Image analyzer, image analysis method, and program

Abstract

To utilize a result of analyzing an image.SOLUTION: An image analyzer 100 includes an analysis result acquisition part 110 and a counting part 111. The analysis result acquisition part 110 acquires analysis information being information obtained by analyzing a static image, the analysis information including an appearance attribute to which a person included in the static image belongs. The counting part 111 uses the analysis information to count, by each of appearance attributes, the number of persons belonging to an appearance attribute in the static image and generates count information showing the result of the counting by a unit of the static image.SELECTED DRAWING: Figure 1

Description

[Technical field]

[0001] The present invention relates to an image analysis device, an image analysis method, and a program. [Background technology]

[0002] Patent Document 1 discloses a surveillance system that counts the number of predetermined people from video captured by a surveillance camera.

[0003] Patent Document 2 discloses a human attribute estimation system that can be used to estimate the attributes of people in a real area.

[0004] This human attribute estimation system includes an information processing device and an AI estimation calculation unit. The information processing device described in Patent Document 2 extracts human feature information representing the appearance features of a person extracted from an image, and obtains human attribute information representing the attributes of a person who has the appearance features represented by the human feature information. The AI ​​estimation calculation unit described in Patent Document 2 uses the human feature information and the human attribute information for a person appearing in each of a plurality of images, learns the attributes of a person whose appearance features are represented in the human feature information according to a predetermined AI learning process, and estimates and calculates the human attribute information representing the person's attributes according to the predetermined AI estimation process.

[0005] Patent Document 3 describes a technology for calculating the feature amount of each of a plurality of key points of a human body included in an image, searching for images including human bodies with similar postures or movements based on the calculated feature amount, and classifying images with similar postures or movements together. Non-Patent Document 1 describes a technology related to human skeleton estimation. [Prior art documents] [Patent documents]

[0006] [Patent Document 1] JP 2020-086994 A [Patent Document 2] JP 2020-067720 A [Patent Document 3] International Publication No. 2021 / 084677 [Non-patent literature]

[0007] [Non-Patent Document 1] Zhe Cao, Tomas Simon, Shih-En Wei, Yaser Sheikh, [Realtime Multi-Person 2D Pose Estimation using Part Affinity Fields];, The IEEE Conference on Computer Vision and Pattern Recognition (CVPR), 2017, P. 7291-7299 Summary of the Invention [Problem to be solved by the invention]

[0008] However, Patent Document 1 does not disclose a method for utilizing human attributes obtained from each image constituting a video. Patent Document 2 does not disclose a method for utilizing human attribute information obtained from each image. Patent Document 3 and Non-Patent Document 1 also do not disclose a technology for utilizing the results of analyzing images.

[0009] In view of the above-mentioned problems, one example of an object of the present invention is to provide an image analysis device, an image analysis method, and a program that solve the problem of utilizing the results of analyzing an image. [Means for solving the problem]

[0010] According to one aspect of the present invention, An analysis result acquisition means for acquiring analysis information including appearance attributes of a person included in a still image, the analysis information being information obtained by analyzing the still image; a counting means for counting the number of people belonging to the appearance attribute in the still image for each of the appearance attributes using the analysis information, and generating count information indicating the counting result for each of the still images. An image analysis device is provided.

[0011] According to one aspect of the present invention, The computer Acquire analysis information obtained by analyzing a still image, the analysis information including appearance attributes to which a person included in the still image belongs; Using the analysis information, the number of people belonging to the appearance attribute in the still image is counted for each appearance attribute, and count information indicating the counting result is generated for each still image. A method for image analysis is provided.

[0012] According to one aspect of the present invention, On the computer, Acquire analysis information obtained by analyzing a still image, the analysis information including appearance attributes to which a person included in the still image belongs; A program is provided for using the analysis information to count the number of people in the still image that belong to the appearance attribute for each appearance attribute, and generating counting information indicating the counting results for each still image.

[0013] According to one aspect of the present invention, an analysis result acquisition means for acquiring analysis information including appearance attributes of each person included in the plurality of images, the analysis information being information obtained by analyzing the plurality of images; a counting means for counting the number of people belonging to the appearance attribute in the plurality of images for each appearance attribute using the analysis information, and generating count information indicating the counting result. An image analysis device is provided.

[0014] According to one aspect of the present invention, The computer acquiring analysis information including appearance attributes of each person included in the plurality of images, the analysis information being information obtained by analyzing the plurality of images; Using the analysis information, the number of people belonging to the appearance attribute in the plurality of images is counted for each appearance attribute, and count information indicating the counting result is generated. A method for image analysis is provided.

[0015] According to one aspect of the present invention, On the computer, acquiring analysis information including appearance attributes of each person included in the plurality of images, the analysis information being information obtained by analyzing the plurality of images; A program is provided for using the analysis information to count the number of people belonging to the appearance attribute in the multiple images for each appearance attribute, and generating count information indicating the counting results.

[0016] According to one aspect of the present invention, an analysis result acquisition means for acquiring analysis information including appearance attributes of each person included in the plurality of images, the analysis information being information obtained by analyzing the plurality of images; and a counting means for counting the number of people belonging to a combination of a plurality of appearance attributes using the analysis information and generating count information indicating the counting result. An image analysis device is provided.

[0017] According to one aspect of the present invention, The computer acquiring analysis information including appearance attributes of each person included in the plurality of images, the analysis information being information obtained by analyzing the plurality of images; Using the analysis information, the number of people belonging to a combination of a plurality of appearance attributes is counted, and count information indicating the counting result is generated. A method for image analysis is provided.

[0018] According to one aspect of the present invention, On the computer, acquiring analysis information including appearance attributes of each person included in the plurality of images, the analysis information being information obtained by analyzing the plurality of images; There is provided a program for counting the number of people belonging to a combination of a plurality of appearance attributes using the analysis information, and generating count information indicating the counting result. Effect of the Invention

[0019] According to one aspect of the present invention, it is possible to utilize the results of analyzing an image. [Brief description of the drawings]

[0020] [Figure 1] FIG. 1 is a diagram showing an overview of an image analysis device according to a first embodiment. [Diagram 2] FIG. 1 is a diagram showing an overview of an image analysis system according to a first embodiment. [Diagram 3] 5 is a flowchart showing an example of an image analysis process according to the first embodiment. [Figure 4] FIG. 2 is a diagram illustrating a detailed example of the configuration of the image analysis system according to the first embodiment. [Diagram 5] FIG. 4 is a diagram showing an example of the configuration of image information. [Figure 6] FIG. 13 is a diagram illustrating an example of a configuration of analysis information. [Figure 7] FIG. 2 is a diagram illustrating a detailed example of a functional configuration of the image analysis device according to the first embodiment. [Figure 8] 1 is a diagram illustrating an example of the physical configuration of an image analysis device according to a first embodiment. [Figure 9] 5 is a flowchart showing an example of an analysis process according to the first embodiment. [Figure 10] 6 is a flowchart showing a detailed example of an image analysis process according to the first embodiment. [Figure 11] FIG. 2 is a diagram showing an example of a first screen SC1. [Figure 12] FIG. 13 is a diagram showing an example of a second screen SC2. [Figure 13] FIG. 13 is a diagram showing an example of a third screen SC3. [Figure 14] FIG. 13 is a diagram showing an example of a fourth screen SC4. [Figure 15] FIG. 13 is a diagram showing an example of a fifth screen SC5. DETAILED DESCRIPTION OF THE PREFERRED EMBODIMENTS

[0021] Hereinafter, an embodiment of the present invention will be described with reference to the drawings. In all the drawings, the same components are denoted by the same reference numerals, and the description thereof will be omitted as appropriate.

[0022] <Embodiment 1> 1 is a diagram showing an overview of an image analysis device 100 according to embodiment 1. The image analysis device 100 includes an analysis result acquisition unit 110 and a counting unit 111.

[0023] The analysis result acquisition unit 110 acquires analysis information, which is information obtained by analyzing a still image and includes appearance attributes to which people included in the still image belong. The counting unit 111 counts the number of people in the still image that belong to each appearance attribute using the analysis information, and generates count information indicating the counting results for each still image.

[0024] According to this image analysis device 100, it becomes possible to utilize the results of analyzing an image.

[0025] 2 is a diagram showing an overview of an image analysis system 120 according to embodiment 1. The image analysis system 120 includes an image analysis device 100, at least one imaging device 121_1, and an analysis device 122.

[0026] The photographing device 121_1 is a device for generating a still image. The analysis device 122 analyzes the still image using a plurality of types of engines.

[0027] According to this image analysis system 120, it becomes possible to utilize the results of analyzing an image.

[0028] FIG. 3 is a flowchart illustrating an example of the image analysis process according to the first embodiment.

[0029] The analysis result acquisition unit 110 acquires analysis information that is obtained by analyzing a still image and includes appearance attributes to which a person included in the still image belongs (step S101).

[0030] The counting unit 111 counts the number of people belonging to each appearance attribute in the still image using the analysis information, and generates count information indicating the counting result for each still image (step S102).

[0031] This image analysis process makes it possible to utilize the results of analyzing the image.

[0032] A detailed example of the image analysis system 120 according to the first embodiment will be described below.

[0033] FIG. 4 is a diagram showing a detailed example of the configuration of the image analysis system 120 according to this embodiment.

[0034] Image analysis system 120 includes image analysis device 100, K image capturing devices 121_1 to 121_K including image capturing device 121_1, and analysis device 122. Here, K is an integer of 1 or more.

[0035] The image analysis device 100, each of the photographing devices 121_1 to 121_K, and the analysis device 122 are connected to each other via a communication network N configured by wired or wireless communication or a combination of these. The image analysis device 100, each of the photographing devices 121_1 to 121_K, and the analysis device 122 transmit and receive information to and from each other via the communication network N.

[0036] (Configuration of the imaging devices 121_1 to 121_K)

[0037] The photographing devices 121_1 to 121_K are, for example, cameras installed to photograph a predetermined photographing area within a predetermined range. The predetermined range may be a building, a facility, a city, town, village, prefecture, etc., or may be an appropriate range within these. The photographing areas of the photographing devices 121_1 to 121_K may partially overlap each other, or may be different areas.

[0038] Each of the imaging devices 121_1 to 121_K generates a moving image by capturing an image of an imaging area. Each of the imaging devices 121_2 to 121_K transmits the generated moving image to the analysis device 122 via the communication network N, for example, in real time.

[0039] The moving images generated by the image capturing devices 121_1 to 121_K are composed of time-series still images captured at a predetermined frame rate, for example. That is, a still image according to the present embodiment is, for example, one of the images constituting the moving image (i.e., a frame image). Therefore, each of the image capturing devices 121_1 to 121_K can generate a still image by capturing an image of a capturing area.

[0040] (Functions of analysis device 122) The analysis device 122 analyzes a plurality of images (moving images or still images) generated by each of the imaging devices 121_1 to 121_K. The analysis device 122 according to the present embodiment analyzes each of the plurality of still images generated by each of the imaging devices 121_1 to 121_K. As shown in FIG. 4, the analysis device 122 includes an analysis unit 123 and an analysis storage unit 124.

[0041] In detail, the analysis unit 123 acquires a plurality of pieces of image information 124a from each of the photographing devices 121_1 to 121_K, and stores the acquired plurality of pieces of image information 124a in the analysis storage unit 124. The analysis unit 123 analyzes a plurality of images (e.g., still images) shown in each of the acquired plurality of pieces of image information 124a. The analysis unit 123 generates analysis information 124b indicating the results of analyzing the plurality of images, and stores the analysis information 124 in the analysis storage unit 124. The analysis unit 123 also transmits the plurality of pieces of image information 124a and the analysis information 124b to the image analyzing device 100 via the communication network N.

[0042] The analysis unit 123 analyzes each of a plurality of images (e.g., still images) using a plurality of types of engines. Each type of engine has a function for analyzing an image, detecting a person included in the image, and determining appearance attributes to which the person belongs.

[0043] Appearance attributes are attributes of a person's appearance. Appearance attributes include, for example, one or more of age group, sex, type and color of clothes, type and color of shoes, hairstyle, whether or not to wear a hat, whether or not to wear a tie, whether or not to wear glasses, whether or not to carry an umbrella, and whether or not to use an umbrella.

[0044] Examples of engine types include (1) an object detection engine, (2) a face analysis engine, (3) a human shape analysis engine, (4) a posture analysis engine, (5) a behavior analysis engine, (6) an appearance attribute analysis engine, (7) a gradient feature analysis engine, (8) a color feature analysis engine, and (9) a movement line analysis engine. The analysis unit 123 may include at least two engines selected from the types of engines exemplified here and other types of engines. The analysis unit 123 uses the appearance attribute analysis engine or multiple types of engines to determine appearance attributes.

[0045] (1) The object detection engine detects people and objects from images. The object detection function can also determine the location of people and objects within an image. An example of a model that can be applied to object detection processing is YOLO (You Only Look Once).

[0046] (2) The face analysis engine detects human faces from images, extracts the features of the detected faces, and classifies the detected faces. The face analysis engine can also determine the position of the face within the image. The face analysis engine can also determine the identity of people detected from different images based on the similarity between the facial features of people detected from different images.

[0047] (3) The human morphology analysis engine extracts the human features of people in an image (for example, values ​​that indicate overall characteristics such as whether the body is fat or thin, height, and clothing) and classifies (classifies) people in the image. The human morphology analysis engine can also identify the position of a person in an image. The human morphology analysis engine can also determine the identity of people in different images based on the human features of the people in different images.

[0048] (4) The posture analysis engine generates posture information indicating the posture of a person. The posture information includes, for example, a posture estimation model of a person. The posture estimation model is a model in which the joints of a person are connected, estimated from an image. The posture estimation model is composed of a plurality of model elements corresponding to, for example, joint elements corresponding to joints, trunk elements corresponding to the torso, and bone elements corresponding to bones connecting the joints. The posture analysis function, for example, detects the joint points of a person from an image and creates a posture estimation model by connecting the joint points.

[0049] Then, the posture analysis engine uses the information of the posture estimation model to estimate the posture of a person, extracts features of the estimated posture (posture features), classifies people included in the image, etc. The posture analysis engine can also determine the identity of people included in different images based on the posture features of people included in different images.

[0050] For example, the techniques disclosed in Patent Document 2 and Non-Patent Document 1 can be applied to the posture analysis engine.

[0051] (5) The behavior analysis engine can estimate human movements using posture estimation model information, posture changes, etc., extract features of human movements (movement features), and classify (classify) people included in images. The behavior analysis engine can also estimate a person's height and identify a person's position in an image using stick figure model information. The behavior analysis engine can estimate behaviors such as posture changes or transitions, and movement (position changes or transitions) from images, and extract movement features related to the behaviors.

[0052] (6) The appearance attribute analysis engine can recognize appearance attributes associated with people. The appearance attribute analysis engine extracts features related to the recognized appearance attributes (appearance attribute features) and classifies (classifies) people included in the image.

[0053] (7) The gradient feature analysis engine extracts gradient features in an image. For example, technologies such as SIFT, SURF, RIFF, ORB, BRISK, CARD, and HOG can be applied to the gradient feature analysis engine.

[0054] (8) The color feature analysis engine can detect objects from an image, extract color features of the detected objects, and classify the detected objects. Color features are, for example, color histograms. The color feature analysis engine can detect, for example, people and objects included in an image.

[0055] (9) The movement line analysis engine can determine the movement line (movement trajectory) of a person included in a video using, for example, the result of identity determination performed by one or more of the above-mentioned engines. In detail, for example, by connecting a person determined to be the same between chronologically different images, the movement line of the person can be determined. Also, for example, the movement line analysis engine can determine a movement feature amount indicating the movement direction and movement speed of the person. The movement feature amount may be either one of the movement direction and movement speed of the person.

[0056] In a case where the traffic flow analysis engine acquires video images generated by multiple imaging devices 121_2 to 121_K capturing different shooting areas, the traffic flow analysis engine can also determine traffic flows spanning multiple images obtained by capturing different shooting areas.

[0057] Furthermore, each of the engines (1) to (9) may appropriately use the results of analysis performed by the other engines. The analysis unit 123 may have a function (analysis function) of analyzing an image using the above-mentioned multiple engines to obtain age group, sex, and the like.

[0058] Furthermore, the engines (1) to (9) can calculate the reliability of the features they each require.

[0059] Image analysis device 100 may include an analysis unit having the functions of analysis device 122 .

[0060] The analysis storage unit 124 is a storage unit for storing various types of information such as image information 124a and analysis information 124b.

[0061] The image information 124a is information indicating each of a plurality of images. Fig. 5 is a diagram showing an example of the configuration of the image information 124a. The image information 124a associates, for example, an image ID, a photographing device ID, a photographing time, and an image. This image may be either a moving image or a still image, but in this embodiment, it is a still image.

[0062] The image ID is information (image identification information) for identifying each image (e.g., still image). The photographing device ID is information (photographing identification information) for identifying each of the photographing devices 121_1 to 121_K. The photographing time is information indicating the time when photographing was performed. The photographing time includes, for example, a date and a time.

[0063] In the image information 124a, an image ID is associated with an image identified by the image ID. Also, in the image information 124a, a photographing device ID for identifying the photographing device 121_1-121_K that generated the image identified by the image ID is associated with a photographing time indicating the time when the image indicated by the image ID was generated (i.e., the time when the photographing area was photographed).

[0064] 6 is a diagram showing an example of the configuration of the analysis information 124b. The analysis information 124b associates an image ID, a photographing device ID, a photographing time, and an analysis result.

[0065] The image ID, the photographing device ID, and the photographing time associated in the analysis information 124b are the same as the image ID, the photographing device ID, and the photographing time associated in the image information 124a, respectively.

[0066] The analysis result is information indicating the result of analyzing an image identified by the associated image ID. In the analysis information 124b, the analysis result is associated with an image ID for identifying the image that was the subject of the analysis to obtain the analysis result.

[0067] The analysis results may associate, for example, a person ID, a person ID, a location, appearance attributes, and a reliability level.

[0068] The person ID is information for identifying each image corresponding to a person included in each image (person image identification information). In the analysis information 124b, the image ID is associated with a person ID corresponding to an image of a person (person image) included in an image identified using the image ID.

[0069] The person ID is information for identifying each person included in each image (person image identification information). When images of the same person are included in multiple images, the same person is assigned a common person ID in the multiple images. In the analysis information 124b, the image ID is associated with a person ID corresponding to the person included in the image identified using the image ID.

[0070] The position is information indicating the position of the human image identified by the associated human ID. This position indicates the position within the image identified by the associated image ID.

[0071] The appearance attribute indicates an appearance attribute to which a person belongs. In the analysis information 124b, a person ID is associated with an appearance attribute related to a person image identified by the person ID.

[0072] The reliability indicates the reliability of the appearance attribute. In the analysis information 124b, the reliability indicates the reliability of the associated appearance attribute.

[0073] (Functions of image analysis device 100) 7 is a diagram showing a detailed example of the functional configuration of the image analysis device 100 according to this embodiment. The image analysis device 100 includes a storage unit 108, a receiving unit 109, an analysis result acquisition unit 110, a counting unit 111, a display control unit 112, and a display unit 113. As described above, the image analysis device 100 may include an analysis unit 123, in which case the image analysis system 120 may not include the analysis device 122.

[0074] The storage unit 108 is a storage unit for storing various types of information.

[0075] Receiving unit 109 receives various types of information such as image information 124a and analysis information 124b from analysis device 122 via communication network N. Receiving unit 109 may receive image information 124a and analysis information 124b from analysis device 122 in real time, or may receive them as needed, such as when they are used for processing in image analysis device 100.

[0076] The receiving unit 109 stores the received information in the storage unit 108. That is, in this embodiment, the information stored in the storage unit 108 includes the image information 124a and the analysis information 124b.

[0077] The receiving unit 109 may receive the image information 124a from the imaging devices 121_1 to 121_K via the communication network N and store the received information in the storage unit 108. The receiving unit 109 may also receive the image information 124a and the analysis information 124b from the analysis device 122 via the communication network N as necessary, for example, when the image information 124a and the analysis information 124b are used for processing in the image analysis device 100. In this case, the image information 124a and the analysis information 124b do not need to be stored in the storage unit 108. Furthermore, for example, when the receiving unit 109 receives all of the image information 124a and the analysis information 124b from the analysis device 122 and stores them in the storage unit 108, the analysis device 122 does not need to hold the image information 124a and the analysis information 124b.

[0078] The analysis result acquisition unit 110 acquires analysis information 124b indicating the results of the analysis unit 123 analyzing each of the multiple images using multiple types of engines from the storage unit 108. Note that the analysis result acquisition unit 110 may receive the analysis information 124b from the analysis device 122 via the communication network N. The analysis information 124b is information obtained by analyzing a still image, and includes appearance attributes to which a person included in the still image belongs.

[0079] The counting unit 111 counts the number of people belonging to each appearance attribute in each of the multiple images using the analysis information 124b, and generates count information indicating the counting results for each image.

[0080] The counting unit 111 may count the number of people belonging to the appearance attribute in the still image for each appearance attribute by using the reliability threshold and the analysis information 124b, and generate counting information indicating the counting result. The reliability threshold is a value set for the reliability. When the reliability threshold is set, the counting unit 111 counts the number of people belonging to the appearance attribute in the still image for each appearance attribute by using the analysis information 124b that associates a reliability equal to or greater than the reliability threshold, for example.

[0081] The display control unit 112 causes various types of information to be displayed on the display unit 113. The display control unit 112 causes still images, moving images, counting information, and the like to be displayed on the display unit 113. When the display control unit 112 causes moving images to be displayed on the display unit 113, the display control unit 112 causes the display unit 113 to display still images in chronological order.

[0082] The still images or videos that the display control unit 112 causes the display unit 113 to display may be designated from one or more of the imaging devices 121_1-121_K that generated the still images or videos, for example, based on a user's input. When a plurality of imaging devices 121_1-121_K are designated, the still images or videos generated by each of the imaging devices 121_1-121_K may be displayed on the display unit 113, for example, simultaneously.

[0083] (Physical configuration of image analysis device 100) 8 is a diagram showing an example of the physical configuration of the image analysis device 100 according to this embodiment. The image analysis device 100 includes a bus 1010, a processor 1020, a memory 1030, a storage device 1040, a network interface 1050, and a user interface 1060.

[0084] The bus 1010 is a data transmission path for transmitting and receiving data among the processor 1020, the memory 1030, the storage device 1040, the network interface 1050, and the user interface 1060. However, the method of connecting the processor 1020 and the like to each other is not limited to a bus connection.

[0085] The processor 1020 is implemented by a central processing unit (CPU) or a graphics processing unit (GPU).

[0086] The memory 1030 is a main storage device realized by a RAM (Random Access Memory) or the like.

[0087] The storage device 1040 is an auxiliary storage device realized by a hard disk drive (HDD), a solid state drive (SSD), a memory card, a read only memory (ROM), etc. The storage device 1040 stores program modules for realizing the functions of the image analyzing device 100. The processor 1020 reads each of these program modules into the memory 1030 and executes them to realize the function corresponding to the program module.

[0088] The network interface 1050 is an interface for connecting the image analysis device 100 to the communication network N.

[0089] The user interface 1060 includes a touch panel, a keyboard, a mouse, etc., as interfaces for the user to input information, and a liquid crystal panel, an organic EL (Electro-Luminescence) panel, etc., as interfaces for presenting information to the user.

[0090] Analysis device 122 may be physically configured in the same manner as image analysis device 100 (see FIG. 8). Therefore, a diagram showing the physical configuration of analysis device 122 will be omitted.

[0091] (Operation of Image Analysis System 120) The operation of the image analysis system 120 will now be described with reference to the figures.

[0092] (Analysis processing) 9 is a flowchart showing an example of the analysis process according to the present embodiment. The analysis process is a process for analyzing images generated by the photographing devices 121_1 to 121_K. The analysis process is repeatedly executed while the photographing devices 121_1 to 121_K and the analysis unit 123 are operating, for example.

[0093] The analysis unit 123 acquires image information 124a from each of the imaging devices 121_1 to 121_K via the communication network N, for example, in real time (step S201).

[0094] The analysis unit 123 stores the image information 124a acquired in step S201 in the analysis storage unit 124, and analyzes the image shown in the image information 124a (step S202).

[0095] For example, as described above, the analysis unit 123 detects the detection target by analyzing the image using multiple types of engines. Furthermore, the analysis unit 123 uses each type of engine to obtain the appearance feature amount of the detected detection target and the reliability of the appearance feature amount. The analysis unit 123 generates analysis information 124b by performing such analysis.

[0096] At this time, the analysis unit 123 may analyze, for example, each of all still images included in the image information 124a acquired in step S201. Also, for example, the analysis unit 123 may analyze each of some still images included in the image information 124a acquired in step S201, such as each of still images captured at a certain time interval.

[0097] The analysis unit 123 stores the analysis information 124b generated by performing the analysis in step S202 in the analysis storage unit 124, and transmits the analysis information 124b to the image analysis device 100 via the communication network N (step S203). At this time, the analysis unit 123 may transmit the image information 124a acquired in step S201 to the image analysis device 100 via the communication network N.

[0098] The receiving unit 109 receives the analysis information 124b transmitted in step S203 via the communication network N (step S204). At this time, the receiving unit 109 may receive the image information 124a transmitted in step S203 via the communication network N.

[0099] The receiving unit 109 stores the analysis information 124b received in step S204 in the storage unit 108 (step S205), and ends the analysis process. At this time, the receiving unit 109 may receive the image information 124a received in step S204 via the communication network N.

[0100] The analysis unit 123 may perform analysis on a moving image designated by a user, for example. In this case, for example, the moving images captured by each of the imaging devices 121_1 to 121_K may be stored in the analysis storage unit 124. The analysis unit 123 may acquire moving images designated using one or more of a target period, imaging device, etc. from the analysis storage unit 124, and analyze all or some of the still images constituting the acquired moving image. In this case, the analysis unit 123 may also generate analysis information 124b as a result of the analysis, and store the analysis information 124b in the analysis storage unit 124.

[0101] (Image analysis processing) The image analysis process is a process for counting the number of people included in an image, as described with reference to Fig. 3. The image analysis process is started when the analysis result acquisition unit 110 acquires a target period, a photographing device, and a reliability threshold value, which are specified based on, for example, a user's input. The photographing device is specified using, for example, a photographing device ID corresponding to any one of the photographing devices 121_1 to 121_K. Note that when one still image is specified, the target period is the photographing time.

[0102] FIG. 10 is a flowchart showing a detailed example of the image analysis process according to this embodiment.

[0103] The analysis result acquisition unit 110 acquires the analysis information 124b from the storage unit 108 (step S101).

[0104] In detail, for example, the analysis result acquisition unit 110 acquires the analysis information 124b according to the specified target period, the imaging device, and the reliability threshold from the storage unit 108. The analysis information 124b according to the specified target period, the imaging device, and the reliability threshold is the analysis information 124b associated with the imaging time included in the target period, the specified imaging devices 121_1 to 121_K, and the reliability equal to or greater than the reliability threshold.

[0105] The counting unit 111 counts the number of people belonging to each appearance attribute in each still image for each appearance attribute using the analysis information 124b acquired in step S101 (step S102). Then, the counting unit 111 generates count information indicating the counting result for each appearance attribute for each still image.

[0106] In detail, for example, the counting unit 111 counts the number of person IDs associated with the same appearance attribute for each still image in the analysis information 124b acquired in step S101. Then, the counting unit 111 generates count information indicating the result of the counting for each still image and for each appearance attribute.

[0107] The display control unit 112 causes the display unit 113 to display, together with the still image, the count information corresponding to the still image (step S103).

[0108] Fig. 11 is an example of a first screen SC1 that displays count information together with a still image. The image (still image) included in the first screen SC1 illustrated in Fig. 11 includes three human images. The first screen SC1 includes count information indicating the results of counting the appearance attributes of the three human images. The count information included in the first screen SC1 illustrated in Fig. 11 indicates, for example, that the three human images include two men and one woman.

[0109] When display control unit 112 causes a moving image to be displayed on display unit 113, it causes each still image constituting the moving image to be displayed together with counting information corresponding to the still image on display unit 113. In detail, for example, display control unit 112 causes the still images to be displayed in chronological order, and also causes display unit 113 to display counting information corresponding to the still image being displayed. That is, when the still image being displayed is switched, the counting information displayed together with it is also switched.

[0110] Furthermore, the display control unit 112 causes the display unit 113 to display each of the appearance attributes in a selectable manner on the first screen SC1. When the display control unit 112 receives a selection of one or more of the appearance attributes based on, for example, a user's input, the display control unit 112 causes the display unit 113 to display additional information indicating a person belonging to the selected appearance attribute superimposed on the still image. In this case, the display control unit 112 causes the display unit 113 to display the reliability of the appearance attribute of a person belonging to the selected appearance attribute among the people included in the still image.

[0111] FIG. 12 is an example of the second screen SC2 that is displayed when "male", one of the appearance attributes, is selected. FIG. 12 shows an example in which additional information indicating a person belonging to the selected appearance attribute is a dotted frame surrounding an image (person image) indicating the person. FIG. 12 also shows an example in which the additional information further includes "P1" and "P2", which are the person IDs of the person. Furthermore, FIG. 12 shows an example in which the reliability that "P1" and "P2" are "male", respectively, are "0.75" and "0.85".

[0112] (Action and effect) As described above, according to this embodiment, the image analyzing device 100 includes the analysis result acquiring unit 110 and the counting unit 111. The analysis result acquiring unit 110 acquires analysis information 124b, which is information obtained by analyzing a still image and includes appearance attributes to which people included in the still image belong. The counting unit 111 counts the number of people in the still image that belong to each appearance attribute using the analysis information 124b, and generates counting information indicating the counting results.

[0113] This makes it possible to obtain information that counts the number of people belonging to each appearance attribute in the image, and therefore makes it possible to utilize the results of analyzing the image.

[0114] According to this embodiment, image analysis device 100 further includes a display control unit 112 that causes display unit 113 to display, together with a still image, count information corresponding to the still image.

[0115] This allows the user to refer to the count information along with the still image, making it possible to utilize the results of analyzing the image.

[0116] According to the present embodiment, the still image is one of the images constituting the moving image. The display control unit 112 causes the display unit 113 to display each still image constituting the moving image together with the count information corresponding to the still image.

[0117] This allows the user to refer to the count information along with each still image that constitutes the moving image, making it possible to utilize the results of analyzing the images.

[0118] According to this embodiment, when the display control unit 112 receives a selection of an appearance attribute, the display control unit 112 causes the display unit 113 to display additional information indicating a person belonging to the selected appearance attribute superimposed on a still image.

[0119] This allows the user to easily check in an image people who have the desired appearance attributes, and therefore makes it possible to utilize the results of analyzing the image.

[0120] According to this embodiment, the analysis information 124b includes the reliability of each of the appearance attributes. The display control unit 112 causes the display unit 113 to display the reliability of the selected appearance attribute of the person belonging to the appearance attribute.

[0121] This allows the user to easily check the reliability of the appearance attributes obtained by analyzing the image, thereby making it possible to utilize the results of analyzing the image.

[0122] According to the present embodiment, the analysis information 124b includes the reliability of each of the appearance attributes. The counting unit 111 counts the number of people belonging to each appearance attribute in the still image by using the reliability threshold value set for the reliability and the analysis information 124b, and generates count information indicating the counting result.

[0123] This allows the user to obtain information counting the number of people who belong to each appearance attribute with a reliability according to the reliability threshold, making it possible to utilize the results of analyzing the image.

[0124] <Embodiment 2> In the first embodiment, an example is described in which the number of human images belonging to each appearance attribute is counted for still images. For multiple images (moving images or still images), the number of people belonging to each appearance attribute may be counted by counting the number of people represented by the same person as one person. In the second embodiment, an example is described in which the number of people belonging to each appearance attribute is counted for multiple images.

[0125] In this embodiment, image analysis system 120 may be configured functionally and physically in a similar manner to that of embodiment 1 (see FIGS. 1 to 8). In this embodiment, the operation of image analysis system 120 may be substantially similar to that of embodiment 1 (see FIGS. 9 to 10). In this embodiment, differences from embodiment 1 will be mainly described, and overlapping points with embodiment 1 will be omitted as appropriate for simplicity of description.

[0126] Please refer to Figure 1. The analysis result acquisition unit 110 according to the present embodiment acquires analysis information 124b, which is information obtained by analyzing a plurality of images and includes appearance attributes for each person included in the plurality of images. The counting unit 111 according to the present embodiment counts the number of people belonging to each appearance attribute in the plurality of images using the analysis information 124b, and generates counting information indicating the counting results.

[0127] According to this image analysis device 100, it becomes possible to utilize the results of analyzing an image.

[0128] The analysis information 124b may be information showing the result of analysis on a still image basis, or may be information showing the result of analysis on a video image basis. The result of analysis on a video image basis may be the result of analysis of all still images included in a unit video, or may be the result of analysis of some of the still images included in the unit video (e.g., still images taken at a certain time interval).

[0129] Please refer to Figure 3. The analysis result acquisition unit 110 acquires analysis information 124b, which is information obtained by analyzing a plurality of images and includes appearance attributes of each person included in the plurality of images (step S101).

[0130] The counting unit 111 counts the number of people belonging to each appearance attribute in a plurality of images using the analysis information 124b, and generates count information indicating the counting result (step S102).

[0131] This image analysis process makes it possible to utilize the results of analyzing the image.

[0132] Here, when the analysis information 124b is information showing the result of analysis on a still image basis, the counting unit 111 may count the number of people for each still image constituting a plurality of images (i.e., for each still image) and generate counting information showing the result of counting on a still image basis. This makes it possible to obtain detailed counting results that take into account the time series.

[0133] In this embodiment, in detail, for example, in step S102, the counting unit 111 counts the number of person IDs associated with the same appearance attribute for the analysis information 124b acquired in step S101. Then, the counting unit 111 generates count information indicating the counting result for each appearance attribute.

[0134] In step S103, the display control unit 112 may cause the display unit 113 to display the count information generated in step S102.

[0135] Furthermore, in step S103, the display control unit 112 may use the analysis information 124b to cause the display unit 113 to display the appearance attributes of each person included in the multiple images.

[0136] Fig. 13 is an example of a third screen SC3 that displays appearance attributes for each person together with a still image. The image (still image) included in the third screen SC3 illustrated in Fig. 13 is one of the images used to obtain the analysis result included in the analysis information 124b acquired in step S101, and includes images of three people. The third screen SC3 includes appearance attributes for each of the three people.

[0137] The display control unit 112 causes the display unit 113 to selectably display person IDs for identifying each person. When the display control unit 112 receives a selection of one or more person IDs based on, for example, a user input, the display control unit 112 causes the display unit 113 to display additional information indicating the person corresponding to the selected person ID superimposed on a still image.

[0138] Fig. 14 is an example of a fourth screen SC4 that is displayed when "Person 1", one of the person IDs of the people shown in Fig. 13, is selected. Fig. 14 shows an example in which the additional information indicating the selected person ID is a dotted frame surrounding an image (human image) corresponding to the person. Fig. 14 also shows an example in which the additional information further includes "Person 1", which is the selected person ID.

[0139] (Action and effect) As described above, according to this embodiment, the image analyzing device 100 includes the analysis result acquiring unit 110 and the counting unit 111. The analysis result acquiring unit 110 acquires analysis information 124b, which is information obtained by analyzing a plurality of images and includes appearance attributes for each person included in the plurality of images. The counting unit 111 counts the number of people belonging to each appearance attribute in the plurality of images using the analysis information 124b, and generates counting information indicating the counting results.

[0140] This makes it possible to obtain information that counts the number of people belonging to each appearance attribute in a plurality of images, and therefore makes it possible to utilize the results of analyzing the images.

[0141] According to this embodiment, the multiple images are images obtained by capturing images using the multiple image capturing devices 121_1 to 121_K.

[0142] This makes it possible to obtain information that counts the number of people belonging to each appearance attribute in a plurality of images captured by the plurality of image capturing devices 121_1 to 121_K for each appearance attribute. This makes it possible to utilize the results of analyzing the images.

[0143] According to this embodiment, the image analyzing device 100 further includes a display control unit 112 that uses the analysis information 124b to cause the display unit 113 to display the appearance attributes of each person included in the multiple images.

[0144] This allows the user to easily check the appearance attributes of each person included in the image, making it possible to utilize the results of analyzing the image.

[0145] <Embodiment 3> In the second embodiment, an example is described in which the number of people belonging to each appearance attribute is counted for a plurality of images. The appearance attribute for counting the number of people is not limited to one, and may be any combination of a plurality of appearance attributes. In the third embodiment, an example is described in which the number of people belonging to a combination of a plurality of appearance attributes is counted for a plurality of images (moving images or still images).

[0146] In this embodiment, image analysis system 120 may be configured functionally and physically in a similar manner to that of embodiment 1 (see FIGS. 1 to 8). In this embodiment, the operation of image analysis system 120 may be substantially similar to that of embodiment 1 (see FIGS. 9 to 10). In this embodiment, differences from embodiment 1 will be mainly described, and overlapping points with embodiment 1 will be omitted as appropriate for simplicity of description.

[0147] Please refer to Figure 1. The analysis result acquisition unit 110 according to the present embodiment acquires analysis information 124b, which is information obtained by analyzing a plurality of images and includes appearance attributes of each person included in the plurality of images. The counting unit 111 according to the present embodiment counts the number of people belonging to a combination of a plurality of appearance attributes using the analysis information 124b, and generates count information indicating the counting result.

[0148] According to this image analysis device 100, it becomes possible to utilize the results of analyzing an image.

[0149] Please refer to Figure 3. The analysis result acquisition unit 110 acquires analysis information 124b, which is information obtained by analyzing a plurality of images and includes appearance attributes of each person included in the plurality of images (step S101).

[0150] The analysis information 124b may be information showing the result of analysis on a still image basis, or may be information showing the result of analysis on a video image basis. The result of analysis on a video image basis may be the result of analysis of all still images included in a unit video, or may be the result of analysis of some of the still images included in the unit video (e.g., still images taken at a certain time interval).

[0151] The counting unit 111 counts the number of people belonging to a combination of a plurality of appearance attributes using the analysis information 124b, and generates count information indicating the counting result (step S102).

[0152] This image analysis process makes it possible to utilize the results of analyzing the image.

[0153] In this embodiment, in detail, for example, the counting unit 111 may receive a user's selection of one or a plurality of combinations of a plurality of appearance attributes, and for each combination of the plurality of appearance attributes selected by the user, count the number of people belonging to all of the plurality of appearance attributes constituting the combination, using the analysis information 124b. Also, the counting unit 111 may count the number of people belonging to all of the plurality of appearance attributes constituting the combination, using the analysis information 124b, for each combination of all or a predetermined portion of the plurality of appearance attributes included in the analysis information 124b.

[0154] Then, the counting unit 111 generates count information indicating the counting result. This count information may be information in which combinations of multiple appearance attributes are arranged in descending order of the number of people belonging to all of the multiple appearance attributes.

[0155] The counting unit 111 may count the number of people belonging to a combination of a plurality of appearance attributes by photographing condition using the analysis information 124b, and generate counting information indicating the counting result. The photographing condition includes at least one of, for example, weather, day of the week, time period, season, and photographing device.

[0156] For example, the counting unit 111 may obtain weather information corresponding to the shooting time from a device (not shown) that manages weather information related to the weather at each time. The season may be determined in advance, for example, by month, and the counting unit 111 may determine the season according to the month included in the shooting time.

[0157] In this embodiment, in detail, for example, in step S102, the counting unit 111 counts the number of person IDs associated with the same appearance attribute for the analysis information 124b acquired in step S101, similarly to embodiment 2. Then, the counting unit 111 generates count information indicating the result of the counting for each appearance attribute.

[0158] Here, when the analysis information 124b is information showing the result of analysis on a still image basis, the counting unit 111 may count the number of people for each still image constituting a plurality of images (i.e., for each still image) and generate counting information showing the result of counting on a still image basis. This makes it possible to obtain detailed counting results that take into account the time series.

[0159] In step S103, the display control unit 112 may cause the display unit 113 to display the count information generated in step S102.

[0160] Furthermore, the display control unit 112 may display information about a first combination, which is a combination of multiple appearance attributes with the largest number of people belonging to the combination, on the display unit 113, based on the count information generated in step S102. The information about the first combination may be displayed using a line graph, a bar graph, a pie chart, or the like.

[0161] Fig. 15 is an example of the fifth screen SC5 for displaying information about the first combination. Fig. 15 shows an example of the fifth screen SC5 when the first combination is "male" and "casual". Fig. 15 also shows an example of the fifth screen SC5 showing the number of people by time period in a line graph by time period.

[0162] (Action and effect) As described above, according to this embodiment, the image analyzing device 100 includes the analysis result acquiring unit 110 and the counting unit 111. The analysis result acquiring unit 110 acquires analysis information 124b, which is information obtained by analyzing a plurality of images and includes appearance attributes of each person included in the plurality of images. The counting unit 111 counts the number of people belonging to a combination of a plurality of appearance attributes using the analysis information 124b, and generates count information indicating the counting result.

[0163] This makes it possible to obtain information counting the number of people who belong to a combination of multiple appearance attributes in multiple images, thereby making it possible to utilize the results of analyzing images.

[0164] According to the present embodiment, the analysis information 124b is information indicating the results of analyzing an image using a plurality of types of engines for analyzing images, and includes appearance attributes of people included in the image.

[0165] This makes it possible to obtain information counting the number of people belonging to a combination of multiple appearance attributes obtained by analyzing multiple images using multiple types of engines, thus making it possible to utilize the results of analyzing images.

[0166] According to this embodiment, the counting unit 111 counts, for each combination of a plurality of appearance attributes, the number of people belonging to all of the plurality of appearance attributes that make up the combination, and generates count information indicating the counting result.

[0167] This makes it possible to obtain information counting the number of people who belong to a combination of multiple appearance attributes in multiple images, thereby making it possible to utilize the results of analyzing images.

[0168] According to this embodiment, the count information is information in which combinations of a plurality of appearance attributes are arranged in descending order of the number of people belonging to all of the plurality of appearance attributes constituting the combination.

[0169] This makes it possible to obtain information that lists combinations of multiple appearance attributes in descending order of the number of people who belong to each combination, thereby making it possible to utilize the results of image analysis.

[0170] According to this embodiment, the image analysis device 100 further includes a display control unit 112 that displays, on the display unit 113, information regarding a first combination, which is a combination of multiple appearance attributes that has the largest number of people belonging to that combination, based on the count information.

[0171] This allows the user to refer to information about the first combination, making it possible to utilize the results of analyzing the image.

[0172] According to this embodiment, the counting unit 111 counts the number of people belonging to a combination of a plurality of appearance attributes for each shooting condition by using the analysis information 124b, and generates count information indicating the counting result.

[0173] This makes it possible to obtain information that counts the number of people belonging to a combination of multiple appearance attributes in multiple images for each shooting condition, thereby making it possible to utilize the results of analyzing images.

[0174] According to this embodiment, the photographing conditions include at least one of the weather, the day of the week, the time period, the season, and the photographing device.

[0175] This makes it possible to obtain information that counts the number of people who belong to a combination of multiple appearance attributes in multiple images for at least one of the weather, day of the week, time of day, season, and shooting device. This makes it possible to utilize the results of analyzing images.

[0176] Although the embodiment and modified examples of the present invention have been described above with reference to the drawings, these are merely examples of the present invention, and various configurations other than those described above can also be adopted.

[0177] In addition, in the multiple flowcharts used in the above description, multiple steps (processing) are described in order, but the execution order of the steps performed in the embodiments is not limited to the order described. In the embodiments, the order of the steps shown in the figures can be changed to the extent that the content is not affected. In addition, the above-mentioned embodiments and modified examples can be combined to the extent that the content is not contradictory.

[0178] A part or all of the above-described embodiments can be described as, but are not limited to, the following supplementary notes.

[0179] 1. An analysis result acquisition means for acquiring analysis information including appearance attributes of a person included in a still image, the analysis information being obtained by analyzing the still image; a counting means for counting the number of people belonging to the appearance attribute in the still image for each of the appearance attributes using the analysis information, and generating count information indicating the counting result for each of the still images. Image analysis equipment. 2. The image forming apparatus further includes a display control means for displaying, on a display means, count information corresponding to the still images together with the still images for each still image. 1. An image analysis device as described in claim 1. 3. The still image is one of images constituting a moving image; The display control means causes the display means to display, together with each still image constituting the moving image, count information corresponding to the still image. 1. An image analysis device according to claim 1 or 2. 4. When the display control means receives the selection of the appearance attribute, the display control means causes the display means to display additional information indicating a person who belongs to the selected appearance attribute superimposed on the still image. 4. An image analysis device according to any one of 1 to 3. 5. The analysis information includes a confidence level for each of the appearance attributes; The display control means causes the display means to display the reliability of the selected appearance attribute of the person who belongs to the appearance attribute. 5. An image analysis device according to any one of 1 to 4. 6. The analysis information includes a confidence level for each of the appearance attributes; The counting means counts the number of people belonging to the appearance attribute in the still image for each of the appearance attributes using a reliability threshold set for the reliability and the analysis information, and generates count information indicating the counting result. 6. An image analysis device according to any one of 1 to 5. 7. An analysis result acquisition means for acquiring analysis information including appearance attributes of each person included in the plurality of images, the analysis information being information obtained by analyzing the plurality of images; a counting means for counting the number of people belonging to the appearance attribute in the plurality of images for each appearance attribute using the analysis information, and generating count information indicating the counting result. Image analysis equipment. 8. The plurality of images are images obtained by taking images using a plurality of photographing devices. 7. An image analysis device as described in claim 7. 9. The method further includes display control means for displaying the appearance attributes of each of the people included in the plurality of images on a display means using the analysis information. 7. The image analysis device according to claim 7 or 8. 10. An analysis result acquisition means for acquiring analysis information including appearance attributes of each person included in the plurality of images, the analysis information being information obtained by analyzing the plurality of images; and a counting means for counting the number of people belonging to a combination of a plurality of appearance attributes using the analysis information and generating count information indicating the counting result. Image analysis equipment. 11. The analysis information is information showing the results of analyzing the image using multiple types of engines for analyzing the image, and includes appearance attributes of people included in the image. 10. An image analysis device as described above. 12. The counting means counts the number of people who belong to all of the plurality of appearance attributes constituting each combination of the plurality of appearance attributes, and generates count information indicating the counting result. 10. The image analysis device according to claim 11. 13. The count information is information in which the combinations of the plurality of appearance attributes are arranged in order of the number of people who belong to all of the plurality of appearance attributes constituting the combination. 12. An image analysis device as described in claim 12. 14. The method further comprises display control means for displaying information on a display means regarding a first combination, which is a combination of the plurality of appearance attributes with the largest number of people belonging to the combination of the plurality of appearance attributes, based on the count information. 12. The image analysis device according to claim 13. 15. The counting means counts the number of people belonging to a combination of a plurality of appearance attributes by photographing conditions using the analysis information, and generates count information indicating the counting results. 15. An image analysis device according to any one of claims 10 to 14. 16. The photographing conditions include at least one of weather, day of the week, time of day, season, and photographing device. 15. An image analysis device as described in claim 15. 17. The computer Acquire analysis information obtained by analyzing a still image, the analysis information including appearance attributes to which a person included in the still image belongs; Using the analysis information, the number of people belonging to the appearance attribute in the still image is counted for each appearance attribute, and count information indicating the counting result is generated for each still image. Image analysis methods. 18. To the computer: Acquire analysis information obtained by analyzing a still image, the analysis information including appearance attributes to which a person included in the still image belongs; A program for executing the following: using the analysis information to count the number of people in the still image that belong to the appearance attribute for each appearance attribute, and generating count information indicating the counting results for each still image. 19. The computer acquiring analysis information including appearance attributes of each person included in the plurality of images, the analysis information being information obtained by analyzing the plurality of images; Using the analysis information, the number of people belonging to the appearance attribute in the plurality of images is counted for each appearance attribute, and count information indicating the counting result is generated. Image analysis methods. 20. To the computer: acquiring analysis information including appearance attributes of each person included in the plurality of images, the analysis information being information obtained by analyzing the plurality of images; A program for executing the steps of: using the analysis information to count the number of people belonging to the appearance attribute in the multiple images for each appearance attribute; and generating count information indicating the counting results. 21. The computer acquiring analysis information including appearance attributes of each person included in the plurality of images, the analysis information being information obtained by analyzing the plurality of images; Using the analysis information, the number of people belonging to a combination of a plurality of appearance attributes is counted, and count information indicating the counting result is generated. Image analysis methods. 22. To the computer: acquiring analysis information including appearance attributes of each person included in the plurality of images, the analysis information being information obtained by analyzing the plurality of images; A program for executing the steps of: counting the number of people belonging to a combination of a plurality of appearance attributes using the analysis information; and generating count information indicating the counting result. [Explanation of symbols]

[0180] 100 Image analysis device 108 Storage section 109 Receiving section 110 Analysis result acquisition section 111 Counting Department 112 Display control unit 113 Display section 120 Image Analysis System 121_1~121_K Imaging Device 122 Analysis equipment 123 Analysis Department 124 Analysis storage section 124a Image information 124b Analysis information

Claims

1. An analysis result acquisition means for acquiring analysis information including appearance attributes of a person included in a still image, the analysis information being information obtained by analyzing the still image; a counting means for counting the number of people belonging to the appearance attribute in the still image for each of the appearance attributes using the analysis information, and generating count information indicating the counting result for each of the still images. Image analysis equipment.

2. The image forming apparatus further includes a display control unit that displays, on a display unit, the count information corresponding to the still image together with the still image.

2. The image analysis device of claim 1.

3. an analysis result acquisition means for acquiring analysis information including appearance attributes of each person included in the plurality of images, the analysis information being information obtained by analyzing the plurality of images; a counting means for counting the number of people belonging to the appearance attribute in the plurality of images for each appearance attribute using the analysis information, and generating count information indicating the counting result. Image analysis equipment.

4. an analysis result acquisition means for acquiring analysis information including appearance attributes of each person included in the plurality of images, the analysis information being information obtained by analyzing the plurality of images; and a counting means for counting the number of people belonging to a combination of a plurality of appearance attributes using the analysis information and generating count information indicating the counting result. Image analysis equipment.

5. The computer Acquire analysis information obtained by analyzing a still image, the analysis information including appearance attributes to which a person included in the still image belongs; Using the analysis information, the number of people belonging to the appearance attribute in the still image is counted for each appearance attribute, and count information indicating the counting result is generated for each still image. Image analysis methods.

6. On the computer, Acquire analysis information obtained by analyzing a still image, the analysis information including appearance attributes to which a person included in the still image belongs; A program for executing the following: using the analysis information to count the number of people in the still image that belong to the appearance attribute for each appearance attribute, and generating count information indicating the counting results for each still image.

7. The computer acquiring analysis information including appearance attributes of each person included in the plurality of images, the analysis information being information obtained by analyzing the plurality of images; Using the analysis information, the number of people belonging to the appearance attribute in the plurality of images is counted for each appearance attribute, and count information indicating the counting result is generated. Image analysis methods.

8. On the computer, acquiring analysis information including appearance attributes of each person included in the plurality of images, the analysis information being information obtained by analyzing the plurality of images; A program for executing the steps of: using the analysis information to count the number of people belonging to the appearance attribute in the plurality of images for each appearance attribute; and generating count information indicating the counting results.

9. The computer acquiring analysis information including appearance attributes of each person included in the plurality of images, the analysis information being information obtained by analyzing the plurality of images; Using the analysis information, the number of people belonging to a combination of a plurality of appearance attributes is counted, and count information indicating the counting result is generated. Image analysis methods.

10. On the computer, acquiring analysis information including appearance attributes of each person included in the plurality of images, the analysis information being information obtained by analyzing the plurality of images; A program for executing the steps of: counting the number of people belonging to a combination of a plurality of appearance attributes using the analysis information; and generating count information indicating the counting result.

Images