JP2019200583A - Information processing device, information processing method, and program - Google Patents

Abstract

To provide an information processing device, an information processing method, and a program, capable of appropriately counting objects to be counted even though when a shielding area which shields objects within a prescribed area including the objects to be counted exists.SOLUTION: An information processing device 200 obtains an image of a matrix area including a plurality of objects to be counted, as an image of a prescribed area including objects to be counted which are photographed by a photographing device 100. Then, from the obtained image of the matrix area, it detects and counts the objects to be counted by applying object detection processing. Moreover, it applies passing detection processing for counting the objects to be counted which are shown in a shielding area shielding the objects in the matrix area. Then, it adds a count result of human bodies in the shielding area to which the passing detection processing is applied, to a count result of human bodies in the matric area to which the object detection processing is applied, and therefrom counts and outputs the objects to be counted which are shown in the matrix area.SELECTED DRAWING: Figure 1

Description

  The present invention relates to an information processing apparatus, an information processing method, and a program.

2. Description of the Related Art In recent years, a technique for analyzing an image captured by an image capturing apparatus and counting objects has attracted attention. By using such a technique, it is possible to collect statistical data obtained by counting human bodies and objects in an image.
Japanese Patent Application Laid-Open No. 2004-133826 describes an imaging device that captures an object that enters and exits a predetermined region at an entrance of the predetermined region and an imaging device that captures the entire predetermined region in order to detect the number of objects existing in the predetermined region. A monitoring system is disclosed.

Japanese Patent No. 3915721

However, the technique described in Patent Document 1 requires a plurality of imaging devices for imaging each entrance / exit of the predetermined area and the entire predetermined area. In addition, the case where there is a shielding object such as a wall or a pillar that shields the object to be counted in the predetermined area is not considered, and when there is a shielding object, the object cannot be counted correctly. Therefore, it is necessary to set a predetermined area so that there is no shielding object.
Therefore, the present invention has an object to appropriately count objects to be counted even when there is a shielding area that shields objects within a predetermined area to be counted.

  In order to solve the above-described problem, an aspect of the information processing apparatus according to the present invention is acquired by an acquisition unit that acquires an image of a predetermined region that is an object counting target, and is acquired by the acquisition unit. Based on the detection results of the detection means, the first counting means for counting the objects detected by the detection means, and the detection results by the detection means, A second counting means for counting the objects shielded in the region; a number of the objects counted by the first counting means; and a number of the objects counted by the second counting means. And a third counting means for outputting a result counted in the predetermined area.

  According to the present invention, it is possible to appropriately count objects to be counted even when there is a shielding area that shields objects within a predetermined area to be counted.

It is a figure which shows the structural example of the imaging system in this embodiment. It is a flowchart which shows the counting process procedure in information processing apparatus. It is an example of the matrix area | region and shielding area | region imaged with an imaging device. It is an example of the matrix area | region and shielding area | region imaged with an imaging device. It is an example of the matrix area | region and shielding area | region imaged with an imaging device. It is a flowchart which shows another example of the count process procedure in information processing apparatus.

DESCRIPTION OF EMBODIMENTS Hereinafter, embodiments for carrying out the present invention will be described in detail with reference to the accompanying drawings.
The embodiment described below is an example as means for realizing the present invention, and should be appropriately modified or changed depending on the configuration and various conditions of the apparatus to which the present invention is applied. It is not limited to the embodiment.

(First embodiment)
FIG. 1 is a configuration example of an imaging system 1000 in the present embodiment.
The imaging system 1000 in this embodiment is a system that counts objects present in a predetermined area in an image captured by an imaging device. Specifically, the imaging system 1000 sets a matrix area including a plurality of objects (in this embodiment, a human body) from an image captured by the imaging apparatus, and sets the set matrix area as an object counting target. The objects included in the matrix area are counted. In addition, when there is a shielding area that shields the counting target object in the matrix area, the imaging system 1000 sets the shielding area in the matrix area, counts the objects shielded in the shielding area, Count as an existing object. Here, the shielding area is an area where a shielding object that shields an object is captured in the image of the matrix area.
In the present embodiment, the object to be counted is described as a human body, and the shielding object is described as a pillar or a wall, but is not limited to the above. The object to be counted may be a part of a human body (for example, a face), a car, an animal, or the like. The shielding object may be an object other than the object to be counted.

As illustrated in FIG. 1, the imaging system 1000 includes an imaging device 100 and an information processing device 200. The imaging device 100 and the information processing device 200 are connected to each other via a network 300 so that they can communicate with each other.
The imaging device 100 is a camera that captures an image. The imaging device 100 can be, for example, a monitoring camera used for monitoring. The image capturing apparatus 100 transmits an image captured via the network 300 to the information processing apparatus 200.
In addition, the imaging device 100 may be installed on a wall surface, a ceiling, or the like, and may be a camera that captures an image including one or more images. Further, the imaging apparatus 100 may be compatible with PoE (Power Over Ethernet (registered trademark)), or may be configured to be supplied with power via a LAN cable or the like.

Next, the configuration of the imaging device 100 will be described. The imaging apparatus 100 includes an imaging unit 101, a communication unit 102, a CPU 103, and a storage unit 104.
The imaging unit 101 includes a lens group and an imaging element that constitute an imaging optical system. The lens group includes an optical lens for imaging incident light, and focuses the incident light on the image sensor. The imaging element is an element that converts light into an analog image signal, and can include, for example, a CCD, a CMOS (Complementary Metal Oxide Semiconductor), or the like. The imaging unit 101 performs image processing on an analog image signal obtained from the imaging element, encodes the signal, and outputs an encoded image signal.

The communication unit 102 provides a wireless or wired communication interface with an external device including the information processing apparatus 200. That is, the communication unit 102 can communicate with an external device such as the information processing apparatus 200 by wireless communication. This wireless communication includes a wireless PAN (Personal Area Network) such as Bluetooth (registered trademark), Z-Wave (registered trademark), ZigBee (registered trademark), UWB (Ultra Wide Band), or the like. Further, a wireless LAN (Local Area Network) such as Wi-Fi (Wireless Fidelity) (registered trademark) and a wireless MAN (Metropolitan Area Network) such as WiMAX (registered trademark) are included. Further, it includes a wireless WAN (Wide Area Network) such as LTE / 3G.
The communication unit 102 may communicate with an external device such as the information processing apparatus 200 via a wired LAN. Examples of the wired LAN include a plurality of routers, switches, cables, and the like that satisfy a communication standard such as Ethernet (registered trademark). The communication unit 102 only needs to be able to communicate with an external device, and the communication standard, scale, and configuration are not limited to the above.

The CPU 103 is an arithmetic processing unit that performs processing such as calculation and logic determination in each unit of the imaging apparatus 100, and controls each component (101, 102, and 104) via the system bus. The functions and processing of the imaging apparatus 100 may be realized by the CPU 103 reading a program stored in the storage unit 104 and executing this program.
The storage unit 104 includes an electrically erasable nonvolatile memory such as an EEPROM (Electrically Erasable Programmable Read Only Memory). The storage unit 104 may include a main memory of the CPU 103, a RAM that functions as a work memory, an external memory, a removable storage medium, and the like. Various information used by the CPU 103 is recorded in the storage unit 104. For example, the image captured by the imaging unit 101 may be stored in the storage unit 104.

Next, the configuration of the information processing apparatus 200 will be described.
The information processing apparatus 200 may be, for example, a PC (Personal Computer) or a portable terminal such as a tablet terminal or a smartphone.
The information processing apparatus 200 includes a communication unit 201, a CPU 202, a storage unit 203, a display unit 204, and an input unit 205. In addition, the information processing apparatus 200 includes a matrix area setting unit 206, a shielding area setting unit 207, a matrix area counting unit 208, and a shielding area counting unit 209.

The communication unit 201 provides a wireless or wired communication interface with an external device including the imaging device 100, similarly to the communication unit 102 of the imaging device 100 described above. The communication unit 201 receives an image from the imaging device 100 via the network 300 and communicates various information with the imaging device 100.
Similar to the CPU 103 of the imaging apparatus 100 described above, the CPU 202 is an arithmetic processing unit that performs processing such as calculation and logic determination in each unit of the information processing apparatus 200, and each component (201, 203 to 209) via the system bus. ) To control.
The storage unit 203 is configured by an electrically erasable nonvolatile memory such as an EEPROM, like the storage unit 104 of the imaging device 100 described above. The storage unit 203 may include a main memory of the CPU 202, a RAM that functions as a work memory, an external memory, a removable storage medium, and the like.

The display unit 204 can display an image received from the imaging device 100. For example, the display unit 204 can display an image of the matrix area. In the present embodiment, a configuration in which the information processing apparatus 200 includes the display unit 204 will be described, but the configuration is not limited to the above configuration. For example, the information processing apparatus 200 may not include the display unit 204 and may perform display control for displaying an image on an external display apparatus (client apparatus).
The input unit 205 receives an instruction input from a user via various user interfaces (UI) such as a mouse input, a keyboard input, and a touch input. For example, when an instruction to change the setting of the imaging device 100 is input to the input unit 205, the CPU 202 generates a control command for changing the setting of the imaging device 100 based on the input information, and the communication unit 201. The control command generated is output to the imaging apparatus 100 via the. Thus, based on the information input to the input unit 205, the information processing apparatus 200 can appropriately change the settings of the imaging apparatus 100.

The matrix area setting unit 206 sets a matrix area from the image captured by the imaging device 100. The matrix area setting unit 206 can set the matrix area based on information on the matrix area specified by the user. In this case, the user designates a matrix area in the image by operating various UIs such as a mouse while confirming the image of the imaging apparatus 100 displayed on the display unit 204. Then, the matrix area setting unit 206 sets a matrix area based on the above-mentioned user designation received by the input unit 205.
The matrix area setting unit 206 analyzes the image captured by the imaging apparatus 100 and sets the matrix area by detecting the moving speed of the human body and the high density area of the human body in the image. Also good. At that time, an arbitrary algorithm can be used for setting the matrix region.

  The shielding area setting unit 207 sets a shielding area from the image captured by the imaging device 100. The shielding area is an area where the human body cannot accurately count due to a shielding object such as a wall or a pillar in the matrix area. The shielding area setting unit 207 can set the shielding area based on the information regarding the shielding area designated by the user. In this case, the shielding region setting method is the same as the matrix region setting method described above. The matrix area setting unit 206 analyzes the image captured by the imaging device 100 and sets a shielding area by detecting a tracking result of a human body existing in the matrix area and a highly dense human body area. May be. At that time, an arbitrary algorithm can be used for setting the shielding area.

The matrix area counting unit 208 acquires an image of the matrix area set by the matrix area setting unit 206 from the image captured by the imaging device 100. Then, the matrix area counting unit 208 detects a human body from the acquired matrix area image by object detection processing (human body detection processing), and counts the detected human bodies. For example, as human body detection processing, there is a method of detecting a human body by a classifier that performs local feature extraction using a sample image of the human body and learns by a statistical learning method. An arbitrary algorithm can be used for detecting and counting human bodies.
In addition, when the matrix in which the human bodies to be counted are located at a position shielded by the shielding object in the shielding area, the matrix area counting unit 208 determines that the human bodies that can be detected in the shielding area are not human bodies that are lined up in the matrix. You may make it exclude from a count object. That is, the matrix area counting unit 208 may detect and count human bodies that exist outside the shielding area in the matrix area.

The shielding area counting unit 209 counts human bodies existing in the shielding area. In the present embodiment, the shielding area counting unit 209 includes an object tracking unit 209a and an object passage detection unit 209b, and uses the object tracking unit 209a and the object passage detection unit 209b to count human bodies that enter and exit the shielding region. Thus, the human body existing in the shielding area is counted.
The object tracking unit 209a tracks the same human body that exists between different frames, and acquires trajectory information on the movement of the tracked human body. Here, as a method of tracking the same human body in different frames, there is a method of using the similarity of histograms of colors included in the tracked human body. An arbitrary algorithm can be used for tracking the human body.

  The object passage detection unit 209b uses the trajectory information acquired by the object tracking unit 209a to determine whether a human body has entered the shielding area set by the shielding area setting unit 207, and to determine whether the human body has come out of the shielding area. judge. Specifically, the object passage detection unit 209b sets passage detection lines for determining whether or not a human body has passed, at two locations of the entrance and exit of the shielding area, and the passage detection lines set at the entrance. And the trajectory information overlap, it is determined that the human body has entered the shielding area. In addition, the object passage detection unit 209b determines that the human body has exited the shielding area when the passage detection line set at the exit and the trajectory information overlap. The entrance / exit of the shielding area can be determined based on the traveling direction of the matrix. Here, the traveling direction of the matrix is the movement direction of the human body included in the matrix.

  The object passage detection unit 209b acquires the moving direction of the human body from the trajectory information overlapped with the passage detection line, and the human body that passes through the passage detection line in the direction opposite to the traveling direction of the matrix enters and leaves the shielding area. It may be excluded from the counting target so as not to count as a human body. In this way, when the direction of travel of the matrix and the direction of movement of the human body do not match, by excluding the human body from the counting object, the human body moving in the direction unrelated to the matrix is not counted. Can do. In this case, the matrix area counting unit 208 may also exclude the human body from being counted when the detected moving direction of the human body does not match the traveling direction of the matrix.

Further, when the tracked human body passes through the passage detection line at the entrance of the shielded area in the direction of entering the shielded area, if the detected human body can be detected in the shielded area, the human body is in front of the shield (on the imaging device 100 side). It can be determined that it is a moving human body and not a human body in a queue. Therefore, in such a case, the object passage detection unit 209b may not count the human body as a human body in the shielding area.
Furthermore, the object passage detection unit 209b is not a human body lined up in a matrix for a human body that moves at a speed faster than the progression speed of the matrix, even if the human body passes through the passage detection line in the same direction as the progression direction of the matrix. Therefore, it may be excluded from the counting target. Here, the traveling speed of the matrix is the moving speed of the human body included in the matrix, and can be an average value of the moving speed, for example.

  As described above, the information processing apparatus 200 according to the present embodiment acquires an image of a matrix area that includes a plurality of objects to be counted as an image of a predetermined area that is to be counted by the imaging apparatus 100. . Then, the information processing apparatus 200 detects the object to be counted from the acquired image of the matrix area by the object detection process and counts it. In addition, the information processing apparatus 200 counts objects to be counted that exist in the shielding area where the objects are shielded in the matrix area by using the passage detection process. Then, the information processing apparatus 200 adds the human body counting result in the shielding area using the passage detection process to the human body counting result in the matrix area using the object detection process, and the counting target object existing in the matrix area Is counted and output. For this reason, even if the object is shielded by the shielding object, the number of objects in the matrix region including the number of objects shielded in the shielding region can be appropriately counted.

Next, the operation of the information processing apparatus 200 in this embodiment will be described.
FIG. 2 is a flowchart showing a process of counting human bodies in the matrix area as an example of the counting process executed by the information processing apparatus 200. The processing in FIG. 2 is started, for example, at the timing when the image capturing apparatus 100 starts capturing an image. However, the start timing of the process of FIG. 2 is not limited to the above timing.
The information processing apparatus 200 can realize the processing shown in FIG. 2 by reading out a necessary program from the storage unit 203 and executing it. However, the processing of FIG. 2 may be realized by operating at least a part of each element of the information processing apparatus 200 shown in FIG. 1 as dedicated hardware. In this case, the dedicated hardware operates based on the control of the CPU 202. Hereinafter, the alphabet S means a step in the flowchart.

First, in S <b> 1, the information processing apparatus 200 acquires an image captured by the imaging apparatus 100. Next, in S2, the information processing apparatus 200 determines whether or not a matrix area is set in the image acquired in S1, and if the matrix area is not set, the process proceeds to S3, where the matrix area is set. If yes, the process proceeds to S6. In S3, the information processing apparatus 200 sets a matrix area in the image acquired in S1.
In S4, the information processing apparatus 200 determines whether or not there is a shielding area in the matrix area. If there is a shielding area, the information processing apparatus 200 proceeds to S5. If there is no shielding area, the information processing apparatus 200 proceeds to S6. In S5, the information processing apparatus 200 sets a shielding area in the matrix area.

In S <b> 6, the information processing apparatus 200 acquires an image of the matrix area and determines whether a human body exists in the matrix area. Then, the information processing apparatus 200 proceeds to S7 when it is determined that a human body exists, and proceeds to S11 when it is determined that no human body exists. In S7, the information processing apparatus 200 detects and counts human bodies from the image of the matrix area. Thereby, the counting result of the human body in the matrix area | region using a human body detection process is obtained. Next, in S <b> 8, the information processing apparatus 200 tracks the human body detected in S <b> 7 and acquires trajectory information of the tracked human body.
In S9, the information processing apparatus 200 performs a human body passage detection process based on the trajectory information acquired by the tracking process in S8, and determines whether or not a human body has entered or exited the shielding area. Then, the information processing apparatus 200 proceeds to S10 when it is determined that a human body has entered or exited the shielding area, and proceeds to S11 when it is determined that there is no access. In S10, the human body in the shielding area is counted. Specifically, when it is determined that the human body has entered the shielding area by the passage detection process, the number of people in the shielding area is added, and when it is determined that the human body has exited the shielding area, the number of people in the shielding area Is subtracted. Thereby, the counting result of the human body in the shielding area using the passage detection process is obtained.

In S11, the information processing apparatus 200 adds the counting result of the human body in the shielding area using the passage detection process obtained in S10 to the counting result of the human body in the matrix area using the human body detection process obtained in S7. . Then, the information processing apparatus 200 uses the added result as the counting result of the human bodies existing in the matrix area including the human bodies shielded in the shielding area. Finally, in S12, the information processing apparatus 200 determines whether or not there is a next image captured by the imaging apparatus 100. If there is a next image, the process returns to S1 and the next image exists. If not, the process ends.
In this way, the information processing apparatus 200 can count the human body shielded in the shielding area by counting the number of human bodies coming and going from the shielding area based on the tracking results of the human body. For this reason, even if there is a shielding area in the matrix area, it is possible to appropriately count the human bodies included in the entire matrix area.

Hereinafter, a method of counting human bodies in the matrix area will be specifically described.
FIG. 3 is an example of an image captured by the image capturing apparatus 100. In FIG. 3, an image 400 </ b> A is an image of the imaging region of the imaging device 100. A matrix area 401 is set in the image 400A. The matrix area 401 is an area where a plurality of human bodies 402 are arranged. The plurality of human bodies 402 are objects to be counted. The matrix direction 403 is a traveling direction of the matrix in which the human bodies 402 are arranged, and corresponds to the movement direction of the human body 402. The shielding area 404 is an area of a shielding object 404 a such as a wall or a pillar that shields the human bodies 402 arranged in a matrix in the matrix area 401. FIG. 3 shows an example in which nine people are lined up and three of them are shielded by the shield 404a.

In this case, in the human body detection process, the human body 402 that is shielded by the shield 404a in the shield region 404 cannot be detected and counted. In other words, in the human body detection process, only six human bodies 402 existing outside the shielding area 404 in the matrix area 401 can be detected and counted.
Therefore, in this embodiment, the human body detected by the human body detection process in the matrix area 401 is tracked, and the human body 402 shielded in the shielding area 404 is counted by detecting passage of the shielding area 404. That is, the human body 402 is tracked, and when it is detected that the human body 402 has entered the shielding area 404 through the passage detection line 405 at the entrance of the shielding area 404, the count of the human body 402 in the shielding area 404 is added. . Further, when it is detected that the tracked human body 402 has passed through the passage detection line 406 at the exit of the shielded area 404 and exited from the shielded area 404, the count of the human body 402 in the shielded area 404 is subtracted.
Thereby, the human body 402 existing behind the shield 404a can be counted without imaging the back of the shield 404a with another imaging device. That is, it is possible to appropriately count a plurality of human bodies 402 included in the entire matrix area 401 including the shielding area 404 from an image captured by one imaging apparatus.

  As described above, the information processing apparatus 200 according to the present embodiment acquires an image of a predetermined area that is imaged by the imaging apparatus 100 and is an object counting target. Here, the predetermined area to be counted for the object can be a matrix area including a plurality of objects, and the object to be counted can be a human body. The information processing apparatus 200 detects a human body that is an object to be counted from the acquired image of the matrix region using human body detection processing, and counts the detected human bodies. Further, the information processing apparatus 200 counts the human bodies that are shielded in the shielding areas in the matrix area based on the detection results of the human bodies. Then, the information processing apparatus 200 adds the number of people in the shielding area to the number of persons counted using the human body detection process, and counts the human bodies existing in the matrix area.

In this way, the information processing apparatus 200 exists in the predetermined area in consideration of the object shielded in the shielding area when the shielding area that shields the object to be counted exists in the predetermined area to be counted of the object. Count objects Therefore, it is possible to appropriately count the total number of objects existing in the predetermined area. As in the present embodiment, when the predetermined area is a matrix area and the object to be counted is a human body, the number of people lined up in the matrix can be appropriately counted. For example, it is possible to appropriately count the number of queues at a station platform, the number of queues at a taxi stand, and the like. In this case, it is possible to accurately estimate the waiting time of the queue, and appropriately guide the number of people waiting in the queue and the waiting time, for example, to the users lining up in the queue.
Further, the information processing apparatus 200 can count the total number of objects including objects shielded in the shielding area, based on an image captured by one imaging apparatus 100. Therefore, it is not necessary to provide another imaging device for imaging an object shielded by the shielding object, and the number of objects in a predetermined area can be counted with a simple system configuration.

Furthermore, the information processing apparatus 200 tracks the human body detected from the image of the matrix area, and counts the human bodies in the shielded area by detecting entry / exit to the shielded area. Therefore, it is possible to appropriately count the human bodies shielded in the shielding area.
Here, the information processing apparatus 200 can determine the entrance / exit of the shielding area based on the traveling direction of the matrix included in the matrix area, and can set a passage detection line at each entrance / exit of the determined shielding area. In addition, the information processing apparatus 200 can detect whether the tracked human body has passed the passage detection line, thereby detecting the human body entering and exiting the shielding area. Thus, since the information processing apparatus 200 sets a passage detection line at the entrance and exit of the shielding area and performs passage detection, it is possible to appropriately count the human bodies that move along the traveling direction of the matrix.

Further, the information processing apparatus 200 can exclude objects that pass through the passage detection line in the direction opposite to the traveling direction of the matrix from being counted. Furthermore, even if the information processing apparatus 200 is a human body that has passed the passage detection line, the human body that can be detected in the shielding area can be excluded from the counting target. In this way, the information processing apparatus 200 can appropriately determine human bodies that are not lined up in the matrix, and can appropriately detect human bodies that enter and exit the shielding area with the human bodies lined up in the matrix.
Furthermore, the information processing apparatus 200 may set a matrix area in the image and a shielding area in the matrix area based on the moving speed, the density, and the like of the object (human body) in the image captured by the imaging apparatus 100. it can. Therefore, the matrix area and the shielding area can be set appropriately, and the objects (human bodies) existing in the matrix area can be counted appropriately.

  In addition, the information processing apparatus 200 performs display control to display an image captured by the imaging apparatus 100 on the display unit 204, accepts the setting of the matrix area in the displayed image from the user, and sets the matrix area. You can also. As a result, the information processing apparatus 200 can appropriately count the number of people in the matrix area that the user wants to check and can guide the user. Further, the information processing apparatus 200 performs display control to display an image captured by the imaging apparatus 100 on the display unit 204, receives a setting of a shielding area in the displayed image from the user, and sets the shielding area. You can also. Thereby, the information processing apparatus 200 can appropriately set the area behind the shield that the user wants to check, and can perform counting processing according to the user's request.

(Modification)
In the above embodiment, the case where the number of human bodies shielded in the shielding area is counted by detecting the passage of the human body at the entrance / exit of the shielding area has been described, but the method of counting the human bodies in the shielding area is not limited to the above. The information processing apparatus 200 may change the shielding area counting method according to the length of the matrix.
When the matrix area 401 is long and the end of the matrix exceeds the shielding area 404 as in the image 400 </ b> A of FIG. 3, the maximum number of human bodies 402 that can exist in the shielding area 404 is determined as the shielding area 404. It may be set as the number of human bodies 402 shielded at. Here, the maximum value can be set in advance according to the size of the shielding region 404. The maximum value may be a value estimated from the density of the human body 402 around the shielding area 404 in the matrix area 401.
Thus, when the head of the matrix is located on the exit side of the shielding area outside the shielding area, and the tail end of the matrix is located on the entrance side of the shielding area outside the shielding area, the matrix is shielded in the shielding area. The number of existing human bodies may be set to the maximum value. In this case, it is possible to easily count the human bodies shielded in the shielding area without performing the tracking process or the passage detection process.

On the other hand, when the end of the matrix is in the shielding area 404 as in the image 400B shown in FIG. 4, the human body 402 that has entered the shielding area 404 and the human body 402 that has exited from the shielding area 404 are counted. That is, the human body 402 shielded in the shielding area 404 is counted by detecting the passage of the human body 402 at the entrance / exit of the shielding area 404.
Further, when the matrix is short and the end of the matrix does not reach the shielding area 404 as in the image 400C shown in FIG. 5, the count value of the human body 402 in the shielding area 404 is initialized to zero or the like. Good. When the head and the tail of the matrix are both located on the exit side of the shielding area outside the shielding area, it can be determined that there is no human body shielded in the shielding area. Therefore, in such a case, setting the number of human bodies shielded in the shielding area to zero eliminates the need for complicated processing for counting the human bodies in the shielding area.

FIG. 6 is a flowchart showing a flow of processing for counting objects shielded in the shielding area according to the length of the matrix. The process of FIG. 6 can be started at the same timing as the process of FIG.
The information processing apparatus 200 can implement the processing illustrated in FIG. 6 by reading out a necessary program from the storage unit 203 and executing it. However, the processing of FIG. 6 may be realized by operating at least a part of each element of the information processing apparatus 200 shown in FIG. 6 as dedicated hardware. In this case, the dedicated hardware operates based on the control of the CPU 202.
6, steps that perform the same processing as in FIG. 2 are assigned the same step numbers as in FIG.

In S21, the information processing apparatus 200 determines whether or not human bodies arranged in a matrix can be detected in the vicinity of the exit of the shielding area. If it can be detected, the process proceeds to S22, and if not detected, the process proceeds to S25. In S22, the information processing apparatus 200 determines whether or not human bodies arranged in a matrix can be detected in the vicinity of the entrance of the shielding area. If it can be detected, the process proceeds to S23, and if not detected, the process proceeds to S24.
In S23, the information processing apparatus 200 sets the number of human bodies shielded in the shielding area to the maximum value, and proceeds to S11. In S24, the information processing apparatus 200 counts the human bodies that are shielded in the shielding area by counting the human bodies entering and exiting the shielding area using the passage detection process, and proceeds to S11. In S25, the information processing apparatus 200 initializes the number of human bodies shielded in the shielding area to 0 or the like, and proceeds to S11.

In this way, when human bodies arranged in a matrix can be detected both near the exit and near the entrance of the shielding area, it is determined that the matrix is long as shown in FIG. 3, and the number of human bodies shielded in the shielding area is as follows. Is set to a preset maximum value. On the other hand, when human bodies lined up in the matrix can be detected only near the exit of the shielding area, it is determined that the last of the matrix is within the shielding area as shown in FIG. Therefore, in this case, passage detection of a human body using a passage detection line set at the entrance / exit of the shielding area is performed, and the number of human bodies shielded in the shielding area is counted. Further, when human bodies arranged in a matrix cannot be detected both near the exit and near the entrance of the shielding area, it is determined that the matrix is short and no human body exists in the shielding area as shown in FIG. Initialize the number of human bodies shielded at.
As described above, by performing the counting process according to the length of the matrix, the shielding area can be easily and appropriately counted.

In the above embodiment, an upper limit value may be set for the counting result of the human body shielded in the shielding area. Here, the said upper limit can be made into the maximum value of the human body which can exist in a shielding area | region, for example. In this case, as a result of counting the number of human bodies shielded in the shielding area using the human body passage detection process, the information processing apparatus 200 sets the count result to the upper limit value when the count result exceeds the upper limit value. You may make it correct | amend.
Moreover, in the said embodiment, although the said embodiment demonstrated the case where there was one shielding area | region in a matrix area | region, there may be two or more shielding areas.
Furthermore, in the above embodiment, the case where the predetermined area that is the object counting target is the matrix area has been described, but the predetermined area is not limited to the matrix area. Furthermore, although the case where the predetermined area is a partial area of an image captured by the imaging apparatus 100 has been described, the predetermined area may be an entire area of the image.

(Other embodiments)
The present invention supplies a program that realizes one or more functions of the above-described embodiments to a system or apparatus via a network or a storage medium, and one or more processors in a computer of the system or apparatus read and execute the program This process can be realized. It can also be realized by a circuit (for example, ASIC) that realizes one or more functions.

  DESCRIPTION OF SYMBOLS 100 ... Imaging device 200 ... Information processing apparatus 201 ... Communication part 202 ... CPU, 203 ... Memory | storage part, 204 ... Display part, 205 ... Input part, 206 ... Matrix area | region setting part, 207 ... Shielding area | region setting part, 208 ... Matrix region counting unit, 209 ... Shielding region counting unit, 209a ... Object tracking unit, 209b ... Object passage detection unit, 300 ... Network

Claims (14)

Acquisition means for acquiring an image of a predetermined area to be counted by an object, which is imaged by the imaging means;
Detection means for detecting an object to be counted from the image acquired by the acquisition means;
First counting means for counting objects detected by the detecting means;
Based on the detection result by the detection means, a second counting means for counting the object shielded in the shielding area within the predetermined area;
Third counting means for outputting a result counted in the predetermined area based on the number of the objects counted by the first counting means and the number of the objects counted by the second counting means; An information processing apparatus comprising: The second counting means includes
Tracking means for tracking an object detected by the detection means;
The information processing apparatus according to claim 1, further comprising: an entry / exit detection unit that detects entry / exit of the object tracked by the tracking unit with respect to the shielding area. First setting means for setting the predetermined areas in the images respectively captured by the imaging means;
The information processing apparatus according to claim 1, further comprising: a second setting unit that sets the shielding area within the predetermined area.   The information processing apparatus according to claim 1, wherein the predetermined area is a matrix area including a plurality of the objects. The entry / exit detection means includes:
Pass detection lines are respectively set at the entrances and exits of the shielding area determined based on the traveling direction of the matrix included in the matrix area, and it is detected that the object tracked by the tracking unit has passed the pass detection line. The information processing apparatus according to claim 4, wherein an entry / exit of the object with respect to the shielding area is detected. The second counting means includes
The information processing apparatus according to claim 5, wherein an object passing through the passage detection line in a direction opposite to a traveling direction of the matrix is excluded from counting. The second counting means includes
The information processing apparatus according to any one of claims 4 to 6, wherein the object shielded in the shielding area is counted based on a length of a matrix included in the matrix area. The second counting means includes
In the case where the head of the matrix is located on the exit side of the shielding area outside the shielding area, and the tail of the matrix is located on the entrance side of the shielding area outside the shielding area, The information processing apparatus according to claim 7, wherein the number of objects that are shielded is set to a maximum value of the number of objects that can exist in the shielding area. The second counting means includes
The number of the objects shielded in the shielding area is set to zero when the head and the tail of the matrix are located on the exit side of the shielding area outside the shielding area. The information processing apparatus according to 7 or 8. The second counting means includes
The information processing apparatus according to claim 1, wherein an object that can be detected in the shielding area is excluded from the counting target. The second counting means includes
11. The information processing apparatus according to claim 1, wherein an upper limit value is set for a count result of the object shielded in the shielding region.   The information processing apparatus according to claim 1, wherein the object to be counted is a human body or a part of a human body. Acquiring an image of a predetermined area to be counted by an object, which is imaged by an imaging means;
Detecting an object to be counted from the acquired image;
Counting the detected object to obtain a first counting result;
Based on the detection result, counting the object shielded in the shielding area in the predetermined area, obtaining a second counting result;
Outputting the result of counting in the predetermined area based on the first count result and the second count result.   The program for functioning a computer as each means of the information processing apparatus of any one of Claim 1 to 12.

Images