Information processing device, information processing system, information processing method and program

Abstract

This information processing device comprises an object acquisition unit and a risk degree acquisition unit. The object acquisition unit acquires, using analysis information obtained by analyzing a video in which an object region is captured, object information relating to an object that appears in the video. The risk degree acquisition unit derives the degree of risk of the object using the object information. The object information includes the position and state of an accommodating tool.

Description

Information processing device, information processing system, information processing method, and recording medium

[0001] The present invention relates to an information processing device, an information processing system, an information processing method, and a recording medium.

[0002] For example, Patent Document 1 discloses a technology for determining the suspiciousness level of a visitor. Patent Document 1 discloses an example in which the suspiciousness level is determined on a three-level scale of 0, 0.5, or 1 based on whether or not a police officer is nearby and whether or not the visitor has put their hand in their bag. With the technology described in Patent Document 1, if a visitor puts their hand in their bag while a police officer is nearby, this may be an action to take out a weapon or dangerous object, so if the visitor puts their hand in their bag when a police officer is nearby, a 1 is output. Even if a police officer is not nearby, this is a movement that requires caution, so a 0.5 is output. If the visitor does not put their hand in their bag, a 0 is output.

[0003] Patent Document 1 states, "When the skeletal position of the person's hand does not overlap with the position of the bag, it is determined that the hand is not in the bag, and when the skeletal position of the person's hand overlaps with the position of the bag, it is determined that the hand is in the bag. When the action information changes from a state in which the hand is not in the bag to a state in which the bag is in the hand, it is determined that the hand is in the bag."

[0004] Patent Document 2 describes a technology that calculates the feature values ​​of each of multiple key points of a human body contained in an image, searches for images containing human bodies with similar postures or movements based on the calculated feature values, and classifies images with similar postures or movements together.

[0005] JP 2021-135646 A International Publication No. 2021 / 084677

[0006] As described above, the technology described in Patent Document 1 determines whether a person's hand is in a bag based on whether the skeletal position of the person's hand overlaps with the position of the bag. However, if the bag lid is closed, for example, even if the skeletal position of the person's hand overlaps with the position of the bag, it is unlikely that the action represents the removal of a weapon or dangerous object. Therefore, the technology described in Patent Document 1 has difficulty accurately detecting the level of danger in the target area.

[0007] It should be noted that Patent Document 2 does not disclose a technique for detecting the degree of danger in a target area.

[0008] In view of the above-mentioned problems, one example of the object of the present invention is to provide an information processing device, an information processing system, an information processing method, a program, a recording medium, etc. that solve the problem of accurately detecting the degree of danger in a target area.

[0009] According to one aspect of the present invention, there is provided an information processing device comprising: a target acquisition means for acquiring target information relating to a target shown in a video using analysis information obtained by analyzing a video of a target area; and a risk acquisition means for determining a risk level of the target using the target information, wherein the target information includes the position and state of a container.

[0010] According to one aspect of the present invention, there is provided an information processing system comprising: the above-mentioned information processing device; at least one photographing device that photographs the target area and generates an image; and an analysis device that analyzes the image generated by the at least one photographing device and generates the analysis information.

[0011] According to one aspect of the present invention, there is provided an information processing method, which includes one or more computers: acquiring object information about an object shown in an image using analysis information obtained by analyzing an image of a target area; and using the object information to determine the degree of danger of the object, wherein the object information includes the position and state of a container.

[0012] According to one aspect of the present invention, a recording medium is provided having recorded thereon a program that causes one or more computers to acquire target information about the target shown in the image using analysis information obtained by analyzing an image of the target area, and to use the target information to determine the degree of danger of the target, and the target information includes the position and status of a container.

[0013] According to one aspect of the present invention, it is possible to accurately detect the degree of danger in a target area.

[0014] 1 is a diagram illustrating an overview of an information processing device according to embodiment 1. FIG. 2 is a diagram illustrating an overview of an information processing system according to embodiment 1. FIG. 3 is a flowchart illustrating an overview of information processing according to embodiment 1. FIG. 4 is a diagram illustrating an example of a configuration of an information processing system according to embodiment 1. FIG. 5 is a diagram illustrating an example of a functional configuration of an information processing device according to embodiment 1. FIG. 6 is a diagram illustrating an example of a physical configuration of an information processing device according to embodiment 1. FIG. 7 is a flowchart illustrating an example of danger detection processing according to embodiment 1. FIG. 8 is a diagram illustrating an example of a danger level determination criterion according to embodiment 1. FIG. 9 is a diagram illustrating an example of a functional configuration of an information processing device according to embodiment 2. FIG. 10 is a flowchart illustrating an example of danger detection processing according to embodiment 2. FIG. 11 is a diagram illustrating an example of a danger level determination criterion according to embodiment 1. FIG. 12 is a diagram illustrating an example of a configuration of an information processing system according to embodiment 3. FIG. 13 is a diagram illustrating an example of a functional configuration of an information processing device according to embodiment 3. FIG. 14 is a flowchart illustrating an example of danger detection processing according to embodiment 3. FIG. 15 is a diagram illustrating an example of a functional configuration of an information processing device according to embodiment 4. FIG. 16 is a flowchart illustrating an example of danger detection processing according to embodiment 4. FIG. 17 is a diagram illustrating an example of a danger level determination criterion according to embodiment 4.

[0015] Hereinafter, embodiments of the present invention will be described with reference to the drawings. In all the drawings, like components are designated by like reference numerals, and the description thereof will be omitted as appropriate.

[0016] 1 is a diagram showing an overview of an information processing device 103 according to embodiment 1. The information processing device 103 includes an object acquisition unit 111 and a risk level acquisition unit 112.

[0017] The object acquisition unit 111 acquires object information about the object shown in the image using analysis information obtained by analyzing the image of the object area. The danger level acquisition unit 112 uses the object information to calculate the danger level of the object. The object information includes the position and state of the container.

[0018] According to this information processing device 103, it is possible to accurately detect the degree of danger in a target area.

[0019] 2 is a diagram showing an overview of an information processing system 100 according to embodiment 1. The information processing system 100 includes an information processing device 103, at least one image capturing device 101, and an analysis device 102. The image capturing device 101 captures an image of a target area and generates an image. The analysis device 102 analyzes the image generated by the at least one image capturing device 101 and generates analysis information.

[0020] According to this information processing system 100, it is possible to accurately detect the degree of danger in a target area.

[0021] FIG. 3 is a flowchart showing an outline of information processing according to the first embodiment.

[0022] The object acquisition unit 111 acquires object information relating to the object shown in the image using analysis information obtained by analyzing the image of the object area (step S102).

[0023] The risk level obtaining unit 112 obtains the risk level of the target using the target information (step S103).

[0024] The target information includes the location and status of the container.

[0025] This information processing makes it possible to accurately detect the degree of danger in the target area.

[0026] A detailed example of the information processing system 100 according to the first embodiment will be described below.

[0027] (Details) (Configuration Example of Information Processing System 100 According to First Embodiment) FIG. 4 is a diagram showing a configuration example of the information processing system 100 according to the first embodiment. The information processing system 100 is a system for accurately detecting the degree of danger in a target area. The target area is any area to be monitored or the like. The information processing system 100 includes at least one of the imaging devices 101_1 to 101_K, an analysis device 102, and an information processing device 103.

[0028] K is an integer equal to or greater than 1. When the image capturing devices 101_1 to 101_K are not particularly distinguished from one another, they are also referred to as "image capturing devices 101."

[0029] At least one of the imaging devices 101_1 to 101_K, the analysis device 102, and the information processing device 103 are connected to each other via a network N that is configured using a wired or wireless connection or a combination of these, and transmit and receive information to and from each other via the network N.

[0030] Each of the at least one image capturing device 101 is a device that captures an image of a target area and generates an image.

[0031] (Example of Functional Configuration of Analysis Device 102 According to First Embodiment) The analysis device 102 acquires images generated by at least one imaging device 101, for example, via a network N. Note that the method by which the analysis device 102 acquires images is not limited to this.

[0032] The analysis device 102 analyzes the video acquired from at least one image capture device 101 to generate analysis information. The analysis information includes, for example, image feature quantities of objects captured in the video. Note that the analysis information may include at least one piece of information generated by the analysis process described below.

[0033] Here, the term "object" includes both objects and people. Note that the object may be only an object.

[0034] In detail, the analysis device 102 has one or more analysis functions that perform processing (analysis processing) to analyze video. The analysis functions that the analysis device 102 has are one or more of: (1) object detection function, (2) face analysis function, (3) human figure analysis function, (4) posture analysis function, (5) behavior analysis function, (6) appearance attribute analysis function, (7) gradient feature analysis function, (8) color feature analysis function, (9) movement line analysis function, etc. However, the analysis functions that the analysis device 102 has are not limited to these.

[0035] (1) The object detection function detects an object from an image. The object detection function can also determine the position of an object within an image. For example, YOLO (You Only Look Once) is a model that can be applied to the object detection process.

[0036] (2) The face analysis function detects human faces from images, extracts the features of the detected faces (facial feature values), and classifies the detected faces (classification). The face analysis function can also determine the position of the face within the image. The face analysis function can also determine the identity of people detected from different images based on the similarity between the facial feature values ​​of people detected from different images.

[0037] (3) The human morphology analysis function extracts the physical characteristics of people in images (for example, values ​​indicating overall characteristics such as whether they are fat or thin, height, and clothing), and classifies (classifies) people in images. The human morphology analysis function can also identify the position of a person in an image. The human morphology analysis function can also determine the identity of people in different images based on the physical characteristics of the people in the different images.

[0038] (4) The posture analysis function detects the joint points of people in the image and creates a stick figure model by connecting the joint points. The posture analysis function then uses the information from the stick figure model to estimate the posture of the people, extract the feature values ​​of the estimated posture (posture feature values), and classify (classify) the people in the image. The posture analysis function can also determine the identity of people in different images based on the posture feature values ​​of the people in the different images.

[0039] For example, the posture analysis function estimates postures such as standing, crouching, and bending from an image and extracts posture feature values ​​that indicate each posture.Furthermore, for example, the posture analysis function can estimate the posture of an object detected using an object detection function or the like from an image and extract posture feature values ​​that indicate that posture.

[0040] For example, the technology disclosed in Patent Document 2 can be applied to the posture analysis function.

[0041] (5) The behavior analysis process can estimate the movement of a person using information about the stick figure model, changes in posture, and the like, extract features of the person's movement (movement features), and classify (classify) people included in the image. The behavior analysis process can also estimate the height of a person and identify the position of the person in the image using information about the stick figure model. The behavior analysis process can estimate behaviors such as changes or transitions in posture and movements (changes or transitions in position) from the image and extract movement features of the behavior.

[0042] (6) The appearance attribute analysis function can recognize appearance attributes associated with a person. The appearance attribute analysis function extracts features (appearance attribute features) related to the recognized appearance attributes and classifies (classifies) people included in an image. Appearance attributes are attributes related to the appearance of a person. Appearance attributes include, for example, one or more of age group, gender, type and color of clothing, type and color of shoes, hairstyle, whether or not a hat is worn, whether or not a tie is worn, whether or not glasses are worn, whether or not an umbrella is carried, whether or not an umbrella is used, and whether or not gloves are worn.

[0043] (7) The gradient feature analysis function extracts gradient feature quantities (gradient feature quantities) in an image. For example, techniques such as SIFT, SURF, RIFF, ORB, BRISK, CARD, and HOG can be applied to the gradient feature detection process. SIFT is an abbreviation for Scale-Invariant Feature Transform. SURF is an abbreviation for Speeded-Up Robust Features. RIFF is an abbreviation for Rotation-Invariant Fast Feature. BRIEF is an abbreviation for Binary Robust Independent Elementary Features. ORB is an abbreviation for Oriented FAST and Rotated BRIEF. BRISK is an abbreviation for Binary Robust Invariant Scalable Keypoints. CARD is an abbreviation for Compact and Real-time Descriptors. HOG is an abbreviation for Histograms of Oriented Gradients.

[0044] (8) The color feature analysis function can detect objects from an image, extract color features of the detected objects, and classify the detected objects. The color features are, for example, color histograms.

[0045] (9) The flow line analysis function can determine the flow line (trajectory of movement) of a person included in a video, for example, using the result of the identity determination in any of the above-mentioned analysis functions (2) to (6). In more detail, for example, by connecting a person determined to be the same between chronologically different images, the flow line of the person can be determined. Note that, in cases where images of different target areas captured by multiple image capture devices 101 are acquired, the flow line analysis function can also determine the flow line spanning multiple images captured in different capture areas.

[0046] The image features described above include, for example, object detection results, facial features, human body features, posture features, movement features, appearance attribute features, gradient features, color features, and movement lines. Note that each of the analysis functions (1) to (9) may appropriately use the results of analysis performed by other analysis functions.

[0047] The information processing device 103 may have the functions of the analysis device 102. In this case, the information processing system 100 does not need to have the functions of the analysis device 102.

[0048] (Example of functional configuration of information processing device 103 according to embodiment 1) Fig. 5 is a diagram showing an example of the functional configuration of the information processing device 103 according to embodiment 1. The information processing device 103 is a device for detecting the level of danger in a target area using analysis information that is the result of analyzing a video. The information processing device 103 functionally includes, for example, a target acquisition unit 111, a risk level acquisition unit 112, and a notification unit 113.

[0049] The object acquiring unit 111 acquires, for example, analysis information from the analysis device 102 via the network N. The object acquiring unit 111 acquires object information related to the object using the acquired analysis information.

[0050] The analysis information includes, for example, image feature amounts of objects shown in the video as described above. The analysis information may also include the video from which the analysis information was generated.

[0051] The target is a predetermined type of object. The target according to this embodiment is a container. The container may be any object capable of containing dangerous goods or other objects. In more detail, examples of the container include a bag, backpack, suitcase, trolley, plastic bottle, and water bottle. Examples of dangerous goods include bladed weapons, swords, blunt objects, guns, toxic drugs, and easily ignitable flammable materials (e.g., gasoline).

[0052] The target information is information about a target, and may be any information that can be obtained using the analysis information.

[0053] The target information according to this embodiment includes the location and status of the container.

[0054] The position of the contained item is, for example, information indicating a position within the video. The position of the contained item may be expressed in a coordinate system appropriately defined for the video, such as a coordinate system used in the video analysis process. Note that the position of the contained item is not limited to this, and may be, for example, a position in real space determined from the position within the video.

[0055] The state of the contained item is, for example, information indicating the state of the contained item that is determined from analytical information related to the contained item.

[0056] The risk level acquisition unit 112 calculates the risk level of the target using the target information acquired by the target acquisition unit 111. The risk level of the target is an index such as a value indicating the degree of risk of the target. An example of a method by which the risk level acquisition unit 112 calculates the risk level of the target from the target information will be described later.

[0057] The notification unit 113 notifies the degree of danger of the target calculated by the danger level acquisition unit 112 .

[0058] (Example of a physical configuration of the information processing system 100 according to the first embodiment) The information processing system 100 is physically configured from at least one image capturing device (e.g., a camera) 101, an analysis device 102, and an information processing device 103, which are connected via a network N. Each of the devices 101 to 103 is configured from a single, physically different device.

[0059] The analysis device 102 and the information processing device 103 may be physically configured as a single device. Alternatively, one or more of the analysis device 102 and the information processing device 103 may be physically configured as multiple devices connected via an appropriate communication line such as a network N.

[0060] The analysis device 102 and the information processing device 103 according to this embodiment may have the same physical configuration. Here, an example of the physical configuration of the information processing device 103 will be described with reference to the drawings.

[0061] 6 is a diagram showing an example of the physical configuration of the information processing device 103 according to embodiment 1. The information processing device 103 physically includes, for example, a bus 1010, a processor 1020, a memory 1030, a storage device 1040, a network interface 1050, an input interface 1060, and an output interface 1070.

[0062] The bus 1010 is a data transmission path for transmitting and receiving data among the processor 1020, memory 1030, storage device 1040, network interface 1050, input interface 1060, and output interface 1070. However, the method of connecting the processor 1020 and the like to each other is not limited to bus connection.

[0063] The processor 1020 is implemented as a CPU (Central Processing Unit) or a GPU (Graphics Processing Unit).

[0064] The memory 1030 is a main storage device realized by a RAM (Random Access Memory) or the like.

[0065] 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), or the like. The storage device 1040 stores program modules for realizing the functions of the device that includes the storage device 1040. The processor 1020 loads each of these program modules into the memory 1030 and executes them to realize the function corresponding to that program module.

[0066] The network interface 1050 is an interface for connecting a device having the network interface 1050 to the network N.

[0067] The input interface 1060 is an interface for a user to input information, and is configured with one or more of, for example, a touch panel, a keyboard, a mouse, and the like.

[0068] The output interface 1070 is an interface for presenting information to the user, and is configured, for example, by a liquid crystal panel, an organic EL (Electro-Luminescence) panel, or the like.

[0069] So far, an example of the configuration of the information processing system 100 according to the first embodiment has been described. Next, the operation of the information processing system 100 according to this embodiment will be described.

[0070] (Operation of Information Processing System 100 According to First Embodiment) The information processing system 100 according to the first embodiment executes information processing including analysis processing and risk detection processing.

[0071] The analysis process is a process for analyzing video. The analysis process is performed by the analysis device 102. In the analysis process, the analysis device 102 acquires at least one video from the imaging device 101. The analysis device 102 analyzes the acquired video and generates analysis information including image feature quantities and the like. The analysis process is performed in real time, for example, by acquiring video as needed. Note that the analysis process is not limited to this, and may be performed using video captured during a predetermined period of time that is stored in a storage unit (not shown). The predetermined period may be specified by the user, for example.

[0072] (Example of danger detection processing according to embodiment 1) FIG. 7 is a flowchart showing an example of danger detection processing according to embodiment 1. The danger detection processing is processing for detecting the degree of danger in a target area using analysis information generated in the analysis processing. The danger detection processing is performed repeatedly in real time, for example. Note that the danger detection processing is not limited to this, and may be performed using analysis information generated based on video captured over a predetermined period of time in response to a user instruction, for example.

[0073] The object acquiring unit 111 acquires, for example, analysis information from the analysis device 102 via the network N (step S101).

[0074] The object acquiring unit 111 acquires object information related to the object using the analysis information acquired in step S101 (step S102).

[0075] In more detail, for example, the target is an object capable of containing hazardous materials. Whether or not a container can contain hazardous materials may be determined based on the size of the contained items. In this case, for example, the target acquisition unit 111 uses the analysis information to extract contained items that are equal to or larger than a predetermined size from the objects detected in the video, and acquires target information related to the extracted contained items.

[0076] The risk level acquisition unit 112 uses the target information acquired in step S102 to determine the risk level of the target (step S103).

[0077] In detail, for example, the risk level acquisition unit 112 further uses predetermined risk level determination criteria to determine the risk level of the target.

[0078] The risk determination criteria are information indicating criteria for determining the risk of an object. The risk determination criteria are stored in advance in the risk acquisition unit 112, for example.

[0079] For example, the risk assessment criteria may associate one or more conditions with a risk level. In this case, the one or more conditions may be, for example, conditions that the target must meet in the event of a predicted risk or a pre-stage of the risk. In addition, in this case, the risk level may be determined according to, for example, the possibility that a risk will occur or the possibility that the risk will materialize under the conditions.

[0080] The risk level acquisition unit 112 determines whether the target satisfies one or more conditions using the target information, for example. If the target satisfies the conditions, the risk level acquisition unit 112 calculates the risk level of the target as the risk level associated with the conditions.

[0081] 8 is a diagram showing an example of the risk determination criterion CT1 according to embodiment 1. The risk determination criterion CT1 illustrated in the drawing includes criterion 1 to criterion 3. Note that the risk determination criterion only needs to include at least one criterion.

[0082] Criterion 1 associates condition A with risk level DR1. Criterion 2 associates conditions B and C with risk level DR2. Criterion 3 associates conditions A and D with risk level DR3. Conditions A and B are examples of conditions that use the state of the contained items. Condition C is an example of a condition that uses the position of the contained items. Condition D is an example of a condition that uses the duration of the associated state.

[0083] More specifically, condition A indicates that the bag is in an open state. Condition A is a condition that is satisfied by the bag in a stage prior to causing injury with a blade, for example.

[0084] Here, the open state means a state in which the lid, zipper, etc. of the contained item is open and the inside is open, and the same applies hereinafter.

[0085] The risk level DR1 may be set to an index such as a value corresponding to the likelihood of a risk of injury with a blade occurring when the bag is open, for example.

[0086] Condition B indicates that the plastic bottle is in an open state. Condition C indicates that the plastic bottle is placed on the floor. Conditions B and C are conditions that are satisfied by a plastic bottle containing a dangerous substance, such as poison or gasoline, before it is kicked in order to spread the substance around.

[0087] The risk level DR2 may be set to an index such as a value corresponding to the likelihood that the danger of the contained dangerous material being dispersed will become a reality if the plastic bottle is placed open on the floor, for example.

[0088] Condition D indicates that the associated state (condition A in the example shown in the figure) continues for a predetermined time T1 or more. Conditions A and D are conditions that are satisfied by a bag in a stage prior to causing an injury with a blade, for example.

[0089] The risk level DR3 may be set to an index such as a value corresponding to the likelihood that the risk of injury with a blade will become a reality if the bag remains open for a predetermined time period T1 or longer.

[0090] In this example, the risks assumed in Criterion 1 and Criterion 3 are similar actions. Because opening a bag and removing its contents is a common occurrence, Condition A is likely to include the state of the bag corresponding to such a common action. In Criterion 3, this possibility can be reduced by adding Condition D to Condition A. Therefore, it is advisable to set DR1 to a value that indicates a lower degree of risk than DR3, for example.

[0091] The risk assessment criteria are not limited to those described here, and for example, the anticipated risk and its precursory stages, the conditions and criteria that the target must meet at that time, etc. are not limited to the above examples. For example, Criterion 2 may further include a condition that the plastic bottle contains liquid.

[0092] When using the risk determination criteria illustrated in Figure 8, the risk acquisition unit 112 determines, for example, whether the target satisfies any of condition A, conditions B and C, or conditions A and D, using the target information.

[0093] If the object satisfies any of the conditions, the risk level obtaining unit 112 obtains the risk level associated with that condition as the risk level of the object.

[0094] For example, if a bag satisfies condition A, the risk level acquisition unit 112 calculates DR1 as the risk level of the bag. If a plastic bottle satisfies conditions B and C, the risk level acquisition unit 112 calculates DR2 as the risk level of the plastic bottle. If a bag satisfies conditions A and D, the risk level acquisition unit 112 calculates DR3 as the risk level of the bag.

[0095] Note that if the conditions of criterion 3 (conditions A and D) are satisfied, the condition of criterion 1 (condition A) is also satisfied. When the conditions included in two criteria are such that one criterion (e.g., condition A of criterion 1) encompasses the conditions of the other criterion (e.g., conditions A and D of criterion 3), the criterion that includes the encompassed condition (e.g., criterion 3) should be applied preferentially. In other words, in such a case, the risk level acquisition unit 112 determines the risk level (e.g., DR3) associated with the encompassed condition (e.g., criterion 3) as the risk level of the target.

[0096] Referring again to Fig. 7, the notification unit 113 notifies the degree of danger of the object calculated in step S103 (step S104), and the danger detection process ends.

[0097] The notification method may be various, for example, one or more of a sound, a display, and the like.

[0098] When notifying by sound, the notifying unit 113 may notify by changing the manner of the sound (type, pitch, volume, etc.) according to the level of the calculated danger level.

[0099] When notifying by display, the notifying unit 113 may display a screen in which a mark indicating the target is superimposed on an image showing the target. The mark may be determined as appropriate, and may be, for example, a frame of a predetermined shape (e.g., rectangle, circle, ellipse, etc.) surrounding the target, an arrow pointing to the target, or a figure associated with the target. When a frame is used as the mark, the notifying unit 113 may, for example, change the form of the frame (type of line, thickness, color, etc.) depending on the magnitude of the calculated risk level.

[0100] Furthermore, when the calculated risk level is equal to or greater than a threshold value, the notification unit 113 may notify, by sound, display, or the like, that an object with a risk level equal to or greater than a predetermined value has been detected.

[0101] According to this type of danger detection process, since the target information includes the location and status of the container, the degree of danger of the container can be determined using both the location and status of the container. Furthermore, by issuing a notification, the user or the like can easily know the determined degree of danger.

[0102] (Operations and Effects) As described above, according to this embodiment, the information processing device 103 includes the object acquisition unit 111 and the risk level acquisition unit 112 .

[0103] The object acquisition unit 111 acquires object information about the object shown in the image using analysis information obtained by analyzing the image of the object area. The danger level acquisition unit 112 uses the object information to calculate the danger level of the object. The object information includes the position and state of the container.

[0104] This allows the degree of danger of the container to be determined using both the position and state of the container, making it possible to accurately detect the degree of danger in the target area.

[0105] Second Embodiment In a second embodiment, an example will be described in which the target includes objects other than the contents and people.

[0106] In this embodiment, for the sake of simplicity, descriptions that overlap with those of the first embodiment will be omitted as appropriate.

[0107] The information processing system according to the second embodiment includes an information processing device 203 instead of the information processing device 103 according to the first embodiment. Except for this, the information processing system according to this embodiment may be configured similarly to the information processing system 100 according to the first embodiment.

[0108] 9 is a diagram illustrating an example of the functional configuration of an information processing device 203 according to embodiment 2. Functionally, the information processing device 203 includes, for example, an object acquisition unit 211 and a risk level acquisition unit 212 that replace the object acquisition unit 111 and the risk level acquisition unit 112 according to embodiment 1. Furthermore, functionally, the information processing device 203 further includes, for example, a positional relationship acquisition unit 214 and a notification unit 113 similar to those in embodiment 1.

[0109] The object acquiring unit 211 acquires object information related to the object using the analysis information acquired from the analysis device 102, similar to the object acquiring unit 111 according to the first embodiment.

[0110] The target according to this embodiment includes objects including contents and people.

[0111] The target information according to this embodiment includes the position and attributes of an object and the position and attributes of a person.

[0112] The positions of the objects and people may be the same as the positions of the contained items described in the first embodiment, and are, for example, information indicating the respective positions within the video.

[0113] The attributes of the object include the state of the container. The attributes of the object may include at least one of the state of objects other than the container, the posture of objects including the container, etc. However, the attributes of the object are not limited to these.

[0114] The attributes of the person may include at least one of the person's movement, the person's movement speed, the person's posture, and the presence or absence and state of an attachment worn by the person.

[0115] For example, the object of wear is a glove, and the state of the object of wear in this case is that the glove is worn on only one hand (symmetry of the object of wear), for example, because a person may wear a glove only on the hand holding a plastic bottle containing a hazardous material.

[0116] The attributes of a person may include, for example, not holding an object in at least one hand, holding an object in only one hand, etc. However, the attributes of a person are not limited to this.

[0117] The positional relationship acquisition unit 214 uses the object information to determine the positional relationship of the objects. When multiple objects appear in the video (i.e., when the object information includes the positions of multiple objects), the positional relationship acquisition unit 214 may determine the positional relationship of the objects.

[0118] The positional relationship of the objects is, for example, the positional relationship between each pair of multiple objects. In detail, for example, the positional relationship of the objects is the positional relationship between an object and a person, and the positional relationship between people when multiple people are included in the video.

[0119] The positional relationship between an object and a person is, for example, a relationship in which a person is holding an object such as a container or a plastic bottle. The positional relationship between an object and a person is, for example, a relationship in which a person is holding an object such as a bag or a backpack in front of them. The positional relationship between an object and a person is, for example, a relationship in which a plastic bottle is placed at the person's feet, or a relationship in which a plastic bottle is placed at the person's feet and in front of them. "At the person's feet" is an example of being within a predetermined range from the person. Note that the positional relationship between an object and a person is not limited to these.

[0120] The risk level acquisition unit 212, like the risk level acquisition unit 112 according to the first embodiment, uses the object information acquired by the object acquisition unit 211 to determine the risk level of the object.

[0121] The danger level of the object in this embodiment includes at least one of the danger level of the object (including the danger level of the container), the danger level of the person, and the danger level of the combination of the object (including the container) and the person.

[0122] The risk level acquisition unit 212 according to the present embodiment may determine the risk level of the target by further using the positional relationship of the target acquired by the positional relationship acquisition unit 214. That is, the risk level acquisition unit 212 may determine the risk level of the target by using the target information and, when multiple targets appear in the video, the positional relationship between the targets.

[0123] So far, we have mainly described an example of the functional configuration of the information processing system according to embodiment 2. The information processing system according to this embodiment may be physically configured in the same manner as the information processing system 100 according to embodiment 1. From here, we will describe an example of the operation of the information processing system according to this embodiment.

[0124] (Operation of Information Processing System According to Embodiment 2) The information processing system according to embodiment 2 executes information processing including analysis processing and danger detection processing, similar to the information processing system 100 according to embodiment 1. The analysis processing may be the same as in embodiment 1. The danger detection processing according to this embodiment is processing that replaces the danger detection processing according to embodiment 1. The danger detection processing according to this embodiment will be described below with reference to the drawings.

[0125] FIG. 10 is a flowchart illustrating an example of a risk detection process according to the second embodiment.

[0126] The object acquisition unit 211 executes step S101 similar to that in the first embodiment.

[0127] As in the first embodiment, the object acquiring unit 211 acquires object information related to the object using the analysis information acquired in step S101 (step S202).

[0128] The target information acquired in step S202 according to this embodiment includes the position and attributes of an object and the position and attributes of a person.

[0129] If the object information acquired in step S202 includes the positions of multiple objects, the positional relationship acquisition unit 214 obtains the positional relationship of the objects (step S205).

[0130] In detail, for example, the positional relationship acquisition unit 214 determines whether the object information acquired in step S202 includes the positions of multiple objects. If the object information includes the positions of multiple objects, the positional relationship acquisition unit 214 determines the positional relationship between the multiple objects. If the object information does not include the positions of multiple objects, the positional relationship acquisition unit 214 does not execute step S205, and the next step S203 is executed.

[0131] The risk level acquisition unit 212 calculates the risk level of the target using the target information and positional relationship acquired in steps S202 and S205 (step S203).

[0132] In detail, for example, if the positional relationship of the target is not acquired in step S205, the risk level acquisition unit 212 calculates the risk level of the target using the target information acquired in step S202. If the positional relationship of the target is acquired in step S205, the risk level acquisition unit 212 calculates the risk level of the target using the target information and positional relationship acquired in steps S202 and S205.

[0133] The risk level acquisition unit 212 may calculate the risk level of the object by further using predetermined risk level determination criteria, similar to the risk level acquisition unit 112 according to embodiment 1. The risk level determination criteria according to this embodiment may include the positional relationship of the object as a condition.

[0134] 11 is a diagram showing an example of the risk determination criterion CT2 according to embodiment 2. The risk determination criterion CT2 illustrated in the drawing includes criterion 4 and criterion 5. Note that the risk determination criterion CT2 is not limited to those described here.

[0135] Criterion 4 associates conditions A and E with a risk level DR4. Criterion 5 associates conditions B and F with a risk level DR5. Conditions E and F are examples of conditions that use the positional relationship between an object and a person. In particular, condition F is an example of a condition that uses the positional relationship between the object and the person, "under and in front of the person," and the state of the object, "placed on the floor."

[0136] Conditions A and E, like condition A or the combination of conditions A and D described in the first embodiment, are conditions that are satisfied by a bag in the stage prior to causing injury with a blade, for example.

[0137] The risk level DR4 may be set to an index such as a value corresponding to the likelihood of a person being injured by a bladed object if the bag is open and held in front of the person, for example.

[0138] Conditions B and F, like the combination of conditions B and C described in embodiment 1, are conditions that are satisfied by a plastic bottle containing a dangerous substance, such as poison or gasoline, before the bottle is kicked in order to spread the dangerous substance around.

[0139] The risk level DR5 may be set to an index such as a value corresponding to the likelihood that the danger of the contained dangerous material being dispersed will become a reality if the plastic bottle is placed in an open state on the floor at and in front of a person.

[0140] When using the danger level determination criterion CT2 illustrated in Figure 11, the danger level acquisition unit 212 determines, for example, whether the object satisfies conditions A and E, or conditions B and F, using the object information and the object's positional relationship.

[0141] If the object satisfies any of the conditions, the risk level acquisition unit 212 determines the risk level of the object to be the risk level associated with that condition.

[0142] For example, if a bag satisfies conditions A and E, the risk level acquisition unit 212 calculates a risk level of DR4 for the bag. If a plastic bottle satisfies conditions B and F, the risk level acquisition unit 212 calculates a risk level of DR5 for the plastic bottle.

[0143] When using criterion 4, the risk level DR4 may be calculated as the risk level of a person who satisfies the conditions included in criterion 4, or as the risk level of a combination of a person and a bag who satisfies the conditions included in criterion 4. Similarly, for criterion 5, the risk level DR5 may be calculated as the risk level of a person who satisfies the conditions included in criterion 5, or as the risk level of a combination of a person and a plastic bottle who satisfies the conditions included in criterion 5.

[0144] Referring again to Fig. 10, the notification unit 113 notifies the degree of danger of the object calculated in step S203 (step S104), as in the first embodiment, and ends the danger detection process.

[0145] According to such danger detection processing, the positional relationship of the target, including objects and people, can be further used to determine the degree of danger of the target.

[0146] (Actions and Effects) As described above, according to this embodiment, the target further includes a person. The target information further includes the position of the person. The risk level acquisition unit 212 uses the target information to determine the risk level for either the container or the person, or for the combination of the container and the person.

[0147] This allows the degree of danger to be calculated for the target (either the container or the person, or a combination of the container and the person) by further using the positional relationship between the container and the person, making it possible to accurately detect the degree of danger in the target area.

[0148] According to this embodiment, the target information includes the positions and attributes of objects including a container, and the positions and attributes of a person. The object attributes include the state of the container. The person attributes include at least one of the person's movement, the person's posture, and the presence or absence and state of an accessory worn by the person.

[0149] This makes it possible to calculate the degree of danger of a target using various information about the object and person, such as the position and attributes of the object and person, thereby enabling the degree of danger in the target area to be detected with high accuracy.

[0150] According to this embodiment, the risk level acquisition unit 212 obtains the risk level of the target using the target information and the positional relationship of the target.

[0151] This allows the positional relationship of the object to be further used to determine the degree of danger of the object, thereby enabling the degree of danger in the object area to be detected with high accuracy.

[0152] Third Embodiment In a third embodiment, an example will be described in which the risk level of an object is calculated when a precondition is satisfied. In addition, in this embodiment, an example will be described in which sensor information generated by a sensor device is used as the precondition.

[0153] In this embodiment, for the sake of simplicity, descriptions that overlap with other embodiments will be omitted as appropriate.

[0154] 12 is a diagram showing an example of the configuration of an information processing system 300 according to embodiment 3. The information processing system 300 includes at least one imaging device 101 and analysis device 102 similar to those of embodiment 1, and an information processing device 303 that replaces the information processing device 103 according to embodiment 1. The information processing system 300 further includes at least one sensor device 104_1 to 104_L.

[0155] L is an integer equal to or greater than 1. When the sensor devices 104_1 to 104_L are not particularly distinguished from one another, they are also referred to as "sensor devices 104."

[0156] At least one imaging device 101, an analysis device 102, an information processing device 103, and at least one sensor device 104 are connected to each other via a network N similar to that of embodiment 1, and send and receive information to and from each other via the network N.

[0157] The sensor device 104 includes one or more sensors, and generates sensor information detected by each of the one or more sensors. The sensor device 104 transmits the generated sensor information to the information processing device 303.

[0158] The sensor may be one or more of a sound sensor for detecting sounds such as screams and shouts, a heat sensor for detecting heat such as flames during a fire, and an odor sensor for detecting odors such as toxic drugs and flammable materials (e.g., gasoline).

[0159] (Example of a functional configuration of an information processing device 303 according to embodiment 3) Fig. 13 is a diagram showing an example of a functional configuration of an information processing device 303 according to embodiment 3. Functionally, the information processing device 303 includes, for example, a risk level acquisition unit 312 that replaces the risk level acquisition unit 112 according to embodiment 1. Except for this point, the information processing device 303 may be configured similarly to the information processing device 103 according to embodiment 1. Note that the information processing device 303 may include, instead of the object acquisition unit 111, an object acquisition unit 211 similar to that of embodiment 2.

[0160] The risk level acquisition unit 312 calculates the risk level of the target using the target information when a predetermined precondition is detected. The precondition is, for example, the detection of one or more of a sound of a predetermined volume or more, heat of a predetermined volume or more, and a predetermined odor.

[0161] In detail, for example, the risk level acquisition unit 312 includes a premise detection unit 312a and a target risk level acquisition unit 312b.

[0162] The premise detection unit 312a detects a predetermined premise by using at least one of the sensor information and the target information. In this embodiment, an example in which the premise detection unit 312a detects a predetermined premise by using the sensor information will be described later.

[0163] When a predetermined precondition is detected, the object danger level acquisition unit 312b uses the object information to determine the object danger level.

[0164] So far, we have mainly described an example of the functional configuration of the information processing system 300 according to embodiment 3. The information processing system 300 according to this embodiment may be physically composed of devices 101, 102, and 303 configured in the same manner as the information processing system 100 according to embodiment 1, and a sensor device 104 including various sensors. From here, we will describe an example of the operation of the information processing system according to this embodiment.

[0165] (Operation of the information processing system 300 according to the third embodiment) The information processing system 300 according to the third embodiment executes information processing including analysis processing and danger detection processing, similar to the information processing system 100 according to the first embodiment. The analysis processing may be the same as that according to the first embodiment. The danger detection processing according to this embodiment is processing that replaces the danger detection processing according to the first embodiment. The danger detection processing according to this embodiment will be described below with reference to the drawings.

[0166] FIG. 14 is a flowchart illustrating an example of a risk detection process according to the third embodiment.

[0167] Steps S101 to S102 similar to those in the first embodiment are executed.

[0168] The premise detection unit 312a detects a predetermined premise using sensor information (step S302).

[0169] In more detail, for example, the premise detection unit 312a acquires sensor information from the sensor device 104 via the network N. The premise detection unit 312a determines whether the acquired sensor information satisfies a predetermined premise. If the sensor information satisfies the premise, the premise detection unit 312a determines that the premise has been detected. If the sensor information does not satisfy the premise, the premise detection unit 312a determines that the premise has not been detected.

[0170] If the precondition is detected (step S302; Yes), the object danger level acquisition unit 312b calculates the danger level of the object using the object information acquired in step S102 (step S103), as in embodiment 1. Then, the notification unit 113 executes step S104, as in embodiment 1, to terminate the danger detection process. If the precondition is not detected (step S302; No), the object danger level acquisition unit 312b terminates the danger detection process.

[0171] (Operations and Effects) As described above, according to this embodiment, when a predetermined precondition is detected, the risk level acquisition unit 312 uses the target information to determine the risk level of the target.

[0172] This allows the degree of danger of the target to be calculated on the condition that the preconditions are satisfied, thereby making it possible to detect the degree of danger in the target area with higher accuracy.

[0173] According to this embodiment, the risk level acquisition unit 312 includes a premise detection unit 312a and an object risk level acquisition unit 312b. The premise detection unit 312a detects a predetermined premise using at least one of the sensor information and the object information. When the predetermined premise is detected, the object risk level acquisition unit 312b calculates the risk level of the object using the object information.

[0174] This allows the degree of danger of the target to be calculated on the condition that the preconditions are satisfied, thereby making it possible to detect the degree of danger in the target area with higher accuracy.

[0175] (Modification 1) The sensor information may be used as a criterion for determining the degree of danger as a condition for determining the degree of danger.

[0176] The preconditions may include conditions detected using the target information or information obtained from the target information. That is, the risk level acquisition unit 112 may detect predetermined preconditions using at least one of the sensor information and the target information. Examples of such preconditions include the following a to d.

[0177] Prerequisite condition a is that the relative relationship between the object (at least one of a person and an object) and the crowd satisfies a criterion. In detail, prerequisite condition a is, for example, that there is a person who is looked at by multiple people within a predetermined distance, or that there is a person who is surrounded by multiple people at a predetermined distance (surrounded), etc.

[0178] Precondition b is that there is a person looking in the direction of the surveillance camera. In detail, for example, the person looking in the direction of the surveillance camera is a person whose line of sight is made contact with the surveillance camera.

[0179] Precondition c is that the frequency or rate (e.g., temporal rate) at which a face can be detected is smaller than the standard value in the target region by a predetermined value or more. This is an example of a precondition that an action to avoid capturing a face is taken.

[0180] Precondition d is that someone has performed an action that is prohibited in the target area. In detail, for example, an action that is prohibited in the target area is taking out a cigarette on a train. This is an example of a precondition that is an action that could lead to a dispute.

[0181] This modification also provides the same effects as those of the third embodiment.

[0182] Fourth Embodiment In a fourth embodiment, an example will be described in which the risk level of a target is calculated by further using the history of target information.

[0183] In this embodiment, for the sake of simplicity, descriptions that overlap with other embodiments will be omitted as appropriate.

[0184] The information processing system according to the fourth embodiment includes an information processing device 403 instead of the information processing device 103 according to the first embodiment. Except for this, the information processing system according to this embodiment may be configured similarly to the information processing system 100 according to the first embodiment.

[0185] 15 is a diagram illustrating an example of the functional configuration of an information processing device 403 according to embodiment 4. The information processing device 403 functionally includes, for example, a target acquisition unit 411 and a risk level acquisition unit 412. The information processing device 403 functionally further includes, for example, a positional relationship acquisition unit 214 similar to that of embodiment 2, and a notification unit 113 similar to that of embodiment 1.

[0186] The object acquiring unit 411 acquires object information related to the object using the analysis information acquired from the analysis device 102, similar to the object acquiring unit 211 according to the second embodiment.

[0187] That is, the target according to this embodiment includes an object including contents and a person, similar to the second embodiment. Furthermore, the target information according to this embodiment includes the position and attributes of the object and the position and attributes of the person, similar to the second embodiment.

[0188] The object acquisition unit 411 according to the present embodiment stores the acquired object information. That is, the object acquisition unit 411 according to the present embodiment stores a history of the object information. The history of the object information is, for example, information that associates the object information with the shooting time of the video that was the source of generating the object information.

[0189] The target and target information may be the same as those in embodiment 1. The target acquisition unit 411 has the same function as the target acquisition unit 111 according to embodiment 1, and may store a history of target information similar to that in embodiment 1.

[0190] Similar to the risk level acquisition unit 212 in embodiment 2, the risk level acquisition unit 412 calculates the risk level of the target using the target information acquired by the target acquisition unit 211 and the positional relationship of the target acquired by the positional relationship acquisition unit 214.

[0191] The risk level acquisition unit 412 according to this embodiment further uses the history of the target information to determine the risk level of the target.

[0192] The risk level acquisition unit 412 may obtain the risk level of the target using the target information and its history similar to those in the first embodiment.

[0193] Up to this point, we have mainly described an example of the functional configuration of the information processing system according to embodiment 4. The information processing system according to this embodiment may be physically configured in the same manner as the information processing system 100 according to embodiment 1. From here, we will describe an example of the operation of the information processing system according to this embodiment.

[0194] (Operation of Information Processing System According to Embodiment 4) The information processing system according to embodiment 4 executes information processing including analysis processing and danger detection processing, similar to the information processing system 100 according to embodiment 1. The analysis processing may be the same as in embodiment 1. The danger detection processing according to this embodiment is processing that replaces the danger detection processing according to embodiment 1. The danger detection processing according to this embodiment will be described below with reference to the drawings.

[0195] FIG. 16 is a flowchart illustrating an example of a risk detection process according to the fourth embodiment.

[0196] The object acquisition unit 411 executes step S101 similar to that in the first embodiment.

[0197] The object acquiring unit 411 acquires object information related to the object in the same manner as in the first embodiment using the analysis information acquired in step S101, and stores the acquired object information (step S402).

[0198] As in the second embodiment, when the object information acquired in step S402 includes the positions of a plurality of objects, the positional relationship acquisition unit 214 obtains the positional relationship of the objects (step S205).

[0199] The positional relationship acquisition unit 214 may store a history of the positional relationship of the target. The history of the positional relationship of the target is, for example, information that associates the positional relationship of the target with the shooting time of the video that was the source of generating the positional relationship of the target.

[0200] The risk level acquisition unit 412 calculates the risk level of the target by using the target information and positional relationship acquired in steps S402 and S205, as well as the target information history (step S403).

[0201] In detail, for example, the risk level acquisition unit 412 may determine the risk level of the target by further using predetermined risk level determination criteria, similar to the risk level acquisition unit 112 according to embodiment 1. The risk level determination criteria according to this embodiment may include a condition that uses at least a part of the history of the target information.

[0202] 17 is a diagram showing an example of the risk determination criterion CT3 according to the fourth embodiment. The risk determination criterion CT3 shown in the drawing includes criterion 6.

[0203] Criterion 6 associates conditions G and H with risk level DR6. Conditions G and H are examples of conditions that use the history of target information for objects and people. Condition G is an example of a condition that uses the history related to a person, that is, "the person has passed by in the past." Condition H is an example of a condition that uses the history related to an object (contents contained therein), that is, "the bag the person is carrying is larger than the previous time."

[0204] Conditions G and H are conditions that are met by, for example, a person who, after inspecting a site, attempts to perform a dangerous act at the site using a dangerous object such as a knife carried in a bag. Carrying a larger bag than the previous time means that there is a high possibility that the bag contains a dangerous object.

[0205] DR6 may be set to an index such as a value corresponding to the likelihood of danger becoming a reality, for example, when a person who has passed by in the past is carrying a larger bag than the previous time.

[0206] When using the danger level determination criterion CT3 illustrated in Figure 17, the danger level acquisition unit 412 determines whether the target satisfies conditions G and H using, for example, the target information, the target's positional relationship, and the target information history.

[0207] Then, when the object satisfies the conditions (i.e., conditions G and H in this embodiment), the risk level acquisition unit 412 determines the risk level of the object as the risk level associated with the conditions (i.e., DR6 in this embodiment).

[0208] The danger level determination criterion CT3 is not limited to the one described here and may include, for example, only condition G. The danger level determination criterion CT3 may also include a condition using the history of the positional relationship of the object. In this case, the danger level acquisition unit 412 may further use the history of the positional relationship of the object to determine the danger level of the object.

[0209] Referring again to Fig. 16, the notification unit 113 notifies the degree of danger of the object calculated in step S403 (step S104), as in the first embodiment, and ends the danger detection process.

[0210] According to such a risk detection process, the risk level of the target can be determined by further using the history of the target information.

[0211] (Operations and Effects) As described above, according to this embodiment, the risk level acquisition unit 412 further uses the history of the target information to determine the risk level of the target.

[0212] This allows the history of the target information to be further used to obtain a more accurate level of risk for the target, thereby making it possible to more accurately detect the level of risk in the target area.

[0213] Although the embodiments and modifications of the present invention have been described above with reference to the drawings, these are merely examples of the present invention, and various other configurations can also be adopted.

[0214] In addition, although the flowcharts used in the above description show multiple steps (processes) in a sequential order, the order of steps performed in each embodiment is not limited to the order shown. In each embodiment, the order of steps shown in the drawings can be changed as long as it does not cause any problems in terms of content. Furthermore, the above-described embodiments and variations can be combined as long as the content is not contradictory.

[0215] Some or all of the above-described embodiments can be described as, but are not limited to, the following supplementary notes.

[0216] 1. An information processing device comprising: an object acquisition means that acquires object information about an object shown in an image by using analysis information obtained by analyzing an image of a target area; and a risk acquisition means that uses the object information to determine a risk level of the object, wherein the object information includes a position and a state of a container. 2. The information processing device described in 1., wherein the object further includes a person, and the object information further includes a position of the person, and the risk acquisition means uses the object information to determine a risk level for either the container or the person, or a combination of the container and the person. 3. The information processing device described in 2., wherein the object information includes a position and an attribute of an object including the container and a position and an attribute of the person, the attribute of the object includes a state of the container, and the attribute of the person includes at least one of a movement of the person, a posture of the person, and the presence or absence and a state of an attachment worn by the person. 4. The information processing device described in any one of 1. to 3., wherein the risk acquisition means uses the object information and the positional relationship of the object to determine a risk level of the object. 5. The information processing device according to any one of 1. to 4., wherein the risk level acquisition means, when a predetermined precondition is detected, calculates a risk level of the object using the object information. 6. The information processing device according to 5., wherein the risk level acquisition means includes: a precondition detection means that detects the predetermined precondition using at least one of sensor information and the object information; and an object risk level acquisition means that, when the predetermined precondition is detected, calculates a risk level of the object using the object information. 7. The information processing device according to any one of 1. to 6., wherein the risk level acquisition means further calculates a risk level of the object by using a history of the object information. 8. An information processing system comprising: the information processing device according to any one of 1. to 7.; at least one imaging device that captures an image of the object area and generates an image; and an analysis device that analyzes the image generated by the at least one imaging means and generates the analysis information.9. An information processing method including one or more computers: acquiring object information about an object shown in an image using analysis information obtained by analyzing an image of a target area, and calculating a degree of danger of the object using the object information, the object information including the position and state of a container. 10. An information processing method described in 9., wherein the object further includes a person, and the object information further includes the position of the person, and calculating the degree of danger includes using the object information to calculate a degree of danger for either the container or the person, or a combination of the container and the person. 11. An information processing method described in 10., wherein the object information includes the position and attributes of an object including the container and the position and attributes of the person, the attributes of the object include the state of the container, and the attributes of the person include at least one of the person's movement, the person's posture, and the presence or absence and state of an attachment worn by the person. 12. Calculating the degree of danger includes using the object information and the positional relationship of the object to calculate the degree of danger of the object. 13. The information processing method according to any one of 9. to 12., wherein calculating the degree of danger includes using the object information to calculate the degree of danger of the object when a predetermined precondition is detected. 14. The information processing method according to 13., wherein calculating the degree of danger includes detecting the predetermined precondition using at least one of sensor information and the object information, and calculating the degree of danger of the object using the object information when the predetermined precondition is detected. 15. The information processing method according to any one of 9. to 14., wherein calculating the degree of danger includes further using a history of the object information to calculate the degree of danger of the object. 16. A program causing one or more computers to: acquire object information related to an object shown in an image using analysis information obtained by analyzing an image of a target area, and calculate the degree of danger of the object using the object information, wherein the object information includes the position and status of a container.17. The program described in 16., wherein the object further includes a person, and the object information further includes the position of the person, and the calculating the degree of danger uses the object information to calculate the degree of danger for either the container or the person, or a combination of the container and the person. 18. The program described in 17., wherein the object information includes the position and attributes of an object including the container and the position and attributes of the person, the attributes of the object include the state of the container, and the attributes of the person include at least one of the movement of the person, the posture of the person, and the presence or absence and state of an attachment worn by the person. 19. The program described in any one of 16. to 18., wherein the calculating the degree of danger uses the object information and the positional relationship of the object to calculate the degree of danger for the object. 20. The program described in any one of 16. to 19., wherein the calculating the degree of danger uses the object information and the positional relationship of the object to calculate the degree of danger for the object when a predetermined precondition is detected. 21. The program according to 20., wherein calculating the degree of risk includes detecting the predetermined precondition using at least one of sensor information and the object information, and calculating the degree of risk of the object using the object information when the predetermined precondition is detected. 22. The program according to any one of 16. to 21., wherein calculating the degree of risk includes further using a history of the object information to calculate the degree of risk of the object. 23. A recording medium having recorded thereon the program according to any one of 16. to 22.

[0217] This application claims priority based on Japanese Patent Application No. 2022-211664, filed December 28, 2022, the disclosure of which is incorporated herein in its entirety.

[0218] 100, 300 Information processing system 101 Imaging device 102 Analysis device 103, 203, 303, 403 Information processing device 104 Sensor device 111, 211, 411 Object acquisition unit 112, 212, 312, 412 Risk level acquisition unit 113 Notification unit 214 Positional relationship acquisition unit 312a Premise detection unit 312b Object risk level acquisition unit CT1 to CT5 Risk level determination criteria

Claims

1. an object acquisition means for acquiring object information relating to an object shown in a captured image by using analysis information obtained by analyzing the captured image of the object area; a risk level acquisition means for acquiring a risk level of the object using the object information, The target information includes the location and status of the container. Information processing device.

2. The object further includes a person; The target information further includes a position of the person; The risk level acquisition means uses the target information to obtain a risk level for either the container or the person, or a combination of the container and the person. The information processing device according to claim 1 .

3. the target information includes the position and attributes of the object including the container and the position and attributes of the person; The attributes of the object include the state of the container; The attributes of the person include at least one of the movement of the person, the posture of the person, and the presence or absence and state of an accessory worn by the person. The information processing device according to claim 2 .

4. The risk level obtaining means obtains a risk level of the object using the object information and a positional relationship of the object. The information processing device according to claim 1 .

5. The risk level obtaining means obtains a risk level of the object using the object information when a predetermined precondition is detected. The information processing device according to claim 1 .

6. The risk level acquisition means a precondition detection means for detecting the predetermined precondition using at least one of the sensor information and the target information; and an object risk level acquisition means for determining a risk level of the object using the object information when the predetermined precondition is detected. The information processing device according to claim 5 .

7. The risk level obtaining means further uses the history of the target information to obtain the risk level of the target. The information processing device according to claim 1 .

8. An information processing device according to any one of claims 1 to 3; at least one image capture device for capturing an image of the target area and generating an image; an analysis device that analyzes the video generated by the at least one imaging device and generates the analysis information; Information processing system.

9. One or more computers Using analysis information obtained by analyzing the video of the target area, target information regarding the target shown in the video is acquired; determining a risk level of the object using the object information; The target information includes the location and status of the container. Information processing methods.

10. On one or more computers, Using analysis information obtained by analyzing the video of the target area, target information regarding the target shown in the video is acquired; Execute determining a degree of risk of the object using the object information; The program for the target information to include the location and status of the container.