Information processing device, information processing method, and recording medium

Abstract

This information processing device is provided with a suspicious person detection unit and a notification control unit. The suspicious person detection unit detects, using an analysis result of sensor information from a sensor monitoring a predetermined range from a residential site, a person, other than a specific non-suspicious person, who is performing a suspicious action on a vehicle parked in a parking lot in the predetermined range. The notification control unit causes a notification unit to issue a notification when a suspicious person is detected.

Description

Information processing device, information processing method, and recording medium

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

[0002] For example, Patent Document 1 discloses a security system that effectively utilizes an in-vehicle camera to improve the crime prevention capabilities of a house.

[0003] The house-side device unit described in Patent Document 1 processes image data transmitted from the vehicle and image data captured by a camera installed on the premises of the house, and determines an abnormal state of the house based on the image-processed data obtained by the house-side image processing unit. The house-side device unit outputs an alarm when the abnormality determination unit determines that an abnormality has occurred.

[0004] Patent Document 1 describes that abnormal conditions in a house include the intrusion of a suspicious person, the outbreak of a fire, etc. It also describes that by performing dual abnormality detection using image data monitoring and obstacle detection means mounted on the vehicle, it is possible to detect a suspicious person approaching the vehicle as an intruder on the premises.

[0005] JP 2011-232877 A

[0006] However, with the technology described in Patent Document 1, there is a risk that all people approaching the vehicle will be detected as suspicious persons, and that alarms will be output frequently. If alarms are output frequently, those who receive the alarms may take them lightly, and as a result, the safety of the vehicle may not be ensured.

[0007] One of the objectives of the present disclosure is to improve the safety of vehicles parked around houses.

[0008] The information processing device of the present disclosure includes a suspicious person detection means that uses the analysis results of sensor information from a sensor that monitors a specified range from the property of a house to detect a suspicious person other than a specific non-suspicious person engaging in suspicious behavior toward vehicles parked in a parking lot within the specified range, and an alarm control means that causes an alarm unit to issue an alarm when the suspicious person is detected.

[0009] The information processing method disclosed herein involves one or more computers using the results of analyzing sensor information from sensors that monitor a specified area from the residential property to detect a suspicious individual, other than a specific non-suspicious individual, engaging in suspicious behavior toward a vehicle parked in a parking lot within the specified area, and having an alarm unit issue an alert when the suspicious individual is detected.

[0010] The recording medium of the present disclosure has recorded thereon a program for causing one or more computers to use the analysis results of sensor information from sensors that monitor a specified range from the residential property to detect a suspicious person other than a specific non-suspicious person engaging in suspicious behavior toward a vehicle parked in a parking lot within the specified range, and to cause an alarm unit to issue an alarm when the suspicious person is detected.

[0011] According to the present disclosure, it is possible to improve the safety of vehicles parked around houses.

[0012] 1 is a block diagram showing an example configuration of a first information processing system according to the present disclosure. FIG. 1 is a block diagram showing an example configuration of a first information processing device according to the present disclosure. FIG. 2 is a flowchart showing an example processing operation of the first information processing device according to the present disclosure. FIG. 3 is a block diagram showing an example configuration of a first analysis device according to the present disclosure. FIG. 4 is a diagram showing an example processing operation of the first information processing system according to the present disclosure. FIG. 5 is a block diagram showing an example physical configuration of a first information processing device according to the present disclosure. FIG. 6 is a block diagram showing an example configuration of a second information processing system according to the present disclosure. FIG. 7 is a block diagram showing an example configuration of a second information processing device according to the present disclosure. FIG. 8 is a diagram showing an example processing operation of the second information processing system according to the present disclosure. FIG. 9 is a block diagram showing an example configuration of a third information processing system according to the present disclosure. FIG. 10 is a block diagram showing an example configuration of a third information processing device according to the present disclosure. FIG. 11 is a diagram showing an example processing operation of the third information processing system according to the present disclosure. FIG. 12 is a block diagram showing an example configuration of a second suspicious person detection unit according to the present disclosure. FIG. 13 is a diagram showing an example processing operation of the second suspicious person detection unit according to the present disclosure. FIG. 14 is a block diagram showing an example configuration of a fourth information processing system according to the present disclosure. FIG. 15 is a block diagram showing an example configuration of a fourth information processing device according to the present disclosure. FIG. 16 is a diagram showing an example processing operation of the fourth information processing system according to the present disclosure.

[0013] Hereinafter, embodiments of the present disclosure will be described with reference to the drawings. In all drawings, similar components are designated by similar reference numerals, and descriptions thereof will be omitted as appropriate. In addition, in this disclosure, the drawings relate to one or more embodiments.

[0014] [Embodiment 1] (Summary) For example, Patent Document 2 (Japanese Patent Laid-Open Publication No. 2006-072928) discloses a vehicle theft prevention system including a management center that provides vehicle theft prevention services. This vehicle theft prevention system detects where a vehicle is parked, detects the location of the vehicle user, and calculates the distance between the vehicle parking location and the user's location.

[0015] The vehicle theft prevention system described in Patent Document 2 calculates a theft probability level, which indicates the likelihood of vehicle theft under the parking conditions, based on parking conditions that include at least the vehicle's parking location and vehicle theft information that includes at least the locations of past vehicle thefts.The vehicle theft prevention system sets a security level based on the calculated distance and the theft probability level.

[0016] Furthermore, the vehicle theft prevention system described in Patent Document 2 detects intrusion into a vehicle and sets conditions for detecting intrusion into the vehicle according to a set security level. The vehicle theft prevention system determines that an intrusion into the vehicle has occurred when the state of the vehicle matches the conditions for detecting intrusion into the vehicle, and if it determines that an intrusion into the vehicle has occurred, notifies the user of the vehicle to that effect.

[0017] According to the technology described in Patent Document 2, conditions are set according to the security level, so there is a possibility that excessive notifications can be suppressed.

[0018] However, according to the technology described in Patent Document 2, the theft occurrence level is set based on at least the location where the vehicle is parked and the locations of past vehicle thefts. Therefore, if the vehicle is parked in a fixed location, such as a parking lot at home or a nearby parking lot under contract, excessive alerts may be issued, which could result in the safety of the vehicle being compromised.

[0019] (Configuration Example of Information Processing System S1) As shown in FIG. 1, the information processing system S1 includes a sensor 10, an analysis unit 52, a suspicious person detection unit 130, and a notification control unit 140.

[0020] The sensor 10 monitors a predetermined range from the premises of the house.

[0021] The analysis unit 52 analyzes the sensor information generated by the sensor 10 .

[0022] The suspicious person detection unit 130 uses the analysis results to detect a suspicious person other than a specific non-suspicious person who is engaging in suspicious behavior toward vehicles parked in a parking lot within a predetermined range.

[0023] The notification control unit 140 causes the notification unit to issue a notification when a suspicious individual is detected.

[0024] According to this information processing system S1, by excluding specific non-suspicious individuals from the list of suspicious individuals, it is possible to appropriately detect suspicious individuals engaging in suspicious behavior toward vehicles parked in parking lots around houses. Therefore, when there is a high risk to vehicles parked around houses, it is possible to notify the detection of a suspicious individual. Therefore, it is possible to improve the safety of vehicles parked around houses.

[0025] (Configuration Example of Information Processing Device 100) As shown in FIG. 2, the information processing device 100 includes a suspicious person detection unit 130 and a notification control unit 140.

[0026] The suspicious person detection unit 130 uses the analysis results of sensor information from a sensor 10 that monitors a specified range from the residential property to detect suspicious persons other than specific non-suspicious persons who are engaging in suspicious behavior toward vehicles parked in a parking lot within the specified range.

[0027] The notification control unit 140 causes the notification unit to issue a notification when a suspicious individual is detected.

[0028] According to this information processing device 100, by excluding specific non-suspicious individuals from the list of suspicious individuals, it is possible to appropriately detect suspicious individuals engaging in suspicious behavior toward vehicles parked in parking lots around houses. Therefore, when there is a high risk to vehicles parked around houses, it is possible to notify the detection of a suspicious individual. Therefore, it is possible to improve the safety of vehicles parked around houses.

[0029] (Example of Processing Operation of Information Processing Device 100) The information processing device 100 executes information processing as shown in FIG.

[0030] The suspicious person detection unit 130 uses the analysis results of sensor information from the sensor 10 that monitors a specified range from the residential property to detect a suspicious person other than a specific non-suspicious person who is engaging in suspicious behavior toward vehicles parked in a parking lot within the specified range (step S130).

[0031] When a suspicious individual is detected, the notification control unit 140 causes the notification unit to issue a notification (step S140).

[0032] This information processing allows for the proper detection of suspicious individuals engaging in suspicious behavior toward vehicles parked in parking lots around residential areas by excluding specific non-suspicious individuals from the list of suspicious individuals. Therefore, when there is a high risk to vehicles parked around residential areas, it is possible to notify the system that a suspicious individual has been detected. This makes it possible to improve the safety of vehicles parked around residential areas.

[0033] (Detailed Example) Hereinafter, a detailed example of the information processing device 100 and its operation will be described.

[0034] (Device Configuration Example of Information Processing System S1) The information processing system S1 includes the above-described sensor 10, an analysis device 50, and the above-described information processing device 100, as shown in FIG. 4, for example.

[0035] The sensor 10, the analysis device 50, and the information processing device 100 are connected to each other via a communication network NT that is configured, for example, by wire, wireless, or a combination of these, and transmit and receive various information to and from each other via the communication network NT.

[0036] The sensor 10 and the analysis device 50, and the analysis device 50 and the information processing device 100 may be connected via different communication networks.

[0037] (Configuration Example of Analysis Device 50) As shown in FIG. 5, the analysis device 50 includes a sensor information acquisition unit 51 and the above-described analysis unit 52.

[0038] The sensor information acquisition unit 51 acquires the sensor information generated by the sensor 10 .

[0039] (Example of Processing Operation of Information Processing System S1) The information processing system S1 executes information processing as shown in FIG. 6, for example.

[0040] The sensor 10 monitors a predetermined range from the premises of the house and generates sensor information (step S10).

[0041] The sensor information acquisition unit 51 acquires the sensor information generated in step S10 (step S51).

[0042] The analysis unit 52 analyzes the sensor information acquired in step S51 (step S52).

[0043] Steps S130 and S140 are executed.

[0044] (Regarding vehicles and parking lots) A parking lot is a parking lot around a house, i.e., within a predetermined range from the house's property. A parking lot is typically provided on the house's property. Note that a parking lot is not limited to a parking lot within the property, but may also be, for example, a parking lot outside the property that has been contracted by the vehicle user.

[0045] The vehicle is, for example, a vehicle used by a resident of a house, and is typically an automobile. Note that the vehicle is not limited to an automobile, and may be, for example, a motorcycle or the like.

[0046] At least one of the parking lot and the vehicle to be monitored may be registered in advance in the information processing device 100. When a parking lot is registered in advance, its location (area) may be registered in the information processing device 100 or the like. When a vehicle is registered in advance, identification information of the vehicle may be registered in the information processing device 100 or the like.

[0047] The vehicle identification information is information for identifying the vehicle, and may be, for example, at least one of an image of the vehicle, an address of the vehicle in the communication network NT, a name of the vehicle in the communication network NT, a vehicle license plate number, etc.

[0048] By registering parking lots or vehicles in advance, it is possible to monitor specific parking lots or specific vehicles.

[0049] (Regarding the sensor 10) The sensor 10 is a sensor for monitoring the periphery of a house, i.e., a predetermined range from the house's site. There may be one or more sensors 10. The sensor 10 may include, for example, at least one of a house sensor installed in association with the house and an on-board sensor installed in a vehicle parked in a parking lot.

[0050] That is, the sensor 10 may include only one or more residential sensors installed in association with a residence, or only one or more vehicle sensors installed in a vehicle parked in a parking lot, or the sensor 10 may be multiple and include one or more residential sensors installed in association with a residence and one or more vehicle sensors installed in a vehicle parked in a parking lot.

[0051] The residential sensor may include, for example, at least one of a camera installed on the premises, a residential object presence detection sensor, etc. The vehicle-mounted sensor may include, for example, at least one of an in-vehicle camera, an in-vehicle LiDAR (Light Detection and Ranging) sensor, an in-vehicle object presence detection sensor, etc. Note that the sensor 10 may include a LiDAR sensor installed on the premises.

[0052] The camera installed on the premises may be installed, for example, at a gate, entrance, fence, wall, pole on the premises, etc. The camera installed on the premises may include a camera installed inside a house. The camera installed on the premises may capture an image of a predetermined capture area according to its installation location and generate sensor information including the captured image.

[0053] The on-board camera may be mounted on a vehicle to capture, for example, an image of the exterior or interior of the vehicle. The on-board camera may capture, for example, an image of a predetermined area outside or inside the vehicle, and generate sensor information including the captured image.

[0054] An on-board LiDAR sensor is a LiDAR sensor mounted on a vehicle. The LiDAR sensor is a sensor used for LiDAR. LiDAR is a technology that irradiates a laser beam and measures the distance to an object, the shape of the object, etc., using the reflected light. The on-board LiDAR sensor may include, for example, a laser irradiator that irradiates the laser beam and an optical receiver that receives the reflected light. The on-board LiDAR sensor may, for example, irradiate a laser beam to a predetermined area outside the vehicle and generate sensor information indicating the reflected light.

[0055] The residential object presence detection sensor is, for example, a sensor that detects an object that exists within a predetermined distance. The vehicle-mounted object presence detection sensor is, for example, a sensor that detects an object that exists within a predetermined distance from the vehicle. The vehicle-mounted object presence detection sensor may be, for example, a sensor installed to prevent vehicle collisions.

[0056] The object presence detection sensor emits, for example, sound waves, electromagnetic waves, etc., and generates sensor information indicating the reflected waves. The sound waves, electromagnetic waves, etc. used by the object presence detection sensor may include at least one of an ultrasonic sensor, an infrared sensor, and a millimeter wave sensor. The object presence detection sensor may include, for example, an oscillator that emits the sound waves, electromagnetic waves, etc., and a receiver that receives the reflected waves.

[0057] (Sensor Information Acquisition Unit 51) The sensor information acquisition unit 51 acquires, for example, sensor information generated by each of one or more sensors 10. The sensor information acquisition unit 51 acquires the sensor information via, for example, the communication network NT.

[0058] (Analysis Unit 52) ​​The analysis unit 52 has an analysis function for performing analysis processing on one or more pieces of sensor information generated by each of one or more sensors 10.

[0059] For example, the analysis unit 52 generates an analysis result using one or more pieces of sensor information acquired by the sensor information acquisition unit 51. The analysis unit 52 transmits the generated analysis result to the information processing device 100, for example, via the communication network NT.

[0060] The analysis unit 52 uses its analysis function to detect objects that exist within a predetermined range from the premises of the house, and generates analysis results regarding the objects.

[0061] The object includes a person and an object. The object is, for example, a vehicle such as a car, but is not limited to this and may include, for example, a bicycle.

[0062] The analysis result may include, for example, an object detected by analysis using sensor information. The analysis result may include, for example, at least one of the position, movement, posture, detection time, attributes, surrounding conditions, etc. of the detected object. For example, if the detected object is a moving object, the analysis result may include at least one of the movement speed, movement path, etc. of the detected object. Here, a moving object is a movable object such as a person or a vehicle.

[0063] The attributes of an object may be, for example, information indicating the characteristics, properties, etc., of the object. In particular, if the object is a person, the attributes may include at least one of height, physique, clothing, gender, age group, etc. If the object is a vehicle, the attributes may include one or more of model, size, color, etc.

[0064] The surrounding conditions may include at least one of brightness, the number of people passing by in the surrounding area (traffic level), etc. The traffic level may be determined based on the number of people detected within a predetermined period of time, for example.

[0065] A detailed example of a function for generating such an analysis result will be described below. Note that the information included in the analysis result is not limited to the above example.

[0066] The analysis unit 52 may have an analysis function according to the type of sensor information, such as the above-mentioned camera, LiDAR sensor, or object presence detection sensor.

[0067] In more detail, for example, the analysis unit 52 may analyze the sensor information generated by each of one or more sensors 10 using an analysis function according to the type of the sensor information. When there are multiple pieces of sensor information, the analysis unit 52 may integrate the analysis results (individual analysis results) of each piece of sensor information to generate an analysis result (overall analysis result) that analyzes the multiple pieces of sensor information as a whole. When simply referring to the "analysis result," this means the overall analysis result.

[0068] When integrating individual analysis results, for example, objects detected from each sensor information (i.e., objects included in the individual analysis results) may be treated as individual objects and combined to generate an analysis result. Furthermore, when integrating individual analysis results, if objects included in the individual analysis results are within a predetermined distance, such nearby objects may be treated as a single object to generate an analysis result. In this case, the position, detection time, etc. of the nearby object may be, for example, an average of the positions, times, etc. included in the individual analysis results, or any one of the positions, times, etc. included in the individual analysis results.

[0069] The method for integrating the individual analysis results is not limited to the method described here, and any general technique may be applied.

[0070] In general, the accuracy of the individual analysis results may vary depending on the environment, such as the brightness around the sensor 10. Therefore, by integrating the individual analysis results, it is possible to obtain more accurate analysis results.

[0071] An example of a method for generating individual analysis results for each type of sensor information will be described below.

[0072] (Example of a method for generating individual analysis results of sensor information generated by a camera) For example, the analysis unit 52 has one or more image analysis functions for analyzing images such as videos and still images. Each of the image analysis functions may extract an image feature vector and perform analysis using, for example, a machine learning model that has been trained to perform analysis according to the function. The machine learning model may be configured using, for example, a neural network. Note that, while an example of analyzing an image using a machine learning model will be described here, image analysis is not limited to this, and general image processing techniques such as pattern matching may also be used.

[0073] The image analysis functions provided by the analysis unit 52 include, for example, 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, and (9) movement line analysis function.

[0074] (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.

[0075] (2) The face analysis function detects human faces from images, extracts feature vectors of the detected faces, and classifies the detected faces. The face analysis function can also determine the position of the face in the image, as well as the direction of the face and gaze. 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.

[0076] (3) The human morphology analysis function extracts the physical characteristics of people in an image (for example, values ​​indicating overall characteristics such as whether they are fat or thin, height, and clothing), and classifies (classifies) people in an image. 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.

[0077] (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 posture of the person, extract a feature vector of the estimated posture (posture feature vector), and classify (classify) the people included in the image. The posture analysis function can also determine the identity of people included in different images based on the posture feature vectors of the people included in the different images.

[0078] For example, the posture analysis function estimates a person's posture, such as standing, crouching, or bending, from an image and extracts a posture feature vector indicating the posture of each person.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 a posture feature vector indicating that posture.

[0079] (5) The behavior analysis function can estimate a person's movements using information about the stick figure model, changes in posture, etc., extract a feature vector of the person's movements (motion feature vector), and classify (classify) people included in the image. The behavior analysis function can also estimate a person's height and identify the person's position in the image using information about the stick figure model. For example, the behavior analysis function can estimate a person's movements, such as changes or transitions in posture and movement (changes or transitions in position), from the image and extract a motion feature vector related to the person's movements.

[0080] (6) The appearance attribute analysis function can recognize appearance attributes associated with a person. The appearance attribute analysis function extracts feature vectors (appearance attribute feature vectors) 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, and whether or not an umbrella is being used.

[0081] (7) The gradient feature analysis function extracts gradient feature quantities (gradient feature quantities) in an image. For gradient feature detection processing, techniques such as SIFT, SURF, RIFF, ORB, BRISK, CARD, and HOG can be applied.

[0082] 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.

[0083] (8) The color feature analysis function can detect an object from an image, extract a color feature vector of the detected object, and classify (classify) the detected object.

[0084] The color feature amount is, for example, a color histogram. The color feature analysis function can, for example, detect people and objects included in an image. Furthermore, for example, the color feature analysis function can classify each of the people and objects into classes.

[0085] (9) The flow line analysis function can determine the flow line (path of movement) of a person included in a video, for example, using the results of the identity determination in any of the analysis functions (2) to (6) described above. In more detail, for example, by connecting people determined to be the same across different images in a time series, the path of movement of the person can be determined. Note that, in cases where video footage is acquired using multiple in-vehicle cameras capturing different shooting areas, the flow line analysis function can also determine the flow line (path of movement) spanning multiple videos captured in different shooting areas.

[0086] The image feature vector includes, for example, the object detection result of the object detection function, a face feature vector, a human body feature vector, a posture feature vector, a movement feature vector, an appearance attribute feature vector, a gradient feature vector, a color feature vector, and a movement line.

[0087] Each of the analysis functions (1) to (9) may appropriately use the results of analysis performed by other analysis functions.

[0088] (Example of a method for generating individual analysis results of sensor information generated by a LiDAR sensor) The analysis unit 52 generates point cloud information using the sensor information generated by the LiDAR sensor. A general technique may be used to generate the point cloud information. The analysis unit 52 uses the point cloud information to generate individual analysis information including at least one of the position, shape, and detection time of an object.

[0089] (Example of a method for generating individual analysis results of sensor information generated by an object presence detection sensor) The analysis unit 52 may use, for example, the sensor information generated by the object presence detection sensor to generate individual analysis information including at least one of the object position, the time of detection, etc. A general technique may be used as a technique for generating such individual analysis information.

[0090] (Regarding the suspicious person detection unit 130) As described above, the suspicious person detection unit 130 uses the analysis results to detect suspicious persons other than specified non-suspicious persons who are engaging in suspicious behavior toward vehicles parked in parking lots within a specified range from the residential property.

[0091] For example, the suspicious person detection unit 130 detects as suspicious persons any person who is engaging in suspicious behavior among the people included in the analysis results of the analysis unit 52, excluding specific non-suspicious people.

[0092] For example, the suspicious person detection unit 130 may detect a suspicious person using the analysis result when the vehicle parks in a parking lot. For example, the suspicious person detection unit 130 may end the detection of a suspicious person using the analysis result when the vehicle leaves the parking lot. By combining these, the suspicious person detection unit 130 may detect a suspicious person using the analysis result while the vehicle is parked in a parking lot.

[0093] Note that the trigger for the suspicious person detection unit 130 to start or end detection of a suspicious person is not limited to this, and may be, for example, receiving a predetermined start instruction or end instruction. Furthermore, when multiple vehicles are parked in a parking lot, the suspicious person detection unit 130 may detect a suspicious person using the analysis result, for example, when at least one vehicle is parked in the parking lot. Furthermore, the suspicious person detection unit 130 may end detection of a suspicious person using the analysis result, for example, when all vehicles have exited the parking lot. By combining these, the suspicious person detection unit 130 may detect a suspicious person using the analysis result, for example, while at least one vehicle is parked in the parking lot.

[0094] (About Suspicious Behavior) Suspicious behavior is a suspicious behavior toward a vehicle parked in a parking lot within a specified range from the residential property. This behavior includes a person moving (person's behavior) and a person being in a certain state (person's state).

[0095] Suspicious behavior may include, for example, at least one of the following examples 1 to 8. (Suspicious behavior example 1) Approaching the area around the vehicle (Suspicious behavior example 2) Loitering around the vehicle (Suspicious behavior example 3) Staying around the vehicle (Suspicious behavior example 4) Being in a predetermined position around the vehicle (for example, crouching, half-squatting) (Suspicious behavior example 5) Peering into the vehicle (Suspicious behavior example 6) Peering under the vehicle (Suspicious behavior example 7) Contacting the vehicle (Suspicious behavior example 8) Entering the vehicle

[0096] Here, the surroundings of the vehicle may be, for example, a predetermined range from the vehicle. Note that the predetermined range regarding the surroundings of the vehicle may be different depending on the suspicious behavior.

[0097] Loitering around the vehicle may be, for example, moving around the vehicle for a predetermined period of time or longer, or repeatedly moving and stopping.

[0098] Staying around the vehicle means, for example, staying around the vehicle for a predetermined period of time or longer.

[0099] Looking into the vehicle interior means, for example, directing one's gaze toward the interior of the vehicle.

[0100] Looking under the vehicle means, for example, squatting with your head below the bottom of the vehicle.

[0101] Suspicious behavior is not limited to the above-mentioned examples 1 to 8. Suspicious behavior may be defined as appropriate and may be composed of, for example, one or more elements (suspicious elements). The suspicious elements may include, for example, one or more of: (A) elements related to the person's behavior; (B) elements related to the time period when the person was detected; (C) elements related to the person's attributes; (D) elements related to the situation around the person; etc.

[0102] (A) Elements related to a person's movements may include, for example, one or more elements related to (A-1) movement speed, (A-2) position, (A-3) behavior, (A-4) movement path, (A-5) frequency, etc.

[0103] (A-1) The elements belonging to the moving speed include, for example, at least one of stopping, a low speed equal to or lower than a predetermined speed, and the like.

[0104] (A-2) The element belonging to the location is, for example, at least one of being around the vehicle, being inside the vehicle (entering the vehicle), and the like.

[0105] (A-3) Elements belonging to behavior include, for example, at least one of a crouching or half-squatting posture, a face or gaze directed toward the inside or bottom of the vehicle, contact with the vehicle, etc.

[0106] (A-4) An element belonging to a travel route is, for example, a travel route that is different from the travel route of the resident.

[0107] (A-5) An element belonging to frequency is, for example, that a predetermined action is performed at a frequency equal to or greater than a predetermined frequency within a predetermined period of time. The predetermined action here may be defined using, for example, one or more of the elements exemplified in (A-1) to (A-4). The predetermined period may be determined, for example, according to the period during which the associated predetermined action is generally repeated in suspicious activity.

[0108] (B) The element relating to the time period in which a person is detected is, for example, at least one of nighttime, early morning, daytime, whether the person is at home, etc. Nighttime is, for example, 10 PM to 12 PM and 12 PM to 3 AM. Early morning is, for example, 3 AM to 5 AM. Daytime is, for example, a time period when residents are often not at home (for example, 10 AM to 3 PM). Note that examples of time periods are not limited to those given here.

[0109] The at-home status includes whether or not the occupants of the home are present, whether the occupants at home are only elderly people over a predetermined age or only children under a predetermined age, and the like.

[0110] (C) Elements related to a person's attributes include, for example, at least one of the following: the person's height is above a predetermined value; the person is of a predetermined gender, either male or female; the person is riding a motorcycle, bicycle, or truck that can carry a vehicle.

[0111] (D) The element relating to the situation around the person is, for example, at least one of the following: the brightness of the premises is dark, below a threshold, the weather is cloudy or rainy, and the like.

[0112] Using these suspicious elements, it is possible to predefine, for example, the suspicious acts of Examples 1 to 8 above, suspicious acts that further define these examples in detail, and suspicious acts that differ from these examples. This makes it possible to define, for example, suspicious acts that may pose a danger to vehicles.

[0113] (Regarding Suspiciousness Levels) Suspicious behavior may be associated with a suspiciousness level according to the degree of likelihood that the suspicious behavior will cause harm to the vehicle. The suspicious person detection unit 130 may detect as a suspicious person a person other than a specific non-suspicious person who engages in suspicious behavior that corresponds to a suspiciousness level equal to or higher than an appropriately set level. The suspiciousness level may be set by, for example, a resident who is a user, or may be set automatically. Examples of suspiciousness levels and automatic setting will be described in other embodiments.

[0114] (Regarding Non-Suspicious Persons) A non-suspicious person is a person who is not suspicious. Examples of non-suspicious persons include a resident of a house, a resident living in the neighborhood of the house (neighborhood resident), a delivery person for a parcel delivery service, a postal worker, etc.

[0115] Non-suspicious individuals may be registered in advance in the information processing device 100. For example, facial images of non-suspicious individuals may be used for registration. Note that the method for registering non-suspicious individuals is not limited to facial images.

[0116] Alternatively, non-suspicious individuals may be identified automatically, the method of which will be described later in another embodiment.

[0117] (Notification Control Unit 140) As described above, the notification control unit 140 causes the notification unit to issue a notification when a suspicious individual is detected.

[0118] The target of the notification may be at least one of a suspicious person, a resident of a house, a security company, the police, and the like.

[0119] The alarm unit that alerts a suspicious person may be, for example, a light, a horn, etc. mounted on the vehicle, or a light, a buzzer, etc. installed on the premises. The alarm control unit 140 may turn on or flash at least one of these lights, or sound a sound from the horn, buzzer, etc. This notifies the suspicious person that the suspicious person has been detected, thereby threatening them and reducing the possibility of danger to the vehicle.

[0120] The method of notifying a suspicious person is not limited to the example given here.

[0121] The notification unit that notifies the resident is, for example, a mobile terminal used by the resident. The mobile terminal is, for example, a smartphone, a tablet terminal, etc. The notification control unit 140 may, for example, send information indicating that a suspicious person has been detected to the mobile terminal, causing the mobile terminal to display or sound a message. This allows the resident to know that a suspicious person has been detected, thereby reducing the possibility of danger to the vehicle.

[0122] The method of notifying the resident is not limited to the example given here.

[0123] The notification unit that notifies the security company, police, etc. is, for example, a device that receives information indicating that a suspicious person has been detected via the communication network NT. The notification control unit 140 may, for example, transmit information indicating that a suspicious person has been detected. The information indicating that a suspicious person has been detected may, for example, be a message indicating that a suspicious person has been detected, but is not limited to this. This allows the security company, police, etc. to be notified that a suspicious person has been detected, thereby reducing the possibility of danger to the vehicle.

[0124] The method of notifying security companies, police, etc. is not limited to the example given here.

[0125] (Example of Physical Configuration of Information Processing Device 100) The information processing device 100 physically includes 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, as shown in FIG.

[0126] 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.

[0127] The processor 1020 is implemented as a CPU (Central Processing Unit) or a GPU (Graphics Processing Unit).

[0128] The memory 1030 is a main storage device realized by a RAM (Random Access Memory) or the like.

[0129] 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.

[0130] The network interface 1050 is an interface for connecting a device equipped with it to a communication network.

[0131] The input interface 1060 is an interface for the user to input information, and is configured from, for example, a touch panel, a keyboard, a mouse, and the like.

[0132] 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.

[0133] In this way, the functions of the information processing device 100 can be realized by the physical components cooperating to execute a software program. Therefore, the present invention may be realized as a software program or as a non-transitory storage medium on which the program is recorded.

[0134] The analysis device 50 may be physically configured in the same manner as the information processing device 100, for example.

[0135] The functions of the analysis device 50 and the information processing device 100 as a whole are not limited to those described above, and may be provided in one or more devices. For example, the information processing device 100 may have the functions of the analysis device 50 and be physically integrated with the analysis device 50.

[0136] (Operations and Effects) As described above, according to this embodiment, the information processing device 100 includes the suspicious person detection unit 130 and the notification control unit 140. The suspicious person detection unit 130 uses the analysis results of sensor information from the sensors 10 that monitor a predetermined range from the residential property to detect a suspicious person other than a specific non-suspicious person who is engaging in suspicious behavior toward vehicles parked in a parking lot within the predetermined range. The notification control unit 140 causes the notification unit to issue a notification when a suspicious person is detected.

[0137] This allows for the proper detection of suspicious individuals engaging in suspicious behavior toward vehicles parked in parking lots around residential areas by excluding specific non-suspicious individuals from the list of suspicious individuals. Therefore, when there is a high risk to vehicles parked around residential areas, it is possible to notify the driver that a suspicious individual has been detected. This makes it possible to improve the safety of vehicles parked around residential areas.

[0138] According to this embodiment, there are a plurality of sensors, including one or more residential sensors associated with the residence and one or more vehicle sensors mounted on vehicles parked in the parking lot.

[0139] This allows the sensor 10 to monitor a wider range than if the sensor 10 were only a residential sensor or an in-vehicle sensor, thereby improving the safety of vehicles parked around homes.

[0140] According to this embodiment, the analysis results include an object detected by analysis using sensor information, and at least one of the position, movement, posture, detection time, attributes, surrounding conditions, movement speed, and movement route of the detected object.

[0141] This allows the system to properly detect suspicious individuals and notify the driver when there is a high risk to vehicles parked near the home, thereby improving safety in the home.

[0142] According to this embodiment, when a vehicle is parked in a parking lot, the suspicious person detection unit 130 detects a suspicious person using the analysis result.

[0143] This allows suspicious individuals to be detected when it is most necessary, and when there is a high risk to vehicles parked around the house, a warning can be given that a suspicious individual has been detected, thereby improving safety in the house.

[0144] (Variation 1) In the first embodiment, an example in which one analysis device 50 is used has been described, but the information processing system may include multiple analysis devices. For example, if the information processing system includes multiple sensors 10, each of the multiple analysis devices may be associated with a sensor group consisting of one or more sensors 10. In this case, each analysis device may analyze sensor information generated by one or more sensors 10 that make up the sensor group and integrate these individual analysis results as necessary. The suspicious person detection unit 130 may integrate the individual analysis results generated by each of the multiple analysis devices or the integrated individual analysis results to generate an analysis result.

[0145] [Embodiment 2] In this embodiment, an example of a method for automatically identifying a non-suspicious individual will be described. Note that in this embodiment, for the sake of simplicity, descriptions that overlap with other embodiments will be omitted as appropriate.

[0146] (Device Configuration Example of Information Processing System S2) The information processing system S2 includes the sensor 10 and the analysis device 50 similar to those in the first embodiment, and an information processing device 200, as shown in FIG. 8, for example.

[0147] (Configuration Example of Information Processing Device 200) The information processing device 200 includes a suspicious person detection unit 130 and a notification control unit 140 similar to those in the first embodiment, and a non-suspicious person identification unit 250, as shown in FIG. 9, for example.

[0148] The non-suspicious individual identification unit 250 identifies a non-suspicious individual using history information of a person detected through analysis using sensor information.

[0149] (Example of Processing Operation of Information Processing System S2) The information processing system S2 executes information processing as shown in FIG. 10, for example.

[0150] Steps S10, S51, and S52 are executed in the same manner as in the first embodiment.

[0151] The non-suspicious individual identification unit 250 identifies a non-suspicious individual using history information of the person detected by the analysis using the sensor information (step S250).

[0152] Step S140 is executed in the same manner as in the first embodiment.

[0153] (Regarding the non-suspicious person identification unit 250) The non-suspicious person identification unit 250 uses history information of people detected through analysis using sensor information to identify non-suspicious people such as residents of the house, neighbors, delivery people, etc.

[0154] The non-suspicious person identification unit 250 uses, for example, history information of the analysis results to identify non-suspicious persons, such as residents of the house, neighbors, delivery people, etc., from among the people included in the analysis results. The analysis results may include, for example, the analysis results of images generated by a camera.

[0155] In more detail, for example, the non-suspicious person identification unit 250 may identify a person as a non-suspicious person by using the frequency at which the same person is detected and a predetermined first threshold value related thereto. In this case, for example, the non-suspicious person identification unit 250 may identify a person who appears more frequently than the predetermined first threshold value as a non-suspicious person. The same person may be identified by using, for example, a facial image of the person, a feature vector extracted from the facial image, or the like, but the method for identifying the same person is not limited to this.

[0156] The first threshold value may be different depending on the type of non-suspicious person, such as a resident, a neighbor, a delivery person, etc. This allows non-suspicious people to be identified by type. Note that, in cases where the types of non-suspicious people are not distinguished, the first threshold value may be one.

[0157] Furthermore, for example, the non-suspicious individual identifying unit 250 may identify a non-suspicious individual using the clothing of the person or the appearance characteristics of the vehicle in which the person is riding.

[0158] Generally, delivery personnel for each company wear the same type of clothing (uniforms) and use vehicles with common exterior characteristics. These exterior characteristics include, for example, the company's logo, company name, color and pattern combinations, etc. Therefore, delivery personnel can be identified by using the exterior characteristics of the person's clothing or the vehicle they are riding in.

[0159] Furthermore, the time period during which delivery personnel make deliveries is often predetermined, such as from 9:00 AM to 9:00 PM. In the case of a nearby resident, the time period during which the person is detected is often determined according to the person, such as the time when the person arrives at work or when the person arrives at or leaves school. Therefore, the non-suspicious person identification unit 250 may further identify a non-suspicious person using the time when the person is detected.

[0160] In this way, the non-suspicious person identification unit 250 may identify a non-suspicious person using, for example, at least one of the frequency with which the same person is detected, the person's clothing, and the appearance characteristics of the vehicle the person is riding in. The non-suspicious person identification unit 250 may also identify a non-suspicious person using, for example, the time at which the person is detected.

[0161] Note that the analysis results used to identify non-suspicious individuals are not limited to image analysis results. For example, assume that a resident has a designated path through the premises when leaving or returning home, and sensor 10 is an object presence detection sensor that detects the presence or absence of an object in this path. In such a case, the analysis results of sensor information generated by the object presence detection sensor may be used to identify non-suspicious individuals (e.g., residents). In this case, the non-suspicious individual identification unit 250 may identify non-suspicious individuals using a history of analysis results of multiple types of sensor information (e.g., images and sensor information from the object presence detection sensor).

[0162] (Operations and Effects) As described above, according to this embodiment, the information processing device 200 includes the non-suspicious person identification unit 250 that identifies non-suspicious people using history information of people detected through analysis using sensor information.

[0163] This allows a specific non-suspicious person to be automatically identified and detected appropriately, eliminating the need to pre-register specific non-suspicious people and thus making it possible to easily improve the safety of vehicles parked around homes.

[0164] [Embodiment 3] The suspicious person detection unit may detect a suspicious person using at least one of the analysis result, presence-at-home information indicating the presence status of the resident in the house, and the movement route of the person included in the analysis result. In this embodiment, an example of detecting a suspicious person using the analysis result and presence-at-home information will be described. In addition, in this embodiment, an example of a method of generating presence-at-home information will be described. Note that in this embodiment, for simplicity of explanation, explanations that overlap with other embodiments will be omitted as appropriate.

[0165] (Device Configuration Example of Information Processing System S3) The information processing system S3 includes the sensor 10 and analysis device 50 similar to those in the first embodiment, and an information processing device 300, as shown in FIG. 11, for example.

[0166] (Configuration Example of Information Processing Device 300) The information processing device 300 includes a suspicious person detection unit 330, a notification control unit 140 similar to that of the first embodiment, and a presence-at-home information generation unit 360, as shown in FIG. 12, for example.

[0167] The presence-at-home information generating unit 360 generates presence-at-home information using at least one of the resident's location information and the resident's history information detected by analysis using sensor information.

[0168] The suspicious person detection unit 330 detects a suspicious person using the analysis result and the presence-at-home information.

[0169] (Example of Processing Operation of Information Processing System S3) The information processing system S3 executes information processing as shown in FIG. 13, for example.

[0170] Steps S10, S51, and S52 are executed in the same manner as in the first embodiment.

[0171] The presence-at-home information generating unit 360 generates presence-at-home information using at least one of the resident's location information and the resident's history information detected by analysis using the sensor information (Step S360).

[0172] The suspicious person detection unit 330 further uses the analysis result and the presence-at-home information to detect a suspicious person (step S330).

[0173] Step S140 is executed in the same manner as in the first embodiment.

[0174] (Regarding the presence-at-home information generation unit 360) As described above, the presence-at-home information generation unit 360 generates presence-at-home information using at least one of the resident's location information and the resident's history information detected by analysis using sensor information.

[0175] The presence-at-home information is information that indicates whether a resident is at home in a house.

[0176] The presence information may include, for example, at least one of the following: information indicating whether the occupants of the home are present in the home; information indicating that the occupants at home are only elderly people above a certain age or children below a certain age; and information indicating when the occupants are out.

[0177] The location information of the resident may be obtained, for example, using a GPS (Global Positioning System) function provided in a mobile device used by the resident. In this case, the presence presence information generation unit 360 may obtain location information indicating the current location of the resident from the mobile device used by the resident. If there are multiple residents, the presence presence information generation unit 360 may store in advance resident information that associates the mobile device with the age of each resident, etc.

[0178] The presence-at-home information generating unit 360 may then determine whether the resident is at home based on, for example, preset location information of the home and the resident's current location, and generate presence-at-home information based on the result of this determination. Also, for example, when the resident goes out, the presence-at-home information generating unit 360 may generate presence-at-home information that includes the time when the resident left the premises of the home as the time of leaving.

[0179] The historical information of the resident detected by the analysis using the sensor information is the historical information of the resident included in the historical information of the analysis results. For example, the sensor information may include an image. Furthermore, the presence-at-home information may include information generated using the historical information of the resident detected by the analysis using the image.

[0180] In detail, for example, the presence-at-home information generation unit 360 may identify a resident using a method similar to the method used by the non-suspicious person identification unit 250 described in embodiment 2 to identify a resident. Note that if the information processing device 300 further includes the non-suspicious person identification unit 250, the presence-at-home information generation unit 360 may generate presence-at-home information using history information of the resident identified by the non-suspicious person identification unit 250.

[0181] The presence-at-home information generating unit 360 may then use the resident history information to determine, for example, when each resident has entered or left the home. Based on this determination result, the presence-at-home information generating unit 360 may generate presence-at-home information indicating whether the resident of the home is present in the home. Based on this determination result, the presence-at-home information generating unit 360 may also generate presence-at-home information indicating that the resident currently at home is only elderly people above a predetermined age or only children below a predetermined age. Based on this determination result, the presence-at-home information generating unit 360 may also generate information indicating when the resident went out.

[0182] (Regarding the suspicious person detection unit 330) The suspicious person detection unit 330 uses the analysis results and the presence information to detect suspicious persons, other than specified non-suspicious persons, who are engaging in suspicious behavior toward vehicles parked in parking lots within a specified range from the residential property.

[0183] As described above, the suspicious person detection unit 330 may detect as a suspicious person a person who engages in suspicious behavior that corresponds to a suspicious level equal to or higher than a set level. The suspicious person detection unit 330 sets the level using, for example, presence-at-home information.

[0184] (Configuration Example of Suspicious Person Detector 330) The suspicious person detector 330 includes a level setting unit 331 and a detection unit 332, as shown in FIG. 14, for example.

[0185] The level setting unit 331 sets a level for detecting suspicious individuals based on the presence-at-home information.

[0186] The detection unit 332 uses the analysis results to detect a suspicious individual other than a specific non-suspicious individual who is engaging in suspicious behavior according to a set level.

[0187] (Example of Operation of Suspicious Person Detector 330) The suspicious person detector 330 executes a suspicious person detection process (step S330) as shown in FIG. 15, for example.

[0188] The level setting unit 331 sets a level for detecting suspicious individuals based on the presence-at-home information (step S331).

[0189] The detection unit 332 uses the analysis results to detect a suspicious individual other than a specific non-suspicious individual who is engaging in suspicious behavior according to the set level (step S332).

[0190] (Level Setting Unit 331) The level setting unit 331 sets a level for detecting suspicious individuals based on the presence-at-home information.

[0191] Generally, if there is no resident in the house, there is an extremely high possibility that a suspicious person will cause harm to a vehicle (e.g., level 1). Also, if the only resident in the house is an elderly person or a child, there is a high possibility that a suspicious person will cause harm to a vehicle (e.g., level 2). If there is no resident in the house, there is a low possibility that a suspicious person will cause harm to a vehicle (e.g., level 3).

[0192] Therefore, the level setting unit 331 may set a predetermined level according to the presence-at-home status of the resident indicated by the presence-at-home information. Note that the method by which the level setting unit 331 sets a level using the presence-at-home information is not limited to the example described here.

[0193] (Regarding the detection unit 332) The detection unit 332, for example, uses the analysis results to detect as a suspicious person a person other than a specific non-suspicious person who is engaging in suspicious behavior corresponding to a suspicious level equal to or higher than the level set by the level setting unit 331.

[0194] Although the example in which the suspicious person detection unit 330 uses the presence-at-home information to set the level has been described, the method of using the presence-at-home information to detect a suspicious person is not limited to that described here. For example, the suspicious person detection unit 330 may detect a person as suspicious if it detects a person approaching the periphery of the vehicle and no resident has left the house within a predetermined time period prior to the person's detection.

[0195] (Operations and Effects) As described above, according to this embodiment, the suspicious person detection unit 330 detects a suspicious person using the analysis results and the presence-at-home information indicating whether the resident is at home in the house.

[0196] This allows the system to properly detect suspicious individuals who are likely to pose a danger to vehicles and notify them of the detection of the suspicious individuals, thereby further improving the safety of vehicles parked near residential areas.

[0197] According to this embodiment, the information processing device 300 is equipped with a presence-at-home information generation unit 360 that generates presence-at-home information using at least one of the resident's location information and the resident's history information detected by analysis using sensor information.

[0198] The presence-at-home information generation unit 360 includes a level setting unit 331 and a detection unit 332. The level setting unit 331 sets a level for detecting suspicious individuals based on the presence-at-home information. The detection unit 332 uses the analysis results to detect suspicious individuals other than specific non-suspicious individuals who are engaging in suspicious behavior according to the set level.

[0199] This allows the presence-at-home information to be used to appropriately detect suspicious individuals who are likely to pose a threat to vehicles, and to notify the detection of such suspicious individuals. This makes it possible to further improve the safety of vehicles parked near homes.

[0200] [Embodiment 4] As described above, the suspicious person detection unit may detect a suspicious person by further using at least one of the analysis result, presence information indicating whether a resident is at home in the house, and the movement route of the person included in the analysis result. In this embodiment, an example will be described in which a suspicious person is detected using the movement route of the person included in the analysis result.

[0201] In this embodiment, an example of a method for automatically generating a route pattern (first pattern) along which a resident travels to use a vehicle parked in a parking lot will also be described.

[0202] In this embodiment, for the sake of simplicity, descriptions that overlap with other embodiments will be omitted as appropriate.

[0203] (Device Configuration Example of Information Processing System S4) The information processing system S2 includes the sensor 10 and analysis device 50 similar to those in the first embodiment, and an information processing device 400, as shown in FIG. 16, for example.

[0204] (Configuration Example of Information Processing Device 400) The information processing device 400 includes, for example, a suspicious person detection unit 430, a notification control unit 140 similar to that of the first embodiment, and a resident information generation unit 470, as shown in FIG.

[0205] The resident information generation unit 470 generates resident information about the resident of the house using history information of the resident detected by analysis using sensor information.

[0206] The suspicious person detection unit 430 detects a suspicious person using the movement route of the person included in the analysis result.

[0207] (Example of Processing Operation of Information Processing System S4) The information processing system S4 executes information processing as shown in FIG. 18, for example.

[0208] Steps S10, S51, and S52 are executed in the same manner as in the first embodiment.

[0209] The resident information generating unit 470 generates resident information about the resident of the house using the history information of the resident detected by the analysis using the sensor information (step S470).

[0210] The suspicious person detection unit 430 detects a suspicious person using the movement route of the person included in the analysis result (step S430).

[0211] Step S140 is executed in the same manner as in the first embodiment.

[0212] (Regarding the Resident Information Generator 470) As described above, the resident information generator 470 generates resident information about the resident of the house using history information of the resident detected by analysis using sensor information.

[0213] The resident information is information about a resident. The resident information may include, for example, at least one of the following for each resident: height, face, body type, sex, information for identifying the mobile device used, and resident route pattern.

[0214] The resident route pattern is information indicating the pattern of the route along which the resident travels. The resident information generating unit 470 may, for example, use the resident's history information to identify the pattern of the route along which the resident travels frequently (e.g., at a frequency equal to or greater than a predetermined frequency) as the resident route pattern. The resident route pattern may be indicated by an area along the route along which the resident travels frequently.

[0215] The resident route pattern may be identified by, for example, statistical processing of travel routes, although the method for identifying the resident route pattern is not limited to this.

[0216] The resident route pattern may include a first pattern that is a pattern of a route that a resident takes to use a vehicle parked in a parking lot. That is, the resident information may include a first pattern that is a pattern of a route that a resident takes to use a vehicle parked in a parking lot.

[0217] The resident information generation unit 470 may, for example, use the resident's historical information to generate a first pattern based on a first route that the resident uses when heading from their home to their vehicle parked in a parking lot.

[0218] In this case, the first pattern may be an average of the first routes, an area of ​​a certain width centered on the first route, or an area including multiple first routes. The multiple first routes may be, for example, routes taken by the resident from the house to the vehicle parked in the parking lot at different times. Furthermore, the area including the multiple first routes may exclude areas corresponding to routes taken by the resident from the house to the vehicle parked in the parking lot that have been traveled less than a predetermined number of times.

[0219] The history information of the resident detected by the analysis using the sensor information is the history information of the resident included in the history information of the analysis result, as described in embodiment 3. The resident information generation unit 470 may identify the resident in a manner similar to the method used by the non-suspicious person identification unit 250 described in embodiment 2 to identify the resident. Note that, if the information processing device 400 further includes the non-suspicious person identification unit 250, the resident information generation unit 470 may generate the resident information using the history information of the resident identified by the non-suspicious person identification unit 250.

[0220] (Regarding the resident information generation unit 470) The suspicious person detection unit 430 uses the movement routes of people included in the analysis results to detect suspicious people other than specific non-suspicious people in vehicles parked in parking lots within a specified range from the residential property.

[0221] For example, the suspicious behavior may include traveling along a route different from the first pattern and approaching within a predetermined range from the vehicle. In this case, the suspicious person detection unit 430 may detect a person included in the analysis result as a suspicious person if the person travels along a route different from the first pattern and approaches within a predetermined range from the vehicle.

[0222] Here, moving along a route different from the first pattern may be substantially determined. That is, moving along a route different from the first pattern may be, for example, a case where a person included in the analysis result moves along a longitude that is a predetermined distance or more away from the route indicated by the first pattern. Also, for example, if the first pattern is indicated by an area, moving along a route different from the first pattern may be a case where a person included in the analysis result moves outside the area indicated by the first pattern.

[0223] Generally, when a resident uses a vehicle, they often move from the entrance of the house toward the vehicle. In contrast, a suspicious person often moves toward the vehicle from the road facing the parking lot. Therefore, by determining that a suspicious person moves along a route different from the first pattern and approaches the vehicle as suspicious behavior, it is possible to detect a suspicious person who is likely to cause harm to the vehicle.

[0224] The first pattern and other resident route patterns may be set in advance based on input from a user such as a resident. The suspicious person detection unit 430 may use the movement route of the person included in the analysis result to detect a person moving along a route different from the resident route pattern as a suspicious person. Moving along a route different from the resident route pattern may be determined substantially in the same manner as in the case of the first pattern described above.

[0225] (Operations and Effects) As described above, according to this embodiment, the suspicious person detection unit 430 detects a suspicious person using the movement route of the person included in the analysis result.

[0226] This allows the system to properly detect suspicious individuals who are likely to pose a danger to vehicles and notify them of the detection of the suspicious individuals, thereby further improving the safety of vehicles parked near residential areas.

[0227] According to this embodiment, the information processing device 400 includes a resident information generation unit 470 that generates resident information about a resident of a house using historical information about the resident detected through analysis using sensor information. The resident information includes a first pattern, which is a pattern of a route that the resident takes to use a vehicle parked in a parking lot. Suspicious behavior includes traveling a route different from the first pattern and approaching within a predetermined range of the vehicle.

[0228] This makes it possible to detect as suspicious persons anyone traveling on a route different from the route normally used by residents. Therefore, it is possible to properly detect suspicious persons who are likely to pose a danger to vehicles and to notify the detection of such suspicious persons. Therefore, it is possible to further improve the safety of vehicles parked around homes.

[0229] Although the present disclosure has been described above with reference to the embodiments, the present disclosure is not limited to the above-described embodiments. Various modifications that can be understood by those skilled in the art can be made to the configuration and details of the present disclosure within the scope of the present disclosure. Furthermore, each embodiment can be combined with other embodiments as appropriate.

[0230] In addition, although the flowcharts used in the above description show a sequence of steps (processes), the order of steps executed in each embodiment is not limited to the sequence shown in the flowcharts. In each embodiment, the order of steps shown in the diagrams can be changed as long as it does not cause any problems in terms of the content.

[0231] Some or all of the above embodiments can be described as, but are not limited to, the following supplementary notes. 1. An information processing device comprising: suspicious person detection means for detecting a suspicious person, other than a specific non-suspicious person, engaging in suspicious behavior toward vehicles parked in a parking lot within a predetermined range, using analysis results of sensor information from sensors monitoring the grounds of a house; and notification control means for causing a notification unit to issue a notification when the suspicious person is detected. 2. The information processing device described in 1., further comprising non-suspicious person identification means for identifying the non-suspicious person using history information of a person detected by analysis using the sensor information. 3. The information processing device described in 1. or 2., wherein the suspicious person detection means detects the suspicious person using at least one of the analysis results, presence information indicating whether a resident is at home in the house, and a person's movement route included in the analysis results. 4. The sensors are multiple, and the multiple sensors include one or more house sensors installed in association with the house and one or more on-board sensors installed in vehicles parked in the parking lot. 5. The information processing device according to any one of 1. to 4., wherein the analysis result includes an object detected by analysis using the sensor information, and at least one of the position, movement, posture, detection time, attributes, surrounding conditions, movement speed, and movement route of the detected object. 6. The information processing device according to any one of 1. to 5., wherein the suspicious person detection means detects the suspicious person using the analysis result when the vehicle parks in the parking lot. 7. The information processing device according to 2., further comprising: presence-at-home information generation means for generating the presence-at-home information using at least one of position information of the resident and history information of the resident detected by analysis using the sensor information, wherein the suspicious person detection means includes: level setting means for setting a level for detecting the suspicious person based on the presence-at-home information; and detection means for using the analysis result to detect the suspicious person other than the specified non-suspicious person performing the suspicious behavior according to the set level.8. The information processing device described in 2., further comprising a resident information generation means for generating resident information about a resident of the house using history information of the resident detected by analysis using the sensor information, wherein the resident information includes a first pattern that is a pattern of a route the resident takes to use the vehicle parked in the parking lot, and the suspicious activity includes traveling a route different from the first pattern and approaching within a predetermined range of the vehicle. 9. The information processing device described in 7., wherein the sensor information includes an image, and the presence-at-home information includes information generated using the history information of the resident detected by analysis using the image. 10. An information processing system comprising: a sensor that monitors a predetermined range from the grounds of the house; analysis means that analyzes the sensor information generated by the sensor; suspicious person detection means that uses the analysis results to detect a suspicious person, other than a specified non-suspicious person, engaging in suspicious activity toward a vehicle parked in the parking lot within the predetermined range; and notification control means that causes a notification unit to issue a notification when the suspicious person is detected. The information processing system according to 10. further comprises non-suspicious person identification means for identifying the non-suspicious person using history information of a person detected by analysis using the sensor information. 12. The information processing system according to 10. or 11., wherein the suspicious person detection means detects the suspicious person using at least one of the analysis results, presence information indicating whether a resident is at home in the house, and the movement route of the person included in the analysis results. 13. The information processing system according to any one of 10. to 12., wherein the sensors are multiple, and the multiple sensors include one or more home sensors installed in association with the house and one or more vehicle sensors installed in a vehicle parked in the parking lot. 14. The information processing system according to any one of 10. to 13., wherein the analysis results include an object detected by analysis using the sensor information, and at least one of the position, movement, posture, detection time, attributes, surrounding conditions, movement speed, and movement route of the detected object. 15. 17. The information processing system according to any one of 10. to 16., wherein the suspicious person detection means detects the suspicious person using the analysis result when the vehicle is parked in the parking lot.16. The information processing system described in 11., further comprising: presence-of-house information generation means for generating the presence-of-house information using at least one of location information of the resident and history information of the resident detected by analysis using the sensor information, wherein the suspicious person detection means includes: level setting means for setting a level for detecting the suspicious person based on the presence-of-house information; and detection means for using the analysis results to detect a suspicious person other than the specific non-suspicious person engaging in the suspicious behavior according to the set level. 17. The information processing system described in 11., further comprising: resident information generation means for generating resident information about a resident of the house using history information of the resident detected by analysis using the sensor information, wherein the resident information includes a first pattern that is a pattern of routes the resident takes to use the vehicle parked in the parking lot, and the suspicious behavior includes traveling on a route different from the first pattern and approaching within a predetermined range of the vehicle. 18. The information processing system described in 16., wherein the sensor information includes an image, and the presence-of-house information includes information generated using the history information of the resident detected by analysis using the image. 19. An information processing method in which one or more computers use analysis results of sensor information from sensors monitoring a predetermined range from the grounds of a house to detect a suspicious person other than a specific non-suspicious person engaging in suspicious behavior toward vehicles parked in a parking lot within the predetermined range, and cause an alarm unit to issue an alarm when the suspicious person is detected. 20. The information processing method described in 19. further includes identifying the non-suspicious person using history information of the person detected by analysis using the sensor information. 21. The information processing method described in 19. or 20., in which the detecting the suspicious person includes detecting the suspicious person using at least one of the analysis results, presence information indicating whether a resident of the house is at home, and the person's movement route included in the analysis results. 22. The information processing method described in any one of 19. to 21., in which the sensors are multiple, and the multiple sensors include one or more home sensors installed in association with the house and one or more on-board sensors installed in vehicles parked in the parking lot.23. The information processing method according to any one of 19. to 22., wherein the analysis result includes an object detected by analysis using the sensor information, and at least one of the position, movement, posture, detection time, attributes, surrounding conditions, movement speed, and movement route of the detected object. 24. The information processing method according to any one of 19. to 23., wherein the step of detecting a suspicious person includes detecting the suspicious person using the analysis result when the vehicle parks in the parking lot. 25. The information processing method according to 20., further including generating the presence information using at least one of location information of the resident and history information of the resident detected by analysis using the sensor information, and wherein the step of detecting the suspicious person includes setting a level for detecting the suspicious person based on the presence information, and using the analysis result to detect the suspicious person other than the specified non-suspicious person who is engaging in the suspicious behavior according to the set level. 26. The information processing method described in 20. further generates resident information about the resident of the house using history information of the resident detected by analysis using the sensor information, wherein the resident information includes a first pattern that is a pattern of a route the resident takes to use the vehicle parked in the parking lot, and the suspicious behavior includes traveling a route different from the first pattern and approaching within a predetermined range of the vehicle. 27. The information processing method described in 25., wherein the sensor information includes an image, and the presence-at-home information includes information generated using the history information of the resident detected by analysis using the image. 28. A program causing one or more computers to use analysis results of sensor information from sensors monitoring a predetermined range from the grounds of the house to detect a suspicious person other than a specified non-suspicious person engaging in suspicious behavior toward a vehicle parked in a parking lot within the predetermined range, and to cause a notification unit to notify when the suspicious person is detected. 29. The program described in 28. further causes the one or more computers to identify the non-suspicious person using history information of the person detected by analysis using the sensor information.30. The program according to 28. or 29., wherein detecting the suspicious person uses at least one of the analysis result, presence information indicating whether the resident is at home at the residence, and the movement route of the person included in the analysis result to detect the suspicious person. 30. The program according to any one of 27. to 29., wherein there are a plurality of sensors, and the plurality of sensors include one or more residence sensors installed in association with the residence and one or more vehicle sensors mounted on a vehicle parked in the parking lot. 31. The program according to any one of 28. to 30., wherein the analysis result includes an object detected by analysis using the sensor information, and at least one of the position, movement, posture, time of detection, attributes, surrounding conditions, movement speed, and movement route of the detected object. 32. The program according to any one of 28. to 31., wherein detecting the suspicious person uses the analysis result to detect the suspicious person when the vehicle parks in the parking lot. 33. The program described in 28., further causing the one or more computers to generate the presence information using at least one of the resident's location information and history information of the resident detected by analysis using the sensor information, and detecting the suspicious person includes setting a level for detecting the suspicious person based on the presence information, and using the analysis results to detect the suspicious person other than the specified non-suspicious person who engages in the suspicious behavior according to the set level. 34. The program described in 28., further causing the one or more computers to generate resident information about the resident of the house using history information of the resident detected by analysis using the sensor information, the resident information including a first pattern that is a pattern of routes the resident takes to use the vehicle parked in the parking lot, and the suspicious behavior includes traveling on a route different from the first pattern and approaching within a predetermined range of the vehicle. 35. The information program described in 33., wherein the sensor information includes an image, and the presence information includes information generated using the history information of the resident detected by analysis using the image.36. A recording medium on which the program according to any one of 28. to 35. is recorded.

[0232] This application claims priority based on Japanese Patent Application No. 2024-003145, filed January 12, 2024, the disclosure of which is incorporated herein by reference in its entirety.

[0233] S1 to S4 Information processing system 10 Sensor 50 Analysis device 51 Sensor information acquisition unit 52 Analysis unit 100, 200, 300, 400 Information processing device 130, 330, 430 Suspicious person detection unit 140 Notification control unit 250 Non-suspicious person identification unit 331 Level setting unit 332 Detection unit 360 Presence information generation unit 470 Resident information generation unit

Claims

1. An information processing apparatus comprising: a suspicious person detecting means for detecting a suspicious person who performs a suspicious act other than a specific non-suspicious person with respect to a vehicle parked in a parking lot within a predetermined range by using an analysis result of sensor information from a sensor that monitors a predetermined range from a residential site; and a notification control means for causing a notification unit to perform notification when the suspicious person is detected.

2. The information processing apparatus according to claim 1, further comprising a non-suspicious person specifying means for specifying the non-suspicious person by using history information of a person detected by analysis using the sensor information.

3. The information processing apparatus according to claim 1 or 2, wherein the suspicious person detecting means detects the suspicious person by using at least one of the analysis result and home information indicating the presence / absence status of a resident in the house and a movement route of a person included in the analysis result.

4. The information processing apparatus according to claim 1 or 2, wherein a plurality of the sensors include one or more home sensors installed in association with the house and one or more in-vehicle sensors mounted on a vehicle parked in the parking lot.

5. The information processing apparatus according to claim 1 or 2, wherein the analysis result includes at least one of an object detected by analysis using the sensor information, a position, an action, a posture, a detection time, an attribute, a surrounding situation, a movement speed, and a movement route of the detected object.

6. The information processing apparatus according to claim 1 or 2, wherein the suspicious person detecting means detects the suspicious person by using the analysis result when the vehicle parks in the parking lot.

7. The information processing apparatus according to claim 2, further comprising a home information generating means for generating the home information by using at least one of the position information of the resident and the history information of the resident detected by analysis using the sensor information, wherein the suspicious person detecting means includes: a level setting means for setting a level for detecting the suspicious person based on the home information; and a detecting means for detecting the suspicious person who performs the suspicious act corresponding to the set level other than the specific non-suspicious person by using the analysis result.

8. The information processing apparatus according to claim 2, further comprising resident information generation means for generating resident information regarding a resident of the house using the history information of the resident person detected by the analysis using the sensor information, wherein the resident information includes a first pattern that is a pattern of a route along which the resident moves to use the vehicle parked in the parking lot, and the suspicious act includes moving along a route different from the first pattern and approaching within a predetermined range from the vehicle.

9. An information processing method, wherein one or more computers use the analysis result of sensor information from a sensor that monitors a predetermined range from the site of a house to detect a suspicious person who performs a suspicious act other than a specific non-suspicious person with respect to a vehicle parked in a parking lot within the predetermined range, and cause a notification unit to perform notification when the suspicious person is detected.

10. A recording medium on which a program for causing one or more computers to use the analysis result of sensor information from a sensor that monitors a predetermined range from the site of a house to detect a suspicious person who performs a suspicious act other than a specific non-suspicious person with respect to a vehicle parked in a parking lot within the predetermined range and cause a notification unit to perform notification when the suspicious person is detected is recorded.

Images