Image processing system, and image processing method

Abstract

An image processing system (1) has a first terminal (10) and a second terminal (20) that are connected to each other so as to be able to communicate. The first terminal (10) has an image data acquisition unit (11) that acquires image data for images of a prescribed space from a camera that photographs the space. At least one of the first terminal (10) and the second terminal (20) has an analysis unit (21) that analyzes whether skeletal data about the structures of the bodies of people included in the images is similar to prescribed reference skeletal data. The second terminal (20) has a detection unit (22) that detects prescribed events on the basis of the results of the analysis and an output unit (23) that outputs results information that are the results of the detection.

Description

Technical Field

[0001] The present disclosure relates to an image processing system, an image processing method, and a non-transitory computer-readable medium.

Background Art

[0002] Techniques for installing a plurality of cameras in a wide area space such as a street to monitor this space have been developed.

[0003] For example, the technique of Patent Document 1 tracks a person in an image input from a camera, determines whether the behavior of this person is non-daily behavior, determines whether the behavior of the person is a suspicious and abnormal behavior, and detects the suspicious behavior of the person based on these determination results.

[0004] The technique of Patent Document 2 classifies the objects existing in the detection area into pedestrians and vehicles from the object information of the objects existing in the detection area, and when it is determined that there is a possibility that the pedestrians and vehicles move to the same position at the same time, sets them as monitoring targets.

[0005] The technique of Patent Document 3, when detecting a person who is not included in the list of face images of a person but satisfies a predetermined criterion from the received image information, adds the face image of the person who satisfies the predetermined criterion to the list and outputs an identifier of the added face image.

Prior Art Documents

Patent Documents

[0006]

Patent Document 1

Patent Document 2

Patent Document 3

Summary of the Invention

Problems to be Solved by the Invention

[0007] Regarding the technology of installing a plurality of cameras as described above to monitor a space, a technology that can efficiently respond to various events is expected.

[0008] An object of the present disclosure is to provide an image processing system or the like that can efficiently process images captured by a plurality of cameras in view of the above-described problems.

Means for Solving the Problems

[0009] An image processing system according to an aspect of the present disclosure includes a first terminal and a second terminal that are communicably connected to each other. The first terminal includes image data acquisition means for acquiring image data related to an image of a space from a camera that photographs a predetermined space. At least one of the first terminal and the second terminal includes analysis means for analyzing whether skeletal data related to the body structure of a person included in the image is similar to predetermined reference skeletal data. The second terminal includes detection means for detecting a predetermined event based on the result of the analysis and output means for outputting result information that is the result of the detection.

[0010] An image processing method according to an aspect of the present disclosure is executed by an image processing system including a first terminal and a second terminal that are communicably connected to each other. The first terminal acquires image data related to an image of a space from a camera that photographs a predetermined space. At least one of the first terminal and the second terminal analyzes whether skeletal data related to the body structure of a person included in the image is similar to predetermined reference skeletal data. The second terminal detects a predetermined event based on the result of the analysis and outputs result information that is the result of the detection.

[0011] A non - transitory computer - readable medium according to one aspect of the present disclosure is a program for causing an image - processing system having a first terminal and a second terminal communicably connected to each other to execute the following image - processing method. The first terminal acquires image data related to an image of a space from a camera that photographs a predetermined space. At least one of the first terminal or the second terminal analyzes whether skeletal data related to the body structure of a person included in the image is similar to predetermined reference skeletal data. The second terminal detects a predetermined event based on the result of the analysis and outputs result information that is the result of the detection.

Effect of the Invention

[0012] According to the present disclosure, it is possible to provide an image - processing system or the like that can efficiently process images photographed by a plurality of cameras.

Brief Description of the Drawings

[0013]

Figure 1

Figure 2

Figure 3

Figure 4

Figure 5

Figure 6

Figure 7

Figure 8

Figure 9

Figure 10

Figure 11

Figure 12

Figure 13

Figure 14

Figure 15

Figure 16

Figure 17

Figure 18

Embodiments for Carrying Out the Invention

[0014] Hereinafter, the present disclosure will be described through embodiments, but the disclosure according to the claims is not limited to the following embodiments. Also, not all of the configurations described in the embodiments are essential as means for solving the problems. In each drawing, the same reference numerals are assigned to the same elements, and redundant descriptions are omitted as necessary.

[0015] <Embodiment 1> First, Embodiment 1 of the present disclosure will be described. FIG. 1 is a block diagram showing the configuration of an image processing system 1 according to Embodiment 1. The image processing system 1 shown in FIG. 1 analyzes, for example, the postures and movements of a person included in an image captured by a camera, and detects that the postures and movements of the person correspond to preset postures and movements. The image processing system 1 includes a first terminal 10 and a second terminal 20. The first terminal 10 and the second terminal 20 are communicably connected to each other.

[0016] The first terminal 10 has an image data acquisition unit 11 that acquires image data related to an image of a space from a camera that photographs a predetermined space. The first terminal 10 transmits the image data acquired by the image data acquisition unit 11 to the second terminal 20.

[0017] The second terminal 20 is communicably connected to the first terminal 10 and receives image data from the first terminal 10. The second terminal 20 has an analysis unit 21, a detection unit 22, and an output unit 23. The second terminal 20 is also communicably connected to a management terminal used by a user who uses the image processing system 1.

[0018] The analysis unit 21 analyzes whether the skeletal data related to the body structure of a person included in the image is similar to predetermined reference skeletal data. Here, the skeletal data is data indicating the body structure of a person for detecting the posture or movement of the person, and is composed of a combination of a plurality of pseudo-joints and a pseudo-skeletal structure. The image data for extracting the skeletal data may be image data including an image of one frame, or may be data including images of a plurality of consecutive frames taken at different times as a moving image. In the following description, an image for one frame may be referred to as a frame image or simply a frame.

[0019] In the image processing system 1, for example, the analysis unit 21 may extract that a person is included in the image related to the image data, and set skeletal data, which is an image of a pseudo-skeleton, for the extracted image of the person. The image processing system 1 may receive from the outside the skeletal data of a person included in the image of the image data acquired by the first terminal 10.

[0020] The predetermined reference skeletal data for comparison with the skeletal data set for the image of a person is pre-set reference image data. The reference skeletal data includes skeletal data configured to be comparable to the above-described skeletal data.

[0021] The detection unit 22 receives the signal of the result analyzed by the analysis unit 21, and detects a predetermined event from the received signal. The result of the analysis includes information indicating whether the skeletal data related to the image of the person matches the predetermined reference skeletal data. Alternatively, when there are multiple pieces of reference skeletal data, the result of the analysis may include information indicating which reference skeletal data the skeletal data related to the image of the person matches when they match.

[0022] The predetermined event is an event caused by the posture or movement of a person. That is, the predetermined event may be, for example, something that indicates the posture or movement of the person itself. In this case, the predetermined event is, for example, standing, walking, running, sitting, etc. The predetermined event may be something that indicates an abstract concept associated with the posture or movement of the person. In this case, the predetermined event is, for example, gathering, running away, fighting, etc.

[0023] The output unit 23 outputs the result information that is the result of the detection. The destination to which the output unit 23 outputs is, for example, the above-mentioned management terminal. The second terminal 20 may have a display device (not shown) on the second terminal 20 itself and output predetermined information to the user.

[0024] Next, with reference to FIG. 2, the processing of the image processing system 1 will be described. FIG. 2 is a flowchart showing the flow of the image processing method according to Embodiment 1. The flowchart shown in FIG. 2 is started, for example, when the image processing system 1 acquires image data.

[0025] First, the first terminal 10 acquires image data related to an image of the space from a camera that photographs a predetermined space (step S11).

[0026] Next, the second terminal 20 analyzes whether the skeletal data related to the body structure of the person included in the image is similar to the predetermined reference skeletal data (step S12).

[0027] Next, based on the result of the analysis, the second terminal 20 detects a predetermined event (step S13) and outputs result information that is the result of the detection (step S14).

[0028] As described above for Embodiment 1, the configuration of the image processing system 1 is not limited to the above. For the image processing system 1, at least one of the first terminal 10 or the second terminal 20 may have an analysis unit 21. That is, in the image processing system 1, the first terminal 10 may have the analysis unit 21 instead of the second terminal 20.

[0029] The image processing system 1 may have a plurality of first terminals 10. Also, the first terminal 10 may acquire a plurality of pieces of image data from a plurality of cameras. In this case, in the image processing system 1, a plurality of first terminals 10 each acquire a plurality of pieces of image data and supply the acquired image data to the second terminal 20. The second terminal 20 receives the image data of the images captured by the respective cameras via the first terminal 10 and detects events regarding the postures and movements of the people included in the respective images. In the image processing system 1, the configuration in which the first terminal 10 acquires image data from a plurality of cameras and the second terminal 20 further acquires and analyzes these images can be adopted in a predetermined space where a large number of people come and go, such as a street or a residential area.

[0030] Note that the first terminal 10 and the second terminal 20 have a processor and a storage device as configurations not shown. The storage device included in the image processing system 1 includes a storage device including a non-volatile memory such as a flash memory or an SSD (Solid State Drive). In this case, the storage device included in the image processing system 1 stores a computer program (hereinafter also simply referred to as a program) for executing the above-described image processing method. Further, the processor causes the computer program to be read from the storage device into a buffer memory such as a DRAM (Dynamic Random Access Memory) and executes the program.

[0031] Each component of the first terminal 10 and the second terminal 20 of the image processing system 1 may be realized by dedicated hardware respectively. Also, some or all of each component may be realized by general-purpose or dedicated circuitry, processors, etc. or combinations thereof. These may be constituted by a single chip or by a plurality of chips connected via a bus. Some or all of each component of each device may be realized by a combination of the circuitry etc. described above and a program. Also, as the processor, a CPU (Central Processing Unit), a GPU (Graphics Processing Unit), an FPGA (field-programmable gate array), etc. can be used. Note that the description regarding the configuration described here can also be applied to other devices or systems described below in the present disclosure.

[0032] Also, when some or all of each component of the image processing system 1 are realized by a plurality of information processing devices, circuitry, etc., the plurality of information processing devices, circuitry, etc. may be centrally arranged or may be distributed. For example, the information processing devices, circuitry, etc. may be realized in a form in which each is connected via a communication network, such as a client-server system, a cloud computing system, etc. Also, the function of the image processing system 1 may be provided in the form of SaaS (Software as a Service).

[0033] According to the present embodiment, an image processing system etc. that can efficiently process an image captured by a camera can be provided.

[0034] <Embodiment 2> Next, Embodiment 2 of the present disclosure will be described. FIG. 3 is a diagram showing the overall configuration of the image processing system 2 according to Embodiment 2. The image processing system 2 includes a plurality of first terminals 100 (100A, 100B) and a second terminal 200. The first terminal 100A, the first terminal 100B, and the second terminal 200 are communicably connected to each other via a network N1. The first terminal 100A is communicably connected to three imaging devices 90 (imaging device 90A1, imaging device 90A2, and imaging device 90A3). The first terminal 100B is communicably connected to two imaging devices 90 (imaging device 90B1 and imaging device 90B2).

[0035] Also, the image processing system 1 is also communicably connected to a management terminal 80 via the network N1. The management terminal 80 is, for example, a smartphone, a tablet terminal, a personal computer, etc., and manages the first terminal 100 or the second terminal 200. Further, the management terminal 80 can receive predetermined information from the user and supply the received information to the first terminal 100 or the second terminal 200. The management terminal 80 can receive predetermined information output by the first terminal 100 or the second terminal 200 and notify the user.

[0036] FIG. 4 is a diagram showing a usage example of the image processing system according to Embodiment 2. FIG. 4 shows an arbitrary urban area including a roadway and a sidewalk. In the urban area shown in FIG. 4, an imaging device 90A, an imaging device 90B, an imaging device 90C, and a first terminal 100A are installed. The imaging devices 90A, 90B, and 90C are installed on top of a predetermined iron pillar and photograph the street from a position higher than the height of a person's back. The imaging devices 90A, 90B, and 90C transmit the image data of the images they respectively captured to the first terminal 100A by wireless communication.

[0037] The first terminal 100A is installed at the upper part of the same iron pillar as the imaging device 90A, and receives the image data supplied by each of the imaging device 90A, the imaging device 90B, and the imaging device 90C. Further, the first terminal 100A performs predetermined processing on the received image data, and transmits the processed data to the second terminal 200. The second terminal 200 is installed at an arbitrary location separated from the first terminal 100, and receives the data transmitted from the first terminal 100A. With such a configuration, the image processing system 2 can monitor the actions of people in a predetermined space.

[0038] Next, with reference to FIG. 5, an example of the configuration of the imaging device 90 will be described. FIG. 5 is a block diagram showing the configuration of the imaging device 90 according to Embodiment 2. The main components of the imaging device 90 include an imaging unit 91, an imaging control unit 92, and a camera communication unit 93. The imaging device 90 may be referred to as a camera. The imaging device 90 captures this image at regular intervals, generates image data for each of the captured images, and sequentially supplies the image data to the first terminal 100. The regular interval is, for example, 1 / 15 second, 1 / 30 second, or 1 / 60 second.

[0039] The imaging unit 91 includes an objective lens and an image sensor, and captures the scenery of the urban area. The imaging unit 91 may have functions such as pan, tilt, or zoom. The imaging control unit 92 controls the operation of the imaging unit 91. Further, the imaging control unit 92 generates image data for the image captured by the imaging unit 91. The image data may include the date and time of shooting, position information, or shooting conditions such as the aperture and shutter speed at the time of shooting. In addition, the imaging control unit 92 controls the transmission of the image data via the camera communication unit 93. The camera communication unit 93 includes an interface for communicating with the first terminal 100. The camera communication unit 93 transmits the image data generated by the imaging control unit 92 to the first terminal 100.

[0040] Next, with reference to FIG. 6, the first terminal 100 will be described. FIG. 6 is a block diagram showing the configuration of the first terminal 100 according to Embodiment 2. The main components of the first terminal 100 include an image data acquisition unit 101, a preprocessing unit 102, and a first communication unit 103.

[0041] The image data acquisition unit 101 sequentially acquires the image data supplied from the imaging device 90 via the first communication unit 103.

[0042] The preprocessing unit 102 performs predetermined preprocessing on the image data supplied from the imaging device 90 to generate preprocessed data. The predetermined preprocessing may be, for example, adjustment of the contrast or tone of the image, or may be to enlarge or reduce the image to a predetermined size. Also, the predetermined preprocessing may be a process of cropping the image. The predetermined preprocessing may be a process of generating extracted image data by extracting an image including a person.

[0043] The predetermined preprocessing may be the setting of the resolution of the image. In that case, for example, when the number of persons included in the image is less than the threshold value, the preprocessing unit 102 sets the resolution of the image to the first resolution, and when the number of persons included in the image is equal to or more than the threshold value, the preprocessing unit 102 sets the resolution of the image to the second resolution. And in this case, the preprocessing unit 102 performs preprocessing by setting the first resolution lower than the second resolution, for example. The first terminal 100 supplies the preprocessed data processed by the preprocessing unit 102 in this way to the second terminal 200.

[0044] The first communication unit 103 is an interface for communicating with the imaging device 90. The first communication unit 103 is also an interface for communicating with the second terminal 200. The first terminal 100 receives image data from the imaging device 90 via the first communication unit 103. Also, the first terminal 100 transmits the preprocessed data generated by the preprocessing unit 102 to the second terminal 200 via the first communication unit 103.

[0045] FIG. 7 is a block diagram showing the configuration of the second terminal 200 according to Embodiment 2. The second terminal 200 mainly includes an image data acquisition unit 201, an extraction unit 202, an analysis unit 203, a detection unit 204, an output unit 205, a second communication unit 206, and a storage unit 210.

[0046] The image data acquisition unit 201 acquires the image data received from the first terminal 100 via the second communication unit 206. The second terminal 200 supplies the received image data to the extraction unit 202.

[0047] The extraction unit 202 extracts skeleton data from the image data. More specifically, the extraction unit 202 detects an image area (body area) of a person's body from the frame images included in the image data, and extracts (for example, cuts out) it as a body image. Then, the extraction unit 202 uses a skeleton estimation technique using machine learning to extract at least a part of the skeleton data of the person's body based on the features such as joints of the person recognized in the body image. The skeleton data is information including "keypoints" which are characteristic points such as joints, and "bone links" indicating links between the keypoints. The extraction unit 202 may use a skeleton estimation technique such as OpenPose. In the present disclosure, the above-mentioned bone link may sometimes be simply referred to as "bone". The bone means a pseudo-skeleton.

[0048] The analysis unit 203 detects a predetermined posture or movement associated with the posture of the person from the extracted skeleton data of the person. When detecting the posture or movement, the analysis unit 203 searches for registered movements registered in the registered movement database 211 stored in the storage unit 210. Then, when the skeleton data of the person is similar to the skeleton data related to the registered movement, the analysis unit 203 recognizes this skeleton data as a predetermined posture or movement. That is, when the analysis unit 203 detects a registered movement similar to the skeleton data of the person, the movement related to this skeleton data is associated with the registered movement and recognized as a predetermined posture or movement.

[0049] In the above similarity determination, the analysis unit 203 detects a posture or movement by calculating the similarity of the forms of the elements constituting the skeletal data. The skeletal data has, as its constituent elements, pseudo-joints or skeletal structures for indicating the posture of the body. The form of the elements constituting the skeletal data can be, for example, the relative geometric relationships such as the positions, distances, and angles of other key points and bones with respect to a certain key point or bone. Alternatively, the form of the elements constituting the skeletal data can be, for example, a single integrated form formed by a plurality of key points and bones.

[0050] The analysis unit 203 analyzes whether the relative forms of these components are similar between the two skeletal data to be compared. At this time, the analysis unit 203 calculates the similarity between the two skeletal data. When calculating the similarity, the analysis unit 203 can calculate the similarity based on, for example, the feature amounts calculated from the components included in the skeletal data.

[0051] Note that the calculation target of the analysis unit 203 may be, instead of the above similarity, the similarity between a part of the extracted skeletal data and the skeletal data related to the registered movement, or the similarity between the extracted skeletal data and a part of the skeletal data related to the registered movement, or the similarity between a part of the extracted skeletal data and a part of the skeletal data related to the registered movement.

[0052] Note that the analysis unit 203 may calculate the above similarity directly using the skeletal data or indirectly using it. For example, the analysis unit 203 may convert at least a part of the skeletal data into another format and calculate the above similarity using the converted data. In this case, the similarity may be the similarity itself between the converted data or a value calculated using the similarity between the converted data.

[0053] The conversion method may be normalization of the image size of the skeleton data, or may be conversion to feature amounts using the angles formed by the skeleton structure (i.e., the degree of bending of joints). Alternatively, the conversion method may be a three-dimensional posture converted by a pre-trained machine learning model.

[0054] Note that the analysis unit 203 may detect a posture or movement from the skeleton data extracted from one image data. Further, the analysis unit 203 may analyze the working operation of a person along the time series from the skeleton data extracted from each of a plurality of image data captured at a plurality of different times. With such a configuration, the image processing system 2 can flexibly analyze the operation corresponding to the change state of the posture or movement to be detected.

[0055] The detection unit 204 receives the signal of the result analyzed by the analysis unit 203, and detects a predetermined event from the received signal. That is, the detection unit 204 in the present embodiment has the same function as the detection unit 22 in the first embodiment.

[0056] The output unit 205 outputs the result information which is the detection result. The destination to which the output unit 205 outputs is the management terminal 80. Note that the second terminal 200 may have a display device (not shown) in the second terminal 200 itself and output predetermined information to the user.

[0057] The second communication unit 206 is a means for communicating with the first terminal 100 and the management terminal 80, and includes, for example, an interface for connecting to the network N1.

[0058] The storage unit 210 is a storage means including a non-volatile memory. The storage unit 210 stores at least a registered operation database 211. The registered operation database 211 includes skeleton data as a registered operation.

[0059] The configuration of the image processing system 2 has been described above. However, the image processing system 2 according to the second embodiment is not limited to the above-described configuration. For example, part or all of the extraction unit 202 included in the image processing system 2 may be included in the imaging device 90. In this case, for example, the imaging device 90 may extract a body image of a person by processing the captured image. Alternatively, the imaging device 90 may further extract at least a part of the skeletal data of the person's body based on features such as joints of the person recognized in the body image from the body image. When the imaging device 90 undertakes such a function, the imaging device 90 supplies at least the skeletal data to the image processing system 2. The imaging device 90 supplies image data to the image processing system 2 in addition to the skeletal data. In addition to the above-described configuration example, the image processing system 2 may include the imaging device 90.

[0060] Next, with reference to FIG. 8, an example of detecting a person's posture will be described. FIG. 8 is a diagram showing skeletal data extracted from image data. The image shown in FIG. 8 is a body image F10 obtained by extracting the body of a person P from an image captured by the imaging device 90. In the image processing system 10, the extraction unit 202 cuts out the body image F10 from the image captured by the imaging device 90 and further sets a skeletal structure.

[0061] The extraction unit 202 extracts, for example, feature points that can be key points of the person P from the image. Further, the extraction unit 202 detects key points from the extracted feature points. When detecting key points, the extraction unit 202 refers to, for example, information learned by machine learning about the images of the key points.

[0062] In the example shown in FIG. 8, the extraction unit 202 detects, as key points of the person P, the head A1, the neck A2, the right shoulder A31, the left shoulder A32, the right elbow A41, the left elbow A42, the right hand A51, the left hand A52, the right hip A61, the left hip A62, the right knee A71, the left knee A72, the right foot A81, and the left foot A82.

[0063] Furthermore, as the pseudo-skeletal structure of the operator P, the extraction unit 202 sets the bones connecting these key points as follows. Bone B1 connects the head A1 and the neck A2. Bone B21 connects the neck A2 and the right shoulder A31, and bone B22 connects the neck A2 and the left shoulder A32. Bone B31 connects the right shoulder A31 and the right elbow A41, and bone B32 connects the left shoulder A32 and the left elbow A42. Bone B41 connects the right elbow A41 and the right hand A51, and bone B42 connects the left elbow A42 and the left hand A52. Bone B51 connects the neck A2 and the right hip A61, and bone B52 connects the neck A2 and the left hip A62. Bone B61 connects the right hip A61 and the right knee A71, and bone B62 connects the left hip A62 and the left knee A72. And bone B71 connects the right knee A71 and the right foot A81, and bone B72 connects the left knee A72 and the left foot A82. When the extraction unit 202 generates the skeletal data related to the above-described skeletal structure, the generated skeletal data is supplied to the analysis unit 103.

[0064] Next, an example of the registration operation database will be described with reference to FIG. 9. FIG. 9 is a diagram for explaining the registration operation database according to the second embodiment. In the table shown in FIG. 9, a registration operation ID (identification, identifier) and a plurality of related words are respectively associated. The related words for the operation with the registration operation ID (or operation ID) of "R01" are "running", "hurrying", etc. The related words for the registration operation ID of "R02" are "walking", "slowly", etc., the related words for the registration operation ID of "R03" are "sitting hunched", "crouching", etc., and the related words for the registration operation ID of "R04" are "sitting hunched", "curled up", etc.

[0065] As described above, the data related to the registration operations included in the registration operation database 211 is stored with an operation ID and related words associated with each operation. Each registration operation ID is associated with one or more skeletal data. That is, for example, the registration operation with the operation ID of "R01" includes the skeletal data indicating the running operation or the hurrying operation.

[0066] Referring to FIG. 10, the skeleton data related to the registration operation will be described. FIG. 10 is a diagram for explaining a first example of the registration operation according to Embodiment 2. FIG. 10 shows the skeleton data related to the operation with the operation ID "R01" among the registration operations included in the registration operation database 211. In FIG. 10, a plurality of skeleton data including the skeleton data F11 and the skeleton data F12 are shown in a state arranged in the left-right direction. The skeleton data F11 is located on the left side of the skeleton data F12. The skeleton data F11 is a posture capturing a scene of a running person. The skeleton data F12 is a scene of a running person and has a posture different from that of the skeleton data F11.

[0067] This means that for the registration operation with the operation ID "R01", after the person takes the posture corresponding to the skeleton data F11, the person takes the posture of the skeleton data F12. Here, although two pieces of skeleton data have been described, the registration operation with the operation ID "R01" may include skeleton data other than the above-described skeleton data.

[0068] FIG. 11 is a diagram for explaining a second example of the registration operation according to Embodiment 2. FIG. 11 shows the skeleton data F31 related to the operation with the operation ID "R03" shown in FIG. 9. For the registration operation with the operation ID "R03", only one piece of skeleton data F31 showing a sitting person is registered.

[0069] As described above, the registration operation included in the registration operation database 211 may include only one piece of skeleton data or may include two or more pieces of skeleton data. The analysis unit 203 of the second terminal 200 compares the registration operation including the above-described skeleton data with the skeleton data received from the extraction unit 202 to determine whether there is a similar registration operation.

[0070] As described above, the second embodiment has been explained. However, the image processing system 2 according to the second embodiment is not limited to the above-described configuration. The first terminal 100 only needs to be communicably connected to one or more imaging devices 90. The first terminal 100 and the imaging device 90 may be connected via the network N1. The image processing system 2 only needs to have one or more first terminals 100. The image processing system 2 may include one or more imaging devices 90. The image processing system 2 may include one or more management terminals 80.

[0071] In the image processing system 2, a configuration in which the first terminal 100 acquires image data from a plurality of cameras and the second terminal 200 further acquires and analyzes these images is adopted, for example, in a predetermined space where a large number of people come and go, such as a street or a residential area. In such a case, it is preferable that the communication between the plurality of imaging devices 90 and the first terminal 100 and the communication between the first terminal 100 and the second terminal 200 have a wide bandwidth. For example, in order to realize such communication, the image processing system 2 may adopt a 5G (fifth-generation mobile communication system) line with a transfer rate of about 10 gigabits per second. By using such a high-speed communication line, the image processing system 2 can transmit and receive and analyze image data having a high frame rate and a high resolution.

[0072] As described above, according to the second embodiment, it is possible to provide an image processing system or the like that can efficiently process images captured by a plurality of cameras. Further, thereby, even when a large number of cameras are installed over a wide area, the present image processing system or the like can efficiently process images captured from various locations over the wide area.

[0073] <Embodiment 3> Next, Embodiment 3 will be described. Embodiment 3 differs from Embodiment 2 in that it further has a search information reception unit 207. FIG. 12 is a block diagram of an image processing system 3 according to Embodiment 3. The image processing system 3 shown in FIG. 12 omits the imaging device 90, the management terminal 80, and the network N1. Also, the first terminal 100 shown in FIG. 12 has the same configuration as in Embodiment 2, and details are omitted. The image processing system 3 has a second terminal 220. The second terminal 220 differs from the second terminal 200 shown in Embodiment 2 in that it has a search information reception unit 207.

[0074] The search information reception unit 207 receives predetermined search information regarding a person's posture or action. The search information is, for example, information supplied from the management terminal 80 to the second terminal 220. When the search information reception unit 207 receives the search information, the analysis unit 203 sets reference skeleton data corresponding to the posture related to the search information, and analyzes whether the reference skeleton data and the skeleton data related to the image are similar. Further, the detection unit 204 detects an event corresponding to the search information based on the result of the analysis. Then, the output unit 205 supplies the detection result corresponding to the search information received from the management terminal 80 to the management terminal 80.

[0075] FIG. 13 is a diagram showing a search process in the image processing system 3 according to Embodiment 3. FIG. 13 shows the information input to the image processing system 3 and the data output by the image processing system 3 according to the input data.

[0076] The image processing system 3 receives, as search conditions, search data indicating a person's posture or movement and accompanying data attached thereto. Here, the search data includes any one of a search word indicating the posture or movement related to the search, body image data, and skeleton data.

[0077] In this case, the search word is, for example, a phrase included in the related words of the registration operation database 211 shown in FIG. 9. Alternatively, the search word may be a phrase that can be associated with the related words of the registration operation database 211. Also, the body image as a search condition is preferably in a form in which skeleton data comparable to the registered operations included in the registration operation database 211 can be extracted. The skeleton data as a search condition is also preferably in a form in which skeleton data comparable to the registered operations included in the registration operation database 211 can be extracted. The additional data as a search condition includes the imaging area to be searched, the imaging date and time, and the like. These search conditions are supplied from the management terminal 80 to the image processing system 3.

[0078] Also, the image processing system 3 acquires image data captured by the imaging device 90 as acquisition data. The image data includes additional data related to the imaging. The additional data may include, for example, the imaging location of the image related to the image data, the ID of the imaging device 90 that captured the image, the imaging date and time, and the like.

[0079] The image processing system 3 has a search information reception unit 207 that receives search information. The image processing system 3 performs processing according to the received search information. Specifically, for example, the detection unit 204 can detect an image of a person corresponding to the posture indicated by the search information as a predetermined event. Then, the image processing system 3 outputs, as a search result corresponding to the search conditions, the image data and the additional data attached to the image data. The image processing system 3 supplies the search result to the management terminal 80.

[0080] With the above configuration, the image processing system 3, for example, receives the search word "running" from the management terminal 80 and answers the management terminal 80 with the image data including the image of the person performing the running motion from the acquired image data. Alternatively, the image processing system 3 answers the management terminal 80 with the data regarding the location and time when the image corresponding to "running" was captured as the information attached to the detected motion.

[0081] The above described Embodiment 3. According to Embodiment 3, it is possible to efficiently perform a search according to desired search conditions set by the user. That is, according to Embodiment 3, it is possible to provide an image processing system or the like that can efficiently process images captured by a camera.

[0082] <Embodiment 4> Next, Embodiment 4 will be described. Embodiment 4 is different from the image processing system 3 according to Embodiment 3 in that it has a first terminal 130 instead of the first terminal 100. FIG. 14 is a block diagram of the image processing system 4 according to Embodiment 4. The image processing system 4 shown in FIG. 14 shows the shooting device 90, the management terminal 80, and the network N1 omitted. Further, the image processing system 4 shown in FIG. 14 shows only the details of 130A among the two first terminals 130 (130A, 130B), and the configuration of 130B is shown omitted, but it is assumed that the two first terminals 130 have the same configuration.

[0083] The first terminal 130 has an extraction unit 112, an analysis unit 113, a detection unit 114, an output unit 115, and a storage unit 120. Note that the extraction unit 112, the analysis unit 113, the detection unit 114, the output unit 115, and the storage unit 120 of the first terminal 130 have the same functions as the extraction unit 202, the analysis unit 203, the detection unit 204, the output unit 205, and the storage unit 210 of the second terminal 200. Therefore, the detailed description is omitted here. Note that the output unit 115 of the first terminal 130 outputs data regarding the result of the detection to the second terminal 200 or the second terminal 220.

[0084] With the above configuration, the image processing system 2 according to the present embodiment has an analysis unit 113 in the first terminal 130 as the first analysis means, and the second terminal 220 has an analysis unit 203 as the second analysis means. In this case, the analysis unit 113 of the first terminal 130 analyzes whether the person image and the first reference skeleton data are similar and generates first analysis result information. The detection unit 114, which is the first detection means, detects an event from the first analysis result information. Also, the analysis unit 203 of the second terminal 220 analyzes whether the person image and the second reference skeleton data are similar and generates second analysis result information. The detection unit 204, which is the second detection means, detects an event from the first analysis result information and the second analysis result information. In this way, the image processing system 4 has the function of the first terminal 130 and the second terminal 220 each extracting skeleton data and further detecting an event. Thereby, the image processing system 4 can distribute the load between the first terminal 130 and the second terminal 220, or share the registration operation to be referred to.

[0085] Note that the image processing system 4 may be such that the analysis unit 113 included in the first terminal 130 generates first analysis result information, and the second terminal 220 detects an event based on a plurality of pieces of first analysis result information acquired from a plurality of first terminals 130. In this way, the image processing system 4 can flexibly perform the function sharing between the first terminal 130 and the second terminal 220.

[0086] Next, the search function of the image processing system 4 in the present embodiment will be described. The search information reception unit 207 in the present embodiment receives, as search information, a search word indicating a predetermined event caused by a person's action. The predetermined event caused by a person's action includes abstract concepts such as "robbery", "fight", "rally", "street performance", "panic", "riot", etc., which do not directly indicate a person's posture or movement. Note that the predetermined event caused by a person's action may also include search words such as "walk" and "run" that have the meaning of directly indicating a person's posture or movement.

[0087] FIG. 15 is a diagram for explaining a registration operation database according to Embodiment 4. The registration operation database shown here has a plurality of operation IDs associated with words or phrases indicating events corresponding to these plurality of operation IDs. Specifically, for example, the skeleton data with the operation ID "R01" and the skeleton data with the operation ID "R11" are associated with the event of "snatching". This indicates that in the event of "snatching", within a predetermined period or simultaneously in parallel, a person performing a plurality of different postures or actions (for example, "R01" indicating "running" and "R11" indicating "falling", etc.) appears. Similarly, in the registration operation database shown in FIG. 15, the skeleton data with the operation IDs "R02", "R12", and "R22" are associated with the event of "fight", and the skeleton data with the operation IDs "R03" and "R13" are associated with the event of "rally".

[0088] Note that the registration operation database shown in FIG. 15 may be possessed by the first terminal 130 or may be possessed by the second terminal 220. The first terminal 130 and the second terminal 220 may store the registration operation database in a shared manner, or one of them may use the registration operation database possessed by the other.

[0089] Next, with reference to FIG. 16, an example of using the above-described registration operation database will be described. FIG. 16 is a diagram showing a search process in an image processing system according to Embodiment 4. FIG. 16 shows information input to the image processing system 4 and data output by the image processing system 4 according to the input data.

[0090] The image processing system 4 receives, as search conditions, a search word indicating an event included in the registration operation database shown in FIG. 15 and its associated data. These search conditions are supplied from the management terminal 80 to the image processing system 4. Alternatively, the search word may be a phrase that can be associated with the events in the registration operation database shown in FIG. 15. The image processing system 4 acquires, as acquisition data, image data captured by the imaging device 90 and its associated data.

[0091] With the above configuration, for example, the image processing system 4 receives a search word "robbery" from the management terminal 80, and answers the management terminal 80 with image data including images of actions related to "robbery" from the acquired image data. Alternatively, the image processing system 4 answers the management terminal 80 with data regarding the location and time when an image corresponding to "robbery" was taken as information attached to the detected action. Thus, in this embodiment, the search information reception unit 207 receives, as search information, a search word indicating a predetermined event caused by a person's action. Then, the detection unit 114 of the first terminal 130 and the detection unit 204 of the second terminal 220 detect an image of a person corresponding to the search word as an event. With the above configuration, the image processing system 4 can detect a predetermined event specified based on skeleton data of at least two persons simultaneously shown in the image. Therefore, the image processing system 4 can detect not only simple postures such as a fall, but also complex situations such as robbery and fight.

[0092] The above describes Embodiment 4. The image processing system 4 according to Embodiment 4 may be such that at least one of the first terminal 130 or the second terminal 220 includes storage means for storing predetermined reference data regarding a person's posture. In the above configuration, when the first terminal 130 performs from acquisition of image data to detection of a predetermined event and the second terminal 220 does not perform analysis of the image data, the second terminal 200 may not have, for example, the extraction unit 202, the analysis unit 203, and the detection unit 204. In this case, the second terminal 220 may have a function of acquiring the results of events respectively detected by the first terminal 130 and aggregating the acquired results. As described above, according to Embodiment 4, it is possible to provide an image processing system or the like that can efficiently process images captured by a camera. Further, thereby, even when a large number of cameras are installed over a wide area, the present image processing system or the like can efficiently process images captured in various locations over the wide area.

[0093] <Modification Example of Embodiment> FIG. 17 is a block diagram showing a variation of the configuration of an image processing system. FIG. 17 shows an image processing system 5. The image processing system 5 has a first terminal 130, a second terminal 220, and a third terminal 300. In the image processing system 5, the first terminal 130, the second terminal 220, and the third terminal 300 are terminals each referred to as MEC (Multi-access Edge Computing). Here, for example, the first terminal 130 may be referred to as L-MEC (Lower-MEC), the second terminal 220 as M-MEC (Middle-MEC), and the third terminal 300 as U-MEC (Upper-MEC).

[0094] The first terminal 130 acquires image data from a plurality of imaging devices 90. The first terminal 130 performs a predetermined first process on the image data acquired from the imaging devices 90. The predetermined first process is the preprocessing described above or a process of detecting predetermined skeleton data. The first terminal 130 performs such a first process and supplies the first-processed data to the second terminal 220.

[0095] The second terminal 220 receives the first-processed data from a plurality of first terminals 130 and performs a second process using the received plurality of first-processed data. The second process is a process of aggregating the first-processed data or a process of detecting predetermined skeleton data from the first-processed data. The second terminal 220 performs such a second process and supplies the second-processed data to the third terminal 300.

[0096] The third terminal 300 receives the second-processed data from a plurality of second terminals 220 and performs a third process using the received plurality of second-processed data. The third process may be, for example, a process of aggregating the second-processed data or a process of further detecting predetermined skeleton data from the second-processed data. The third terminal 300 may be communicably connected to a predetermined management terminal.

[0097] The above describes the modification examples of the embodiments. The modification examples described here can be applied to any of the above-described image processing systems. By dispersedly arranging terminals having such a cascaded processing configuration, the image processing system 5 can suppress more delays and perform image processing efficiently. Further, even when a large number of cameras are installed over a wide area by such a distributed system or a cascaded system, the present image processing system or the like can efficiently process images captured at various locations over a wide area.

[0098] Although the embodiments of the present invention have been described above, these are examples of the present invention, and various configurations other than the above can also be adopted. The configurations of the above-described embodiments may be combined with each other, or some configurations may be replaced with other configurations. Further, the configurations of the above-described embodiments may be variously modified within a range not departing from the gist. Also, the configurations and processes disclosed in the above-described embodiments and modification examples may be combined with each other.

[0099] Also, in the plurality of flowcharts used in the above description, a plurality of steps (processes) are described in order, but the execution order of the steps executed in each embodiment is not limited to the described order. In each embodiment, the order of the illustrated steps can be changed within a range that does not hinder the functions realized by this embodiment. Also, the above-described embodiments can be combined within a range where the contents do not conflict with each other.

[0100] <Example of Hardware Configuration> Hereinafter, a case where each functional configuration of the determination device in the present disclosure is realized by a combination of hardware and software will be described.

[0101] FIG. 18 is a block diagram illustrating the hardware configuration of a computer. The determination device in the present disclosure can realize the above-described functions by a computer 500 including the hardware configuration shown in the figure. The computer 500 may be a portable computer such as a smartphone or a tablet terminal, or may be a stationary computer such as a PC. The computer 500 may be a dedicated computer designed to realize each device, or may be a general-purpose computer. The computer 500 can realize a desired function by installing a predetermined application.

[0102] The computer 500 includes a bus 502, a processor 504, a memory 506, a storage device 508, an input / output interface 510 (the interface is also referred to as an I / F (Interface)), and a network interface 512. The bus 502 is a data transmission path for the processor 504, the memory 506, the storage device 508, the input / output interface 510, and the network interface 512 to transmit and receive data to and from each other. However, the method of connecting the processor 504 and the like to each other is not limited to bus connection.

[0103] The processor 504 is various processors such as a CPU, a GPU, or an FPGA. The memory 506 is a main storage device realized using a RAM (Random Access Memory) or the like.

[0104] The storage device 508 is an auxiliary storage device realized using a hard disk, an SSD, a memory card, or a ROM (Read Only Memory). The storage device 508 stores a program for realizing a desired function. The processor 504 reads this program into the memory 506 and executes it to realize each functional component of each device.

[0105] The input / output interface 510 is an interface for connecting the computer 500 and an input / output device. For example, an input device such as a keyboard and an output device such as a display device are connected to the input / output interface 510.

[0106] The network interface 512 is an interface for connecting the computer 500 to a network.

[0107] As described above, an example of the hardware configuration in the present disclosure has been described, but the above-described embodiments are not limited thereto. The present disclosure can also realize any process by causing a processor to execute a computer program.

[0108] In the above example, when the program is loaded into a computer, it includes a group of instructions (or software code) for causing the computer to perform one or more functions described in the embodiment. The program may be stored in a non-transitory computer-readable medium or a tangible storage medium. By way of example and not limitation, the computer-readable medium or tangible storage medium includes random-access memory (RAM), read-only memory (ROM), flash memory, solid-state drive (SSD) or other memory technologies, CD-ROM, digital versatile disc (DVD), Blu-ray (registered trademark) disc or other optical disc storage, magnetic cassette, magnetic tape, magnetic disk storage or other magnetic storage devices. The program may be transmitted on a transitory computer-readable medium or a communication medium. By way of example and not limitation, the transitory computer-readable medium or communication medium includes electrical, optical, acoustic, or other forms of propagated signals.

[0109] Some or all of the above-described embodiments may be described as follows in the appended claims, but are not limited thereto. (Appended Claim 1) An image processing system having a first terminal and a second terminal that are communicably connected to each other, The first terminal includes image data acquisition means for acquiring image data related to an image of the space from a camera that photographs a predetermined space, At least one of the first terminal or the second terminal includes analysis means for analyzing whether skeletal data related to the body structure of a person included in the image is similar to predetermined reference skeletal data, The second terminal includes detection means for detecting a predetermined event based on the result of the analysis, And output means for outputting result information that is the result of the detection. Image processing system. (Appendix 2) The detection means detects the predetermined event based on the skeletal data of at least two persons included in the image at the same time. The image processing system according to Appendix 1. (Appendix 3) At least one of the first terminal or the second terminal further includes storage means for storing predetermined reference data related to a person's posture. The image processing system according to Appendix 1 or 2. (Appendix 4) The second terminal includes the analysis means, The first terminal supplies preprocessed data obtained by performing predetermined preprocessing on the image data to the second terminal. The image processing system according to any one of Appendices 1 to 3. (Appendix 5) As the preprocessing, the first terminal generates extraction image data obtained by extracting a person image including a person from the image, and supplies the extraction image data to the second terminal. The image processing system according to Appendix 4. (Appendix 6) As the preprocessing, when the number of persons included in the image is less than a threshold value, the first terminal sets a first resolution of the image to be lower than a second resolution of the image when the number of persons included in the image is greater than or equal to the threshold value, and supplies the image to the second terminal. The image processing system described in Supplementary Note 4 or 5. (Supplementary Note 7) The first terminal is provided with first extraction means for generating extraction image data obtained by extracting a first person image from the image data, and first analysis means for analyzing whether or not the first person image and first reference skeleton data are similar to generate first analysis result information. The second terminal is provided with second extraction means for generating extraction image data obtained by extracting a second person image from the image data, and second analysis means for analyzing whether or not the second person image and second reference skeleton data are similar to generate second analysis result information. The detection means performs detection of the event based on the first analysis result information and the second analysis result information. The image processing system according to any one of Supplementary Notes 1 to 3. (Supplementary Note 8) The first terminal is provided with first extraction means for generating extraction image data obtained by extracting a person image from the image data, and analysis means for analyzing whether or not the person image and the reference skeleton data are similar to generate first analysis result information. The second terminal performs detection of the event based on a plurality of pieces of first analysis result information acquired from a plurality of the first terminals. The image processing system according to any one of Supplementary Notes 1 to 3. (Supplementary Note 9) The second terminal further includes a search information reception unit that receives predetermined search information regarding a person's posture or action, the analysis means sets the reference skeleton data corresponding to the posture related to the search information, analyzes whether or not the reference skeleton data and the skeleton data related to the image are similar, and the detection means detects the event corresponding to the search information based on the result of the analysis. The image processing system according to any one of Supplementary Notes 1 to 8. (Supplementary Note 10) The search information receiving unit receives the search information indicating the posture of a person, The detecting means detects an image of a person corresponding to the posture indicated by the search information as the event. The image processing system according to Supplementary Note 9. (Supplementary Note 11) The search information receiving unit receives, as the search information, a search word indicating a predetermined event caused by the action of a person. The detecting means detects an image of a person corresponding to the search word as the event. The image processing system according to Supplementary Note 9. (Supplementary Note 12) An image processing method executed by an image processing system having a first terminal and a second terminal connected to be communicable with each other, The first terminal acquires the image data related to the image of the space from a camera that photographs a predetermined space. At least one of the first terminal and the second terminal analyzes whether the skeletal data related to the body structure of a person included in the image is similar to predetermined reference skeletal data. The second terminal performs detection of a predetermined event based on the result of the analysis. Outputs the result information that is the result of the detection. Image processing method. (Supplementary Note 13) A non-transitory computer-readable medium storing a program for causing an image processing system having a first terminal and a second terminal connected to be communicable with each other to execute the following image processing method, The first terminal acquires the image data related to the image of the space from a camera that photographs a predetermined space. At least one of the first terminal and the second terminal analyzes whether the skeletal data related to the body structure of a person included in the image is similar to predetermined reference skeletal data. The second terminal performs detection of a predetermined event based on the result of the analysis. Outputs the result information that is the result of the detection. Non-transitory computer-readable medium.

Description of Symbols

[0110] 1, 2, 3, 4, 5 Image Processing System 10 First Terminal 11 Image Data Acquisition Unit 20 Second Terminal 21 Analysis Unit 22 Detection Unit 23 Output Unit 80 Management Terminal 90 Photographing Device 91 Photographing Unit 92 Photographing Control Unit 93 Camera Communication Unit 100 First Terminal 101 Image Data Acquisition Unit 102 Pretreatment Unit 103 First Communication Unit 112 Extraction Unit 113 Analysis Unit 114 Detection Unit 115 Output Unit 120 Storage Unit 121 Registered Operation Database 130 First Terminal 200 Second Terminal 201 Image Data Acquisition Unit 202 Extraction Unit 203 Analysis Unit 204 Detection Unit 205 Output Unit 206 Second Communication Unit 207 Search Information Reception Unit 210 Storage Unit 220 Second Terminal 211 Registered Operation Database 300 Third Terminal 500 Computer 504 Processor 506 Memory 508 Storage Device 510 Input / Output Interface 512 Network Interface N1 Network

Claims

1. An image processing system having a first terminal and a second terminal connected to be communicable with each other, wherein the first terminal includes image data acquisition means for acquiring image data relating to an image of a space from a camera that photographs a predetermined space, the second terminal includes analysis means for analyzing whether skeletal data regarding the body structure of a person included in the image is similar to predetermined reference skeletal data, detection means for detecting a predetermined event resulting from a person's posture or movement based on the result of the analysis, and output means for outputting result information that is the result of the detection, wherein the first terminal supplies the second terminal with preprocessed data obtained by performing preprocessing on the image data to set a first resolution of the image when the number of persons included in the image is less than a threshold value to be lower than a second resolution of the image when the number of persons included in the image is greater than or equal to the threshold value, an image processing system.

2. The detection means performs detection of the predetermined event based on the skeletal data of at least two persons simultaneously included in the image. The image processing system according to Claim 1.

3. At least one of the first terminal and the second terminal further includes storage means for storing predetermined reference data regarding a person's posture. The image processing system according to Claim 1 or 2.

4. The first terminal generates extraction image data obtained by extracting a person image including a person from the image as the preprocessing, and supplies the extraction image data to the second terminal. The image processing system according to any one of Claims 1 to 3.

5. The first terminal includes first extraction means for generating extraction image data obtained by extracting a first person image from the image data, and first analysis means for analyzing whether the first person image is similar to first reference skeletal data to generate first analysis result information. The second terminal includes second extraction means for generating extraction image data obtained by extracting a second person image from the image data, and second analysis means for analyzing whether the second person image is similar to second reference skeletal data to generate second analysis result information. The detection means performs detection of the event based on the first analysis result information and the second analysis result information. The image processing system according to any one of Claims 1 to 3.

6. The first terminal includes first extraction means for generating extraction image data obtained by extracting a person image from the image data, analysis means for analyzing whether or not the person image and the reference skeleton data are similar and generating first analysis result information; The second terminal detects the event based on a plurality of pieces of first analysis result information obtained from a plurality of the first terminals. The image processing system according to any one of claims 1 to 3.

7. An image processing system having a first terminal and a second terminal connected to be communicable with each other, The first terminal, image data acquisition means for acquiring image data related to an image of the space from a camera that photographs a predetermined space; first extraction means for generating extracted image data by extracting a first person image from the image data; first analysis means for analyzing whether or not skeleton data related to the structure of the body of the person included in the first person image is similar to first reference skeleton data and generating first analysis result information; The second terminal, second extraction means for generating extracted image data by extracting a second person image from the image data; second analysis means for analyzing whether or not skeleton data related to the structure of the body of the person included in the second person image is similar to second reference skeleton data and generating second analysis result information; detection means for detecting a predetermined event caused by a person's posture or movement based on the first analysis result information and the second analysis result information; output means for outputting result information that is the result of the detection; Image processing system.

8. An image processing method executed by an image processing system having a first terminal and a second terminal connected to be communicable with each other, The first terminal acquires image data related to an image of the space from a camera that photographs a predetermined space, The second terminal analyzes whether or not skeleton data related to the structure of the body of the person included in the image is similar to predetermined reference skeleton data, Based on the result of the analysis, detection for detecting a predetermined event caused by a person's posture or movement is performed, Result information that is the result of the detection is output, The first terminal supplies the second terminal with pre-processed data obtained by performing pre-processing on the image data to set a first resolution of the image when the number of persons included in the image is less than a threshold to be lower than a second resolution of the image when the number of persons included in the image is greater than or equal to the threshold. Image processing method.

9. An image processing method executed by an image processing system having a first terminal and a second terminal connected to be communicable with each other, The first terminal acquires image data related to an image of the space from a camera that captures a predetermined space, generates extraction image data by extracting a first person image from the image data, analyzes whether skeletal data related to the body structure of the person included in the first person image is similar to first reference skeletal data to generate first analysis result information, The second terminal generates extraction image data by extracting a second person image from the image data, analyzes whether skeletal data related to the body structure of the person included in the second person image is similar to second reference skeletal data to generate second analysis result information, detects a predetermined event caused by a person's posture or movement based on the first analysis result information and the second analysis result information, outputs result information that is the result of the detection, An image processing method.

Images