Information processing device and information processing method

Abstract

This reduces the workload when analyzing the flow of people in captured images. [Solution] The information processing device 1 includes a determination unit 131 that determines means for determining the proportion of multiple people who appear in the captured image taken by the imaging device 2 that visit the predetermined area, based on the positional relationship between the imaging area captured by the imaging device 2 and a predetermined area within a predetermined range from the imaging area; an estimation unit 133 that estimates information relating to people who appear in the captured image taken by the imaging device 2 that visit the predetermined area, based on the means determined by the determination unit 131; and an output unit 134 that outputs the information relating to people who visit the predetermined area estimated by the estimation unit 133.

Description

Technical Field

[0001] The present invention relates to an information processing apparatus and an information processing method.

Background Art

[0002] Conventionally, analysis has been performed on the movement lines of people reflected in a captured image captured by an imaging device. For example, Patent Document 1 discloses creating a rectangle that includes an object indicating a person included in a captured image that captures a predetermined area, and creating a movement line by connecting the center points of the rectangles.

Prior Art Documents

Patent Documents

[0003]

Patent Document 1

Summary of the Invention

Problems to be Solved by the Invention

[0004] In the conventional technology, by creating the movement lines of people, it is possible to analyze the flow of people of the people reflected in the captured image. However, when there are many people included in the imaging device, there is a problem that it takes a load to create the movement lines and it takes a load to analyze the flow of people.

[0005] Therefore, the present invention has been made in view of these points, and an object thereof is to reduce the load when analyzing the flow of people of the people reflected in the captured image.

Means for Solving the Problems

[0006] An information processing device according to a first aspect of the present invention includes: an identification unit that identifies means for identifying the proportion of a plurality of people who appear in an image captured by an imaging device that visit the predetermined area, based on the positional relationship between an imaging area captured by an imaging device and a predetermined area within a predetermined range from the imaging area; an estimation unit that estimates information relating to people who visit the predetermined area, as seen in the image captured by the imaging device, based on the means identified by the identification unit; and an output unit that outputs the information relating to people who visit the predetermined area estimated by the estimation unit.

[0007] Multiple predetermined areas exist, and the identifying unit may specify the means for each of the multiple predetermined areas of multiple people that appear in the captured image captured by the imaging device. The estimation unit may estimate the number of visitors to the predetermined area corresponding to multiple people appearing in the captured image captured by the imaging device, based on the means identified by the identification unit. The identifying unit may identify the means based on the distance between the imaging area and the predetermined area.

[0008] The specified unit may further specify the means based on the arrangement of pathways for people to walk in the vicinity of the imaging area and the predetermined area. The identifying unit may further identify the means based on at least one of the orientation of the person in the captured image and the position of the person in the captured image in the captured image. The identifying unit may further identify the means based on attributes that have been pre-assigned to the predetermined area, which indicate the number of visitors to the predetermined area.

[0009] The identifying unit may identify the means based on the number of visitors to the predetermined area corresponding to at least one of the weather and temperature of the predetermined area and the area including the imaging device, and the time of day. The estimation unit may estimate information relating to persons visiting the predetermined area, corresponding to at least one of the weather and temperature of the predetermined area and the area including the imaging device, and the time of day, at the time the image was captured, based on the means.

[0010] The identifying unit may acquire actual values ​​of the number of visits to the predetermined area by multiple people shown in the image captured by the imaging device, and identify the means based on the acquired actual values.

[0011] There may be multiple imaging devices, the identification unit may identify the means for each of the multiple imaging devices, and the estimation unit may estimate the number of visitors to the predetermined area based on the number of people appearing in the images captured by each of the multiple imaging devices and the means for each of the multiple imaging devices identified by the identification unit.

[0012] The identification unit may determine the overlap ratio, which is the percentage of people who appear in the same image captured by at least two of the multiple imaging devices, based on the relative positions of the multiple imaging devices, and the estimation unit may further estimate the number of visitors to the predetermined area based on the overlap ratio.

[0013] The identification unit may identify the means for determining the proportion of persons corresponding to predetermined attributes who visit the predetermined area among a plurality of persons appearing in the captured image taken by the imaging device, and the estimation unit may estimate, based on the means, information relating to persons of the predetermined attributes who visit the predetermined area and who appear in the captured image taken by the imaging device.

[0014] The identification unit may identify the means for identifying the attributes of a person who visits the predetermined area from among a plurality of people who appear in the captured image captured by the imaging device, and the estimation unit may estimate the attributes of the person who visits the predetermined area as information relating to the person who visits the predetermined area who appears in the captured image captured by the imaging device, based on the means.

[0015] The identification unit may identify the means for determining the proportion of multiple people appearing in the captured image captured by the imaging device who are staying in the predetermined area, and the estimation unit may estimate the number of people staying in the predetermined area who appear in the captured image captured by the imaging device, based on the number of people appearing in the captured image captured by the imaging device and the means identified by the identification unit.

[0016] A second aspect of the present invention relates to an information processing method which includes the steps of: identifying means for determining the proportion of a plurality of people who appear in an image captured by an imaging device that visit the predetermined area, based on the positional relationship between an imaging area captured by an imaging device and a predetermined area within a predetermined range from the imaging area; estimating information relating to people who visit the predetermined area, as seen in the image captured by the imaging device, based on the identified means; and outputting the estimated information relating to people who visit the predetermined area. [Effects of the Invention]

[0017] According to the present invention, the load on the system when analyzing the flow of people in captured images can be reduced. [Brief explanation of the drawing]

[0018] [Figure 1] This is a diagram illustrating the overview of an information processing device. [Figure 2] This diagram shows the functional configuration of an information processing device. [Figure 3] This diagram shows the relationship between the imaging areas of multiple imaging devices and a predetermined area. [Figure 4] This figure shows an example of incoming information. [Figure 5] It is a flowchart showing the processing flow in an information processing apparatus.

Embodiments for Carrying Out the Invention

[0019] [Overview of Information Processing Apparatus 1] FIG. 1 is a diagram showing an overview of an information processing apparatus 1. The information processing apparatus 1 is a computer that outputs information related to a person who visits a predetermined area among the persons shown in the captured image captured by the imaging apparatus 2. As shown in FIG. 1, the information processing apparatus 1 is communicably connected to the imaging apparatus 2. One or more imaging apparatuses 2 are provided, arranged in the vicinity of a predetermined area, and image an imaging area within a predetermined range from the predetermined area.

[0020] When outputting information related to a person who visits a predetermined area, the information processing apparatus 1 first identifies specific means for identifying the ratio of a plurality of persons shown in the captured image captured by the imaging apparatus 2 who visit the predetermined area based on the positional relationship between the imaging area captured by the imaging apparatus 2 and the predetermined area.

[0021] In the example shown in FIG. 1, the predetermined area is, for example, an area indicating the site of Company A's building, and the information processing apparatus 1 identifies specific means for identifying the visit ratio, which is the ratio of the plurality of persons shown in the captured image captured by the imaging apparatus 2 who visit the area including Company A's building, based on the positional relationship between the imaging area of the imaging apparatus 2 and the predetermined area within a predetermined range from the position of the imaging area.

[0022] Then, the information processing apparatus 1 estimates information related to a person who visits a predetermined area, which is shown in the captured image captured by the imaging apparatus 2, based on the visit ratio identified by the specific means. The information related to a person who visits a predetermined area is, for example, the number of persons who visit the predetermined area among the persons shown in the captured image captured by the imaging apparatus 2.

[0023] In the example shown in Figure 1, people entering the premises of Company A are shown in black. The information processing device 1 estimates the proportion of people visiting the premises of Company A, which is a designated area, as captured in the image captured by the imaging device 2 located near the entrance of Company A, and the proportion of people visiting the premises of Company A, as captured in the image captured by the imaging device 2 located at spot B. The information processing device 1 then outputs information relating to the estimated people visiting the premises of Company A.

[0024] In this way, the information processing device 1 can reduce the workload when analyzing the flow of people captured by an imaging device compared to generating and analyzing the movement paths of people captured in an image, by estimating information about people visiting a predetermined area based on specific means.

[0025] [Functional configuration of the information processing device 1] Next, the functions of the information processing device 1 will be explained. Figure 2 is a diagram showing the functional configuration of the information processing device 1. The information processing device 1 includes a communication unit 11, a storage unit 12, and a control unit 13.

[0026] The communication unit 11 is a communication interface for sending and receiving data with external devices such as the imaging device 2 via a communication network such as the Internet. The memory unit 12 is a storage medium for storing various types of data, and includes ROM (Read Only Memory), RAM (Random Access Memory), and hard disks. The memory unit 12 stores programs to be executed by the control unit 13. The memory unit 12 stores programs that cause the control unit 13 to function as a specific unit 131, an acquisition unit 132, an estimation unit 133, and an output unit 134.

[0027] The control unit 13 is, for example, a CPU (Central Processing Unit). The control unit 13 functions as a locating unit 131, an acquisition unit 132, an estimation unit 133, and an output unit 134 by executing a program stored in the storage unit 12.

[0028] The identification unit 131 identifies an identification means for determining the visit rate, which is the proportion of multiple people who appear in the captured image captured by the imaging device 2 that visit the predetermined area, based on the positional relationship between the imaging device 2 and a predetermined area within a predetermined range from the position of the imaging device 2. Here, the identification means is a program or learning model that outputs the visit rate corresponding to the imaging device 2 in response to the input of the visit rate itself or a camera ID (Identification) for identifying the imaging device 2. The identification unit 131 identifies an identification means for each of the multiple imaging devices 2.

[0029] For example, the identification unit 131 identifies a means for identification based on the area proximity distance, which is the distance between the imaging area, which is the area imaged by the imaging device 2, and a predetermined area. Specifically, the storage unit 12 stores relationship identification information for identifying the relationship between multiple area proximity distances and visit rates. Relationship identification information includes, for example, a visit rate table that associates a visit rate with each of multiple area proximity distances, or a function that outputs a visit rate in response to an input area proximity distance. For example, the identification unit 131 calculates the area proximity distance corresponding to the imaging device 2 and uses the relationship identification information to identify the visit rate corresponding to the calculated area proximity distance as a means for identification.

[0030] The identification unit 131 may further identify the identification means based on the arrangement of pedestrian walkways, which are pathways for people to walk, in the vicinity of the imaging area captured by the imaging device 2 and a predetermined area. For example, the identification unit 131 analyzes map information or the image captured by the imaging device 2 to determine whether or not there are pedestrian walkways passing through the imaging area and the predetermined area between the imaging area and the predetermined area, or in the vicinity of the imaging area and the predetermined area. If the identification unit 131 determines that there are pedestrian walkways, it corrects the visit rate by multiplying the visit rate associated with the calculated proximity distance to the area by a correction coefficient, which is a coefficient greater than 1, and then identifies the identification means.

[0031] The identification unit 131 may determine the width of the pedestrian walkway based on map information or captured images, and may change the coefficient based on the determined width of the pedestrian walkway. For example, the identification unit 131 may increase the coefficient as the width of the pedestrian walkway increases.

[0032] Furthermore, the identification unit 131 may further identify the identification means based on at least one of the orientation of the person captured by the imaging device 2 and the position of the person in the captured image. For example, the identification unit 131 identifies the orientation of a predetermined area in the captured image and identifies a neighboring area, which is a partial area close to the predetermined area, among a plurality of partial areas included in the imaging area. The identification unit 131 calculates the proportion of people facing the predetermined area among a plurality of people captured in each of the plurality of captured images taken by the imaging device 2. The identification unit 131 also calculates the number of people captured in the neighboring area included in each of the plurality of captured images taken by the imaging device 2. The identification unit 131 then increases the correction coefficient as the proportion of people facing the predetermined area increases, and increases the correction coefficient as the number of people captured in the neighboring area increases.

[0033] In this way, the information processing device 1 can increase the visit rate in cases where the probability of visiting a designated area is considered high because many of the people captured by the imaging device 2 are facing the designated area or are located near the designated area.

[0034] Furthermore, the identification unit 131 may acquire actual values ​​for the number of visits to a predetermined area by multiple people appearing in the captured image taken by the imaging device 2, and identify the identification means based on the acquired actual values. For example, the identification unit 131 identifies the feature quantities of each of the multiple people appearing in the captured image (first captured image) taken by the imaging device 2 during the first period, and also identifies the feature quantities of each of the multiple people appearing in the captured image (second captured image) taken during the second period by an imaging device (not shown) provided in the predetermined area. The second period is, for example, the period after a predetermined time has elapsed since the first period. The predetermined time is the travel time assumed when a pedestrian moves from the imaging area to the predetermined area, which is determined based on the distance between the imaging area and the predetermined area.

[0035] The identification unit 131 identifies the same person based on the feature quantities of each person in the first captured image and the feature quantities of each person in the second captured image. The identification unit 131 identifies the identified same person as a person who visited a predetermined area in the first captured image, thereby determining the number of people who visited the predetermined area out of the multiple people in the captured image taken by the imaging device 2. The identification unit 131 then identifies identification means based on the number of people in the captured image taken by the imaging device 2 and the number of identified visiting people. In this way, the information processing device 1 can identify identification means for accurately determining the visit rate based on the actual actions of the multiple people in the captured image taken by the imaging device 2.

[0036] Here, the identification unit 131 may identify identification means for determining the proportion of people with predetermined attributes who visit a predetermined area among a group of people who appear in the captured image taken by the imaging device 2. The predetermined attributes are, for example, predetermined age groups such as the elderly, adults, and children, or gender such as male and female. For example, the identification unit 131 identifies people with predetermined attributes based on the feature quantities of people who visited the predetermined area among a group of people who appear in the first captured image, and identifies people with predetermined attributes who visited the predetermined area among a group of people who appear in the first captured image. If information indicating the purpose of visit of visitors to the predetermined area can be obtained, the predetermined attributes may include the purpose of visit to the predetermined area. The identification unit 131 then identifies identification means based on the number of people who appear in the captured image taken by the imaging device 2 and the number of visits by the identified people with predetermined attributes.

[0037] Furthermore, the identification unit 131 may identify identification means for identifying the attributes of individuals who visit a predetermined area from among multiple individuals captured in the image captured by the imaging device 2. For example, the identification unit 131 identifies attributes corresponding to predetermined items of individuals who visit a predetermined area from among multiple individuals captured in the first image, based on the feature quantities of those individuals. The identification unit 131 then identifies the proportion of individuals who visit a predetermined area who possess each of the multiple attributes corresponding to the predetermined item. For example, if the predetermined item is gender, the identification unit 131 identifies the proportion of male individuals and the proportion of female individuals among the multiple individuals who visit a predetermined area.

[0038] Furthermore, the identification unit 131 may identify identification means based on attributes that have been pre-assigned to a predetermined area and indicate the number of visitors to that area. For example, the identification unit 131 obtains attribute information from an analysis device (not shown) that analyzes the number of visitors to a predetermined area, indicating the relative number of visitors to that area compared to other areas, based on the actual number of visitors to that area, using labels such as "high," "average," or "low," or in multiple stages. The identification unit 131 then adjusts a correction coefficient based on the attribute information indicating the attributes assigned to the predetermined area. For example, if the attribute indicated by the attribute information indicates "high," the identification unit 131 increases the correction coefficient compared to when the attribute indicates "average," and if it indicates "average," it increases the correction coefficient compared to when it indicates "low." In this way, the information processing device 1 can adjust the visit ratio by taking into account the number of visitors to the predetermined area that has been pre-analyzed.

[0039] Furthermore, the identification unit 131 may identify the identification means based on the number of visitors to the predetermined area corresponding to at least one of the weather and temperature of the predetermined area and the area including the imaging device 2, and the time of day. For example, the identification unit 131 obtains actual values ​​of the number of visitors to the predetermined area for each weather, temperature, and time of day of the predetermined area and the area including the imaging device 2 from an analysis device that analyzes the number of visitors.

[0040] The identification unit 131 then identifies a correction coefficient for each weather, temperature, and time of day in the predetermined area and the area including the imaging device 2, based on the acquired actual values. By multiplying the identified correction coefficient by the visit rate, the identification unit 131 identifies a means for identifying each weather, temperature, and time of day in the predetermined area and the area including the imaging device 2. For example, the identification unit 131 may identify a classification model that outputs a visit rate in response to the input of the camera ID of the imaging device 2 and the weather, temperature, and time of day in the predetermined area and the area including the imaging device 2 as the means for identifying. In this way, the information processing device 1 can identify an appropriate visit rate for each weather, temperature, and time of day in the predetermined area and the area including the imaging device 2.

[0041] Here, there may be multiple predetermined areas. In this case, the identification unit 131 identifies identification means for each of the multiple predetermined areas for multiple people appearing in the captured image captured by the imaging device 2. For example, if there are two predetermined areas, area A and area B, the identification unit 131 identifies identification means for area A to identify the proportion of visits to area A by multiple people appearing in the captured image captured by the imaging device 2, and identification means for area B to identify the proportion of visits to area B.

[0042] The acquisition unit 132 acquires the captured images taken by each of the one or more imaging devices 2. For example, the acquisition unit 132 acquires the captured images taken by each of the one or more imaging devices 2 and associates them with the camera ID of the imaging device 2.

[0043] The estimation unit 133 estimates information relating to people visiting a predetermined area, based on the identification means identified by the identification unit 131, as captured in the image captured by the imaging device 2 acquired by the acquisition unit 132. For example, if the identification means is the percentage of visits to a predetermined area, the estimation unit 133 identifies the number of people in the image by analyzing the image captured by the imaging device 2 acquired by the acquisition unit 132. By multiplying the identified number of people by the visit percentage used as the identification means, the estimation unit 133 estimates the number of visits to the predetermined area, corresponding to the multiple people in the image captured by the imaging device 2, as information relating to people visiting the predetermined area.

[0044] Furthermore, if the identification means is a classification model for identifying the proportion of visits to a predetermined area corresponding to each of the multiple imaging devices 2, and is a classification model that outputs the proportion of visits corresponding to the weather, temperature, and time of day, the estimation unit 133 inputs the camera ID of the imaging device 2 and the weather, temperature, and time of day of the predetermined area and the area including the imaging device 2 at the time the image was captured by the imaging device 2 into the classification model.

[0045] The estimation unit 133 obtains the visit rate corresponding to the weather, temperature, and time of day for a predetermined area and the area including the imaging device 2 from the classification model. Then, by multiplying the number of identified individuals by the visit rate, the estimation unit 133 estimates the number of visits to the predetermined area corresponding to the multiple individuals captured in the image captured by the imaging device 2, and the number of visits corresponding to the weather, temperature, and time of day for the predetermined area and the area including the imaging device 2 at the time the image was captured by the imaging device 2.

[0046] Furthermore, if the identification means is an identification means for determining the proportion of people corresponding to a predetermined attribute who visit a predetermined area, the estimation unit 133 estimates the number of visits by people with a predetermined attribute who visit the predetermined area, based on the identification means, as information relating to people with a predetermined attribute who visit the predetermined area and are captured in the image captured by the imaging device 2. For example, the estimation unit 133 estimates the number of visits by people with a predetermined attribute who visit the predetermined area by multiplying the number of visits to the predetermined area corresponding to multiple people captured in the image captured by the imaging device 2 by the proportion of visits by people with a predetermined attribute determined based on the identification means.

[0047] Furthermore, if the identification means is an identification means for identifying the attributes of a person visiting a predetermined area, the estimation unit 133 estimates the attributes of the person visiting the predetermined area as information relating to the person visiting the predetermined area, as captured in the image captured by the imaging device 2, based on the identification means. For example, the estimation unit 133 estimates the number of visits by a person visiting the predetermined area corresponding to each of the multiple attributes corresponding to a predetermined item by multiplying the number of visits to the predetermined area corresponding to multiple people captured in the image captured by the imaging device 2 by the proportion of each of the multiple attributes corresponding to a predetermined item, which are identified based on the identification means.

[0048] Furthermore, the estimation unit 133 estimates the number of visitors to a predetermined area, corresponding to the multiple people shown in the captured images, based on the captured images taken by each of the multiple imaging devices 2. In addition, if there are multiple predetermined areas, the estimation unit 133 estimates information relating to the people visiting each of the multiple predetermined areas, as shown in the captured images taken by the imaging device 2, based on the identification means.

[0049] The estimation unit 133 may also estimate the number of visitors to a predetermined area based on the number of people appearing in the captured images taken by each of the multiple imaging devices 2 and the identification means for each of the multiple imaging devices 2 identified by the identification unit 131. For example, the estimation unit 133 sums up the estimated number of visitors to the predetermined area for each of the multiple imaging devices 2. The estimation unit 133 estimates the number of visitors to a predetermined area based on the ratio of the number of paths passing through the imaging area of ​​the imaging device 2 to the predetermined area and the number of paths to the predetermined area, and the sum of the estimated number of visitors to the predetermined area for each of the multiple imaging devices 2.

[0050] For example, if there are three paths that pass through the imaging areas of multiple imaging devices 2 to reach a predetermined area, and three paths that pass through the imaging area of ​​one imaging device 2 to reach the predetermined area, the total number of visitors to the predetermined area estimated for each of the multiple imaging devices 2 is estimated as the total number of visitors to the predetermined area. Also, for example, if there are three paths that pass through the imaging areas of multiple imaging devices 2 to reach a predetermined area, and two paths that pass through the imaging area of ​​one imaging device 2 to reach the predetermined area, the total number of visitors to the predetermined area estimated for each of the multiple imaging devices 2 multiplied by 1.5 is estimated as the total number of visitors to the predetermined area.

[0051] Here, depending on the positional relationship between the imaging area captured by each of the multiple imaging devices 2 and a predetermined area, the same person may appear in the images captured by each of the multiple imaging devices 2. In response to this, the identification unit 131 may determine the overlap ratio, which is the ratio of a person who appears in at least two of the multiple imaging devices 2, based on the positional relationship between each of the multiple imaging devices 2 and the predetermined area.

[0052] For example, based on the positional relationship between the imaging area of ​​each of the multiple imaging devices 2 and a predetermined area, the proportion of people who flow into the predetermined area from other imaging areas is identified. Figure 3 is a diagram showing the relationship between the imaging areas of the multiple imaging devices 2 and the predetermined area. As shown in Figure 3, if there are areas A, B, and C as imaging areas, and area B exists between areas A and C and the predetermined area, it is thought that some of the people who visit the predetermined area and are captured in the image of area A or area C will pass through area B.

[0053] In response to this, the identification unit 131 identifies the proportion of people visiting the predetermined area that flow in from other imaging areas to each of the multiple imaging areas, based on the positional relationship between these imaging areas and the predetermined area. For example, the identification unit 131 identifies the routes from each of the multiple imaging areas to the predetermined area. Then, the identification unit 131 identifies the proportion of people visiting the predetermined area that flow in from other imaging areas to each of the multiple imaging areas, based on the number of routes that pass through the predetermined imaging area after passing through other imaging areas, relative to the number of routes that pass through the predetermined imaging area.

[0054] For example, suppose there are three paths that pass through imaging area B and reach a predetermined area, one of which passes through imaging area A and the other passes through imaging area C. In this case, the identification unit 131 identifies the proportion of people visiting the predetermined area from imaging area A as 1 / 3 of the people in imaging area B. Similarly, the identification unit 131 identifies the proportion of people visiting the predetermined area from imaging area C as 1 / 3 of the people in imaging area B.

[0055] In this way, the identification unit 131 generates inflow information for each of the multiple imaging areas, showing the proportion of people who come in from other imaging areas to visit a predetermined area. Figure 4 is a diagram showing an example of inflow information. In the example shown in Figure 4, it can be seen that of the people who come in to the predetermined area in area B, 1 / 3 come in from area A and 1 / 3 come in from area C.

[0056] The estimation unit 133 estimates the number of visitors to a predetermined area based on the inflow information indicating the overlap rate generated by the identification unit 131. For example, the estimation unit 133 subtracts the number of overlapping visitors based on the inflow information from the sum of the estimated number of visitors to the predetermined area for each of the multiple imaging devices 2. In this way, the estimation unit 133 can estimate the total number of visitors to the predetermined area from the imaging areas captured by the multiple imaging devices 2, taking into account the overlap in the number of visitors to the predetermined area that are captured by each of the multiple imaging devices 2.

[0057] The output unit 134 outputs information relating to people visiting a predetermined area estimated by the estimation unit 133. For example, it outputs visitor count information, which shows the number of visitors to the predetermined area estimated for each of the multiple imaging devices 2 estimated by the estimation unit 133, and the sum of these visitor counts, to an analysis device (not shown) that performs visitor count analysis.

[0058] [flowchart] Next, we will explain the processing flow of the information processing device 1. Figure 5 is a flowchart showing the processing flow in the information processing device 1. First, the identification unit 131 identifies identification means for determining the proportion of multiple people who appear in the image captured by the imaging device 2 that visit the predetermined area, based on the positional relationship between the imaging area captured by the imaging device 2 and a predetermined area (S1). If the identification means has been identified in advance, the process related to S1 does not need to be executed.

[0059] Next, the acquisition unit 132 acquires the captured image taken by the imaging device 2 (S2). Subsequently, the estimation unit 133 analyzes the acquired image to determine the number of people in the captured image (S3).

[0060] Next, the estimation unit 133 estimates the number of people who visit a predetermined area, based on the identification means identified in S1 and the number of people in the captured image identified in S3 (S4). Subsequently, the output unit 134 outputs visit count information indicating the number of visits estimated in S4 (S5).

[0061] [Differentiation] In the above-described embodiment, the identification unit 131 identifies a means for identifying the proportion of multiple people appearing in the captured image captured by the imaging device 2 that visit a predetermined area, but is not limited to this. The identification unit 131 may also identify a means for identifying the proportion of multiple people appearing in the captured image captured by the imaging device 2 that stay in a predetermined area.

[0062] In this case, the identification unit 131 acquires stay ratio information, which is the proportion of visitors to a predetermined area who stay for a predetermined time or longer. The identification unit 131 then identifies an identification means that indicates the proportion of multiple people who stay in the predetermined area, by multiplying the proportion of multiple people who visit the predetermined area, as captured in the image captured by the imaging device 2, by the stay ratio information.

[0063] The identification unit 131 may identify identification means for determining the proportion of multiple people appearing in the captured images taken by the imaging device 2 who are staying in a predetermined area, corresponding to each of the multiple time periods. In this case, first, the identification unit 131 identifies the visit proportion corresponding to each of the multiple time periods. The identification unit 131 also acquires the dwell proportion information for each of the multiple time periods.

[0064] The identification unit 131 then multiplies the proportion of multiple people who appear in the captured images taken by the imaging device 2 and visit a predetermined area, corresponding to each of the multiple time periods, by the proportion of stay indicated by the stay proportion information corresponding to each of the multiple time periods. In this way, the identification unit 131 identifies a means for identifying the proportion of multiple people who appear in the captured images taken by the imaging device 2 and stay in a predetermined area, corresponding to each of the multiple time periods.

[0065] The estimation unit 133 estimates the number of people in a predetermined area as captured in the image captured by the imaging device 2, based on the number of people in the image captured by the imaging device 2 and the identification means identified by the identification unit 131. For example, if the identification unit 131 identifies the identification means for each of several time periods, the estimation unit 133 identifies the time period in which the imaging device 2 captured the image, and estimates the number of people in a predetermined area corresponding to the identified time period as captured in the image captured by the imaging device 2, based on the number of people in the image captured by the imaging device 2 and the identification means corresponding to the identified time period. In this way, the information processing device 1 can easily estimate the number of people in a predetermined area in an image captured by the imaging device 2.

[0066] [Effects of Information Processing Device 1] As described above, the information processing device 1 according to this embodiment identifies means for determining the proportion of multiple people who appear in the image captured by the imaging device 2 that visit the predetermined area, based on the positional relationship between the imaging area captured by the imaging device 2 and a predetermined area within a predetermined range from the imaging area, estimates information relating to people who appear in the image captured by the imaging device 2 that visit the predetermined area, and outputs the estimated information relating to people who visit the predetermined area. In this way, the information processing device 1 can reduce the load when analyzing the flow of people appearing in the image captured.

[0067] Furthermore, this invention will make it possible to contribute to Goal 9 of the United Nations-led Sustainable Development Goals (SDGs), "Build resilient infrastructure, promote inclusive and sustainable industrialization and foster innovation."

[0068] Although the present invention has been described above using embodiments, the technical scope of the present invention is not limited to the scope described in the above embodiments, and various modifications and changes are possible within the scope of its gist. For example, all or part of the apparatus can be configured by functionally or physically distributing and integrating in any unit. Furthermore, new embodiments resulting from any combination of multiple embodiments are also included in the embodiments of the present invention. The effects of the new embodiments resulting from the combinations are combined with the effects of the original embodiments. [Explanation of symbols]

[0069] 1. Information Processing Device 2. Imaging device 11 Communications Department 12 Storage section 13 Control Unit 131 Specific part 132 Acquisition Department 133 Estimation Department 134 Output section

Claims

1. A identifying unit that identifies means for determining the proportion of multiple people appearing in the captured image captured by the imaging device that visit the predetermined area, based on the positional relationship between the imaging area captured by the imaging device and a predetermined area within a predetermined range from the imaging area, An estimation unit estimates information relating to persons visiting the predetermined area, which is captured in the image captured by the imaging device, based on the means identified by the identification unit, and which includes the number of visitors to the predetermined area, corresponding to multiple persons captured in the image captured by the imaging device. An output unit that outputs information relating to a person who will visit the predetermined area estimated by the estimation unit, An information processing device having

2. There are multiple designated areas. The identifying unit identifies the means for each of the plurality of predetermined areas of a plurality of persons that appear in the captured image captured by the imaging device. The information processing apparatus according to claim 1.

3. The identifying unit identifies the means based on the distance between the imaging area and the predetermined area. The information processing apparatus according to claim 1.

4. The identifying unit further identifies the means based on the arrangement of pathways for people to walk in the vicinity of the imaging area and the predetermined area. The information processing apparatus according to claim 1.

5. The identifying unit further identifies the means based on at least one of the orientation of the person in the captured image and the position of the person in the captured image in the captured image. The information processing apparatus according to claim 1.

6. The identifying unit further identifies the means based on attributes that have been pre-assigned to the predetermined area, which indicate the number of visitors to the predetermined area. The information processing apparatus according to claim 1.

7. The identifying unit identifies the means based on the number of visitors to the predetermined area corresponding to at least one of the weather and temperature of the predetermined area and the area including the imaging device, and the time of day. The estimation unit estimates information relating to a person visiting the predetermined area, corresponding to at least one of the weather and temperature of the predetermined area and the area including the imaging device at the time the image was captured, and the time of day, based on the means. The information processing apparatus according to claim 1.

8. The identifying unit acquires actual values ​​of the number of visits to the predetermined area by multiple people shown in the image captured by the imaging device, and identifies the means based on the acquired actual values. The information processing apparatus according to claim 1.

9. Multiple imaging devices exist, The specified unit specifies the means for each of the plurality of imaging devices, The estimation unit estimates the number of visitors to the predetermined area based on the number of people appearing in the captured images taken by each of the multiple imaging devices and the means of each of the multiple imaging devices identified by the identification unit. The information processing apparatus according to claim 1.

10. The identification unit identifies the overlap ratio, which is the percentage of a person that appears in the images of at least two of the multiple imaging devices, based on the positional relationship of the multiple imaging devices. The estimation unit further estimates the number of visitors to the predetermined area based on the overlap ratio. The information processing apparatus according to claim 9.

11. The identifying unit identifies the means for determining the proportion of persons corresponding to predetermined attributes who visit the predetermined area among a plurality of persons appearing in the captured image captured by the imaging device, The estimation unit estimates, based on the means, information relating to a person with predetermined attributes who visits the predetermined area, as captured in the image captured by the imaging device. The information processing apparatus according to claim 1.

12. The identifying unit identifies the means for identifying the attributes of a person who visits the predetermined area from among a plurality of people who appear in the captured image captured by the imaging device, Based on the means, the estimation unit estimates the attributes of the person visiting the predetermined area as information relating to the person visiting the predetermined area as captured image captured by the imaging device. The information processing apparatus according to claim 1.

13. The specified unit identifies the means for determining the proportion of multiple people appearing in the captured image captured by the imaging device that are staying in the predetermined area. The estimation unit estimates the number of people staying in the predetermined area, as shown in the image captured by the imaging device, based on the number of people appearing in the image captured by the imaging device and the means identified by the identification unit. The information processing apparatus according to claim 1.

14. A step of identifying means for determining the proportion of multiple people appearing in the captured image captured by the imaging device that visit the predetermined area, based on the positional relationship between the imaging area captured by the imaging device and a predetermined area within a predetermined range from the imaging area; Based on the identified means, the step of estimating information relating to persons visiting the predetermined area, which are captured in the image captured by the imaging device, and which includes the number of visitors to the predetermined area, corresponding to multiple persons captured in the image captured by the imaging device; The steps include outputting information relating to a person who is estimated to visit the predetermined area, An information processing method having

Images