Information processing device, 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

Technical Field

[0001] The present invention relates to an information processing apparatus , love an information processing method, and a program.

Background Art

[0002] For example, Patent Document 1 discloses a technique for determining the suspiciousness of a visitor. Patent Document 1 discloses an example of determining the suspiciousness in three levels of 0, 0.5, or 1 based on whether a police officer is nearby to and whether the visitor puts a hand into a bag. In the technique described in Patent Document 1, when the visitor puts a hand into the bag, since there is a possibility that it is an action of taking out a weapon or a dangerous object, 1 is output when the visitor puts a hand into the bag when a police officer is nearby. Since it is also a movement that requires caution even when a police officer is not nearby, 0.5 is output. When the action of putting a hand into the bag is not performed, 0 is output.

[0003] Patent Document 1 also states that "when the skeletal position of a person's hand and the position of the bag do not overlap, it is determined that the hand is not in the bag, and when the skeletal position of the person's hand and the position of the bag overlap, it is determined that the hand is in the bag. When changing from the state where the hand is not in the bag, which is the motion information, to the state where the hand is in the bag, it is determined that the hand is being put into the bag."

[0004] Note that Patent Document 2 describes a technique for calculating the feature amount of each of a plurality of key points of a human body included in an image, and searching for an image including a human body with a similar posture or a human body with a similar motion based on the calculated feature amount, or classifying together those with similar postures and motions.

Prior Art Documents

Patent Documents

[0005]

Patent Document 1

Patent Document 2

[0006] The technology described in Patent Document 1 determines whether a hand is inside a bag based on whether the skeletal position of a person's hand and the position of the bag overlap. However, if the bag's lid is closed, for example, even if the skeletal position of a person's hand and the position of the bag overlap, the likelihood of the action being to retrieve a weapon or dangerous object is low. Therefore, the technology described in Patent Document 1 makes it difficult to accurately detect the degree of danger in the target area.

[0007] Furthermore, Patent Document 2 does not disclose any technology for detecting the degree of danger in the target area.

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

[0009] According to one aspect of the present invention, A target acquisition means that uses analytical information obtained by analyzing video footage of a target area to acquire target information about the object shown in the video, When predetermined conditions are detected, The system includes a risk acquisition means for determining the risk level of the target using the aforementioned target information, The aforementioned information includes the location and condition of the storage container. fruit, The aforementioned predetermined preconditions include at least one of the following: the relative relationship between the object and the crowd satisfies predetermined criteria; the person is looking in the direction of the surveillance camera; the frequency or proportion of face detection is less than or equal to a predetermined value compared to the standard value in the target area; and the person has performed an act prohibited in the target area. nothing An information processing device is provided.

[0011] According to one aspect of the present invention, One or more computers, Using the analysis information obtained by analyzing the video of the target area, target information regarding the target shown in the video is acquired. When predetermined conditions are detected, This includes obtaining the degree of risk of the target using the target information. The target information includes the position and state of the storage device. fruit, The aforementioned predetermined preconditions include at least one of the following: the relative relationship between the object and the crowd satisfies predetermined criteria; the person is looking in the direction of the surveillance camera; the frequency or proportion of face detection is less than or equal to a predetermined value compared to the standard value in the target area; and the person has performed an act prohibited in the target area. including An information processing method is provided.

[0012] According to one aspect of the present invention, one or more computers are caused to Using the analysis information obtained by analyzing the video of the target area, target information regarding the target shown in the video is acquired. When predetermined conditions are detected, execute obtaining the degree of risk of the target using the target information, where the target information includes the position and state of the storage device. fruit, The aforementioned predetermined preconditions include at least one of the following: the relative relationship between the object and the crowd satisfies predetermined criteria; the person is looking in the direction of the surveillance camera; the frequency or proportion of face detection is less than or equal to a predetermined value compared to the standard value in the area in question; and the person has performed an act prohibited in the area in question. program Mu is provided.

Advantages of the Invention

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

Brief Description of the Drawings

[0014] [Figure 1] It is a diagram showing an overview of the information processing apparatus according to Embodiment 1. [Figure 2] It is a diagram showing an overview of the information processing system according to Embodiment 1. [Figure 3] It is a flowchart showing an overview of the information processing according to Embodiment 1. [Figure 4] It is a diagram showing a configuration example of the information processing system according to Embodiment 1. [Figure 5] It is a diagram showing a functional configuration example of the information processing apparatus according to Embodiment 1. [Figure 6]This figure shows an example of the physical configuration of the information processing device according to Embodiment 1. [Figure 7] This flowchart shows an example of the hazard detection process according to Embodiment 1. [Figure 8] This figure shows an example of the risk assessment criteria according to Embodiment 1. [Figure 9] This figure shows an example of the functional configuration of the information processing device according to Embodiment 2. [Figure 10] This flowchart shows an example of the hazard detection process according to Embodiment 2. [Figure 11] This figure shows an example of the risk assessment criteria according to Embodiment 2. [Figure 12] This figure shows an example configuration of the information processing system according to Embodiment 3. [Figure 13] This figure shows an example of the functional configuration of the information processing device according to Embodiment 3. [Figure 14] This flowchart shows an example of the hazard detection process according to Embodiment 3. [Figure 15] This figure shows an example of the functional configuration of the information processing device according to Embodiment 4. [Figure 16] This flowchart shows an example of the hazard detection process according to Embodiment 4. [Figure 17] This figure shows an example of the risk assessment criteria according to Embodiment 4. [Modes for carrying out the invention]

[0015] Embodiments of the present invention will be described below with reference to the drawings. In all drawings, similar components are denoted by the same reference numerals, and their descriptions are omitted where appropriate.

[0016] <Embodiment 1> (overview) Figure 1 shows an overview of the information processing device 103 according to Embodiment 1. The information processing device 103 includes a target acquisition unit 111 and a risk level acquisition unit 112.

[0017] The target acquisition unit 111 acquires target information about the object shown in the video by analyzing the video footage of the target area. The risk assessment unit 112 uses the target information to determine the risk level of the object. The target information includes the location and condition of the containment device.

[0018] This information processing device 103 makes it possible to accurately detect the degree of danger in the target area.

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

[0020] This information processing system 100 makes it possible to accurately detect the degree of danger in the target area.

[0021] Figure 3 is a flowchart showing an overview of the information processing according to Embodiment 1.

[0022] The target acquisition unit 111 acquires target information relating to the object shown in the video by analyzing the video footage of the target area (step S102).

[0023] The risk assessment unit 112 uses the target information to determine the risk level of the target (step S103).

[0024] The information includes the location and condition of the storage containers.

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

[0026] The following describes a detailed example of the information processing system 100 according to Embodiment 1.

[0027] (detail) (Example of the configuration of the information processing system 100 according to Embodiment 1) Figure 4 shows an example configuration of the information processing system 100 according to Embodiment 1. 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, etc. The information processing system 100 comprises at least one imaging device 101_1 to 101_K, an analysis device 102, and an information processing device 103.

[0028] K is an integer greater than or equal to 1. If no particular distinction is made between the imaging devices 101_1 to 101_K, they are also referred to as "imaging device 101".

[0029] At least one imaging device 101_1 to 101_K, an analysis device 102, and an information processing device 103 are connected to each other via a network N configured by wire, wireless, or a combination thereof, and transmit and receive information to each other via the network N.

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

[0031] (Example of functional configuration of the analysis device 102 according to Embodiment 1) The analysis device 102 acquires the video generated by at least one of the imaging devices 101, for example, via a network N. However, the method by which the analysis device 102 acquires the video is not limited to this.

[0032] The analysis device 102 analyzes the video acquired from at least one imaging device 101 and generates analysis information. The analysis information includes, for example, image features of objects shown in the video. The analysis information may also include at least one of the pieces of information generated by the analysis process described below.

[0033] Here, "object" includes both things and people. However, "object" may refer only to things.

[0034] In detail, the analysis device 102 is equipped with one or more analysis functions that perform processing (analysis processing) for analyzing video. The analysis functions provided by the analysis device 102 include one or more of the following: (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, and (9) movement path analysis function. However, the analysis functions provided by the analysis device 102 are not limited to these.

[0035] (1) Object detection functionality detects objects from an image. Object detection functionality can also determine the location of objects within an image. One example of a model applied to object detection processing is YOLO (You Only Look Once).

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

[0037] (3) The human figure analysis function extracts the physical characteristics of people in an image (for example, values ​​indicating overall characteristics such as body shape, height, and clothing), and classifies (categorizes) the people in the image. The human figure analysis function can also identify the position of a person within an image. The human figure analysis function can also determine the identity of people in different images based on the physical characteristics of people in those different images.

[0038] (4) The posture analysis function detects the joint points of a person from an 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 person's posture, extracts the estimated posture features, and classifies the person in the image. The posture analysis function can also determine the identity of a person in different images based on the posture features of the person in those different images.

[0039] For example, the posture analysis function estimates postures such as standing, squatting, and crouching from an image and extracts posture features that represent each posture. Alternatively, the posture analysis function can estimate the posture of an object detected using an object detection function from an image and extract posture features that represent that posture.

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

[0041] (5) Behavioral analysis function This method uses information from stick figure models, changes in posture, etc., to estimate human movement, extract movement features (motion features), and classify (categorize) people contained in images. (Behavioral analysis) function Therefore, information from a stick-figure model can be used to estimate a person's height or to determine their position within an image. (Behavioral analysis) function For example, it can estimate actions such as changes or transitions in posture or movement (changes or transitions in position) from an image and extract motion features of those actions.

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

[0043] (7) The gradient feature analysis function extracts gradient features (gradient features) from an image. Analysis functionTechnologies such as SIFT, SURF, RIFF, ORB, BRISK, CARD, and HOG can be applied to this. 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 from the detected objects, and classify the detected objects. Color features include, for example, a color histogram.

[0045] (9) The movement analysis function can determine the movement (trajectory of movement) of a person included in the video by using, for example, the result of identity determination in any of the analysis functions (2) to (6) described above. More specifically, for example, the movement of a person can be determined by connecting a person who has been determined to be the same person across images that are different in time series. The movement analysis function can also determine movement that spans across multiple videos taken from different shooting areas, for example, when videos of different target areas have been acquired from each of the multiple shooting devices 101.

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

[0047] The information processing device 103 may also 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 the functional configuration of the information processing device 103 according to Embodiment 1) Figure 5 shows 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 degree of danger in a target area using analysis information obtained as a result of analyzing video. Functionally, the information processing device 103 includes, for example, a target acquisition unit 111, a danger level acquisition unit 112, and a notification unit 113.

[0049] The target acquisition unit 111 acquires analysis information from, for example, the analysis device 102 via the network N. The target acquisition unit 111 then uses the acquired analysis information to acquire target information about the target.

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

[0051] The object is an object of a predetermined type. In this embodiment, the object is a container. The container can be any object capable of containing dangerous goods or other items. Specifically, for example, the container may be a bag, backpack, suitcase, trolley, plastic bottle, water bottle, etc. Dangerous goods may be knives, firearms and bladed weapons, blunt instruments, guns, toxic drugs, easily ignitable flammable materials (e.g., gasoline), etc.

[0052] The target information is information about the subject. The target information can be any information that can be obtained using the analytical information.

[0053] The information to be considered in this embodiment includes the position and state of the storage container.

[0054] Detention Ingredients The location is, for example, information indicating the position within the video. Ingredients The position should be expressed in a coordinate system that is appropriately determined for the video, such as the coordinate system used in video analysis processing. Ingredients The position is not limited to this; for example, it could be a position in real space determined from the position within the video.

[0055] Detention Ingredients The state is, for example, containment. Ingredients The containment determined from the analytical information relating to the above Ingredients This is information indicating the state of [something].

[0056] The risk assessment unit 112 uses the target information acquired by the target acquisition unit 111 to determine the risk level of the target. The risk level of the target is an indicator such as a value that shows the degree of danger of the target. An example of how the risk assessment unit 112 determines the risk level of the target from the target information will be described later.

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

[0058] (Example of physical configuration of the information processing system 100 according to Embodiment 1) The information processing system 100 consists of at least one imaging device (e.g., a camera) 101, an analysis device 102, and an information processing device 103, all physically connected via a network N. Each of the devices 101 to 103 consists of a single, physically distinct device.

[0059] The analysis device 102 and the information processing device 103 may be physically composed of a single device. Alternatively, one or more of the analysis device 102 and the information processing device 103 may be physically composed of 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 are preferably configured similarly in terms of physical structure. Here, using the information processing device 103 as an example, a physical configuration example will be described with reference to the figure.

[0061] Figure 6 shows an example of the physical configuration of the information processing device 103 according to Embodiment 1. Physically, the information processing device 103 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] Bus 1010 is a data transmission path for the processor 1020, memory 1030, storage device 1040, network interface 1050, input interface 1060, and output interface 1070 to send and receive data to and from each other. However, the method of connecting the processor 1020 and other components to each other is not limited to bus connection.

[0063] The 1020 processor is a processor implemented in components such as the CPU (Central Processing Unit) and GPU (Graphics Processing Unit).

[0064] Memory 1030 is a main memory device implemented using RAM (Random Access Memory), etc.

[0065] The storage device 1040 is an auxiliary storage device implemented as an HDD (Hard Disk Drive), SSD (Solid State Drive), memory card, or ROM (Read Only Memory). The storage device 1040 stores program modules for realizing the functions of the device equipped with it. The processor 1020 loads each of these program modules into memory 1030 and executes them, thereby realizing the functions corresponding to those program modules.

[0066] The network interface 1050 is an interface for connecting a device equipped with it to network N.

[0067] The input interface 1060 is an interface for the user to input information. The input interface 1060 consists of one or more components, such as a touch panel, keyboard, and mouse.

[0068] The output interface 1070 is an interface for presenting information to the user. The output interface 1070 is composed of, for example, a liquid crystal panel, an organic EL (Electro-Luminescence) panel, etc.

[0069] We have so far described an example configuration of the information processing system 100 according to Embodiment 1. From here, we will describe the operation of the information processing system 100 according to this embodiment.

[0070] (Operation of the information processing system 100 according to Embodiment 1) The information processing system 100 according to Embodiment 1 performs information processing including analysis processing and risk detection processing.

[0071] The analysis process is the process for analyzing the video. The analysis process is performed by the analysis device 102. In the analysis process, the analysis device 102 , small At least one video is acquired from the camera 101. The analysis device 102 analyzes the acquired video and generates analysis information including image features. The analysis process is performed in real time, for example, by acquiring video as it progresses. However, the analysis process is not limited to this, and may also be performed using video captured during a predetermined period stored in a memory unit (not shown). The predetermined period may be specified by the user, for example.

[0072] (Example of risk detection processing according to Embodiment 1) Figure 7 is a flowchart illustrating an example of hazard detection processing according to Embodiment 1. Hazard detection processing is a process for detecting the degree of hazard in a target area using analysis information generated in the analysis process. Hazard detection processing is performed repeatedly in real time, for example. However, hazard detection processing is not limited to this, and may also be performed using analysis information generated based on video footage taken over a predetermined period, for example, in response to user instructions.

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

[0074] The target acquisition unit 111 acquires target information about the target using the analysis information acquired in step S101 (step S102).

[0075] More specifically, the subject is an object capable of containing hazardous materials. Whether or not a container is capable of containing hazardous materials depends on the container's capacity. Ingredients The determination may also be based on the size. In this case, for example, the target acquisition unit 111 uses the analysis information to determine whether an object detected from the video is of a predetermined size or larger. Ingredients Extract the extracted contents Ingredients Obtain relevant information.

[0076] The risk assessment 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 assessment unit 112 uses predetermined risk assessment criteria to determine the risk level of the target.

[0078] The risk assessment criteria are information that indicates the criteria for determining the risk level of an object. The risk assessment criteria are stored in advance in the risk acquisition unit 112, for example.

[0079] For example, risk assessment criteria associate one or more conditions with a degree of risk. In this case, one or more conditions may be, for example, the anticipated risk or the conditions that the subject must meet in the preceding stage. Furthermore, the degree of risk in this case may be determined, for example, according to the likelihood that the risk is occurring under those conditions or the likelihood that the risk will materialize.

[0080] The risk assessment unit 112, for example, uses the target information to determine whether the target satisfies one or more conditions. If the target satisfies the conditions, the risk assessment unit 112 calculates the risk associated with those conditions as the risk level of the target.

[0081] Figure 8 shows an example of the risk assessment criterion CT1 according to Embodiment 1. The risk assessment criterion CT1 illustrated in the figure includes criteria 1 to 3. Note that the risk assessment criterion only needs to include at least one criterion.

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

[0083] In detail, condition A indicates that the bag is open. Condition A is a condition that the bag must satisfy in the stage prior to, for example, inflicting injury with a knife.

[0084] Here, the open state refers to the containment state. Ingredients This refers to a state where the lid, zipper, etc., is open and the interior is exposed, and the same applies below.

[0085] For the DR1 risk level, it would be good to set an index that reflects the likelihood of a real-world risk of injury from a knife, for example, if the bag is left open.

[0086] Condition B indicates that the plastic bottle is open. Condition C indicates that the plastic bottle is placed on the floor. Conditions B and C are conditions that a plastic bottle must satisfy before it is kicked to scatter a hazardous substance, such as poison or gasoline, into the surrounding area.

[0087] For the hazard level DR2, it would be good to set indicators such as a value corresponding to the likelihood of the hazardous material contained in a plastic bottle being spilled if it is left open on the floor.

[0088] Condition D indicates that the associated state (condition A in the example shown in the figure) continues for a predetermined time T1 or longer. Conditions A and D are, for example, conditions that the bag must satisfy in the stage prior to inflicting injury with a bladed weapon.

[0089] For the hazard level DR3, it would be good to set an index that corresponds to the likelihood of a real-world risk of injury from a knife, for example, if the bag remains open for a predetermined period of time T1 or longer.

[0090] In this example, the risks assumed by Criterion 1 and Criterion 3 are similar. Opening a bag and removing its contents is a common practice, so Condition A is likely to include the state of the bag corresponding to such a common practice. Criterion 3 reduces this possibility by adding Condition D to Condition A. Therefore, it would be good to set a value for DR1 that indicates a lower degree of risk than, for example, DR3.

[0091] It should be noted that the criteria for determining the degree of risk are not limited to those described here. For example, the anticipated risks and their precursors, the conditions and standards that the subject must meet at that time, etc., are not limited to the examples given above. For example, Criterion 2 may have an additional condition added: that the plastic bottle contains liquid.

[0092] When using the risk assessment criteria illustrated in Figure 8, the risk acquisition unit 112 uses the target information to determine, for example, whether the target satisfies any of the following conditions: A, B and C, or A and D.

[0093] Then, the risk assessment unit 112 determines the risk level of the target as the risk level of the target, if the target meets any of the conditions.

[0094] For example, the risk assessment unit 112 determines DR1 as the risk level of a bag if the bag meets condition A. The risk assessment unit 112 determines DR2 as the risk level of a plastic bottle if the plastic bottle meets conditions B and C. The risk assessment unit 112 determines DR3 as the risk level of a bag if the bag meets conditions A and D.

[0095] Furthermore, if the conditions of Criterion 3 (Conditions A and D) are met, then the condition of Criterion 1 (Condition A) will also be met. When the conditions of one criterion (for example, Condition A of Criterion 1) encompass the conditions of the other criterion (for example, Conditions A and D of Criterion 3), it is preferable that the criterion containing the encompassing conditions (for example, Criterion 3) be applied preferentially. That is, in such cases, the risk acquisition unit 112 determines the risk level (for example, DR3) associated with the encompassing conditions (for example, Criterion 3) as the target risk level.

[0096] Refer to Figure 7 again. The notification unit 113 notifies the degree of danger of the target determined in step S103 (step S104), and terminates the danger detection process.

[0097] There can be various methods of notification. For example, one or more methods of notification are acceptable, such as sound or a display.

[0098] When providing notification by sound, the notification unit 113 may change the nature of the sound (type, pitch, volume, etc.) according to the required level of danger.

[0099] When notification is given via display, the notification unit 113 may display a screen in which a mark indicating the target is superimposed on the video showing the target. The mark can 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. If a frame is used for the mark, the notification unit 113 may change the appearance of the frame (type of line, thickness, color, etc.) depending on the required level of danger.

[0100] Furthermore, if the required level of risk is above a threshold, the notification unit 113 will threshold The detection of an object with the above level of risk may be notified using sound, a display, or other means.

[0101] This type of hazard detection process includes the location and condition of the container, allowing the hazard level of the container to be determined using both its location and condition. Furthermore, notification makes it easy for users to understand the determined hazard level.

[0102] (Effects / Actions) As described above, according to this embodiment, the information processing device 103 comprises a target acquisition unit 111 and a risk level acquisition unit 112.

[0103] The target acquisition unit 111 acquires target information about the object shown in the video by analyzing the video footage of the target area. The risk assessment unit 112 uses the target information to determine the risk level of the object. The target information includes the location and condition of the containment device.

[0104] This allows the hazard level of the containment to be determined using both its position and condition. Therefore, it becomes possible to accurately detect the degree of hazard in the target area.

[0105] <Embodiment 2> In Embodiment 2, the object is housed Ingredients Explain examples that include things and people other than those mentioned above.

[0106] In this embodiment, in order to simplify the explanation, explanations that overlap with those in Embodiment 1 will be omitted as appropriate.

[0107] The information processing system according to Embodiment 2 includes an information processing device 203 that replaces the information processing device 103 according to Embodiment 1. Except for this, the information processing system according to this embodiment may be configured in the same way as the information processing system 100 according to Embodiment 1.

[0108] Figure 9 shows an example of the functional configuration of the 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, which replace the object acquisition unit 111 and risk level acquisition unit 112 according to Embodiment 1. Furthermore, the information processing device 203 further includes, for example, a position relationship acquisition unit 214 and a notification unit 113 similar to that in Embodiment 1.

[0109] The target acquisition unit 211, similar to the target acquisition unit 111 in Embodiment 1, acquires target information about the target using analysis information acquired from the analysis device 102.

[0110] The subject of this embodiment is accommodation Ingredients Includes things that contain and people.

[0111] The information of this embodiment includes the location and attributes of objects and the location and attributes of people.

[0112] The positions of objects and people are as described in Embodiment 1. Ingredients This can be similar to the position shown in the image, for example, it is information indicating the position within each video.

[0113] The attributes of an object include the state of its container. The attributes of an object may also include at least one other aspect, such as the state of objects other than the container, or the orientation of the object including the container. However, the attributes of an object are not limited to these.

[0114] The attributes of a person may include at least one of the following: the person's actions, the person's movement speed, the person's posture, and the presence and condition of any clothing or accessories the person is wearing.

[0115] For example, the item being worn is a glove, and in this case, the state of the item being worn is that the glove is worn on only one hand, either the left or the right (symmetry of the item being worn). This is because, for example, a glove might be worn only on the hand holding a plastic bottle containing hazardous materials.

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

[0117] The position relationship acquisition unit 214 uses the target information to determine the positional relationships of the objects. The position relationship acquisition unit 214 is best used when multiple objects are visible in the video (i.e., when the positions of multiple objects are included in the target information).

[0118] The positional relationships of objects refer to, for example, the positional relationships of pairs of multiple objects. More specifically, the positional relationships of objects include the positional relationships between objects and people, and the positional relationships between people when the image contains multiple people.

[0119] The positional relationship between an object and a person can be, for example, a person holding an object such as a storage container or a plastic bottle. It can also be, for example, a person holding an object such as a bag or backpack in front of them. Furthermore, it can be, for example, a plastic bottle being placed at a person's feet, or a plastic bottle being placed both at a person's feet and in front of them. "At the feet" is an example of being within a predetermined range from the person. Note that the positional relationships between objects and people are not limited to these examples.

[0120] The risk level acquisition unit 212, similar to the risk level acquisition unit 112 in Embodiment 1, uses the target information acquired by the target acquisition unit 211 to determine the risk level of the target.

[0121] The degree of risk of the subject according to this embodiment includes at least one of the following: the degree of risk of the object (including the degree of risk of the container), the degree of risk of the person, and the degree of risk of the combination of the object (including the container) and the person.

[0122] In this embodiment, the risk level acquisition unit 212 may further use the positional relationships of the objects acquired by the positional relationship acquisition unit 214 to determine the risk level of the objects. That is, the risk level acquisition unit 212 may use the object information and the positional relationships between objects when multiple objects are visible in the video to determine the risk level of the objects.

[0123] Up to this point, we have mainly described an example of the functional configuration of the information processing system according to Embodiment 2. Physically, the information processing system according to this embodiment may be configured in the same way as the information processing system 100 according to Embodiment 1. From here, an example of the operation of the information processing system according to this embodiment will be described.

[0124] (Operation of the information processing system according to Embodiment 2) The information processing system according to Embodiment 2 performs information processing including analysis processing and hazard 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 hazard detection processing according to this embodiment is a process that replaces the hazard detection processing according to Embodiment 1. The hazard detection processing according to this embodiment will be described below with reference to the figures.

[0125] Figure 10 is a flowchart showing an example of the hazard detection process according to Embodiment 2.

[0126] The target acquisition unit 211 performs the same step S101 as in Embodiment 1.

[0127] The target acquisition unit 211 acquires target information about the target using the analysis information acquired in step S101, similar to the first embodiment (step S202).

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

[0129] The position relationship acquisition unit 214 determines the positional relationship of the objects if the object information acquired in step S202 includes the positions of multiple objects (step S205).

[0130] In detail, for example, the position relationship acquisition unit 214 determines whether the target information acquired in step S202 includes the positions of multiple targets. If the positions of multiple targets are included in the target information, the position relationship acquisition unit 214 determines the positional relationships between the multiple targets. If the positions of multiple targets are not included in the target information, the position relationship acquisition unit 214 does not execute step S205 and proceeds to the next step S203.

[0131] The risk assessment unit 212 uses the target information and positional relationship acquired in steps S202 and S205 to determine the risk level of the target (step S203).

[0132] In detail, for example, if the positional relationship of the object is not obtained in step S205, the risk assessment unit 212 uses the object information obtained in step S202 to determine the risk level of the object. If the positional relationship of the object is obtained in step S205, the risk assessment unit 212 uses the object information and positional relationship obtained in steps S202 and S205 to determine the risk level of the object.

[0133] The risk assessment unit 212, similar to the risk assessment unit 112 in Embodiment 1, may determine the risk level of the target using predetermined risk assessment criteria. The risk assessment criteria in this embodiment may include the positional relationship of the target as a condition.

[0134] Figure 11 shows an example of the risk assessment criterion CT2 according to Embodiment 2. The risk assessment criterion CT2 illustrated in the figure includes criteria 4 and criteria 5. Note that the risk assessment criterion CT2 is not limited to that described herein.

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

[0136] Conditions A and E are conditions that the bag must satisfy in the stage prior to inflicting injury with a bladed weapon, similar to condition A or a combination of conditions A and D described in Embodiment 1.

[0137] For a risk level of DR4, it would be good to set indicators such as a value corresponding to the likelihood of a real-world risk of injury from a knife when, for example, a bag is open and being held in front of a person.

[0138] Conditions B and F are similar to the combination of conditions B and C described in Embodiment 1, and are conditions that a plastic bottle containing a dangerous substance, such as poison or gasoline, must satisfy before being kicked in order to scatter the dangerous substance into the surrounding area.

[0139] For a hazard level of DR5, it would be good to set indicators such as a value corresponding to the likelihood that the hazardous material contained in a plastic bottle will be spilled if it is placed on the floor at a person's feet and in front of them while open.

[0140] When using the risk assessment criterion CT2 illustrated in Figure 11, the risk acquisition unit 212 determines, for example, whether the target satisfies any of conditions A and E, or conditions B and F, using the target information and the positional relationship of the target.

[0141] The risk assessment unit 212 then determines the risk level associated with the target if the target meets any of the conditions, and uses that condition as the target's risk level.

[0142] For example, the risk assessment unit 212 determines DR4 as the risk level of a bag if the bag satisfies conditions A and E. The risk assessment unit 212 determines DR5 as the risk level of a plastic bottle if the plastic bottle satisfies conditions B and F.

[0143] Furthermore, when using Criterion 4, the risk level DR4 may be determined as the risk level of a person who meets the conditions included in Criterion 4, or as the risk level of a combination of a person and a bag who meet the conditions included in Criterion 4. Similarly, for Criterion 5, the risk level DR5 may be determined as the risk level of a person who meets the conditions included in Criterion 5, or as the risk level of a combination of a person and a plastic bottle who meet the conditions included in Criterion 5.

[0144] Refer to Figure 10 again. The notification unit 113, similar to Embodiment 1, notifies the degree of danger of the target determined in step S203 (step S104), and terminates the danger detection process.

[0145] This type of hazard detection process allows for the determination of the degree of danger of an object, including objects and people, by further utilizing the spatial relationships of the objects.

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

[0147] This allows us to determine the degree of danger of the target (either the target or the person, or a combination of the target and the person) by further utilizing the positional relationship between the containment and the person. Therefore, it becomes possible to accurately detect the degree of danger in the target area.

[0148] According to this embodiment, the target information includes the location and attributes of an object, including a storage container, and the location and attributes of a person. The attributes of the object include the state of the storage container. The attributes of the person include at least one of the person's actions, the person's posture, and the presence and state of any wearable items the person is wearing.

[0149] This allows us to determine the degree of danger to a target using various information about objects and people, such as their location and attributes. Therefore, it becomes possible to accurately detect the degree of danger in the target area.

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

[0151] This allows us to determine the degree of danger of an object by further utilizing its positional relationship. Therefore, it becomes possible to accurately detect the level of danger within the target area.

[0152] <Embodiment 3> Embodiment 3 describes an example of determining the risk level of an object when the preconditions are met. This embodiment also describes an example in which sensor information generated by a sensor device is used as a precondition.

[0153] In this embodiment, in order to simplify the explanation, descriptions that overlap with other embodiments will be omitted as appropriate.

[0154] Figure 12 shows an example configuration of the 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 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 greater than or equal to 1. If no particular distinction is made between sensor devices 104_1 to 104_L, they are also referred to as "sensor device 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 in Embodiment 1, and they 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 sensors include one or more sound sensors for detecting sounds such as screams and shouts, heat sensors for detecting heat such as flames during a fire, and odor sensors for detecting smells such as toxic drugs and flammable materials (e.g., gasoline).

[0159] (Example of the functional configuration of the information processing device 303 according to Embodiment 3) Figure 13 shows an example of the functional configuration of the information processing device 303 according to Embodiment 3. Functionally, the information processing device 303 includes, for example, a risk acquisition unit 312 that replaces the risk acquisition unit 112 according to Embodiment 1. Except for this point, the information processing device 303 may be configured in the same way as the information processing device 103 according to Embodiment 1. Note that the information processing device 303 may also include a target acquisition unit 211 similar to that in Embodiment 2 instead of the target acquisition unit 111.

[0160] The risk assessment unit 312 determines the risk level of an object using the object information when predetermined preconditions are detected. The preconditions are, for example, the detection of one or more of the following: a sound above a certain level, heat above a certain level, or a predetermined smell.

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

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

[0163] The target risk acquisition unit 312b determines the risk level of the target using the target information when predetermined preconditions are detected.

[0164] Up to this point, we have mainly described an example of the functional configuration of the information processing system 300 according to Embodiment 3. Physically, the information processing system 300 according to this embodiment may consist of devices 101, 102, and 303 configured in the same way as the information processing system 100 according to Embodiment 1, and a sensor device 104 including various sensors. From here, an example of the operation of the information processing system according to this embodiment will be described.

[0165] (Operation of the information processing system 300 according to Embodiment 3) The information processing system 300 according to Embodiment 3 performs information processing including analysis processing and hazard 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 hazard detection processing according to this embodiment is a process that replaces the hazard detection processing according to Embodiment 1. The hazard detection processing according to this embodiment will be described below with reference to the figures.

[0166] Figure 14 is a flowchart showing an example of the hazard detection process according to Embodiment 3.

[0167] Steps S101 to S102, similar to those in Embodiment 1, are performed.

[0168] The prerequisite detection unit 312a uses sensor information to detect predetermined prerequisites (step S302).

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

[0170] If the precondition is detected (Step S302; Yes), the target risk acquisition unit 312b, in the same manner as in Embodiment 1, uses the target information acquired in Step S102 to determine the risk level of the target (Step S103). Then, the notification unit 113 executes Step S104, in the same manner as in Embodiment 1, and terminates the risk detection process. If the precondition is not detected (Step S302; No), the target risk acquisition unit 312b terminates the risk detection process.

[0171] (Effects / Actions) As described above, according to this embodiment, when predetermined preconditions are detected, the risk level acquisition unit 312 uses the target information to determine the risk level of the target.

[0172] This allows us to determine the level of risk for a target subject, provided that certain preconditions are met. Therefore, it becomes possible to detect the degree of risk in the target area with greater accuracy.

[0173] According to this embodiment, the risk acquisition unit 312 includes a prerequisite detection unit 312a and a target risk acquisition unit 312b. The prerequisite detection unit 312a detects predetermined prerequisites using at least one of sensor information and target information. When the predetermined prerequisites are detected, the target risk acquisition unit 312b uses the target information to determine the risk level of the target.

[0174] This allows us to determine the level of risk for a target subject, provided that certain preconditions are met. Therefore, it becomes possible to detect the degree of risk in the target area with greater accuracy.

[0175] (Variation 1) Sensor information may be used as a condition for determining the degree of risk in the risk assessment criteria.

[0176] Furthermore, the preconditions may include conditions detected using the target information or information obtained from the target information. That is, the risk acquisition unit. 3 12 may use at least one of the sensor information and the target information to detect predetermined preconditions. Examples of such preconditions are listed below (a) to (d).

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

[0178] Prerequisite b is that there is someone looking in the direction of the surveillance camera. More specifically, for example, a person looking in the direction of the surveillance camera is someone whose gaze is made with the surveillance camera.

[0179] Prerequisite c is that the frequency or proportion (e.g., temporal proportion) at which faces can be detected is less than or equal to a predetermined value compared to the standard value in the target area. This is an example where the prerequisite is an action to avoid capturing faces.

[0180] Prerequisite d is that someone has performed an action that is prohibited in the area in question. Specifically, for example, an action that is prohibited in the area in question might be taking out a cigarette on a train. This is an example of a prerequisite that involves an action that could trigger a dispute.

[0181] This modified version also produces the same effects as Embodiment 3.

[0182] <Embodiment 4> Embodiment 4 describes an example of determining the risk level of a target by further using the history of the target information.

[0183] In this embodiment, in order to simplify the explanation, descriptions that overlap with other embodiments will be omitted as appropriate.

[0184] The information processing system according to Embodiment 4 includes an information processing device 403 that replaces the information processing device 103 according to Embodiment 1. Except for this, the information processing system according to this embodiment may be configured in the same way as the information processing system 100 according to Embodiment 1.

[0185] Figure 15 shows an example of the functional configuration of the information processing device 403 according to Embodiment 4. Functionally, the information processing device 403 includes, for example, a target acquisition unit 411 and a risk level acquisition unit 412. Functionally, the information processing device 403 further includes, for example, a position relationship acquisition unit 214 similar to that of Embodiment 2 and a notification unit 113 similar to that of Embodiment 1.

[0186] The target acquisition unit 411, similar to the target acquisition unit 211 in Embodiment 2, acquires target information about the target using analysis information acquired from the analysis device 102.

[0187] In other words, the object according to this embodiment is, similar to Embodiment 2, accommodating Ingredients This includes objects and people. Furthermore, the target information according to this embodiment includes the location and attributes of objects and the location and attributes of people, similar to Embodiment 2.

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

[0189] The target and target information may be the same as in Embodiment 1. The target acquisition unit 411 may have the same functions as the target acquisition unit 111 in Embodiment 1 and may store the same history of target information as in Embodiment 1.

[0190] The risk level acquisition unit 412 is similar to the risk level acquisition unit 212 in Embodiment 2, and the target acquisition unit 4 The degree of danger of the target is determined using the target information acquired by unit 11 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 assessment unit 412 may determine the risk level of the target using the same target information and its history as in Embodiment 1.

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

[0194] (Operation of the information processing system according to Embodiment 4) The information processing system according to Embodiment 4 performs information processing including analysis processing and hazard 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 hazard detection processing according to this embodiment is a process that replaces the hazard detection processing according to Embodiment 1. The hazard detection processing according to this embodiment will be described below with reference to the figures.

[0195] Figure 16 is a flowchart showing an example of the hazard detection process according to Embodiment 4.

[0196] The target acquisition unit 411 performs the same step S101 as in Embodiment 1.

[0197] The target acquisition unit 411 uses the analysis information acquired in step S101 to acquire target information about the target, similar to Embodiment 1, and stores the acquired target information (step S402).

[0198] The position relationship acquisition unit 214, similar to Embodiment 2, determines the position relationship of multiple objects if the object information acquired in step S402 includes the positions of multiple objects (step S205).

[0199] The position relationship acquisition unit 214 may also store a history of the position relationships of the objects. The history of the position relationships of the objects is, for example, information that associates the position relationship of an object with the shooting time of the video that generated that position relationship.

[0200] The risk assessment unit 412 uses the target information and positional relationship acquired in steps S402 and S205, as well as the history of the target information, to determine the risk level of the target (step S403).

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

[0202] Figure 17 shows an example of the risk assessment criterion CT3 according to Embodiment 4. The risk assessment criterion CT3 illustrated in the figure 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 of a person, such as "This person has been here before." Condition H is an example of an object (containment) such as "The bag the person is carrying is larger than last time." Ingredients This is an example of a condition that uses the history related to ).

[0204] Conditions G and H are, for example, conditions that a person who, after inspecting a site, intends to use a dangerous object such as a knife contained in a bag to perform a dangerous act at that site, must satisfy. Carrying a larger bag than the previous time indicates a higher probability of containing dangerous objects.

[0205] Danger level DR6 should ideally include indicators such as a value corresponding to the likelihood of danger materializing, for example, if a person who has visited the area before is carrying a larger bag than the last time.

[0206] When using the risk assessment criterion CT3 illustrated in Figure 17, the risk acquisition unit 412 determines whether the target satisfies conditions G and H, for example, using target information, the positional relationship of the target, and the history of the target information.

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

[0208] Note that the risk assessment criterion CT3 is not limited to those described herein, and may include, for example, only condition G. Furthermore, the risk assessment criterion CT3 may include conditions that use the history of the object's positional relationships. In this case, the risk acquisition unit 412 may further determine the risk level of the object using the history of the object's positional relationships.

[0209] Refer to Figure 16 again. The notification unit 113, similar to Embodiment 1, notifies the degree of danger of the target determined in step S403 (step S104), and terminates the danger detection process.

[0210] This type of risk detection process allows for the determination of the risk level of an object by further utilizing the history of the object's information.

[0211] (Effects / Actions) 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 for the determination of a more accurate risk level for a target by further utilizing the history of the target information. Therefore, it becomes possible to detect the degree of risk in the target area with greater precision.

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

[0214] Furthermore, while the flowcharts used in the above description show multiple steps (processes) in sequence, the execution order of the steps performed in each embodiment is not limited to the order in which they are described. In each embodiment, the order of the illustrated steps can be changed to the extent that it does not impede the content. Also, the above embodiments and modifications can be combined to the extent that their content is not contradictory.

[0215] Some or all of the above embodiments may also be described as follows, but are not limited to the following:

[0216] 1. A target acquisition means that acquires target information about an object shown in a video by analyzing video footage of a target area, The system includes a risk acquisition means for determining the risk level of the target using the aforementioned target information, The aforementioned information includes the location and condition of the storage container. Information processing device. 2. The aforementioned subject further includes persons, The aforementioned information further includes the location of the person, The risk assessment means uses the target information to determine the risk level for either the containment device or the person, or for any combination of the containment device and the person. The information processing device described in 1. 3. The aforementioned information includes the location and attributes of the object, including the container, and the location and attributes of the person. The attributes of the aforementioned object include the state of the container, The attributes of the person include at least one of the person's actions, posture, presence or absence of any clothing or accessories worn by the person, and their condition. The information processing device described in 2. 4. The risk acquisition means determines the risk level of the target using the target information and the positional relationship of the target. An information processing device as described in any one of items 1 to 3. 5. The risk acquisition means determines the risk level of the target using the target information when predetermined preconditions are detected. An information processing device as described in any one of items 1 through 4. 6. The means for obtaining the risk level is: A prerequisite detection means that detects the predetermined prerequisite using at least one of the sensor information and the target information, When the aforementioned predetermined preconditions are detected, the system includes a target risk acquisition means that uses the target information to determine the risk level of the target. The information processing device described in 5. 7. The risk acquisition means further uses the history of the target information to determine the risk level of the target. An information processing device as described in any one of items 1 through 6. 8. An information processing device described in any one of items 1 to 7, A camera that captures the aforementioned target area and generates an image, The system comprises an analysis device that analyzes the video generated by the at least one of the aforementioned shooting means and generates the analysis information. Information processing system. 9. One or more computers, By analyzing video footage of the target area and using the analysis information obtained, we acquire target information about the objects shown in the video. This includes determining the degree of risk of the subject using the aforementioned subject information, The aforementioned information includes the location and condition of the storage container. Information processing methods. 10. The aforementioned subject further includes persons, The aforementioned information further includes the location of the person, In determining the degree of risk, the aforementioned target information is used to determine the degree of risk for either the containment device or the person, or for any combination of the containment device and the person. The information processing method described in 9. 11. The aforementioned information includes the location and attributes of the object including the container, and the location and attributes of the person. The attributes of the aforementioned object include the state of the container, The attributes of the person include at least one of the person's actions, posture, presence or absence of any clothing or accessories worn by the person, and their condition. The information processing method described in 10. 12. In determining the degree of risk, the degree of risk of the target is determined using the target information and the positional relationship of the target. An information processing method described in any one of items 9 through 11. 13. In determining the risk level, if the predetermined preconditions are detected, the risk level of the target is determined using the target information. An information processing method described in any one of items 9 through 12. 14. In determining the degree of risk, Using at least one of the sensor information and the target information, the predetermined preconditions are detected. When the aforementioned predetermined conditions are detected, the risk level of the subject is determined using the subject information. The information processing method described in 13. 15. In determining the risk level, the risk level of the subject is determined by further using the history of the subject information. An information processing method described in any one of items 9 through 14. 16. On one or more computers, By analyzing video footage of the target area and using the analysis information obtained, we acquire target information about the objects shown in the video. Using the aforementioned target information, the system is made to determine the risk level of the target. A program for which the aforementioned target information includes the location and state of the storage container. 17. The aforementioned subject further includes persons, The aforementioned information further includes the location of the person, In determining the degree of risk, the aforementioned target information is used to determine the degree of risk for either the containment device or the person, or for any combination of the containment device and the person. The program described in section 16. 18. The aforementioned subject information includes the location and attributes of the object including the container, and the location and attributes of the person, The attributes of the aforementioned object include the state of the container, The attributes of the person include at least one of the person's actions, posture, presence or absence of any clothing or accessories worn by the person, and their condition. The program described in section 17. 19. In determining the degree of risk, the degree of risk of the target is determined using the target information and the positional relationship of the target. A program described in any one of items 16 through 18. 20. In determining the risk level, if the predetermined preconditions are detected, the risk level of the target is determined using the target information. A program described in any one of items 16 through 19. 21. In determining the degree of risk, Using at least one of the sensor information and the target information, the predetermined preconditions are detected. When the aforementioned predetermined conditions are detected, the risk level of the subject is determined using the subject information. The program described in section 20. 22. In determining the risk level, the history of the target information is further used to determine the risk level of the target. A program described in any one of items 16 through 21. 23. A recording medium on which a program described in any one of items 16 through 22 is recorded.

[0217] This application claims priority based on Japanese Patent Application No. 2022-211664, filed on 28 December 2022, and incorporates all of its disclosures herein. [Explanation of symbols]

[0218] 100,300 Information Processing Systems 101 Imaging device 102 Analysis equipment 103,203,303,403 Information Processing Equipment 104 Sensor device 111,211,411 Target acquisition section 112,212,312,412 Risk Assessment Section 113 Hochi Department 214 Positional relationship acquisition unit 312a Premise detection unit 312b Target Risk Assessment Section CT1-CT5 Risk Assessment Criteria

Claims

1. A target acquisition means that uses analytical information obtained by analyzing video footage of a target area to acquire target information about the object shown in the video, The system includes a risk acquisition means that, when predetermined preconditions are detected, uses the target information to determine the risk level of the target, The aforementioned information includes the location and state of the storage container. The aforementioned predetermined preconditions include at least one of the following: the relative relationship between the object and the crowd satisfies predetermined criteria; the person is looking in the direction of the surveillance camera; the frequency or proportion of face detection is less than or equal to a predetermined value compared to the standard value in the target area; and the person has performed an act prohibited in the target area. Information processing device.

2. The aforementioned subject further includes persons, The aforementioned information further includes the location of the person, The risk assessment means uses the target information to determine the risk level for either the containment device or the person, or for any combination of the containment device and the person. The information processing apparatus according to claim 1.

3. The aforementioned information includes the location and attributes of the object, including the container, and the location and attributes of the person. The attributes of the aforementioned object include the state of the container, The attributes of the person include at least one of the person's actions, posture, presence or absence of any clothing or accessories worn by the person, and their condition. The information processing apparatus according to claim 2.

4. The risk assessment means uses the target information and the positional relationship of the target to determine the risk level of the target. The information processing apparatus according to any one of claims 1 to 3.

5. The aforementioned risk level acquisition means is A prerequisite detection means that detects the predetermined prerequisite using at least one of the sensor information and the target information, When the aforementioned predetermined preconditions are detected, the system includes a target risk acquisition means that uses the target information to determine the risk level of the target. The information processing apparatus according to any one of claims 1 to 3.

6. The risk acquisition means further uses the history of the target information to determine the risk level of the target. The information processing apparatus according to any one of claims 1 to 3.

7. The container includes a PET bottle, The state of the aforementioned container includes the state in which the PET bottle is open and placed on the floor. The information processing apparatus according to any one of claims 1 to 3.

8. One or more computers, By analyzing video footage of the target area and using the analysis information obtained, we acquire target information about the objects shown in the video. This includes determining the risk level of the target using the target information when predetermined preconditions are detected. The aforementioned information includes the location and state of the storage container. The aforementioned predetermined preconditions include at least one of the following: the relative relationship between the object and the crowd satisfies predetermined criteria; the person is looking in the direction of the surveillance camera; the frequency or proportion of face detection is less than or equal to a predetermined value compared to the standard value in the target area; and the person has performed an act prohibited in the target area. Information processing methods.

9. On one or more computers, By analyzing video footage of the target area and using the analysis information obtained, we acquire target information about the objects shown in the video. When predetermined preconditions are detected, the system will use the aforementioned target information to determine the risk level of the target. The aforementioned information includes the location and state of the storage container, The aforementioned predetermined preconditions include a program that includes at least one of the following: the relative relationship between an object and a crowd satisfies predetermined criteria; the person is looking in the direction of the surveillance camera; the frequency or proportion of face detection is less than or equal to a predetermined value compared to the standard value in the target area; and the person has performed an act prohibited in the target area.

Images