acquisition unit 53 acquires various types of information from the outside and stores them in the memory 52. ​​This information includes antenna information ANT and camera information CAM1 and CAM2. Furthermore, the information acquisition unit 53 reads the various types of information stored in the memory 52. ​​Then, the information acquisition unit 53 sends the antenna information ANT to the first discrimination unit 54 and the second discrimination unit 56, sends the camera information CAM1 to the first discrimination unit 54 and the first display control unit 55, and sends the camera information CAM2 to the second discrimination unit 56 and the second display control unit 57.

[0156] 2-2-2. First Discrimination Section

[0157] The first discrimination unit 54 performs a first discrimination process. In this first discrimination process, it identifies people contained within the image of camera information CAM1 (i.e., the image within the shooting range SR3). If a person is identified within the image within the shooting range SR3, discrimination information for that person is generated. This discrimination information includes, for example, information about the location of the identified person. The discrimination information may also include feature information such as the face image of the identified person.

[0158] In the first identification process, antenna information ANT of antenna 1 corresponding to camera 3 is also obtained. Antenna 1 corresponding to camera 3 refers to antenna 1 whose communication range DR1 is partially contained within the shooting range SR3. For example, antenna 1 corresponding to camera 3 is determined based on information about the location of camera 3, information about the location of antenna 1, and information about the communication range CR1 of antenna 1. Furthermore, information about the location of camera 3 is obtained from the identification information of camera 3. Information about the location of antenna 1 and the communication range CR1 of antenna 1 are obtained from the identification information of antenna 1.

[0159] If antenna information ANT corresponding to antenna 1 of camera 3 is obtained, the user information contained in this antenna information ANT is compared with the person identification information contained in the image of the shooting range SR3. In this comparison, for example, the user information USR (specifically, the location information of user terminal 2) obtained by antenna 1 is compared with the location information of the identified person. Simultaneously, the time information of when antenna 1 obtained the user information is compared with the time information of when it obtained the image contained in camera information CAM1. Furthermore, if the user information and identification information regarding location and time are consistent, the identified person is identified as user U. Additionally, design errors of antenna 1 and camera 3 can be considered, and margins can be set for location and time.

[0160] If user U is identified in the image within the shooting range SR3, identification information IDN is assigned to the identified person in the first identification process. The identification information IDN is information set by the system according to the embodiment and consists of information different from the identification information of user terminal 2. Furthermore, assigning identification information IDN is not mandatory in this disclosure; other information that can associate the identified person with the identification information of user terminal 2 can also be assigned to the identified person. The identification information IDN is sent to the first display control unit 55.

[0161] If user U is identified in the image within the shooting range SR3, tracking support information TRA is also generated in the first identification process. The tracking support information TRA includes, for example, user information USR (specifically, identification information and location information of user terminal 2) of user U identified in the image within the shooting range SR3, identification information of the camera 3 that acquired the image within the shooting range SR3, and information about the time the image was acquired. The tracking support information TRA is then sent to the second identification unit 56.

[0162] 2-2-3. First Display Control Unit

[0163] The first display control unit 55 performs first display control. In the first display control, image data DIMG is generated based on the image of the shooting range SR3 processed in the first discrimination process executed by the first discrimination unit 54, and output to an external device (e.g., display 6). If discrimination information IDN is assigned to the user U identified in the first discrimination process, the discrimination information IDN is overlaid near the user U in the image encompassed by the shooting range SR3 in the first display control.

[0164] 2-2-4. The second distinguishing part

[0165] The second discrimination unit 56 performs a second discrimination process. In this second discrimination process, it identifies people contained within the image of camera information CAM2 (i.e., the image within the shooting range SR4). If a person is identified within the image of the shooting range SR4, discrimination information for that person is generated. This discrimination information includes, for example, information about the location of the identified person. The discrimination information may also include feature information such as the face image of the identified person.

[0166] Furthermore, in the second identification process, tracking support information (TRA) of the camera 3 corresponding to camera 4 is obtained. An example of a camera 3 located around camera 4 is a camera 3 that corresponds to camera 4. For example, the camera 3 corresponding to camera 4 is determined based on information about the location of camera 4 and the location of camera 3. Additionally, information about the locations of cameras 3 and 4 is obtained from the identification information of cameras 3 and 4.

[0167] If tracking support information TRA for camera 3 corresponding to camera 4 is obtained, the position information of camera 3 contained in the tracking support information TRA is compared with the position information of camera 4. Simultaneously, the time information at which camera 3 captured an image within the shooting range SR3 is compared with the time information at which camera 4 captured an image within the shooting range SR4. Furthermore, design errors of cameras 3 and 4 can be considered, and margins can be set for position and timing.

[0168] Furthermore, for example, if there is a camera 3 that has acquired an image of the SR3 field of view within a predetermined distance from camera 4 and within a predetermined time difference between the moment the image of the SR4 field of view is acquired and the moment the image of the SR3 field of view is acquired, the person identified in the image of the SR4 field of view is identified as user U included in the tracking support information TRA generated based on the image of the SR3 field of view. To improve the accuracy of this identification, a comparison may also be made between the feature information of the person identified in the image of the SR4 field of view and the feature information of the user U included in the tracking support information TRA.

[0169] If user U is identified in the image within the shooting range SR4, identification information IDN is assigned to the identified person in the second identification process. Regarding the identification information IDN, either the identification information IDN received from the first identification unit 54 can be assigned as is, or a unique identification information IDN set specifically for the image within the shooting range SR4 can be assigned. For efficient tracking of user U, the identification information IDN preferably uses information received from the first identification unit 54. The identification information IDN is then sent to the second display control unit 57.

[0170] Furthermore, if user U is identified in the image within the shooting range SR4, a tracking confirmation information (TRC) can be generated in the second identification process. The tracking confirmation information (TRC) may include, for example, user information USR (specifically, the identification information and location information of user terminal 2) of user U identified in the image within the shooting range SR4, identification information of the camera 4 that acquired the image within the shooting range SR4, and information about the time the image was acquired.

[0171] When a tracking confirmation information (TRC) is generated, in the second discrimination process, the position information of the camera 4 (hereinafter referred to as the "comparison object camera") containing the tracking confirmation information TRC is compared with the position information of the camera 4 (hereinafter referred to as the "processing object camera") that obtained the image of the shooting range SR4, which is the object of the second discrimination process. At the same time, the information of the time when the comparison object camera obtained the image of the shooting range SR4 is compared with the information of the time when the processing object camera obtained the image of the shooting range SR4.

[0172] Furthermore, for example, if there is a comparison camera that is within a predetermined distance from the processing target camera and whose time difference between the times when the images of the shooting range SR4 are acquired is within a predetermined time, it can be determined that the person identified in the image of the shooting range SR4 acquired by the processing target camera is the user U included in the tracking confirmation information TRC generated based on the information from the comparison target camera. To improve the accuracy of this identification, a comparison can also be made between the feature information of the person identified in the image of the shooting range SR4 and the feature information of the user U included in the tracking confirmation information TRC.

[0173] 2-2-5. Second Display Control Unit

[0174] The second display control unit 57 performs second display control. In this second display control, image data DIMG is generated based on the image of the shooting range SR4 processed in the second discrimination process performed by the second discrimination unit 56, and output to an external device (e.g., display 6). If discrimination information IDN is assigned to the user U identified in the second discrimination process, the discrimination information IDN is overlaid near the user U in the image encompassed by the shooting range SR4 in the second display control.

[0175] 2-2-6. Other examples of the second discriminative part

[0176] Here, the second discrimination unit 56 may also reduce the tracking support information TRA or tracking confirmation information TRC used in the second discrimination process. Hereinafter, an example of reduction will be described using tracking support information TRA as an example.

[0177] Figure 5 This is a diagram illustrating a reduced example of the tracking support information TRA used in the second discrimination process. In this reduced example, focusing on camera 41, it is assumed that an image of the shooting range SR41 was acquired at time t1. In this reduced example, a time (t4-Tp) is set to be traced back from time t1 to a predetermined time Tp. Furthermore, a circle CA1 of predetermined time Tp×V (where V is the average pedestrian movement speed) is set with the location of camera 41 as the center. Thus, camera 3 located inside this circle CA1 (in...) is determined. Figure 5 In the example shown, cameras 31-35).

[0178] exist Figure 5 In the example shown, tracking support information TRA is extracted based on the image generated from the shooting range SR3 of camera 3 located inside circle CA1. Figure 5 In the example shown, the tracking support information TRA also extracts only the information generated from the images of the shooting range SR3 obtained from time (t1-Tp) to time t1.

[0179] 2-2-7. Other examples of the first and second discriminative parts

[0180] As explained above, there are a total of two cameras 3. Therefore, consider the scenario where the same user U is identified among the images captured by the two cameras 3 within the shooting range SR3. In this case, the user's direction of movement (direction of movement path) can be predicted based on information about the positions of the two cameras 3 and information about the times at which the two types of images of the shooting range SR3 were captured by these cameras 3. This prediction of the direction of movement is then calculated separately by the processor 51.

[0181] In this example, we consider the case where the direction of movement is calculated. When the first discrimination unit 54 identifies user U in the image within the shooting range SR3, it obtains information about the direction of movement of user U. Furthermore, based on this direction of movement information, the first discrimination unit 54 determines which camera 4 is located in front of the camera in that direction of movement from the perspective of the camera 3 that has acquired the image within the shooting range SR3. Moreover, the first discrimination unit 54 adds the identification information of camera 4 (e.g., information about the location of camera 4) to the tracking support information TRA.

[0182] Figure 6 This diagram illustrates an example of a method for determining the identity information of camera 4, which is supplemented with tracking support information (TRA). Figure 6 In the example shown, we focus on cameras 34 and 38. Figure 6 In the example shown, it is also assumed that an image of the shooting range SR38 was obtained at time t2 and an image of the shooting range SR34 was obtained at time t3, which is after time t2.

[0183] If user U is identified as a result of the first discrimination process based on the image of the shooting range SR34 acquired at time t3, the first discrimination unit 54 determines whether the movement direction Du of user U has been calculated. Furthermore, if the movement direction Du has been calculated, the first discrimination unit 54 determines that a camera 4 exists in front of that movement direction Du (in...). Figure 6 In the example shown, cameras 41 and 45 are used. When determining camera 4, reduction can be performed based on either the general pedestrian movement speed V or the user U's movement speed Vu. For example, the movement speed Vu can be calculated based on the position information of cameras 34 and 38 and the time difference between times t2 and t3.

[0184] As explained above, the tracking support information TRA includes user information USR of user U identified in the image captured in the shooting range SR3. Therefore, by adding the identification information of the camera 4, which is located in front of the moving direction Du, to the tracking support information TRA, user U can be easily identified in the second identification process based on the image captured in the shooting range SR4 obtained by the camera 4.

[0185] When the second discrimination unit 56 obtains the tracking support information TRA of the camera 3 corresponding to the camera 4, it determines whether the tracking support information TRA includes identification information of the target camera. Furthermore, if it determines that the identification information of the target camera is included in the tracking support information TRA, it reduces the number of people identified in the image within the shooting range SR4 based on that identification information.

[0186] 2-3. Example of processing performed by the management server

[0187] Figure 7 This is a flowchart illustrating an example of the flow of the first discrimination process executed by the management server 5 (processor 51). For example, it is repeated at predetermined intervals for each camera 3. Figure 7 The processing routine shown.

[0188] exist Figure 7 In the illustrated routine, firstly, information is acquired (step S11). In the processing of step S11, for example, antenna information ANT and camera information CAM1 are acquired. As explained above, the antenna information ANT includes, for example, identification information of antenna 1 (location information and communication range CR1 information), user information USR (identification information of user terminal 2) acquired by antenna 1, and information about the time when the user information USR was acquired. The camera information CAM1 includes, for example, identification information (location information) of camera 3 and image information acquired by camera 3 (image of shooting range SR3 and the time when the image information was acquired).

[0189] Following step S11, the person within the image captured by the SR3 camera is identified (step S12). In step S12, the position of the person within the image captured by the SR3 camera is identified using known image processing techniques. Once the position of the person within the image captured by the SR3 camera is identified, identification information for that person is generated. In step S12, in addition to identifying the position of the person within the image captured by the SR3 camera, the person's features may also be identified. In this case, feature information is added to the identification information.

[0190] Following step S12, it is determined whether a person within the image range SR3 has been identified (step S13). For example, the determination for step S13 is based on whether person identification information was generated in step S12. If the determination result in step S13 is negative, the first identification process ends. Otherwise, the process proceeds to step S14.

[0191] In step S14, it is determined whether the user information (USR) is included in the antenna information ANT of the antenna 1 corresponding to the camera 3. As explained above, the antenna 1 corresponding to the camera 3 refers to the antenna 1 whose communication range DR1 is partly included in the shooting range SR3. If the determination result in step S14 is negative, the first identification process ends. Otherwise, the process proceeds to step S15.

[0192] In step S15, the identification information and user information USR generated in step S12 are compared. Specifically, the location of the person included in the identification information is compared with the location of user U included in the user information USR. Simultaneously, the time when the image of the shooting range SR3, which is the object of step S12, was obtained is compared with the time when the user information USR was obtained. Furthermore, if the location and time identification information and user information USR are consistent, the person included in the identification information is identified as user U. Additionally, design errors of antenna 1 and camera 3 can be considered, and margins can be set for the location and time.

[0193] In step S15, if there is no user information USR that matches the identification information, no identification of the person included in the identification information is performed, and the first identification process ends. Alternatively, in this case, information that the person included in the identification information does not represent the user U's intent may be assigned to that person.

[0194] If a person is identified in step S15, identification information IDN is assigned to that person (step S16). As explained above, the identification information IDN is arbitrary information set by the system according to the embodiment, and is composed of information different from the identification information of user terminal 2. Furthermore, in step S16, user information USR and identification information IDN are associated and recorded in a predetermined memory. An example of a predetermined memory is a higher-level memory than memory 52, such as a cache memory.

[0195] Following step S16, tracking support information TRA is generated (step S17). As explained above, the tracking support information TRA includes, for example, user information USR (specifically, the identification information and location information of user terminal 2) of user U identified in the image within the shooting range SR3, identification information of camera 3 that acquired the image within the shooting range SR3, and information about the time when the image was acquired. Furthermore, in step S17, the generated tracking support information TRA is recorded into a predetermined memory.

[0196] In the processing of step S17, it is also possible to determine the appropriate method based on the given information. Figure 6 The information on the direction of movement Du described herein determines the presence of camera 4 in front of that direction of movement Du. Furthermore, once camera 4 is identified, its identification information can be added to the tracking support information TRA.

[0197] Figure 8 This is a flowchart illustrating an example of the second discrimination process executed by the management server 5 (processor 51). For example, it is repeated at predetermined intervals for each camera 4. Figure 8 The processing routine shown.

[0198] exist Figure 8 In the example shown, steps S21 to S23 are performed first. The content of step S21 is related to... Figure 7 The process is the same as step S11, and the content of step S22 is the same. Figure 7 Step S12 is the same, and the content of step S23 is the same. Figure 7 The process is the same as step S13. If the determination result in step S23 is negative, the second discrimination process ends. Otherwise, proceed to step S24.

[0199] In step S24, it is determined whether tracking support information (TRA) for the camera 3 corresponding to camera 4 exists. As explained above, a camera 3 located around camera 4 is an example of a camera 3 corresponding to camera 4. If the determination result in step S24 is negative, the second identification process ends. Otherwise, the process proceeds to step S25.

[0200] Alternatively, in step S24, before determining whether tracking support information (TRA) exists, this process can be performed. Figure 5The reduction of the tracking support information TRA as described in the text. In this case, for example, the reduction is performed based on information about the position of the camera 4, information about the time when the image of the shooting range SR4 of the object to be processed in step S22 was obtained, information about the position of the camera 3 corresponding to the camera 4, and information generated from the image of the shooting range SR3 obtained by the camera 3 in the tracking support information TRA.

[0201] In step S25, the tracking support information TRA and the identification information of camera 4 are compared, along with the information of the time when the image of the shooting range SR4, which is set as the object of step S22, was obtained. Specifically, the positions of camera 3 and camera 4 are compared, indicating that the image of the shooting range SR3 contained in the tracking support information TRA was obtained. Simultaneously, the time when the image of the shooting range SR3 was obtained is compared with the time when the image of the shooting range SR4 was obtained.

[0202] Furthermore, for example, if there is a camera 3 that has acquired an image of the shooting range SR3 within a predetermined distance from camera 4 and within a predetermined time difference between the moment the image of the shooting range SR4 is acquired and the moment the image of the shooting range SR3 is acquired, it is determined that the person identified in the process of step S22 is a user U included in the tracking support information TRA.

[0203] In steps S24 and S25, the tracking confirmation information TRC can be used instead of the tracking support information TRA to identify the person in the image within the shooting range SR4. In this case, "camera 3" can be replaced with "comparison object camera" and "camera 4" can be replaced with "processing object camera" in the description of steps S24 and S25 above.

[0204] In the process of step S25, the method included in... Figure 6 The tracking support information TRA described in the text refers to the identification information of camera 4, which narrows down the identification of people in the image of the object to be captured in step S22, SR4.

[0205] If person identification was performed in step S25, then identification information IDN is assigned to that person (step S26). The content of step S26 is the same as... Figure 7 The process in step S16 is the same.

[0206] Following step S26, tracking confirmation information TRC is generated (step S27). As explained above, the tracking support information TRC includes, for example, user information of user U who is determined to be included in the image within the shooting range SR4, identification information of camera 4 that acquired the image within the shooting range SR4, and information about the time when the image was acquired. Furthermore, in step S27, the generated tracking confirmation information TRC is recorded in a predetermined memory.

[0207] 3. Effects

[0208] According to the implementation described above, when user U is identified in the process of identifying people in the image within the shooting range SR3 (first identification process), tracking support information TRA is generated. Furthermore, this tracking support information TRA is used in the process of identifying people in the image within the shooting range SR4 (second identification process). Therefore, even when the total number of antennas 1 is less than the total number of cameras, user U within the shooting range SR4 can still be identified. This contributes to efficient tracking of user U in environments with limited infrastructure resources.

[0209] Furthermore, according to the embodiment, if user U is identified in the process of identifying a person included in the image within the shooting range SR4 (the second identification process), a tracking confirmation information TRC can be generated, or the tracking confirmation information TRC can be used in other second identification processes. In this case, if user U is identified in the first identification process, user U can be continuously tracked by repeatedly performing the second identification process and other second identification processes. This contributes to improved service convenience.

[0210] Additionally, according to the implementation method, it is also possible to perform in Figure 5 The reduction of the tracking support information TRA described in the text, in Figure 6 The identification information of camera 4 described in the diagram is added to the tracking support information TRA. In this case, the processing load on the computer performing the second identification process can be reduced. This contributes to more efficient tracking for user U.

Claims

1. A method for identifying people in a camera image, characterized in that, include: The steps include obtaining user information assigned to a user terminal through short-range wireless communication using an antenna, and sending the user information to the outside through long-range communication using the same antenna. The step of using the first camera to acquire an image of a first range that includes at least a portion of the range of short-range wireless communication utilizing the antenna; The step of using a second camera to acquire an image of a second range that does not include the range of the near-field wireless communication; The step of identifying the person in the image contained within the first range; as well as The step of identifying the people in the image contained within the second range. The steps for identifying persons within the first range of images include: The step of generating identification information of persons contained in the image within the first range; The step of determining whether a user associated with the user terminal is included in the first range of images based on the identification information of persons in the images contained in the first range, the identification information of the antenna, and the user information obtained by the antenna; and The step of generating tracking support information for a user who is determined to be associated with the user terminal and whose image is included in the first range. The steps for identifying persons within the second range of images include: The step of generating identification information of persons within the image of the second range; and The step of determining whether a user who is the same as the user determined to be included in the first range of images is included in the second range of images, without using the user information obtained by the antenna, based on the identification information of the person included in the image of the second range and the tracking support information. The tracking support information includes user information of the user identified as being included in the first range of images, information about the location of the first camera that obtained the first range of images, and information about the time when the first camera obtained the first range of images.

2. The person identification method according to claim 1, characterized in that, The step of identifying persons within the second range of images further includes: The step of reducing the tracking support information based on the information included in the tracking support information regarding the time when the image of the first range was acquired, the information included in the tracking support information regarding the position of the first camera when the image of the first range was acquired, the information included in the tracking support information regarding the time when the image of the second range was acquired, and the information included in the tracking support information regarding the position of the second camera. The steps to reduce the tracking support information include: The step of extracting tracking support information generated from images of the first range obtained by a first camera located within a predetermined distance from the position of the second camera during a predetermined time period tracing back from the moment the image of the second range was obtained.

3. The person identification method according to claim 1 or 2, characterized in that, The second camera includes at least two cameras. The step of identifying persons within the second range of images further includes: In the case where it is determined that a user, who is also identified as a user included in the first range of images, is included in the second range of images, the step of generating tracking confirmation information for that user is as follows: user information of the user identified as being included in the second range of images, information on the location of the second camera that captured the second range of images, and information on the time when the second camera captured the second range of images; and The step of reducing the tracking confirmation information is based on the information including the time when the image of the second range was obtained, the information including the location of the second camera in the tracking confirmation information, the information including the time when the image of the second range as the object of person identification was obtained, and the information including the location of the second camera that obtained the image of the second range as the object of person identification. The steps to reduce the tracking support information include: The step of extracting tracking confirmation information is generated based on images of the second range acquired by another second camera located within a predetermined distance from the position of the second camera that acquired the image of the second range as the object of person identification during a predetermined time period tracing back from the moment the image of the second range as the object of person identification was acquired.

4. The person identification method according to claim 1 or 2, characterized in that, The first camera includes at least two cameras. The method for identifying individuals also includes: If it is determined that the same user is included in at least two images within the first range captured by the at least two first cameras, the step of calculating the user's direction of movement is performed based on information about the positions of the first cameras that captured the at least two images and information about the times at which the at least two images were captured. The step of identifying persons within the first range of images further includes: If a user associated with the user terminal is found to be included in the image within the first range, the step of determining whether to calculate information about the user's direction of movement; and If it is determined that the information of the movement direction has been calculated, then, based on that movement direction information, the step of adding the identification information of the second camera, which is located in front of the movement direction from the perspective of the first camera that has acquired the image of the first range, to the tracking support information is as follows: The step of identifying persons within the second range of images further includes: The step of determining whether the identification information of the second camera located ahead in the direction of movement is included in the tracking support information; and If the identification information of the second camera, which is determined to be located in front of the direction of movement, is included in the tracking support information, the step of reducing the number of people in the image included in the second range is based on the identification information of the second camera.

5. A person recognition system for recognizing people contained in a camera image, characterized in that, The person identification system has the following features: The antenna acquires user information assigned to the user terminal through short-range wireless communication and transmits the user information to the outside through long-range communication. The first camera captures a first range that includes at least a portion of the range of short-range wireless communication utilizing the antenna; A second camera, capturing images of a second range excluding the range of the short-range wireless communication; and The management server performs a first identification process to identify people in images within the first range and a second identification process to identify people in images within the second range. In the first identification process, the management server... Generate identification information for the person contained in the image within the first range. Based on the identification information of the person in the image within the first range, the identification information of the antenna, and the user information obtained by the antenna, it is determined whether the user associated with the user terminal is included in the image within the first range. If the image is determined to be within the first range and is associated with the user terminal, tracking support information for that user is generated. In the second identification process, the management server... Generate identification information for the person contained in the image within the second range. Without using the user information obtained by the antenna, based on the identification information of people included in the image within the second range and the tracking support information, it is determined whether a user who is the same as the user determined to be included in the image within the first range is included in the image within the second range. The tracking support information includes user information of the user identified as being included in the first range of images, information about the location of the first camera that obtained the first range of images, and information about the time when the first camera obtained the first range of images.

6. The person identification system according to claim 5, characterized in that, The management server also performs the following in the second identification process: The processing of the tracking support information is reduced based on the information included in the tracking support information regarding the time when the image of the first range was acquired, the information included in the tracking support information regarding the position of the first camera when the image of the first range was acquired, the information included in the tracking support information regarding the time when the image of the second range was acquired, and the information included in the tracking support information regarding the position of the second camera. The management server reduces the processing of the tracking support information. Extract tracking support information generated from images of the first range obtained by a first camera located within a predetermined distance from the position of the second camera during a predetermined time period tracing back from the moment the image of the second range was obtained.

7. The person recognition system according to claim 5 or 6, characterized in that, The second camera includes at least two cameras. In the second identification process, the management server, further, If a user is determined to be the same user as the user determined to be included in the first range of images, and is also included in the second range of images, then tracking confirmation information for that user is generated. The tracking confirmation information includes: user information of the user identified as being included in the image within the second range, information on the location of the second camera that captured the image within the second range, and information on the time when the image within the second range was captured by the second camera. In the second identification process, the management server further performs the following: Based on the information included in the tracking confirmation information regarding the time when the image of the second range was acquired, the information included in the tracking confirmation information regarding the location of the second camera, the information regarding the time when the image of the second range, which is the object of the second discrimination process, was acquired, and the information regarding the location of the second camera, which is the object of the second discrimination process, the processing of the tracking confirmation information is reduced. The management server reduces the processing of the tracking confirmation information. Extract tracking confirmation information, which is generated based on images of the second range obtained by another second camera located within a predetermined distance from the position of the second camera that obtained the image of the second range as the object of the second identification process during a predetermined time period tracing back from the moment when the image of the second range as the object of the second identification process was obtained.

8. The person recognition system according to claim 5 or 6, characterized in that, The first camera includes at least two cameras. The management server then, If it is determined that the same user is included in at least two images within the first range captured by the at least two first cameras, the user's direction of movement is calculated based on information about the positions of the first cameras that captured the at least two images and information about the times at which the at least two images were captured. In the first identification process, the management server, further, If a user associated with the user terminal is found to be included in the image within the first range, it is determined whether information about the user's direction of movement has been calculated. If it is determined that the information of the movement direction has been calculated, then based on that movement direction information, the identification information of the second camera, which is located in front of the movement direction from the perspective of the first camera that acquired the image of the first range, is added to the tracking support information. In the second identification process, the management server, further, Determine whether the identification information of the second camera located ahead in the direction of movement is included in the tracking support information. If the identification information of the second camera, which is determined to be located in front of the direction of movement, is included in the tracking support information, the number of people in the image included in the second range is reduced based on the identification information of the second camera.

9. A person recognition program that enables a computer to perform the recognition of persons contained in a camera image, characterized in that, The person identification program is executed by the computer: User information assigned to a user terminal is obtained through short-range wireless communication using an antenna, and this user information is then transmitted to an external processing facility through long-range communication using the same antenna. Processing of acquiring an image of a first range, including at least a portion of the range of short-range wireless communication utilizing the antenna, using the first camera; Processing of acquiring images of a second range that does not include the range of the near-field wireless communication using a second camera; Processing to identify people in images contained within the first range; as well as The process of identifying people in the image contained within the second range. The process of identifying persons within the first range of images includes: Processing to generate identification information of people in the image contained in the first range; The process of determining whether a user associated with the user terminal is included in the first range of images based on the identification information of persons in the images contained in the first range, the identification information of the antenna, and the user information obtained by the antenna; and If an image is determined to be associated with the user terminal and is included in the first range, the process of generating tracking support information for that user is performed. The process of identifying persons within the second range of images includes: Processing to generate identification information of persons within the image of the second range; and The process of determining whether a user who is the same as the user determined to be included in the image of the first range is included in the image of the second range, without using the user information obtained by the antenna, based on the identification information of the person included in the image of the second range and the tracking support information. The tracking support information includes user information of the user identified as being included in the first range of images, information about the location of the first camera that obtained the first range of images, and information about the time when the first camera obtained the first range of images.

Images