Vehicle theft / robbery recognition method and apparatus, and terminal device and storage medium

Abstract

A vehicle theft / robbery recognition method, comprising: acquiring vehicle state data and driver state data that correspond to a current vehicle, wherein the vehicle state data reflects a traveling state of the current vehicle, and the driver state data at least reflects postures of the head and hands of a driver of the current vehicle; on the basis of the vehicle state data and the driver state data, determining whether a threatening event occurs; and when it is determined that the threatening event occurs, performing alarm processing on the basis of the threatening event. The method can improve the accuracy of vehicle theft / robbery recognition. In addition, the present invention further relates to a vehicle theft / robbery recognition apparatus, and a terminal device and a storage medium.

Description

Vehicle theft identification method and device, terminal equipment and storage medium TECHNICAL FIELD

[0001] The present application relates to the technical field of vehicles, in particular to a vehicle theft identification method and device, terminal equipment and computer readable storage medium. BACKGROUND

[0002] With the rapid development of economy, vehicles are increasingly widely used in daily travel and logistics transportation, and especially with the continuous expansion of the logistics transportation network, the number of logistics transportation vehicles is increasingly large. However, with the increase in the number of vehicles such as logistics transportation vehicles, criminals have turned their sights to theft of vehicles, resulting in loss of vehicles and transported goods, and in serious cases, threatening the personal safety of drivers and passengers.

[0003] Currently, whether a vehicle is stolen or robbed is usually determined by detecting whether the vehicle door has been subjected to violence or whether there is an abnormal sound near the vehicle, which can easily lead to misjudgment and false alarms, affecting the normal use of the vehicle. TECHNICAL PROBLEM

[0004] One of the purposes of the embodiments of the present application is to provide a vehicle theft identification method and device, terminal equipment and storage medium, which can improve the accuracy of vehicle theft identification. TECHNICAL SOLUTION

[0005] The technical solution adopted by the embodiments of the present application is:

[0006] In a first aspect, a vehicle theft identification method is provided, comprising:

[0007] obtaining vehicle state data and driver state data corresponding to a current vehicle, the vehicle state data reflecting the driving state of the current vehicle, and the driver state data reflecting at least the posture of the head and hands of the driver of the current vehicle;

[0008] determining whether a coercion event has occurred based on the vehicle state data and the driver state data;

[0009] if it is determined that the coercion event has occurred, performing an alarm process based on the coercion event.

[0010] In a second aspect, a vehicle theft identification device is provided, comprising:

[0011] a data acquisition module for acquiring vehicle state data and driver state data corresponding to a current vehicle, the vehicle state data reflecting the driving state of the current vehicle, and the driver state data reflecting at least the posture of the head and hands of the driver of the current vehicle;

[0012] a stress judgment module, configured to judge whether a stress event occurs based on the vehicle state data and the driver state data;

[0013] an alarm module, configured to perform alarm processing based on the stress event in a case where it is determined that the stress event occurs.

[0014] In a third aspect, a terminal device is provided, which comprises a memory, a processor, and a computer program stored in the memory and executable on the processor, and the processor implements the steps of the vehicle theft identification method according to the first aspect when executing the computer program.

[0015] In a fourth aspect, a computer readable storage medium is provided, which stores a computer program, and the computer program implements the steps of the vehicle theft identification method according to the first aspect when executed by a processor.

[0016] In a fifth aspect, a computer program product is provided, which, when executed on a terminal device, causes the terminal device to perform the vehicle theft identification method according to the first aspect. Advantages

[0017] The method according to the first aspect of the embodiments of the present application has the advantages that, since the vehicle state data can reflect the driving state of the current vehicle, and the driver state data can at least reflect the posture of the head and hands of the driver of the current vehicle, the posture of the driver in a stressed posture such as hands around the head can be better judged according to the driving state of the vehicle and the posture of the head and hands of the driver, so that the current vehicle cannot be normally driven, and thus whether a stress event occurs can be accurately judged, and further, alarm processing can be performed in time when the stress event occurs, which improves the accuracy of vehicle theft identification, reduces false judgments and false alarms, and improves user experience and ensures user safety. BRIEF DESCRIPTION OF DRAWINGS

[0018] In order to more clearly illustrate the technical solutions in the embodiments of the present application, the drawings required to be used in the embodiments or exemplary technical descriptions will be briefly introduced. Obviously, the drawings in the following description are only some embodiments of the present application, and other drawings can be obtained by those skilled in the art without any creative effort.

[0019] FIG. 1 is a flowchart of a vehicle theft identification method according to an embodiment of the present application;

[0020] FIG. 2 is a flowchart of another vehicle theft identification method according to an embodiment of the present application;

[0021] FIG. 3 is a flow diagram of another vehicle theft identification method according to an embodiment of the present application;

[0022] FIG. 4 is a flow diagram of another vehicle theft identification method according to an embodiment of the present application;

[0023] FIG. 5 is a flow diagram of another vehicle theft identification method according to an embodiment of the present application;

[0024] FIG. 6 is a structural diagram of a vehicle theft identification apparatus according to an embodiment of the present application;

[0025] FIG. 7 is a structural diagram of a terminal device according to an embodiment of the present application. Embodiments of the present application

[0026] In order to make the objects, technical solutions and advantages of the present application clearer, the present application will be further described in detail below with reference to the accompanying drawings and embodiments. It should be understood that the specific embodiments described herein are only used to explain the present application and should not be used to limit the present application. However, it should be understood by those skilled in the art that the present application can also be implemented in other embodiments without these specific details. In other cases, detailed descriptions of well-known systems, devices, circuits and methods are omitted so as not to obscure the description of the present application with unnecessary details.

[0027] It should be understood that when used in the specification and the appended claims of the present application, the term "comprising" indicates the presence of the described features, integers, steps, operations, elements and / or components, but does not exclude the presence or addition of one or more other features, integers, steps, operations, elements, components and / or groups thereof.

[0028] It should also be understood that the term "and / or" used in the specification and the appended claims of the present application means any combination of one or more of the associated listed items and all possible combinations, and includes these combinations.

[0029] In addition, in the description of the specification and the appended claims of the present application, the terms "first", "second", "third" and the like are only used to distinguish descriptions, and cannot be understood as indicating or implying relative importance.

[0030] In the specification of the present application, the reference "one embodiment" or "some embodiments" and the like means that the specific features, structures or characteristics described in connection with the embodiment are included in one or more embodiments of the present application. Therefore, the statements "in one embodiment", "in some embodiments", "in other some embodiments", "in further some embodiments" and the like appearing in different places in the specification are not necessarily all referring to the same embodiment, but mean "one or more but not all embodiments", unless otherwise specifically emphasized.

[0031] In order to illustrate the technical solutions provided in the present application, the following will be described in detail in combination with specific drawings and embodiments.

[0032] FIG. 1 shows a flowchart of a vehicle theft identification method provided in an embodiment of the present application, which is described in detail as follows.

[0033] In step S101, vehicle state data corresponding to the current vehicle and driver state data are acquired, the vehicle state data reflecting the driving state of the current vehicle, and the driver state data at least reflecting the posture of the head and hands of the driver of the current vehicle.

[0034] Optionally, the current vehicle can be a vehicle in a driving state. Since the logistics transport vehicle is more likely to be stolen, in some embodiments, the current vehicle can be a logistics transport vehicle in a driving state.

[0035] It should be noted that the vehicle theft identification method provided in the embodiments of the present application can be applied to a vehicle terminal, in which case the current vehicle can be a logistics transport vehicle or the like loaded with a vehicle terminal; the vehicle theft identification method provided in the embodiments of the present application can also be applied to a management platform such as a logistics vehicle management platform, in which case the management platform can take the vehicles in a driving state among the vehicles managed by the management platform as the current vehicle, acquire the vehicle state data and driver state data corresponding to the current vehicle, and make a judgment on the coercion event, i.e., identify the vehicle theft.

[0036] In step S102, it is judged whether a coercion event occurs based on the vehicle state data and the driver state data.

[0037] Specifically, since the vehicle state data can reflect the driving state of the current vehicle, and the driver state data can at least reflect the posture of the head and hands of the driver, the judgment based on the vehicle state data and the driver data can better analyze whether the current vehicle has an abnormal event such as sudden stop based on the driving state of the current vehicle, and at the same time, analyze whether the driver makes an abnormal posture such as holding head or raising hands based on the posture of the head and hands of the driver, i.e., the coercion event can be comprehensively analyzed in combination with the abnormality of the vehicle and the abnormality of the posture of the driver, thereby improving the accuracy of the theft identification.

[0038] In some embodiments, the driver state data also reflects the facial expression of the driver, and the driver is analyzed whether in a state of tension or terror based on the facial expression of the driver, i.e., the coercion event is judged in combination with the abnormality of the vehicle, the abnormality of the posture of the driver, and the abnormality of the emotion, thereby further improving the accuracy of the theft identification.

[0039] Step S103, in the case of determining that the above-mentioned coercion event occurs, an alarm processing is performed based on the above-mentioned coercion event.

[0040] Optionally, when the alarm is performed based on the coercion event, the position information of the current vehicle can be acquired to obtain a target position, and then the alarm information is generated according to the target position and the coercion event, and the alarm information is sent to, for example, a highway safety management department or the police, so as to alarm and seek help through the alarm information, and ensure the safety of the user.

[0041] In the embodiment of the present application, the vehicle state data capable of reflecting the driving state of the current vehicle is acquired, and the driver state data capable of reflecting at least the posture of the head and the hand of the driver of the current vehicle is acquired, so that when the coercion event is judged according to the vehicle state data and the driver state data, whether the driver is in a coerced posture such as holding the head with both hands, which leads to the driver being unable to normally drive the current vehicle, can be better judged, so that whether the coercion event occurs can be accurately judged, the accuracy of the vehicle theft and robbery identification is improved, the misjudgment and false alarm situation is reduced, the safety of the user is ensured, and the user experience is improved.

[0042] In some embodiments, before the above-mentioned step S101, the method further comprises:

[0043] According to the current environment data, it is determined whether the current vehicle is in a dangerous environment, and the current environment data includes the current scene and / or the traffic flow.

[0044] Correspondingly, the above-mentioned step S101 comprises:

[0045] In the case of determining that the above-mentioned current vehicle is in the above-mentioned dangerous environment, the above-mentioned vehicle state data and the above-mentioned driver state data corresponding to the above-mentioned current vehicle are acquired.

[0046] Since when the vehicle drives to a scene with more vehicles or people such as a toll station or a gas station, the events such as theft or robbery usually rarely occur, therefore, before the theft and robbery identification of the current vehicle is performed, the current environment data can be acquired according to the environment where the current vehicle is located, and then the current environment data is analyzed to determine whether the current vehicle is in a dangerous environment. When it is determined that the current vehicle is in a dangerous environment, the vehicle state data and the driver state data of the current vehicle are acquired for the theft and robbery identification, i.e. whether the coercion event occurs is determined.

[0047] The current environment data can include the scene where the current vehicle is located, i.e. the current scene, such as a gas station, an urban area or a red and green light intersection, etc. Alternatively, the current environment data can include the traffic flow at the location where the current vehicle is located. Alternatively, in order to further improve the accuracy, the current environment data can include the current scene and the traffic flow, and whether the current vehicle is in a dangerous environment is determined according to the current scene and the traffic flow together, so as to improve the accuracy of the determination.

[0048] In some embodiments, in determining whether the current vehicle is in a dangerous environment according to the current environment data, for the current scene, it can be determined whether the current scene is safe by determining whether the current scene matches a preset safe scene (such as a toll station), and when the current scene does not match the safe scene, it can be determined that the current scene belongs to a dangerous scene, i.e., the current vehicle is in a dangerous environment; for the traffic flow, it can be analyzed whether the traffic flow is less than a preset flow threshold (such as 10), and when the traffic flow is less than the flow threshold, it is determined that the current vehicle is in a dangerous environment.

[0049] It can be understood that when the current environment data includes the current scene and the traffic flow, the current vehicle is determined to be in a dangerous environment only when the current scene belongs to a dangerous scene and the traffic flow is less than the flow threshold, so as to further improve the accuracy of the dangerous environment determination.

[0050] Through the above processing, it is determined whether the current vehicle is in a dangerous environment according to the current environment data, and the robbery identification is performed when the current vehicle is in a dangerous environment. If the current vehicle is not in a dangerous environment, the robbery identification does not need to be performed by obtaining the vehicle state data, which can reduce unnecessary robbery identification, thereby reducing resource occupation and being conducive to application in devices with limited resources such as vehicle terminals.

[0051] In some embodiments, before the step S102, the method further includes:

[0052] A1, determining whether a vehicle insertion event occurs.

[0053] A2, in a case where it is determined that the vehicle insertion event occurs, determining whether a forced stop event occurs based on the speed data of the current vehicle in a first time period and whether there is a vehicle in front of the current vehicle, the first time period being determined according to the occurrence time of the vehicle insertion event.

[0054] Correspondingly, the step S102 includes:

[0055] In a case where it is determined that the vehicle insertion event occurs and the forced stop event occurs, determining whether a coercion event occurs based on the vehicle state data and the driver state data.

[0056] Since the criminal usually forces the vehicle to stop before robbing the vehicle, in order to further improve the accuracy of the robbery identification, it can be detected whether a vehicle is inserted in front of the current vehicle to determine whether a vehicle insertion event occurs.

[0057] If the vehicle insertion event occurs, it indicates that a vehicle may want to force stop the current vehicle. At this time, the first time period can be determined according to the occurrence time of the vehicle insertion event, the vehicle speed data can be determined according to the vehicle speed of the current vehicle in the first time period, and then it is determined whether the force stop event occurs according to the vehicle speed data of the current vehicle in the first time period and whether there is a vehicle in front of the current vehicle in the first time period, that is, whether the force stop event occurs is determined according to the change of the vehicle speed of the current vehicle in the first time period and whether there is a vehicle in front of the current vehicle.

[0058] As shown in FIG. 2, if it is determined that the vehicle insertion event occurs and the force stop event occurs, the coercion event is further determined according to the vehicle state data and the driver state data; if it is determined that the vehicle insertion event does not occur or the force stop event does not occur after the vehicle insertion event occurs, the subsequent determination is not required, so as to reduce unnecessary resource occupation.

[0059] Optionally, when it is determined whether there is a vehicle in front of the current vehicle in the first time period, it can be determined whether there is an insertion vehicle corresponding to the insertion event in front of the current vehicle in the first time period, so as to reduce the interference of other vehicles and improve the accuracy of the force stop event determination.

[0060] In some embodiments, the first time period can be determined according to a first preset time length (for example, 10 seconds) and the occurrence time of the vehicle insertion event. For example, assuming that the first preset time length is 15 seconds, the first time period can be a time period corresponding to 15 seconds after the occurrence of the vehicle insertion event, or the first time period can be a time period corresponding to 15 seconds before and 15 seconds after the occurrence time of the vehicle insertion event.

[0061] In the embodiments of the present application, after it is determined that the vehicle insertion event occurs, it is determined whether the force stop event occurs, and if the force stop event occurs, the coercion event is further determined, so as to further improve the accuracy of the vehicle theft and robbery identification through the event determination in sequence, and if a certain event is not satisfied, the subsequent determination is not required, so as to avoid continuous resource occupation.

[0062] In some embodiments, the step A1 includes:

[0063] The lane line data and the position information of the reference vehicle are acquired, the lane line data at least includes lane markings, and the reference vehicle includes a vehicle located behind the current vehicle in a current lane where the current vehicle is located and a vehicle in a neighboring lane.

[0064] It is determined whether the reference vehicle is located in front of the current vehicle according to the lane line data and the position information.

[0065] In a case that it is determined that the reference vehicle is located in front of the current vehicle and the current vehicle does not have a lane changing behavior, it is determined that the vehicle insertion event occurs.

[0066] The lane line data at least includes lane markings. Optionally, the lane line data can further include one or more of lane line fitting parameters (i.e., parameters of a curve fitting equation of the lane line), lane line confidence, and lane line curvature, etc., to more accurately determine the position of the lane through the lane markings and other data. It can be understood that the lane markings can be determined through target detection on images of the current vehicle shooting the lane, and the embodiments of the present application do not make specific limitations thereto.

[0067] In order to accurately determine whether the vehicle insertion event occurs, when determining the vehicle insertion event, the lane line data and the position information of the reference vehicle can be obtained first, and then the positions of the lanes are determined according to the lane line data, and the position of the reference vehicle is combined with the positions of the lanes to determine whether the reference vehicle is located in front of the current lane in which the current vehicle is located. Optionally, the proportion of the vehicle body of the reference vehicle located in the front region of the current vehicle (i.e., the proportion of the vehicle body of the reference vehicle located in the front region in the entire vehicle body of the reference vehicle) can be analyzed according to the position information of the reference vehicle and the positions of the lanes, and if the proportion of the vehicle body of the reference vehicle located in the front region of the current vehicle is greater than or equal to a proportion threshold (such as 30%), it can be determined that the reference vehicle is located in front of the current lane in which the current vehicle is located.

[0068] If it is determined that the reference vehicle is located in front of the current vehicle, it indicates that the reference vehicle can be inserted in front of the current vehicle, at this time, it can be determined whether the current vehicle has a lane changing behavior, and if the current vehicle does not have a lane changing behavior, it indicates that the reference vehicle is inserted in front of the current vehicle, so that the position of the reference vehicle changes from the adjacent lane or the rear of the current vehicle to the front of the current vehicle, at this time, it can be determined that the vehicle insertion event occurs; if the current vehicle has a lane changing behavior, it indicates that the lane changing of the current vehicle causes the reference vehicle to be located in front of the current vehicle, at this time, it is determined that the vehicle insertion event does not occur.

[0069] It can be understood that if it is determined that the reference vehicle is not located in front of the current lane in which the current vehicle is located, the subsequent determination steps do not need to be performed.

[0070] In some embodiments, in the step A2, before determining whether the forced stop event occurs based on the speed data of the current vehicle in the first time period and whether there is a vehicle in front of the current vehicle, the step A2 further includes:

[0071] determining whether the forced stop event belongs to a forced stop event occurring in a pursuit process;

[0072] Correspondingly, the step A2 includes:

[0073] In a case where it is determined that the vehicle insertion event occurs and the stop-by event occurs in the pursuit process, it is determined whether the coercion event occurs based on the vehicle state data and the driver state data.

[0074] To further improve the accuracy of vehicle theft identification, before determining the coercion event, if it is determined that the vehicle insertion event occurs and the stop-by event occurs after the vehicle insertion event, it can be determined whether the stop-by event belongs to the stop-by event occurring in the pursuit process, i.e., whether there is a situation that other vehicles such as the insertion vehicle corresponding to the vehicle insertion event pursue the current vehicle and stop the current vehicle.

[0075] Optionally, when determining whether the occurring stop-by event belongs to the stop-by event occurring in the pursuit process, it can be first determined whether the current vehicle occurs at least two severe driving events in a reference time period. If the current vehicle occurs at least two severe driving events in the reference time period, it can be determined that the current vehicle occurs pursuit in the reference time period, and at this time, the reference time period can be used as the pursuit time period. Optionally, the above-mentioned severe driving event at least includes the sudden acceleration event, the sudden turn event and the sudden deceleration event.

[0076] It should be noted that the reference time period is a time period longer than the first time period and includes the first time period, which is determined according to the occurrence time of the vehicle insertion event. Optionally, the reference time period can be determined according to the reference preset time length (such as 80 seconds) and the occurrence time of the vehicle insertion event, wherein the reference preset time length is greater than the first preset time length.

[0077] For example, assuming that the reference preset time length is 60 seconds, the first preset time length is 10 seconds, and assuming that the current vehicle occurs the vehicle insertion event at 12:30:00, in combination with the first preset time length, the first time period is determined to be 12:29:50-12:30:10, and the reference time period is 12:59:00-12:31:00.

[0078] Assuming that the current vehicle occurs the sudden deceleration event A at 12:30:05, it can be determined that the stop-by event M occurs in the first time period (12:29:50-12:30:10). At this time, it is necessary to determine whether the current vehicle occurs at least two severe driving events in the reference time period (12:59:00-12:31:00).

[0079] Assuming that the current vehicle has an emergency turn event B at 12:29:37, combined with the emergency deceleration event A of the current vehicle, it can be determined that the current vehicle has at least two severe driving events in the reference time period, which is the pursuit time period, that is, the current vehicle has a forced stop event M in the pursuit time period (i.e. in the pursuit process). It should be noted that in other embodiments, it can also be determined whether the current vehicle has at least two severe driving events in the reference time period except for the emergency deceleration event A (target emergency deceleration event, i.e. an emergency deceleration event occurring in the first time period, such as the first emergency deceleration event in the first time period).

[0080] In some embodiments, whether the current vehicle has a severe driving event in the reference time period can be determined according to the six-axis data of the current vehicle and the vehicle speed data, the six-axis data being the data collected by the six-axis inertial sensor arranged on the current vehicle, at least the acceleration of the current vehicle in the x-axis and y-axis, the direction of the x-axis and y-axis being the direction of the transverse axis and the longitudinal axis of the current vehicle. The acceleration in different directions of the current vehicle and the vehicle speed of the current vehicle can more accurately determine whether the current vehicle has a severe driving event.

[0081] In the embodiments of the present application, since the driver usually tries to escape by accelerating and the like during the process of encountering the illegal person stealing the vehicle, and the illegal person chases the vehicle, that is, the current vehicle and the vehicle of the illegal person usually have a pursuit during the process of stealing, therefore, in the case of a vehicle insertion event and a forced stop event, first, it is determined whether the forced stop event occurs in the pursuit process based on the occurrence time of the vehicle insertion event, and if the forced stop event occurs in the pursuit process, the coercion event is determined, further improving the accuracy of the theft identification.

[0082] In some embodiments, in the above step A2, the determination of whether the forced stop event occurs based on the vehicle speed data of the current vehicle in the first time period and whether there is a vehicle in front of the current vehicle includes:

[0083] A21, determine the insertion type corresponding to the vehicle insertion event, and obtain a target insertion type.

[0084] A22, in the case that the target insertion type is rear overtaking insertion, determine whether the current vehicle has an emergency deceleration event and / or a stop event in the first time period based on the vehicle speed data.

[0085] A23, in the case that the current vehicle has the emergency deceleration event and / or the stop event in the first time period, if there is a vehicle in front of the current vehicle, it is determined that the forced stop event occurs.

[0086] In order to reduce the interference caused by the lane change of the vehicle at the position such as the side front, the target insertion type of the vehicle insertion event occurred can be determined first. The insertion type of the vehicle insertion event can include front vehicle insertion, side vehicle insertion and rear vehicle insertion. It should be noted that in the embodiments of the present application, when the insertion vehicle is a side rear vehicle (i.e. the vehicle located behind the current vehicle in the adjacent lane) or a rear vehicle of the current vehicle, the corresponding vehicle insertion event can be determined as rear overtaking insertion.

[0087] If the target insertion type of the vehicle insertion event is rear overtaking insertion, it is determined whether the current vehicle has an emergency deceleration event in the first time period according to the vehicle speed data; or it is determined whether the current vehicle has a parking event in the first time period according to the vehicle speed data; or it is determined whether the current vehicle has an emergency deceleration event and a parking event in the first time period according to the vehicle speed data.

[0088] As shown in FIG. 3, if the target insertion type is not rear overtaking insertion, it indicates that the vehicle insertion event can be caused by the lane change of the side or front vehicle, and at this time, the subsequent emergency deceleration event and / or parking event can not be determined. In some embodiments, in order to further ensure the accuracy of the forced stop event determination, in the case that the target insertion type is not rear overtaking insertion, it can be analyzed whether the insertion vehicle (i.e. the vehicle corresponding to the vehicle insertion event) has been located at the side or front of the current vehicle in a preset time period (such as the time period corresponding to 1 minute before the occurrence time of the vehicle insertion event) before the occurrence time of the vehicle insertion event. If the insertion vehicle has been located at the side or front of the current vehicle in the preset time period, it can be considered that the insertion vehicle is a normal lane change insertion, and the subsequent emergency deceleration event and / or parking event determination can not be performed; if the insertion vehicle has not been located at the side or front of the current vehicle in the preset time period, it can be considered that the insertion vehicle can not be a normal lane change insertion, and at this time, the emergency deceleration event and / or parking event determination can be performed to determine whether the forced stop event occurs.

[0089] Optionally, when determining whether the emergency deceleration event occurs in the first time period according to the vehicle speed data, the acceleration of the current vehicle can be analyzed according to the vehicle speed data, and it is determined whether the current vehicle has an emergency deceleration event according to the acceleration.

[0090] For example, assuming that the duration corresponding to the first time period is 10 seconds, the acceleration every 2 seconds can be calculated according to the vehicle speed data, and 5 accelerations are obtained. If the value of any one of the 5 accelerations is greater than or equal to the acceleration threshold (such as 7), it can be determined that the current vehicle has an emergency deceleration event in the first time period.

[0091] If it is determined that the current vehicle has an emergency deceleration event or a stop event in the first time period, or has both an emergency deceleration event and a stop event, it can be determined whether there is a vehicle in front of the current vehicle, and if there is a vehicle in front of the current vehicle, it is determined that a forced stop event occurs. If there is no vehicle in front of the current vehicle, it means that the current vehicle may be decelerated and / or stopped due to other reasons, and at this time, it can be determined that the forced stop event does not occur.

[0092] In some embodiments, the forced stop event can be determined when it is determined that the current vehicle has the emergency deceleration event and / or the stop event in the first time period, and the distance between the current vehicle and the vehicle in front of the current vehicle is less than or equal to the distance threshold (such as 2 meters). That is, when the current vehicle has an emergency deceleration event and / or a stop event in the first time period, the distance between the current vehicle and the vehicle in front of the current vehicle is combined to more accurately determine whether the current vehicle is forced to stop.

[0093] In the embodiments of the present application, when the insertion type of the vehicle insertion event is rear vehicle overtaking insertion, subsequent judgments are performed, reducing the interference caused by normal vehicle insertion. At the same time, when the current vehicle has an emergency deceleration event and / or a stop event in the first time period, and there is a vehicle in front of the current vehicle, it is determined that a forced stop event occurs, which ensures the accuracy of the forced stop event determination.

[0094] In some embodiments, before determining whether the current vehicle has an emergency deceleration event and / or a stop event in the first time period based on the vehicle speed data in step A23, the step A23 further includes:

[0095] Determining a time interval between the appearance time of the insertion vehicle corresponding to the vehicle insertion event and the occurrence time of the vehicle insertion event to obtain a target time interval, wherein the appearance time of the insertion vehicle is determined according to the time when the insertion vehicle is detected.

[0096] Determining whether the target time interval is less than or equal to an interval threshold.

[0097] Correspondingly, the step A23 includes:

[0098] When the target insertion type is rear vehicle overtaking insertion, and the target time interval is less than or equal to the interval threshold, it is determined whether the current vehicle has an emergency deceleration event and / or a stop event in the first time period based on the vehicle speed data.

[0099] Specifically, in order to further improve the accuracy of the forced stop event judgment, before judging whether the sudden deceleration event and / or the parking event occurs, the appearance time of the insertion vehicle corresponding to the vehicle insertion event can be determined first, and then the target time interval is determined according to the time interval between the appearance time and the occurrence time of the vehicle insertion event.

[0100] It can be understood that in the current vehicle driving process, the vehicle existing around the current vehicle can be detected by detecting the video data captured by the rearview camera or other camera equipment of the current vehicle, or by sensor detection, and the appearance time of the insertion vehicle is the time when the insertion vehicle is detected, which is earlier than the occurrence time of the vehicle insertion event.

[0101] If the target time interval is less than or equal to the interval threshold (such as 15 seconds), it indicates that the insertion vehicle is a sudden overtaking insertion, and the forced stop event may occur. At this time, whether the current vehicle has a sudden deceleration event and / or a parking event in the first time period can be judged based on the vehicle speed data to determine whether the forced stop event occurs. If the target time interval is greater than the interval threshold, it can be considered that the insertion vehicle is a normal overtaking insertion, and subsequent judgment is not required.

[0102] In the embodiments of the present application, whether the insertion vehicle is a normal overtaking insertion is judged in combination with the appearance time of the insertion vehicle and the time interval between the occurrence time of the insertion vehicle in front of the current vehicle. When it is determined that it is not a normal overtaking insertion, subsequent judgment is performed, thereby reducing the interference caused by the normal overtaking insertion vehicle and further improving the accuracy of the forced stop event judgment.

[0103] In some embodiments, the above step S102 comprises:

[0104] B1, judging whether the current posture of the driver matches the target posture based on the above driver state data.

[0105] B2, in the case where it is determined that the current posture matches the target posture, judging whether the current vehicle is in a static state according to the vehicle state data.

[0106] B3, in the case where it is determined that the current vehicle is in the static state, determining that the coercion event occurs.

[0107] In order to improve the accuracy of the theft and robbery identification, the current posture of the driver can be determined according to the driver state data reflecting the posture of the hands and head of the driver, and then it is judged whether the current posture matches the target posture (such as the hand-raising posture or the squatting and head-holding posture).

[0108] If the current posture of the driver matches the target posture, it is determined whether the current vehicle is in a static state according to vehicle state data reflecting a driving state of the vehicle; if the current posture of the driver does not match the target posture, subsequent determination is not needed.

[0109] If it is determined that the current vehicle is in a static state, it can be considered that the current vehicle stops driving and the driver is coerced, that is, it can be determined that a coercion event occurs; if it is determined that the current vehicle is in a non-static state, that is, the current vehicle is in a driving state, it can be determined that no coercion event occurs, and no alarm processing is needed.

[0110] In the embodiments of the present application, whether a coercion event occurs is determined according to the current posture of the driver and the static state of the vehicle, so as to ensure the accuracy of the determination of the coercion event; meanwhile, in the case where it is determined that the current posture of the driver does not match the target posture, subsequent determination is not needed, which can reduce unnecessary processing steps, thereby reducing resource occupation and saving resources.

[0111] In some embodiments, the driver state data includes image data obtained by photographing the driver, the target posture includes a hand-raising posture, and the step B1 includes:

[0112] The hand position and the head position of the driver are determined based on the image data.

[0113] The current posture is determined according to the relative positional relationship between the hand position and the head position.

[0114] It is determined whether the current posture matches the hand-raising posture.

[0115] Specifically, in the case where an illegal person holds a weapon, the driver may make a posture of raising both hands or holding head with both hands, etc., which means surrender, in order to avoid being hurt. Therefore, in order to accurately determine whether the current posture of the driver matches the hand-raising posture, the hand position and the head position of the driver can be determined according to the image data obtained by photographing the driver, and then the relative positional relationship between the hand position and the head position is analyzed, and the current posture of the driver is determined according to the relative positional relationship, and then whether the current posture of the driver matches the hand-raising posture (i.e., the target posture) can be better determined.

[0116] Optionally, when the current posture of the driver is determined according to the relative positional relationship between the hand position and the head position, the height of the hands of the driver can be determined according to the hand position, and the height of the head of the driver can be determined according to the synchronous position. If the height of the hands of the driver is the same as the height of the head, it can be determined that the current posture of the driver is the hand-raising posture. If the height of any one of the hands of the driver is not the same as the height of the head, it can be determined that the current posture of the driver is the hand-lowering posture.

[0117] In the embodiments of the present application, the target posture includes the hand-raising posture. When it is determined whether the current posture of the driver matches the hand-raising posture, the characteristics of the hand-raising posture are combined, and the relative positional relationship between the hands and the head of the driver is determined to determine the current posture of the driver. Therefore, when it is determined whether the current posture of the driver matches the hand-raising posture, the determination can be quickly and accurately performed, thereby ensuring the accuracy of the determination result.

[0118] In some embodiments, the above step B2 includes:

[0119] B21, in the case where it is determined that the current posture matches the target posture, the holding duration of the current posture is determined.

[0120] B22, in the case where the holding duration is greater than or equal to a holding duration threshold, it is determined whether the current vehicle is in the static state according to the vehicle state data.

[0121] To further improve the accuracy of the determination of the coercion event, when it is determined that the current posture of the driver matches the target posture, the duration for which the driver holds the current posture can be determined according to the target video data, and the holding duration is obtained. Then, the holding duration is compared with a holding duration threshold (such as 3 seconds).

[0122] Since the driver is in a coerced state when holding the hand-raising posture, the current vehicle is usually in a static state. Therefore, to accurately determine whether a coercion event occurs, if the holding duration of the hand-raising posture of the driver is greater than or equal to a duration threshold, it is determined whether the current vehicle is in a static state according to the vehicle state data.

[0123] As shown in FIG. 4, if the holding duration is less than the duration threshold, it can be considered that the current posture matching the target posture is a coincidence, and therefore, the determination of the static state of the vehicle is not required.

[0124] In some embodiments, when it is determined that the duration of the current posture matching the target posture is less than the duration threshold, a target time period (e.g., one minute before and one minute after the posture occurrence time) can be determined according to the posture occurrence time of the current posture matching the target posture, and then the current posture of the driver in the target time period is detected, the occurrence number of the current posture matching the target posture in the target time period is determined, and if the occurrence number is greater than or equal to the number threshold (greater than 1, such as 3), the vehicle stationary state determination can be performed; if the occurrence number is less than the number threshold, the vehicle stationary state determination is not performed. That is, when the duration of the current posture matching the target posture does not meet the requirement, the occurrence number of the current posture matching the target posture in the time period is further used to determine whether the driver is coerced, so as to reduce the possibility of misjudgment and better protect the safety of the user.

[0125] In the embodiments of the present application, when the current posture of the driver matches the target posture, the duration of the current posture is used to determine whether the vehicle stationary state determination needs to be performed, so as to reduce the interference caused by the coincidence of the current posture matching the target posture, and further improve the accuracy of the coercion event determination.

[0126] In some embodiments, the step B22 includes:

[0127] In the case where the duration is greater than or equal to the duration threshold, the vehicle state data is used to determine whether the current vehicle is in the stationary state in the time period corresponding to the duration.

[0128] Correspondingly, the step B23 includes:

[0129] In the case where it is determined that the current vehicle is in the stationary state in the time period corresponding to the duration, it is determined that the coercion event occurs.

[0130] Optionally, when determining whether the current vehicle is in the stationary state, the duration of the hand posture (matching the target posture) of the driver can be used to determine a time period (the holding time period) corresponding to the duration, and then the target vehicle state data corresponding to the holding time period is determined according to the vehicle state data, and the current vehicle is determined to be in the stationary state in the holding time period according to the target vehicle state data, without the need to determine based on the complete vehicle state data, so as to reduce the calculation amount and improve the efficiency.

[0131] It can be understood that the current posture of the driver is maintained as a posture matched with the target posture in the holding time period, and if the current vehicle is in a stationary state in the holding time period, it can be considered that the driver is coerced, and it can be determined that a coercion event occurs; if the current vehicle is in a non-stationary state in the holding time period, it indicates that the coercion event may not occur, and at this time, whether the coercion event occurs can be further determined in combination with whether a help-seeking signal of the driver is received.

[0132] In the embodiments of the present application, whether the coercion event occurs is determined according to whether the current vehicle is in a stationary state in the holding time period corresponding to the holding duration, that is, when the current posture of the driver is maintained as a posture matched with the target posture in the holding time period, and the vehicle is continuously in a stationary state, it is determined that the coercion event occurs, thereby avoiding interference caused by various coincidences and improving the accuracy of the determination.

[0133] In some embodiments, before the alarm processing based on the coercion event in the above-mentioned step S103, the following steps are further included:

[0134] C1, obtaining target video data corresponding to a second time period, the target video data at least including video data obtained by shooting a driver of the current vehicle, and the second time period being determined according to the occurrence time of the coercion event.

[0135] C2, determining whether a driver replacement event of the current vehicle occurs based on the target video data.

[0136] Correspondingly, the S103 includes:

[0137] In the case that it is determined that the coercion event occurs and the driver replacement event of the current vehicle occurs, the alarm processing based on the coercion event is performed.

[0138] In order to reduce the occurrence of false alarm events, when it is determined that the coercion event occurs according to the vehicle state data and the driver state data, a second time period can be determined according to the occurrence time of the coercion event, and then target video data corresponding to the second time period is obtained. Alternatively, the second time period can be determined according to the occurrence time of the coercion event and a second preset duration (such as 90 seconds), for example, assuming that the second preset duration is 100 seconds, the time period corresponding to the 100 seconds before and after the occurrence time of the coercion event can be taken as the second time period.

[0139] The target video data at least includes video data of the driver of the current vehicle. Optionally, the target video data can further include video data of the surroundings (e.g., the front of the current vehicle and the outside of the driver's door) captured by the camera of the current vehicle, so as to analyze whether there is danger in the surroundings according to the video data reflecting the situation of the surroundings, thereby being able to more accurately determine whether to perform the alarm processing.

[0140] As shown in FIG. 5, after obtaining the target video data, it is determined whether the driver of the current vehicle is replaced according to the target video data. If the driver of the current vehicle is replaced after the coercive event is determined to occur, i.e., a driver replacement event is sent, it indicates that the driver is coerced and the current vehicle is stolen, and the alarm processing can be directly performed based on the coercive event.

[0141] If the coercive event is determined to occur, but the driver replacement event does not occur, in order to further improve the safety of the user and reduce the occurrence of false alarm events, it can be further analyzed whether the driver is in danger according to the surroundings of the current vehicle, so as to determine whether to perform the alarm processing. The alarm processing can also be determined according to whether the alarm signal or the help signal of the driver is received.

[0142] In the embodiments of the present application, after the coercive event is determined to occur, the video data of the driver of the current vehicle captured in a target time period related to the occurrence time of the coercive event is obtained first, and then the target video data is obtained. After obtaining the target video data, it is determined whether the driver of the current vehicle is replaced, and the alarm processing is performed when the driver is replaced, so as to reduce the occurrence of false alarm events and improve the accuracy of vehicle theft identification.

[0143] In some embodiments, the step C2 includes:

[0144] It is determined whether the driver gets off the vehicle based on the target video data.

[0145] In the case where the driver getting off the vehicle is determined to occur, it is determined whether the driver gets on the vehicle according to the video data corresponding to a third time period in the target video data, and the time corresponding to the third time period is later than the occurrence time of the driver getting on the vehicle.

[0146] In the case where the driver getting on the vehicle is determined to occur and the driver corresponding to the driver getting on the vehicle is different from the driver corresponding to the driver getting off the vehicle, it is determined that the driver replacement event occurs.

[0147] Specifically, since when replacing the driver of the vehicle, the original driver usually needs to get off the vehicle first, and the replacement driver needs to get on the vehicle, in order to improve the accuracy of the judgment of the driver replacement event, in the judgment process, the target video data can be analyzed first to determine whether the driver getting off the vehicle behavior occurs, if it is determined that the driver getting off the vehicle behavior occurs, the third time period later than the getting off time of the driver getting off the vehicle behavior is determined, and then the video data corresponding to the third time period in the target video data is analyzed to determine whether the driver getting on the vehicle behavior occurs, without analyzing the driver getting on the vehicle behavior based on the entire target video data, the calculation amount in the judgment process is reduced.

[0148] If it is determined that the driver getting off the vehicle behavior occurs, and the driver getting on the vehicle behavior occurs after the driver getting off the vehicle behavior occurs, it can be determined whether the driver corresponding to the driver getting off the vehicle behavior and the driver corresponding to the driver getting on the vehicle behavior are the same driver, if not, it is determined that the driver replacement event occurs; if the same, it indicates that the driver is not replaced, at this time, it can be determined that the driver replacement event does not occur.

[0149] In some embodiments, the third time period can be determined according to the third preset time length (such as 25 seconds) and the getting off time. The third preset time length is less than the second preset time length. For example, assuming that the third preset time length is 30 seconds, the time period corresponding to 30 seconds after the getting off time can be taken as the third time period.

[0150] It can be understood that when the occurrence time of the driver getting off the vehicle behavior is later, the complete video data corresponding to the third time period cannot be obtained based on the target video data, at this time, the video data corresponding to the third time period in the video data obtained by shooting the driver can be directly obtained, so as to guarantee the completeness of the video data corresponding to the third time period, and thus the accuracy of the judgment of the driver getting off the vehicle behavior is guaranteed.

[0151] Optionally, when judging whether the driver getting off the vehicle behavior and the driver getting on the vehicle behavior occur, the body movement trajectory of the driver can be analyzed to determine whether the driver getting off the vehicle behavior and the driver getting on the vehicle behavior occur.

[0152] In the embodiments of the present application, whether the driver gets off the vehicle is first determined according to the target video data, and whether the driver gets on the vehicle is determined according to the video data after the time when the driver gets off the vehicle. The driver getting on the vehicle and the driver getting off the vehicle do not need to be directly analyzed on the whole target video data, and the calculation amount in the judgment process is reduced. Moreover, whether the driver gets on the vehicle after the driver gets off the vehicle is determined in combination with the characteristics of the driver replacement event, and the driver replacement event is determined only when the drivers corresponding to the driver getting off the vehicle and the driver getting on the vehicle are not the same driver, so that the accuracy of the obtained judgment result is ensured, thereby ensuring the accuracy of the vehicle theft and robbery identification.

[0153] Corresponding to the vehicle theft and robbery identification method provided in the above embodiments, FIG. 6 shows a structural schematic diagram of a vehicle theft and robbery identification apparatus provided in some embodiments of the present application. For ease of illustration, only parts related to the embodiments of the present application are shown. Referring to FIG. 6, the apparatus includes a data acquisition module 61, a coercion judgment module 62, and an alarm module 63. Among them,

[0154] The data acquisition module 61 is configured to acquire vehicle state data corresponding to a current vehicle and driver state data. The vehicle state data reflects the driving state of the current vehicle, and the driver state data at least reflects the posture of the head and hands of the driver of the current vehicle.

[0155] The coercion judgment module 62 is configured to determine whether a coercion event occurs based on the vehicle state data and the driver state data.

[0156] The alarm module 63 is configured to perform alarm processing based on the coercion event when it is determined that the coercion event occurs.

[0157] In the embodiments of the present application, the vehicle state data reflecting the driving state of the current vehicle is acquired, and the driver state data at least reflecting the posture of the head and hands of the driver of the current vehicle is acquired. When the coercion event is determined based on the vehicle state data and the driver state data, whether the driver is in a coerced posture such as holding the head with both hands so as to be unable to normally drive the current vehicle can be better determined, so that whether the coercion event occurs can be accurately determined, the accuracy of the vehicle theft and robbery identification is improved, the false judgment and false alarm are reduced, the user safety is ensured, and the user experience is improved.

[0158] It should be noted that the information interaction, execution process, and the like between the above apparatuses / units are based on the same concept as the method embodiments of the present application, and the specific functions and the technical effects brought by the same can be referred to the method embodiments part. Therefore, no further description is given here.

[0159] FIG. 7 is a structural schematic diagram of a terminal device according to an embodiment of the present application. As shown in FIG. 7, the terminal device 7 according to the embodiment includes at least one processor 70 (only one processor is shown in FIG. 7), a memory 71, and a computer program 72 stored in the memory 71 and capable of running on the at least one processor 70, wherein the processor 70 implements the steps in any of the method embodiments described above when running the computer program 72.

[0160] The terminal device 7 can be a desktop computer, a notebook computer, a palm computer, a cloud server, or the like. The terminal device can include, but is not limited to, the processor 70 and the memory 71. Those skilled in the art can understand that FIG. 7 is only an example of the terminal device 7, and does not limit the terminal device 7, which can include more or fewer components than those shown in the figure, or combine certain components, or different components, for example, can also include input / output devices, network access devices, and the like.

[0161] The processor 70 can be a central processing unit (CPU), and can also be other general-purpose processors, digital signal processors (DSP), application specific integrated circuits (ASIC), field programmable gate arrays (FPGA) or other programmable logic devices, discrete gates or transistor logic devices, discrete hardware components, or the like. The general-purpose processor can be a microprocessor or the processor can also be any conventional processor.

[0162] The memory 71 can be an internal storage unit of the terminal device 7 in some embodiments, for example, a hard disk or a memory of the terminal device 7. The memory 71 can also be an external storage device of the terminal device 7 in other embodiments, for example, a plug-in hard disk, a smart media card (SMC), a secure digital (SD) card, a flash card, or the like. Further, the memory 71 can include both the internal storage unit and the external storage device of the terminal device 7. The memory 71 is used to store an operating system, application programs, a boot loader, data, and other programs, for example, program codes of the computer program, and the like. The memory 71 can also be used to temporarily store data that has been output or will be output.

[0163] The embodiment of the present application further provides a network device, comprising at least one processor, a memory, and a computer program stored in the memory and executable on the at least one processor, wherein the processor implements the steps in any of the method embodiments described above when executing the computer program.

[0164] The embodiment of the present application further provides a computer readable storage medium, which stores a computer program, wherein the computer program is executable by a processor to implement the steps in any of the method embodiments described above.

[0165] In the above embodiments, the description of each embodiment has its own focus, and the parts not described or recorded in a certain embodiment can be referred to the relevant description of other embodiments.

[0166] The above-described embodiments are only used to illustrate the technical solutions of the present application, rather than limit them; although the present application has been described in detail with reference to the foregoing embodiments, those skilled in the art should understand that the technical solutions recorded in the foregoing embodiments can still be modified, or some technical features can be replaced equivalently; and these modifications or replacements do not make the essence of the corresponding technical solutions deviate from the spirit and scope of the technical solutions of the embodiments of the present application, and should be included in the protection scope of the present application.

Claims

1. A method of identifying theft of a vehicle, characterized by, The method comprises: obtaining vehicle state data and driver state data corresponding to a current vehicle, the vehicle state data reflecting a driving state of the current vehicle, and the driver state data reflecting at least a posture of a head and a hand of a driver of the current vehicle; determining whether a coercion event occurs based on the vehicle state data and the driver state data; in a case where it is determined that the coercion event occurs, performing an alarm process based on the coercion event.

2. The vehicle theft detection method according to claim 1, wherein Before the determining whether the coercion event occurs based on the vehicle state data and the driver state data, the method further comprises: determining whether a vehicle insertion event occurs; in a case where it is determined that the vehicle insertion event occurs, determining whether a forced stop event occurs based on vehicle speed data of the current vehicle within a first time period and whether there is a vehicle in front of the current vehicle, the first time period being determined according to a time of occurrence of the vehicle insertion event; correspondingly, the determining whether the coercion event occurs based on the vehicle state data and the driver state data comprises: in a case where it is determined that the vehicle insertion event occurs and the forced stop event occurs, determining whether the coercion event occurs based on the vehicle state data and the driver state data.

3. The vehicle theft detection method according to claim 2, characterized in that, The determining whether the forced stop event occurs based on the vehicle speed data of the current vehicle within the first time period and whether there is the vehicle in front of the current vehicle comprises: determining an insertion type corresponding to the vehicle insertion event to obtain a target insertion type; in a case where the target insertion type is a rear vehicle overtaking insertion, determining whether the current vehicle has an emergency deceleration event and / or a stop event within the first time period based on the vehicle speed data; in a case where it is determined that the current vehicle has the emergency deceleration event and / or the stop event within the first time period, if there is the vehicle in front of the current vehicle, it is determined that the forced stop event occurs.

4. The vehicle theft detection method according to claim 3, characterized in that, Before the determining whether the current vehicle has the emergency deceleration event and / or the stop event within the first time period based on the vehicle speed data, the method further comprises: determining a time interval between a time of appearance of an insertion vehicle corresponding to the vehicle insertion event and the time of occurrence of the vehicle insertion event to obtain a target time interval, the time of appearance of the insertion vehicle being determined according to a time when the insertion vehicle is detected; determining whether the target time interval is less than or equal to an interval threshold value; correspondingly, the determining whether the current vehicle has the emergency deceleration event and / or the stop event within the first time period based on the vehicle speed data in a case where the target insertion type is the rear vehicle overtaking insertion comprises: in a case where the target insertion type is the rear vehicle overtaking insertion and the target time interval is less than or equal to the interval threshold value, determining whether the current vehicle has the emergency deceleration event and / or the stop event within the first time period based on the vehicle speed data.

5. The vehicle theft detection method according to claim 2, characterized by, The determining whether the vehicle insertion event occurs comprises: obtain lane line data and position information of a reference vehicle, the lane line data at least including lane markings, the reference vehicle including a vehicle behind the current vehicle in a current lane in which the current vehicle is located and a vehicle in an adjacent lane; determine whether the reference vehicle is in front of the current vehicle according to the lane line data and the position information; in a case where it is determined that the reference vehicle is in front of the current vehicle and the current vehicle does not have a lane changing behavior, determine that the vehicle insertion event occurs.

6. The vehicle theft detection method according to claim 2, wherein Before the determining whether the coercion event occurs based on the vehicle state data and the driver state data, the method further comprises: determining whether the forced stop event is a forced stop event occurring in a pursuit process; Correspondingly, the determining whether the coercion event occurs based on the vehicle state data and the driver state data in a case where it is determined that the vehicle insertion event occurs and the forced stop event occurs comprises: determining whether the coercion event occurs based on the vehicle state data and the driver state data in a case where it is determined that the vehicle insertion event occurs and the forced stop event occurs in the pursuit process.

7. The vehicle theft detection method according to claim 1, characterized by, The determining whether the coercion event occurs based on the vehicle state data and the driver state data comprises: determining whether a current posture of the driver matches a target posture based on the driver state data; in a case where it is determined that the current posture matches the target posture, determining whether the current vehicle is in a static state according to the vehicle state data; in a case where it is determined that the current vehicle is in the static state, determining that the coercion event occurs.

8. The vehicle theft identification method according to claim 7, characterized by, The determining whether the current vehicle is in the static state according to the vehicle state data in a case where it is determined that the current posture matches the target posture comprises: determining a holding duration of the current posture in a case where it is determined that the current posture matches the target posture; in a case where the holding duration is greater than or equal to a holding duration threshold, determining whether the current vehicle is in the static state according to the vehicle state data.

9. The vehicle theft detection method according to claim 7, characterized by, The driver state data includes image data obtained by shooting the driver, and the target posture includes a hand-raising posture, and the determining whether the current posture of the driver matches the target posture based on the driver state data comprises: determining a hand position and a head position of the driver based on the image data; determining the current posture according to a relative positional relationship between the hand position and the head position; determining whether the current posture matches the hand-raising posture.

10. The vehicle theft detection method according to claim 1, characterized by, Before the performing alarm processing based on the coercion event, the method further comprises: obtaining target video data corresponding to a second time period, the target video data at least including video data obtained by shooting a driver of the current vehicle, the second time period being determined according to an occurrence time of the coercion event; determining whether a driver replacement event occurs in the current vehicle based on the target video data; Correspondingly, the performing alarm processing based on the coercion event in a case where it is determined that the coercion event occurs comprises: In a case where it is determined that the stress event occurs and the driver replacement event occurs in the current vehicle, an alarm process is performed based on the stress event.

11. The vehicle theft detection method according to claim 10, characterized in that, The determining whether the driver replacement event occurs in the current vehicle based on the target video data comprises: determining whether a driver getting-off behavior occurs based on the target video data; In a case where it is determined that the driver getting-off behavior occurs, determining whether a driver getting-on behavior occurs according to video data corresponding to a third time period in the target video data, the third time period corresponding to a time later than a time of occurrence of the driver getting-on behavior; In a case where it is determined that the driver getting-on behavior occurs and a driver corresponding to the driver getting-on behavior is different from a driver corresponding to the driver getting-off behavior, it is determined that the driver replacement event occurs.

12. The vehicle theft identification method according to any one of claims 1 to 11, characterized in that, Before the obtaining the vehicle state data and the driver state data corresponding to the current vehicle, the method further comprises: determining whether the current vehicle is in a dangerous environment according to current environment data, the current environment data comprising a current scene and / or a traffic flow; Correspondingly, the obtaining the vehicle state data and the driver state data corresponding to the current vehicle comprises: In a case where it is determined that the current vehicle is in the dangerous environment, obtaining the vehicle state data and the driver state data corresponding to the current vehicle.

13. A vehicle theft identification apparatus characterized by comprising: The method comprises: a data obtaining module, configured to obtain vehicle state data and driver state data corresponding to a current vehicle, the vehicle state data reflecting a driving state of the current vehicle, and the driver state data reflecting at least a head posture and a hand posture of a driver of the current vehicle; a stress determining module, configured to determine whether a stress event occurs based on the vehicle state data and the driver state data; an alarm module, configured to perform an alarm process based on the stress event in a case where it is determined that the stress event occurs.

14. A terminal device comprising a memory, a processor, and a computer program stored in the memory and executable on the processor, characterized in that, The processor executes the computer program to implement the method in any one of claims 1 to 12.

15. A computer-readable storage medium, the computer-readable storage medium storing a computer program, characterized in that, The computer program is executed by the processor to implement the method in any one of claims 1 to 12.

Images