Information processing device and viewing analysis system

Abstract

An information processing device capable of analyzing the attributes of viewers of advertising media while suppressing the processing load is provided. [Solution] The information processing device includes an image acquisition unit that acquires an image of a shooting range in which advertising media can be viewed, and a control unit that analyzes the attributes of multiple viewers from images of the viewers included in an area image selected from the image, and reflects the results of the analysis in the shooting range, thereby estimating the distribution of attributes for viewers included in the shooting range.

Description

[Technical Field]

[0001] The present disclosure relates to an information processing device and an audience analysis system. [Background technology]

[0002] In order to install advertising media in places where many people pass by and operate them efficiently, it is desirable to know the number of viewers and their attributes.

[0003] Patent document 1 discloses a technology for generating statistical analysis information showing the effectiveness of an advertising medium by using a first camera for measuring the number of visitors in an area near the advertising medium and a second camera for analyzing the number of viewers of the advertising medium, the gender and age of the viewers. [Prior art documents] [Patent documents]

[0004] [Patent Document 1] Japanese Patent Application Laid-Open No. 2011-233119 Summary of the Invention [Problem to be solved by the invention]

[0005] The technology disclosed in Patent Document 1 analyzes the effectiveness of advertising media by comparing the number of visitors measured from captured images taken by a first camera with the number of viewers and viewer attributes measured from captured images taken by a second camera. Therefore, the technology disclosed in Patent Document 1 requires image processing to be performed on the captured images taken by the first camera and the captured images taken by the second camera. Furthermore, the technology disclosed in Patent Document 1 requires appropriate adjustment of the capture range of the first camera and the capture range of the second camera. Therefore, an object of the present invention is to provide an information processing device and a viewer analysis system that can analyze the attributes of viewers of advertising media while reducing processing load. [Means for solving the problem]

[0006] An information processing device according to one embodiment of the present disclosure includes an image acquisition unit that acquires an image of a shooting range in which advertising media can be viewed, and a control unit that analyzes the attributes of multiple viewers from images of the viewers included in an area image selected from the image, and reflects the results of the analysis in the shooting range, thereby estimating the distribution of attributes of viewers included in the shooting range.

[0007] An audience analysis system according to an embodiment of the present disclosure includes a camera that captures an image of a shooting range in which advertising media can be viewed, and an information processing device, wherein the information processing device includes an image acquisition unit that acquires an image of the shooting range from the camera, and a control unit that analyzes attributes of multiple viewers from images of the multiple viewers included in an area image selected from the image, and reflects the results of the analysis in the shooting range to estimate a distribution of attributes of viewers included in the shooting range. Equipped with. [Brief explanation of the drawings]

[0008] [Figure 1] FIG. 1 illustrates an example of a viewing analysis system. [Figure 2] FIG. 1 is a block diagram illustrating an example of a configuration of an information processing device. [Figure 3] 5 is a flowchart illustrating an example of an operation of the information processing device according to the first embodiment. [Figure 4] 4 is a flowchart illustrating an example of the operation of the information processing device following FIG. 3. [Figure 5] FIG. 10 is a diagram showing an example of nine regions into which a shooting range is divided in the audience analysis system. [Figure 6] FIG. 6 is a diagram showing an example of the imaging range illustrated in FIG. 5. [Figure 7] FIG. 10 is a diagram showing an example of weights assigned according to the number of people represented by area images showing each area. [Figure 8] 10A and 10B are diagrams showing an example of the results of counting the number of people included in the shooting range and the number of viewers included in the shooting range 104 in time series. [Figure 9] FIG. 10 is a diagram showing an example of the results of chronologically tallying the number of people included in the shooting range at each time and the number of viewers included in the shooting range at each time. [Figure 10] FIG. 10 is a diagram showing an example of the age distribution of viewers included in a shooting range. [Figure 11] FIG. 10 is a diagram showing an example of the gender distribution of viewers included in a shooting range. [Figure 12] 10 is a flowchart illustrating an example of an operation of the information processing device according to the second embodiment. [Figure 13] 13 is a flowchart illustrating an example of the operation of the information processing device 102, following FIG. 12. [Figure 14] 10 is a flowchart showing an example of the operation of the information processing device 102 according to the third embodiment. DETAILED DESCRIPTION OF THE INVENTION

[0009] (First embodiment) The first embodiment will be described with reference to Figures 1 to 11. In the drawings, the same or similar elements are denoted by the same reference numerals, and redundant explanations will be omitted.

[0010] 1 is a diagram showing an example of an audience analysis system 100. The audience analysis system 100 includes a shooting device 101 and an information processing device .

[0011] The camera device 101 captures a capture range 104 in which the advertising medium 103 can be viewed. Specifically, the camera device 101 transmits an image 211 (see FIG. 2) of the captured capture range 104 to the information processing device 102 via a network. For example, the camera device 101 is attached to the advertising medium 103 so as to be able to capture the range in which the advertising medium 103 can be viewed. FIG. 1 shows a state in which the camera device 101 is attached to the top of the advertising medium 103. The advertising medium 103 is installed in a place where multiple people pass by. For example, the advertising medium 103 is a digital signage.

[0012] The information processing device 102 acquires the image 211 from the image capturing device 101 and analyzes the image 211 by image processing to estimate the distribution of attributes of viewers included in the capturing range 104. For example, the information processing device 102 is a PC (Personal Computer).

[0013] 2 is a block diagram showing an example of the configuration of the information processing device 102. The information processing device 102 includes a communication unit 201, a storage unit 202, an image acquisition unit 203, and a control unit 204.

[0014] The communication unit 201 is an interface that connects to a network and receives, from the image capturing device 101, an image 211 captured by the image capturing device 101.

[0015] The storage unit 202 is a storage medium capable of storing programs, various data, etc. The storage unit 202 is configured by one or more Read Only Memories (ROMs), one or more Random Access Memories (RAMs), one or more Hard Disk Drives (HDDs), or a combination of these.

[0016] The control unit 204 executes various processes in accordance with the programs stored in the storage unit 202. For example, the control unit 204 is configured by one or more processors such as a CPU (Central Processing Unit).

[0017] The image acquisition unit 203 acquires an image 211 from the image capturing device 101 .

[0018] The control unit 204 selects a region image that is a part of the image 211, and analyzes the attributes of the multiple viewers included in the selected region image from the images of the multiple viewers included in the region image selected from the image 211. In the following description, the region image in which the attributes of the multiple viewers are analyzed is referred to as a specific region.

[0019] For example, the specific region indicates the region with the largest number of human images among the multiple regions obtained by dividing the image 211. As a result, the control unit 204 analyzes the attributes of the multiple viewers for the images of the multiple viewers indicated by the region with the largest number of people among the multiple regions obtained by dividing the image 211. In other words, the control unit 204 analyzes the attributes of the multiple viewers for the multiple viewers in the range with the largest number of people among the multiple ranges obtained by dividing the shooting range 104. For example, the attributes indicated by the analysis result indicate at least one of the viewer's gender and age.

[0020] The control unit 204 estimates the distribution of attributes of the viewers included in the shooting range 104 by reflecting the results of the analysis in the shooting range 104. That is, the control unit 204 estimates the distribution of attributes of the viewers included in the shooting range 104 by reflecting the distribution of attributes of the viewers included in the shooting range 104 in the range with the largest number of viewers among the ranges obtained by dividing the shooting range 104 into multiple ranges. The process of making this estimation includes a process of reflecting the results of the analysis in the shooting range 104 according to a first ratio, which is the ratio of the number of people indicated by the specific area to the number of people indicated by the image 211. That is, the control unit 204 estimates the distribution of attributes of the viewers included in the shooting range 104 by reflecting the results of the analysis in the shooting range 104 according to the first ratio.

[0021] FIG. 3 is a flowchart showing an example of the operation of the information processing device 102 according to this embodiment.

[0022] In step S301, the control unit 204 sets the coordinates of a plurality of regions. For example, when the control unit 204 divides the image 211 into a grid, the control unit 204 sets the vertices of a rectangle that is each of the plurality of regions. For example, when the control unit 204 divides the image 211 into nine grid-like regions, the set coordinates indicate the vertices of the rectangles obtained by dividing the image 211 into 3x3 regions.

[0023] In step S302, the image acquisition unit 203 acquires the image 211 from the image capturing device 101. For example, the image acquisition unit 203 transmits a signal to the image capturing device 101 instructing it to capture an image. The image capturing device 101 executes a capturing process in response to the instruction from the image acquisition unit 203 and acquires the image 211. Then, the image capturing device 101 transmits the image 211 to the information processing device 102.

[0024] In step S303, the control unit 204 extracts an area from the multiple areas obtained by dividing the image 211 acquired in step S302, based on the coordinates set in step S301. The extracted area indicates one area of ​​the image 211 indicated by the coordinates set in step S301.

[0025] In step S304, the control unit 204 identifies the number of people represented by the area extracted in step S303 from the image of people included in the area. Specifically, the control unit 204 extracts all face areas from the extracted area by image processing. For example, the control unit 204 detects feature points representing the eyes, nose, etc. from the extracted area and extracts face areas based on the detected feature points. The control unit 204 then determines the number of extracted face areas as the number of people represented by the extracted area.

[0026] In step S305, the control unit 204 determines whether the number of people has been identified for all regions. If the number of people has not been identified for all regions in step S305, the control unit 204 returns the process to step S303 and extracts a new region from the image 211. On the other hand, if the number of people has been identified for all regions in step S305, the control unit 204 proceeds to step S401 illustrated in FIG. 4.

[0027] FIG. 4 is a flowchart showing an example of the operation of the information processing device 102 following FIG.

[0028] In step S401, the control unit 204 identifies a specific area from the multiple areas determined based on the coordinates set in step S301 illustrated in Fig. 3, based on the number of people represented by the multiple areas extracted in step S304 illustrated in Fig. 3. For example, the control unit 204 identifies the area with the largest number of people among the multiple areas as the specific area. Note that if there are multiple areas with the largest number of people among the number of people in the multiple areas, for example, the control unit 204 identifies the area relatively close to the center as the specific area.

[0029] In step S402, the control unit 204 identifies the number of viewers indicated by the specific region identified in step S401. The viewers are people who are viewing the advertising medium 103. Specifically, the control unit 204 detects a face region from the specific region. The control unit 204 estimates the face direction from the detected face region. For example, the control unit 204 estimates the face direction from the relative positional relationship of feature points indicating the eyes, nose, etc. included in the detected face region.

[0030] When the face direction estimated from the detected face area is the direction of the advertisement displayed by the advertising medium 103, the control unit 204 determines that the person indicated by the face area is a viewer. For example, assume that the image capturing device 101 faces in the front direction of the advertisement displayed by the advertising medium 103. In this case, when the face direction estimated from the detected face area is the front face direction, the control unit 204 determines that the person indicated by the face area is a viewer.

[0031] In step S403, the control unit 204 analyzes the number of viewers indicated by the specific region and the attributes of the viewers. Specifically, for all face regions included in the specific region, the control unit 204 determines whether the people indicated by the face regions are viewers. In this way, the control unit 204 identifies the number of viewers indicated by the specific region. Furthermore, the control unit 204 analyzes the attributes of the viewers by performing image processing on the images of the viewers indicated by the specific region. The attributes indicate at least one of gender and age.

[0032] For example, it is assumed that the storage unit 202 stores a discrimination model configured from feature amounts for each attribute. The feature amounts for each attribute indicate, for example, feature amounts for each gender and feature amounts for each age group. For example, the discrimination model is generated by learning feature amounts extracted from a plurality of face images that are training images through machine learning using a support vector machine (SVM) or the like. For example, the storage unit 202 stores a plurality of discrimination models according to the type of attribute. For example, the storage unit 202 may store a discrimination model configured from feature amounts for each gender and a discrimination model configured from feature amounts for each age group. Note that the discrimination models may be registered in a server device with which the information processing device 102 can communicate.

[0033] The control unit 204 extracts features for identifying attributes from the face region of the viewer identified in step S402. The control unit 204 inputs the extracted features into an identification model to identify the attributes of the viewer having the extracted features. Alternatively, the control unit 204 compares the extracted features with features for each attribute that constitute the identification model to identify the attributes of the viewer having the extracted features.

[0034] In step S404, the control unit 204 estimates the number of viewers represented by the entire area and the distribution of viewer attributes from the analysis result for the specific area. That is, the control unit 204 estimates the number of viewers included in the shooting range 104 and the distribution of viewer attributes from the analysis result for the specific area.

[0035] Specifically, the control unit 204 calculates the number of viewers included in the shooting range 104 by reflecting the number of viewers indicated by the specific area in the shooting range 104 according to the first ratio. The first ratio is the ratio of the number of people indicated by the specific area to the number of people indicated by the image 211. Furthermore, the control unit 204 estimates the distribution of attributes of viewers included in the shooting range 104 by reflecting the results of the analysis of the specific area in the shooting range 104 according to the first ratio. For example, the control unit 204 estimates the distribution of gender, age, etc. of all viewers included in the shooting range 104 from the results of the analysis of the specific area.

[0036] Alternatively, the control unit 204 may assign a weight to each area according to the number of people represented by each area. In this case, the control unit 204 calculates the first ratio from the ratio of the weight assigned to the specific area to the total weight assigned to each area.

[0037] As described above, the viewing analysis system 100 according to this embodiment does not use multiple cameras, and therefore does not need to adjust the shooting range 104 for the multiple cameras. Furthermore, when multiple cameras are used, image processing must be performed on multiple images. However, the viewing analysis system 100 according to this embodiment performs image processing only on the image 211 captured by one camera. Therefore, the viewing analysis system 100 according to this embodiment can estimate the number of viewers included in the shooting range 104 and the distribution of viewer attributes from the image 211 captured by one imaging device 101 with less processing load than a system that uses multiple cameras. Therefore, the viewing analysis system 100 according to this embodiment can analyze the viewer attributes of the advertising medium 103 with less processing load.

[0038] For example, when analyzing the attributes of viewers within a predetermined range, the control unit 204 may analyze the attributes of viewers within a range with a relatively small number of viewers. In this case, even if the control unit 204 reflects the results of the analysis in the shooting range 104, the distribution of the estimated viewer attributes may not appropriately represent the distribution of the attributes of viewers within the shooting range 104. In this case, the user cannot appropriately analyze the advertising effectiveness from the distribution of the estimated viewer attributes.

[0039] However, the audience analysis system 100 according to this embodiment identifies a specific area from the image 211 based on the number of people represented by each of a plurality of areas, and analyzes the attributes of the viewers represented by the specific area. Therefore, the audience analysis system 100 according to this embodiment can improve the accuracy of estimating the attributes of viewers compared to analyzing the attributes of viewers included in a predetermined range.

[0040] In step S405, the control unit 204 stores the estimation results for the attributes of viewers in all regions in chronological order in the storage unit 202. Specifically, the control unit 204 associates information indicating the date and time with the estimation results for the attributes of viewers in all regions and stores them in the storage unit 202.

[0041] In step S406, the control unit 204 determines whether a predetermined time has passed since the image 211 was acquired. If the predetermined time has passed since the image 211 was acquired in step S406, the control unit 204 returns the process to step S302 illustrated in FIG. 3 and continues the process. As a result, the control unit 204 determines the range indicated by the specific area every predetermined time. This allows the audience analysis system 100 according to the present embodiment to identify the specific area indicating the area with the most people, according to the movement of people in the shooting range 104. As a result, the audience analysis system 100 according to the present embodiment can analyze the attributes of viewers included in the area with the most people in the shooting range 104, according to the movement of people in the shooting range 104.

[0042] On the other hand, if it is determined in step S406 that a predetermined time has not elapsed since the image 211 was acquired, the control unit 204 determines in step S407 whether or not to end the process of estimating the distribution of viewer attributes. If it is not determined in step S407 that the process of estimating the distribution of viewer attributes should be ended, the control unit 204 returns the process to step S406. On the other hand, if it is determined in step S407 that the process of estimating the distribution of viewer attributes should be ended, the control unit 204 ends the process of estimating the distribution of viewer attributes.

[0043] Fig. 5 is a diagram showing an example of nine ranges obtained by dividing the imaging range 104. Specifically, Fig. 5 shows an example of nine ranges obtained by dividing the imaging range 104 into ranges X1, X2, and X3 in the X direction and ranges YA, YB, and YC in the Y direction. In the following description, the ranges obtained by dividing the imaging range 104 will be expressed as (x, y). x indicates the range divided in the X direction, and y indicates the range divided in the Y direction. For example, (X1, YA) indicates the range X1 in the X direction and the range YA in the Y direction.

[0044] Fig. 6 is a diagram showing a model of a person's image. The person's image shown in Fig. 6 is a model of a person included in the image 211 showing the shooting range 104 shown in Fig. 5. For example, the area showing the range (X3, YC) includes five people's images. Also, for example, the area showing the range (X1, YC) includes two people's images.

[0045] Fig. 7 is a diagram showing an example of weights assigned to multiple regions obtained by dividing image 211 showing shooting range 104 shown in Fig. 5, according to the number of people shown in each region. In the weights shown in Fig. 7, a weight of 1 is assigned to one person included in a region. For example, the region showing the range (X3, YC) includes the images of five people, so a weight of 5 is assigned to the region showing the range (X3, YC). Also, for example, the region showing the range (X1, YA) includes the images of two people, so a weight of 2 is assigned to the region showing the range (X1, YA). A weight of 24 (= 2 + 4 + 1 + 3 + 4 + 2 + 2 + 1 + 5), which is the sum of the weights assigned to each region, is assigned to the entire region showing shooting range 104.

[0046] 4, the control unit 204 identifies the area with the largest number of people among the extracted multiple areas as the specific area. In this case, since the area indicating the range of (X3, YC) is the area with the largest number of people, the control unit 204 identifies the area indicating the range of (X3, YC) as the specific area.

[0047] Then, in step S403, the control unit 204 analyzes the attributes of the viewers indicated by the specific region (X3, YC). For example, in step S403 illustrated in Fig. 4, the control unit 204 analyzes the images of people included in the specific region and determines that the number of viewers is four. Furthermore, in step S403, the control unit 204 estimates that the viewers indicated by the specific region indicating the range (X3, YC) are two men and two women.

[0048] In this case, in step S404 illustrated in FIG. 4, the control unit 204 estimates the number of viewers included in the shooting range 104 and the distribution of viewer attributes from the ratio of the weight (=5) assigned to the specific region to the total weight (=24) assigned to each region. Specifically, the control unit 204 reflects the ratio of the weight (=5) assigned to the specific region to the total weight (=24) assigned to each region in the viewers (=4) for the specific region, thereby estimating the number of viewers included in the shooting range 104 to be 19.2 (=24 / 5×4=19.2). Furthermore, the control unit 204 reflects the ratio of the weight (=5) assigned to the specific region to the total weight (=24) assigned to each region in the distribution of viewer attributes for the specific region. As a result, for example, the control unit 204 estimates that the number of men included in the shooting range 104 is 9.6 (=24 / 5×2) and the number of women included in the shooting range 104 is 9.6 (=24 / 5×2).

[0049] 8 and 9 are diagrams showing an example of a chronological count result of the number of people included in the shooting range 104 and the estimated number of viewers included in the shooting range 104. Fig. 8 is a diagram showing an example of a chronological count result of the number of people included in the shooting range 104 and the estimated number of viewers included in the shooting range 104 from March 19th to April 17th. Fig. 9 is a diagram showing an example of a chronological count result of the number of people included in the shooting range 104 at each time and the estimated number of viewers included in the shooting range 104 at each time from midnight to 11pm from March 19th to April 17th.

[0050] 10 and 11 are diagrams showing an example of the distribution of the attributes of the estimated viewers included in the shooting range 104. Fig. 10 is a diagram showing an example of the distribution of the ages of the estimated viewers included in the shooting range 104 from March 19th to April 17th. Fig. 11 is a diagram showing an example of the distribution of the genders of the estimated viewers included in the shooting range 104 from March 19th to April 17th.

[0051] For example, in step S405, for the period from March 19 to April 17, the control unit 204 associates the date and time with the estimation result for the shooting range 104 and stores the result in the storage unit 202. Then, when the communication unit 201 receives a signal instructing the communication unit 201 to transmit the estimation result, the control unit 204 executes processing to cause the communication unit 201 to transmit the estimation result stored in the storage unit 202 to the sender of the signal. Then, the terminal that received the estimation result displays the tabulated result exemplified in FIG. 8 on its display screen. Alternatively, the terminal that received the estimation result may display the tabulated result shown in FIG. 9 on its display screen. In this way, the viewing analysis system 100 can present the user with the tabulated result of the estimated number of viewers in chronological order.

[0052] (Variation) As a modified example of the audience analysis system 100 according to this embodiment, the information processing device 102 may store the estimation result for the shooting range 104 in association with the content of the advertising medium 103. For example, if the advertising medium 103 is digital signage, the control unit 204 acquires the image 211 and the advertising image presented by the advertising medium 103 when the image 211 was captured. This allows the audience analysis system 100 to allow the user to analyze the association between the content of the advertisement shown by the advertising medium 103 and the viewer attributes.

[0053] Second Embodiment The second embodiment will be described with reference to Figures 12 and 13. In the drawings, the same or similar elements are denoted by the same reference numerals, and duplicated explanations will be omitted. Configurations and processes having substantially the same functions as those of other embodiments will be denoted by the same reference numerals, and explanations will be omitted, and differences from other embodiments will be described.

[0054] The control unit 204 according to this embodiment selects a specific area indicating the area with the largest number of viewer images from among the multiple areas obtained by dividing the image 211. Then, the control unit 204 analyzes the attributes of the multiple viewers indicated by the specific area from the multiple viewer images included in the specific area selected from the image 211. In this way, the control unit 204 analyzes the attributes of the viewers in the range with the largest number of viewers from among the multiple ranges obtained by dividing the shooting range 104.

[0055] The control unit 204 estimates the distribution of attributes of viewers included in the shooting range 104 by reflecting the results of the analysis of the specific area in the shooting range 104. Specifically, the estimation process according to this embodiment includes a process of reflecting the results of the analysis of the specific area in the shooting range 104 according to a second ratio, which is the ratio of the number of viewers indicated by the specific area to the number of viewers indicated by the image 211. In other words, the control unit 204 estimates the distribution of attributes of viewers included in the shooting range 104 by reflecting the results of the analysis of the specific area in the shooting range 104 according to the second ratio.

[0056] 12 is a flowchart showing an example of the operation of the information processing device 102 according to this embodiment. The processes of steps S1201 to S1203 are the same as the processes of steps S301 to S303 shown in FIG. 3, and therefore detailed description thereof will be omitted.

[0057] In step S1204, control unit 204 identifies the number of viewers represented by the region extracted in step S1203, based on the images of viewers included in that region. That is, through the processes of steps S1203 and S1204, control unit 204 calculates the number of viewers represented by each region, based on the images of viewers included in each of the multiple regions. The process of identifying the number of viewers is the same as step S403 illustrated in Fig. 4, and therefore a detailed description thereof will be omitted.

[0058] In step S1205, the control unit 204 determines whether the number of viewers has been determined for all regions. If the number of viewers has not been determined for all regions in step S1205, the control unit 204 returns the process to step S1203. On the other hand, if the number of viewers has been determined for all regions in step S1205, the control unit 204 proceeds to step S1301 illustrated in FIG. 13.

[0059] FIG. 13 is a flowchart showing an example of the operation of the information processing device 102 following FIG.

[0060] In step S1301, the control unit 204 identifies a specific area from the multiple areas based on the number of viewers indicated by the multiple areas extracted in step S1204 illustrated in Fig. 12. For example, the control unit 204 identifies the area with the largest number of viewers among the number of viewers indicated by the multiple extracted areas as the specific area. Note that if two or more areas indicate the largest number of viewers, for example, the control unit 204 identifies, from the two or more areas, the area that is relatively close to the center of the image 211 as the specific area.

[0061] In step S1302, the control unit 204 analyzes the attributes of the viewer indicated by the specific region. The process of step S1302 is similar to the process of step S403 exemplified in FIG.

[0062] In step S1303, the control unit 204 estimates the distribution of viewer attributes represented by the entire area from the analysis result of the specific area. That is, the control unit 204 estimates the distribution of viewer attributes included in the shooting range 104 from the analysis result of the specific area.

[0063] Specifically, the control unit 204 estimates the distribution of attributes of viewers included in the shooting range 104 by reflecting the results of the analysis of the specific region in the shooting range 104 according to the second ratio. The second ratio is the ratio of the number of viewers indicated by the specific region to the number of viewers indicated by the image 211. Note that the control unit 204 may assign a weight to each region according to the number of viewers indicated by each region. In this case, the control unit 204 calculates the second ratio from the ratio of the weight assigned to the specific region to the total of the weights assigned to each region.

[0064] Then, the control unit 204 moves the process to step S1304. The processes of steps S1304 to S1306 are the same as the processes of steps S405 to S407 illustrated in FIG.

[0065] For example, suppose that Fig. 7 shows an example of weights assigned according to the number of viewers indicated by each area, instead of weights assigned according to the number of people indicated by each area. Furthermore, in the weights exemplified in Fig. 7, a weight of 1 is assigned to the image of one viewer included in an area. For example, if an area indicating a range (X3, YC) includes images of five viewers, a weight of 5 is assigned to the area indicating the range (X3, YC). Furthermore, for example, if an area indicating a range (X1, YA) includes images of two viewers, a weight of 2 is assigned to the area indicating the range (X1, YA). For example, if 24 viewers are included in the shooting range 104, a weight of 24 is assigned to the entire area indicating the shooting range 104.

[0066] For example, suppose that the control unit 204 identifies the area indicating the range of (X3, YC) as the specific area in step S1301 illustrated in Fig. 13. In this case, the control unit 204 analyzes the attributes of the viewers indicated by the specific area indicating the range of (X3, YC) in step S1302 illustrated in Fig. 13. Here, suppose that the viewers indicated by the specific area indicating the range of (X3, YC) are estimated to be three men and two women in step S1302.

[0067] 13, the control unit 204 estimates the distribution of viewer attributes included in the shooting range 104 from the ratio of the weight (=5) assigned to the specific area to the total weight (=24) assigned to each area. Specifically, the control unit 204 reflects the ratio of the weight (=5) assigned to the specific area to the total weight (=24) assigned to each area in the distribution of viewer attributes for the specific area. As a result, for example, the control unit 204 estimates that there are 14.4 men (=24 / 5×3) and 9.6 women (=24 / 5×2) included in the shooting range 104.

[0068] As described above, the information processing device 102 according to this embodiment estimates the distribution of attributes of viewers included in the shooting range 104 by reflecting the distribution of viewer attributes in the range with the largest number of viewers among the multiple ranges obtained by dividing the shooting range 104 into the shooting range 104. As a result, the audience analysis system 100 according to this embodiment can more appropriately analyze the effectiveness of the advertising medium 103 by identifying a specific area based on the number of viewers.

[0069] (Variation) As a modified example of the audience analysis system 100 according to the present embodiment, the information processing device 102 may estimate the distribution of viewer attributes included in the shooting range 104 from a third ratio, which is the ratio of the number of viewers indicated by the specific area to the number of people indicated by the specific area. Specifically, in the information processing device 102 according to this modified example, the process of making this estimation may include a process of reflecting the results of the analysis of the specific area in each area according to the third ratio. That is, in the information processing device 102 according to this modified example, the control unit 204 estimates the distribution of viewer attributes for the shooting range 104 by reflecting the results of the analysis of the specific area in each area according to the third ratio. As described above, the audience analysis system 100 according to this modified example can estimate the distribution of viewer attributes for the shooting range 104 using the ratio of the number of viewers included in the specific area to the number of people included in the specific area.

[0070] (Third embodiment) The third embodiment will be described with reference to Fig. 14. In the drawings, the same or similar elements are denoted by the same reference numerals, and redundant explanations will be omitted. Configurations and processes having substantially the same functions as those of other embodiments will be denoted by the same reference numerals, and explanations will be omitted, and differences from other embodiments will be described.

[0071] The control unit 204 according to this embodiment calculates the number of subjects represented by each of the multiple regions based on the positions of the images of the subjects included in the image 211. The subjects are people or viewers.

[0072] When the subject is a person, the control unit 204 according to this embodiment calculates the number of people represented by each of the multiple areas based on the positions of the images of people included in the image 211. In this case, the specific area indicates the area among the multiple areas with the largest calculated number of people.

[0073] Alternatively, if the target persons are viewers, the control unit 204 according to this embodiment calculates the number of viewers indicated by each of the multiple regions based on the positions of the viewer images included in the image 211. The specific region indicates the region among the multiple regions that has the largest calculated number of viewers.

[0074] 14 is a flowchart showing an example of the operation of the information processing device 102 according to this embodiment. The processing in steps S1401 to S1402 is the same as the processing in steps S301 to S302 shown in FIG. 3, and therefore detailed description thereof will be omitted.

[0075] In step S1403, the control unit 204 identifies the position of the image of the subject included in the image 211 acquired in step S1402.

[0076] For example, assume that the subject is a person included in the shooting range 104. In this case, for example, the position of the subject's image is the position of the person's facial area included in the image 211. In this case, the control unit 204 extracts all human facial areas from the image 211 by image processing. The process of extracting human facial areas from the image 211 is similar to the process in step S304 exemplified in FIG. 3, and therefore a detailed description thereof will be omitted. Then, the control unit 204 specifies the position of the subject's image included in the image 211 by extracting the human facial area from the image 211.

[0077] Alternatively, the subject may be a viewer included in the shooting range 104. In that case, for example, the position of the image of the subject is the position of the face area of ​​the viewer included in the image 211. In that case, the control unit 204 extracts the face areas of all the viewers from the image 211 by image processing. The process of extracting the face areas of the viewers from the image 211 is similar to the process in step S402 exemplified in FIG. 4, and therefore a detailed description thereof will be omitted. Then, the control unit 204 specifies the position of the image of the subject included in the image 211 by extracting the face areas of the viewers from the image 211.

[0078] In step S1404, the control unit 204 divides the image 211 into a plurality of regions based on the coordinates set in step S1401.

[0079] In step S1405, the control unit 204 identifies the number of subjects represented by each of the multiple regions based on the positions of the images of the subjects identified in step S1403. Then, the control unit 204 proceeds to step S401 illustrated in FIG.

[0080] As described above, the audience analysis system 100 according to this embodiment identifies the positions of the images of the target persons and then divides the image 211 into a plurality of regions. Therefore, the audience analysis system 100 according to this embodiment identifies the number of target persons represented by each of the plurality of regions without extracting the image of the target person individually for each of the plurality of regions. This allows the audience analysis system 100 according to this embodiment to efficiently identify the number of target persons represented by each of the plurality of regions.

[0081] The processes executed in the above embodiments are not limited to the processing modes exemplified in the above embodiments. The above-described functional blocks may be realized using either a logic circuit (hardware) formed in an integrated circuit or the like, or software using a CPU. The processes executed in the above embodiments may be executed by multiple computers. For example, some of the processes executed by the control unit 204 may be executed by another computer, or all of the processes may be shared and executed by multiple computers.

[0082] The present disclosure is not limited to the above-described embodiments, and may be replaced with a configuration that is substantially the same as the configuration shown in the above-described embodiments, a configuration that achieves the same effect, or a configuration that can achieve the same purpose. The present disclosure also includes within its technical scope embodiments obtained by appropriately combining the technical means disclosed in different embodiments. Furthermore, new technical features can be formed by combining the technical means disclosed in each embodiment. [Explanation of symbols]

[0083] 100 Viewing analysis system, 101 Filming device, 102 Information processing device, 103 Advertising medium, 104 Filming range, 201 Communication unit, 202 Storage unit, 203 Image acquisition unit, 204 Control unit, 211 Image

Claims

1. an image acquisition unit that acquires an image of a shooting range in which the advertising medium can be viewed; a control unit that analyzes attributes of a plurality of viewers from images of the viewers included in a region image selected from the image, and reflects the results of the analysis in the shooting range, thereby estimating a distribution of attributes of the viewers included in the shooting range; Equipped with Information processing device.

2. The region image indicates the region with the largest number of human figures among the plurality of regions into which the image is divided. The information processing device according to claim 1 .

3. the control unit calculates the number of people represented by each of a plurality of regions into which the image is divided, based on positions of people included in the image; The region image indicates the region among the plurality of regions where the calculated number of people is the largest. The information processing device according to claim 1 .

4. The estimation includes a process of reflecting the result in the photographing range in accordance with a first ratio, which is a ratio of the number of people shown in the area image to the number of people shown in the image.

4. The information processing device according to claim 2 or 3.

5. The control unit executes a process of calculating the number of viewers included in the shooting range by reflecting the number of the viewers in the shooting range according to the first ratio. The information processing device according to claim 4 .

6. The region image indicates the region with the largest number of viewer images among the plurality of regions into which the image is divided. The information processing device according to claim 1 .

7. the control unit calculates the number of viewers represented by each of a plurality of regions into which the image is divided, based on positions of images of viewers included in the image; The region image indicates the region among the plurality of regions where the calculated number of viewers is the largest. The information processing device according to claim 1 .

8. The estimation includes a process of reflecting the result in the shooting range in accordance with a second ratio, which is a ratio of the number of the viewers to the number of viewers shown by the image.

8. The information processing device according to claim 6 or 7.

9. The estimation includes a process of reflecting the result in the shooting range in accordance with a third ratio, which is a ratio of the number of the viewers to the number of people shown in the area image.

8. The information processing device according to claim 6 or 7.

10. The attribute indicates at least one of gender and age. The information processing device according to claim 1 .

11. The control unit executes a process of determining a range indicated by the area image at predetermined time intervals. The information processing device according to claim 1 .

12. a photographing device that photographs a photographing range in which the advertising medium can be viewed; an information processing device; Including, The information processing device includes: an image acquisition unit that acquires an image of the imaging range from the imaging device; a control unit that analyzes attributes of a plurality of viewers from images of the viewers included in a region image selected from the image, and reflects the results of the analysis in the shooting range, thereby estimating a distribution of attributes of the viewers included in the shooting range; Equipped with Audience analysis system.

Images