Vehicle abnormal area determination method, device, equipment and medium

Abstract

Embodiments of the present application disclose a vehicle abnormal area determination method, device, equipment and medium, the method comprises: acquiring the vehicle environment video of the current vehicle, determining the candidate gaze focus and candidate gesture focus of the candidate pedestrian; according to the vehicle boundary interval and the preset focus distance threshold, determine the target pedestrian from the candidate pedestrian; determine the number of pedestrians of the target pedestrian, when the number of pedestrians reaches the preset number of pedestrians threshold, according to the target gaze focus and target gesture focus of each target pedestrian, determine the center of the abnormal area of the current vehicle; based on the vehicle environment video, determine the candidate gaze time and candidate visual angle of each target pedestrian, and determine the target gaze duration and target visual angle; according to the number of pedestrians, target gaze duration and target visual angle, determine the radius of the abnormal area, and based on the radius of the abnormal area and the center of the abnormal area, determine the vehicle abnormal area of the current vehicle. The accuracy of the determined vehicle abnormal area is improved.

Description

Technical Field

[0001] The embodiments of the present invention relate to the field of automotive technology, and in particular to a method, apparatus, device and medium for determining abnormal areas of a vehicle. Background Technology

[0002] With the development of technology, vehicles are frequently used in daily life. To improve vehicle safety, fault diagnosis is necessary. Current technologies typically rely on in-vehicle sensors and diagnostic tools to pinpoint abnormal areas, but the accuracy is relatively low. Summary of the Invention

[0003] This invention provides a method, apparatus, device, and medium for determining abnormal vehicle areas, thereby improving the accuracy of the determined abnormal vehicle areas.

[0004] According to one aspect of the present invention, a method for determining abnormal vehicle regions is provided, comprising:

[0005] Acquire a video of the current vehicle's environment, and determine the candidate gaze focus and candidate gesture focus of the candidate pedestrians around the current vehicle from the initial vehicle environment image in the video.

[0006] Based on the candidate gaze focus, the candidate gesture focus, the vehicle boundary interval, and a preset focus distance threshold, a target gaze focus and a target gesture focus are selected from the candidate gaze focus and the candidate gesture focus, and the candidate pedestrians corresponding to the target gaze focus and the target gesture focus are taken as the target pedestrians;

[0007] The number of pedestrians of the target pedestrian is determined. When the number of pedestrians reaches a preset pedestrian number threshold, the abnormal area center of the current vehicle is determined based on the target gaze focus and target gesture focus of each target pedestrian.

[0008] Based on the vehicle environment video, the candidate gaze time and candidate line of sight angle of each of the target pedestrians are determined, and the target gaze duration is determined based on the candidate gaze time, and the target line of sight angle is determined based on the candidate line of sight angle.

[0009] The radius of the abnormal region is determined based on the number of pedestrians, the duration of the target gaze, and the angle of the target line of sight. Based on the radius of the abnormal region and the center of the abnormal region, the abnormal region of the current vehicle is determined.

[0010] According to another aspect of the present invention, a vehicle abnormality area determination device is provided, comprising:

[0011] The focus determination module is used to acquire a video of the current vehicle's environment and determine the candidate gaze focus and candidate gesture focus of the candidate pedestrians around the current vehicle from the initial vehicle environment image in the video.

[0012] The target pedestrian determination module is used to select a target gaze focus and a target gesture focus from the candidate gaze focus and the candidate gesture focus based on the candidate gaze focus, the candidate gesture focus, the vehicle boundary interval and a preset focus distance threshold, and to identify the candidate pedestrians corresponding to the target gaze focus and the target gesture focus as the target pedestrians;

[0013] An abnormal region center determination module is used to determine the number of pedestrians of the target pedestrian. When the number of pedestrians reaches a preset pedestrian number threshold, the abnormal region center of the current vehicle is determined based on the target gaze focus and target gesture focus of each target pedestrian.

[0014] The target data determination module is used to determine the candidate gaze time and candidate line-of-sight angle of each target pedestrian based on the vehicle environment video, and to determine the target gaze duration based on each candidate gaze time and the target line-of-sight angle based on each candidate line-of-sight angle.

[0015] The abnormal region determination module is used to determine the radius of the abnormal region based on the number of pedestrians, the target gaze duration, and the target line of sight angle, and to determine the vehicle abnormal region of the current vehicle based on the radius of the abnormal region and the center of the abnormal region.

[0016] According to another aspect of the present invention, an electronic device is provided, comprising:

[0017] One or more processors;

[0018] Memory, used to store one or more programs;

[0019] When one or more programs are executed by one or more processors, the one or more processors are able to execute any of the vehicle abnormality area determination methods provided in the embodiments of the present invention.

[0020] According to another aspect of the present invention, a computer-readable storage medium is provided, which stores computer instructions for causing a processor to execute any of the vehicle abnormality area determination methods provided in the embodiments of the present invention.

[0021] This invention provides a scheme for determining abnormal vehicle regions. It involves acquiring a video of the current vehicle's environment and determining candidate gaze points and candidate gesture points of pedestrians around the vehicle from the initial vehicle environment image within the video. Based on these candidate gaze points, candidate gesture points, vehicle boundary intervals, and a preset focus distance threshold, target gaze points and target gesture points are selected from the candidate gaze points and candidate gesture points, and the candidate pedestrians corresponding to these target gaze points and target gesture points are designated as target pedestrians. The number of target pedestrians is determined, and when the number of pedestrians reaches a preset pedestrian number threshold, the center of the abnormal region of the current vehicle is determined based on the target gaze points and target gesture points of each target pedestrian. Based on the vehicle environment video, the candidate gaze time and candidate line-of-sight angle of each target pedestrian are determined, and the target gaze duration and target line-of-sight angle are determined based on the candidate gaze time and candidate line-of-sight angle, respectively. Finally, the radius of the abnormal region is determined based on the number of pedestrians, the target gaze duration, and the target line-of-sight angle, and the abnormal region of the current vehicle is determined based on the radius and the center of the abnormal region. The above-mentioned scheme, by introducing candidate gaze focus and candidate gesture focus of candidate pedestrians, determines the abnormal vehicle area, realizing the identification of abnormal vehicle areas based on the actions of pedestrians around the vehicle, thus achieving rapid location of abnormal vehicle areas and improving the efficiency of identifying abnormal vehicle areas. At the same time, by introducing a preset threshold for the number of pedestrians, it realizes the use of multiple target gaze focus and target gesture focus, and comprehensively considers the factors of target gaze duration and target line of sight angle, improving the accuracy and reliability of the identified abnormal vehicle areas. Furthermore, by analyzing the behavioral data of people outside the vehicle, it enhances the human-computer interaction capability.

[0022] It should be understood that the description in this section is not intended to identify key or essential features of the embodiments of the present invention, nor is it intended to limit the scope of the invention. Other features of the invention will become readily apparent from the following description. Attached Figure Description

[0023] To more clearly illustrate the technical solutions in the embodiments of the present invention, the accompanying drawings used in the description of the embodiments will be briefly introduced below. Obviously, the accompanying drawings described below are only some embodiments of the present invention. For those skilled in the art, other drawings can be obtained based on these drawings without creative effort.

[0024] Figure 1 This is a flowchart of a method for determining abnormal vehicle areas provided in Embodiment 1 of the present invention;

[0025] Figure 2 This is a flowchart of a method for determining abnormal vehicle areas provided in Embodiment 2 of the present invention;

[0026] Figure 3 This is a schematic diagram of the structure of a vehicle abnormality area determination device provided in Embodiment 3 of the present invention;

[0027] Figure 4 This is a schematic diagram of the structure of an electronic device for implementing a method for determining abnormal areas of a vehicle, provided in Embodiment 4 of the present invention. Detailed Implementation

[0028] The present invention will now be described in further detail with reference to the accompanying drawings and embodiments. It should be understood that the specific embodiments described herein are merely illustrative of the invention and not intended to limit it. Furthermore, it should be noted that, for ease of description, the accompanying drawings show only the parts relevant to the present invention, and not all of the structures.

[0029] Example 1

[0030] Figure 1 This is a flowchart of a method for determining abnormal areas in a vehicle according to Embodiment 1 of the present invention. This embodiment is applicable to the situation of determining abnormal areas in a vehicle. The method can be executed by a vehicle abnormal area determination device, which can be implemented in software and / or hardware and can be configured in an electronic device that carries the function of determining abnormal areas in a vehicle.

[0031] See Figure 1 The method for determining abnormal vehicle areas shown includes:

[0032] S110. Acquire the vehicle environment video of the current vehicle, and determine the candidate gaze focus and candidate gesture focus of the candidate pedestrians around the current vehicle from the initial vehicle environment image in the vehicle environment video.

[0033] In this invention, the "current vehicle" refers to the vehicle for which anomaly area determination is needed at the current moment. The current vehicle can be stationary or in motion. The vehicle environment video refers to the video of the surrounding environment where the current vehicle is located. This embodiment of the invention does not limit the method of acquiring the vehicle environment video; it can be set by a technician based on experience. For example, it can be acquired through a camera installed externally to the current vehicle, as long as the camera covers the entire surrounding area of ​​the current vehicle. Sensors installed externally to the current vehicle can identify the pedestrian's gaze direction (including gaze angle and gaze start point) and gesture direction (including gesture angle and gesture start point) in each frame of the vehicle environment video. The sensors can cover the entire surrounding area of ​​the current vehicle. The sensors can include gesture recognition sensors and gaze recognition sensors. This embodiment of the invention does not limit the duration of the vehicle environment video; it can be set by a technician based on experience.

[0034] Here, the initial vehicle environment image refers to any frame in the vehicle environment video. For example, the initial vehicle environment image could be the first frame in the vehicle environment video. Candidate pedestrians refer to pedestrians in the initial vehicle environment image. Candidate pedestrians can be understood as people currently outside the vehicle.

[0035] Among them, the candidate gaze focus refers to the focal point of the candidate pedestrian's gaze. The candidate gesture focus refers to the focal point of the candidate pedestrian's hand gesture.

[0036] For example, the initial vehicle environment image includes at least one candidate person. For any candidate person, the gaze direction of that candidate person is determined from the initial vehicle environment image. Based on a facial feature point detection algorithm (such as OpenFace), the gaze direction is analyzed and calculated according to the current vehicle's location area to determine the candidate gaze focus of that candidate person. The gesture direction of that candidate person is also determined from the initial vehicle environment image. Based on a gesture recognition algorithm (such as OpenPose), the gesture direction is analyzed and calculated according to the current vehicle's location area to determine the candidate gesture focus of that candidate person. Here, the vehicle location area refers to the area where the current vehicle is located. This embodiment of the invention does not specifically limit the method for determining the vehicle location area; it can be set by a technician based on experience. For example, it can be determined using a high-precision map.

[0037] For example, based on the gaze start point and gaze angle in the candidate's gaze direction, a gaze prediction extension line is drawn, and the intersection of this gaze prediction extension line and the area where the vehicle is located is taken as the candidate's gaze focus. Similarly, based on the gesture start point and gesture angle in the candidate's gesture direction, a gesture prediction extension line is drawn, and the intersection of this gesture prediction extension line and the area where the vehicle is located is taken as the candidate's gesture focus. Here, the gaze prediction extension line refers to the candidate's virtual gaze predicted based on a facial feature detection algorithm. The gesture prediction extension line refers to the candidate's virtual pointing direction predicted based on a gesture recognition algorithm.

[0038] It should be noted that a candidate user should correspond to a candidate gaze focus and a candidate gesture focus, that is, a candidate user has a candidate gaze focus and a candidate gesture focus; candidates with only one candidate gaze focus or only one candidate gesture focus are deleted in order to update the candidates.

[0039] S120. Based on the candidate gaze focus, candidate gesture focus, vehicle boundary interval and preset focus distance threshold, select the target gaze focus and target gesture focus from the candidate gaze focus and candidate gesture focus, and take the candidate pedestrians corresponding to the target gaze focus and target gesture focus as the target pedestrians.

[0040] The vehicle boundary interval refers to the pre-determined boundary range of the current vehicle. This embodiment of the invention does not impose any limitation on the size of the preset focus distance threshold; it can be set by technicians based on experience or determined through extensive experimentation.

[0041] Here, the target gaze focus refers to the candidate gaze focus located on the current vehicle surface. The target gesture focus refers to the candidate gesture focus located on the current vehicle surface. The target pedestrian refers to the candidate pedestrian corresponding to the target gaze focus and the target gesture focus.

[0042] S130. Determine the number of pedestrians for the target pedestrian. When the number of pedestrians reaches the preset pedestrian number threshold, determine the center of the abnormal area of ​​the current vehicle based on the target gaze focus and target gesture focus of each target pedestrian.

[0043] Here, the number of pedestrians refers to the target number of pedestrians. This embodiment of the invention does not impose any limitation on the size of the preset pedestrian number threshold; it can be set by technicians based on experience or determined through repeated trials. For example, the preset pedestrian number threshold can be 2. The center of the abnormal area refers to the center point of the abnormal vehicle area.

[0044] In one optional embodiment, determining the center of the abnormal region of the current vehicle based on the target gaze focus and target gesture focus of each target pedestrian includes: determining the gaze weight of the target gaze focus and the gesture weight of the target gesture focus; and determining the center of the abnormal region of the current vehicle based on the gaze weight, the target gaze focus, the gesture weight, and the target gesture focus.

[0045] The gaze weight can be used to quantify the importance of the target gaze focus. The gesture weight can be used to quantify the importance of the target gesture focus. This embodiment of the invention does not impose any limitations on the magnitude of the gaze weight and / or gesture weight; these can be set by a technician based on experience or determined through extensive experimentation. It is understood that the gaze weight and gesture weight can be used to balance the relative importance of the target gaze focus and the target gesture focus in determining the center of the abnormal region of the current vehicle.

[0046] For example, the center of an anomaly region can be determined using the following formula:

[0047]

[0048] Where M represents the center of the abnormal region; n represents the number of pedestrians in the target area; i represents the i-th target pedestrian; w i Z represents the gaze weight; i Indicates the focus of attention; w i 'Indicates gesture weight; S i Indicates the focus of the target gesture.

[0049] Understandably, by introducing gaze weight and gesture weight, and using gaze weight, target gaze focus, gesture weight, and target gesture focus to determine the center of the abnormal region of the current vehicle, the accuracy of the determined abnormal region center is improved.

[0050] It should be noted that if the number of pedestrians in the initial vehicle environment image is less than a preset pedestrian number threshold, then any other frame image from the vehicle environment video other than the initial vehicle environment image will be selected as the new initial vehicle environment image.

[0051] S140. Based on the vehicle environment video, determine the candidate gaze time and candidate line-of-sight angle of each target pedestrian, and determine the target gaze duration based on each candidate gaze time, and determine the target line-of-sight angle based on each candidate line-of-sight angle.

[0052] Here, candidate gaze time refers to the duration during which a pedestrian gazes at the current vehicle. For example, candidate gaze time may include candidate gaze start time and candidate gaze end time. Candidate gaze start time refers to the point in time when the pedestrian begins to gaze at the current vehicle; correspondingly, candidate gaze end time refers to the point in time when the pedestrian stops gazing at the current vehicle. Candidate gaze angle refers to the angle between the focal points of gaze of any two pedestrians.

[0053] Among them, target fixation duration refers to the fixation duration that can be used to determine the radius of the abnormal region. Target line-of-sight angle refers to the candidate line-of-sight angle that can be used to determine the radius of the abnormal region.

[0054] In one optional embodiment, determining the candidate gaze time of each target pedestrian based on vehicle environment video includes: tracking and monitoring the target pedestrian based on vehicle environment video, determining the reference gaze focus of each target pedestrian in each reference vehicle environment image in the vehicle environment video; determining whether each reference gaze focus is within a preset gaze focus range, and determining the candidate gaze time of each target pedestrian based on the determination result.

[0055] The reference vehicle environment image refers to any frame in the vehicle environment video other than the initial vehicle environment image. The reference gaze focus refers to the gaze focus of the target pedestrian determined based on the reference vehicle environment image.

[0056] The preset fixation focus interval can be understood as a range that can deviate from the reference fixation focus. For example, using the target fixation focus as a reference, a certain range around the target fixation focus is defined as the preset fixation focus interval. This embodiment of the invention does not impose any limitation on the size of this range; it can be set by a person skilled in the art based on experience.

[0057] For example, determining whether each reference gaze focus is within a preset gaze focus range, and determining the candidate gaze time for each target pedestrian based on the determination result, includes: for any reference gaze focus, if the reference gaze focus is within the preset gaze focus range, then the reference vehicle environment image where the reference gaze focus is located is valid; if the reference gaze focus is not within the preset gaze focus range, then the reference vehicle environment image where the reference gaze focus is located is invalid; and determining the candidate gaze time of the target pedestrian based on the time point corresponding to the initial vehicle environment image and the time point of the valid reference vehicle environment image.

[0058] It should be noted that if any reference vehicle environment image is invalid for any reference gaze focus, then the reference vehicle environment image may be valid for another reference gaze focus; that is, the valid reference vehicle environment images corresponding to different target persons may be different.

[0059] In this embodiment of the invention, gaze duration (or fixation time) is a key indicator for assessing the importance of an object or event. A longer gaze duration indicates a higher level of attention from pedestrians to that location, and a greater likelihood of an anomaly. Furthermore, a longer gaze duration generally indicates a higher degree of certainty from pedestrians regarding the location they are focusing on. Pedestrians confirm the presence of an anomaly at that location through prolonged fixation. In this embodiment of the invention, if a person outside a vehicle gazes at a certain location for a long time, it indicates that the anomaly at that location warrants further investigation. Therefore, the longer the gaze duration, the larger the radius of the anomaly area should be to ensure comprehensive detection of the anomaly.

[0060] Understandably, by tracking and monitoring the target pedestrian based on vehicle environment video, the accuracy of the determined candidate gaze time is improved. At the same time, by introducing a preset gaze focus range, the reference gaze focus is filtered out, avoiding the influence of invalid reference gaze focus on the determination of candidate gaze time, thus improving the accuracy of the determined candidate gaze time.

[0061] In one optional embodiment, determining the target gaze duration based on each candidate gaze time includes: determining the gaze intersection time of the target pedestrian based on the candidate gaze times of each target pedestrian; and determining the target gaze duration based on the gaze intersection time.

[0062] Among them, gaze intersection time refers to the time during which all target pedestrians jointly gaze at the current vehicle. Target gaze duration refers to the total duration during which target individuals jointly gaze at the current vehicle.

[0063] For example, if the candidate gaze time of target person A is from the 1st to the 5th second, the candidate gaze time of target person B is from the 2nd to the 4th second, and the candidate gaze time of target person C is from the 3rd to the 7th second, then the gaze intersection time is from the 3rd to the 4th second, and the target gaze duration is 1 second.

[0064] Understandably, by introducing fixation intersection time to determine the target fixation duration, the accuracy of the determined target fixation duration is improved.

[0065] In one optional embodiment, determining the candidate gaze angles of each target pedestrian includes: determining the intersecting vehicle environment image from the vehicle environment video based on the gaze intersection time; determining the candidate gaze angles between each target pedestrian in the intersecting vehicle environment image based on the intersection gaze focus of each target pedestrian in the intersecting vehicle environment image; correspondingly, determining the target gaze angle based on each candidate gaze angle includes: comparing each candidate gaze angle and taking the candidate gaze angle with the largest value as the target gaze angle.

[0066] The intersecting vehicle environment image refers to an image determined from the vehicle environment video based on the gaze intersection time. For example, the intersecting vehicle environment image may include an initial vehicle environment image and / or a reference vehicle environment image.

[0067] The intersection gaze focus refers to the gaze focus of each target pedestrian in the intersection vehicle environment image. For example, the intersection gaze focus may include the target gaze focus and / or the reference gaze focus.

[0068] In this embodiment of the invention, the line-of-sight angle can reflect the location distribution information of multiple pedestrians. By calculating the line-of-sight angle between pedestrians, their level of attention to the same location can be assessed. The larger the angle, the more dispersed the pedestrian distribution, the higher the independence, and the more each person confirms the anomaly at that location from different angles. A larger line-of-sight angle indicates that pedestrians from different locations are all paying attention to the same location, and this independent verification result is more convincing. In practical applications, by calculating the line-of-sight angle of multiple pedestrians, it is possible to assess whether their gaze points are concentrated at the same location. The larger the line-of-sight angle, the more likely an anomaly is that pedestrians from different locations have noticed this information. Therefore, a larger line-of-sight angle requires setting a larger radius for the anomaly area.

[0069] Understandably, by introducing the intersection of vehicle environment images and intersection of gaze focus, the accuracy of the determined candidate line-of-sight angles is improved, which in turn improves the accuracy of the determined target line-of-sight angles.

[0070] S150. Determine the radius of the abnormal area based on the number of pedestrians, the duration of the target gaze, and the angle of the target line of sight. Based on the radius and center of the abnormal area, determine the abnormal area of ​​the current vehicle.

[0071] The abnormal area radius refers to the radius of the abnormal area within the vehicle. The abnormal area refers to the region within the vehicle where a fault or abnormality exists.

[0072] In this embodiment of the invention, the increased gaze and gestures of more pedestrians towards the same location generally indicate a higher probability of anomalies at that location. This collective attention can be seen as a manifestation of "collective wisdom," as conclusions drawn independently by multiple pedestrians are often more reliable. In practical applications, if multiple people outside a vehicle simultaneously gaze at or point to a certain location, it suggests that the anomaly at that location warrants serious attention. Therefore, the more people involved, the larger the radius of the anomaly area needs to be to ensure coverage of all possible anomalies.

[0073] For example, the radius of the abnormal region is determined based on the number of pedestrians, the duration of the target gaze, and the angle of the target line of sight, including: determining the pedestrian weight of the number of pedestrians, determining the duration weight of the target gaze, and determining the angle weight of the target line of sight; and determining the radius of the abnormal region based on the pedestrian weight, duration weight, angle weight, number of pedestrians, target gaze duration, and target line of sight.

[0074] Among them, pedestrian weight can be used to quantify the importance of pedestrian quantity in determining the radius of the abnormal region. Duration weight can be used to quantify the importance of target gaze duration in determining the radius of the abnormal region. Angle weight can be used to quantify the importance of target gaze angle in determining the radius of the abnormal region. It can be understood that pedestrian weight, duration weight, and angle weight can be used to balance the relative importance of pedestrian quantity, target gaze duration, and target gaze angle in determining the radius of the abnormal region. The embodiments of the present invention do not impose any limitations on the magnitude of pedestrian weight, duration weight, and angle weight, which can be set by technicians based on experience or needs, or determined repeatedly through a large number of experiments.

[0075] For example, the radius of the abnormal region can be determined using the following formula:

[0076] R=αN+βT+γ·θ max ;

[0077] Where R represents the radius of the abnormal region; N represents the number of pedestrians; T represents the target fixation duration; θ max α represents the target line-of-sight angle; β represents the pedestrian weight; γ represents the duration weight; and γ represents the angle weight.

[0078] This invention provides a scheme for determining abnormal vehicle regions. It involves acquiring a video of the current vehicle's environment and determining candidate gaze points and candidate gesture points of pedestrians around the vehicle from the initial vehicle environment image within the video. Based on these candidate gaze points, candidate gesture points, vehicle boundary intervals, and a preset focus distance threshold, target gaze points and target gesture points are selected from the candidate gaze points and candidate gesture points, and the candidate pedestrians corresponding to these target gaze points and target gesture points are designated as target pedestrians. The number of target pedestrians is determined, and when the number of pedestrians reaches a preset pedestrian number threshold, the center of the abnormal region of the current vehicle is determined based on the target gaze points and target gesture points of each target pedestrian. Based on the vehicle environment video, the candidate gaze time and candidate line-of-sight angle of each target pedestrian are determined, and the target gaze duration and target line-of-sight angle are determined based on the candidate gaze time and candidate line-of-sight angle, respectively. Finally, the radius of the abnormal region is determined based on the number of pedestrians, the target gaze duration, and the target line-of-sight angle, and the abnormal region of the current vehicle is determined based on the radius and the center of the abnormal region. The above-mentioned scheme, by introducing candidate gaze focus and candidate gesture focus of candidate pedestrians, determines the abnormal vehicle area, realizing the identification of abnormal vehicle areas based on the actions of pedestrians around the vehicle, thus achieving rapid location of abnormal vehicle areas and improving the efficiency of identifying abnormal vehicle areas. At the same time, by introducing a preset threshold for the number of pedestrians, it realizes the use of multiple target gaze focus and target gesture focus, and comprehensively considers the factors of target gaze duration and target line of sight angle, improving the accuracy and reliability of the identified abnormal vehicle areas. Furthermore, by analyzing the behavioral data of people outside the vehicle, it enhances the human-computer interaction capability.

[0079] Based on the above technical solutions, embodiments of the present invention can determine whether a vehicle has an anomaly based on an abnormal area in the vehicle through the following methods. For example, the image of the determined abnormal area can be displayed on a screen visible to the driver, allowing the driver to determine whether an anomaly exists through careful observation; alternatively, the image of the abnormal area can be fed into a vehicle anomaly judgment model, which analyzes the image to determine whether an anomaly exists; or, vehicle diagnostic tools and sensors can be used to perform detailed detection of the abnormal area to confirm whether a fault exists. The vehicle anomaly judgment model is used to determine whether an anomaly or fault exists in the abnormal area of ​​the vehicle. The vehicle anomaly judgment model can be a deep learning network model.

[0080] Example 2

[0081] Figure 2This is a flowchart of a method for determining abnormal vehicle areas provided in Embodiment 2 of the present invention. Based on the above embodiments, this embodiment further refines the operation of "selecting a target gaze focus and a target gesture focus from candidate gaze focuses and candidate gesture focuses based on candidate gaze focuses, candidate gesture focuses, vehicle boundary intervals, and a preset focus distance threshold" into "for any candidate pedestrian, determining whether both the candidate gaze focus and candidate gesture focus of the candidate pedestrian are within the vehicle boundary interval; if so, determining the candidate focus distance of the candidate pedestrian based on the candidate gaze focus and candidate gesture focus; and determining whether the candidate gaze focus and candidate gesture focus of the candidate pedestrian are the target gaze focus and target gesture focus based on the candidate focus distance and the preset focus distance threshold," thereby improving the target focus determination mechanism. It should be noted that for parts not detailed in this embodiment, please refer to the descriptions in other embodiments.

[0082] See Figure 2 The method for determining abnormal vehicle areas shown includes:

[0083] S210. Acquire the vehicle environment video of the current vehicle, and determine the candidate gaze focus and candidate gesture focus of the candidate pedestrians around the current vehicle from the initial vehicle environment image in the vehicle environment video.

[0084] S220. For any candidate pedestrian, determine whether the candidate gaze focus and candidate gesture focus of the candidate pedestrian are both within the vehicle boundary interval.

[0085] For example, the vehicle boundary interval may include a first direction boundary interval and a second direction boundary interval. The first direction boundary interval may be an x-direction boundary interval; the second direction boundary interval may be a y-direction boundary interval. This embodiment of the invention does not limit the method of determining the vehicle boundary interval; it can be set by a technician based on experience. For example, the vehicle boundary interval can be determined based on the current vehicle's 3D model and a high-precision map to determine the current vehicle's position, and then determined based on the vehicle's 3D model and its position.

[0086] For example, if the candidate's focus of attention is (x g ,y g The candidate gesture focus is (x) h ,y h ), the first directional boundary interval is [x min ,x max The second directional boundary interval is [y]. min ,y max ], if and only if x g Located in [x min ,x max ], x h Located in [xmin ,x max [Inside, and y] g Located in [y min ,y max ] within, y h Located in [y min ,y max When the distance is within the specified range, determine the candidate focal distance for the candidate pedestrian.

[0087] S230. If present, determine the candidate focus distance of the candidate pedestrian based on the candidate gaze focus and the candidate gesture focus.

[0088] Here, candidate focus distance refers to the distance between candidate gaze focus and candidate gesture focus. For example, for any candidate pedestrian, the candidate focus distance between the candidate gaze focus and candidate gesture focus of that candidate pedestrian is determined.

[0089] For example, the candidate focal distance can be determined using the following formula:

[0090]

[0091] Where L represents the candidate focal distance; x g The first direction coordinate representing the candidate gaze focus; x h The first direction coordinate representing the focus of the candidate gesture; y g The second direction coordinates representing the candidate gaze focus; y h The second direction coordinates represent the focus of the candidate gesture.

[0092] S240. Based on the candidate focus distance and the preset focus distance threshold, determine whether the candidate gaze focus and candidate gesture focus of the candidate pedestrian are the target gaze focus and target gesture focus.

[0093] In this embodiment of the invention, the size of the preset focus distance threshold is not limited in any way. It can be set by technicians based on experience or determined repeatedly through a large number of experiments.

[0094] In an optional embodiment, determining whether the candidate gaze focus and candidate gesture focus of the candidate pedestrian are the target gaze focus and target gesture focus based on the candidate focus distance and a preset focus distance threshold includes: if the candidate focus distance is less than or equal to the preset focus distance threshold, then determining the candidate gaze focus and candidate gesture focus of the candidate pedestrian as the target gaze focus and target gesture focus; if the candidate focus distance is greater than the preset focus distance threshold, then prohibiting the candidate gaze focus and candidate gesture focus of the candidate pedestrian from being used as the target gaze focus and target gesture focus.

[0095] Understandably, by comparing the candidate focus distance with the preset focus distance threshold, the accuracy of the determined target gaze focus and target gesture focus is improved.

[0096] S250, The candidate pedestrians corresponding to the target gaze focus and the target gesture focus are taken as the target pedestrians.

[0097] S260. Determine the number of pedestrians for the target pedestrian. When the number of pedestrians reaches a preset pedestrian number threshold, determine the center of the abnormal area of ​​the current vehicle based on the target gaze focus and target gesture focus of each target pedestrian.

[0098] S270. Based on the vehicle environment video, determine the candidate gaze time and candidate line-of-sight angle of each target pedestrian, and determine the target gaze duration based on each candidate gaze time, and determine the target line-of-sight angle based on each candidate line-of-sight angle.

[0099] S280. Determine the radius of the abnormal area based on the number of pedestrians, the duration of the target gaze, and the angle of the target line of sight. Based on the radius and center of the abnormal area, determine the abnormal area of ​​the current vehicle.

[0100] This invention provides a scheme for determining abnormal vehicle areas. By refining the process of selecting target gaze and gesture focuses from candidate gaze and gesture focuses based on candidate gaze focuses, candidate gesture focuses, vehicle boundary intervals, and a preset focus distance threshold, the scheme further refines the process to: for any candidate pedestrian, determining whether both the candidate gaze and gesture focuses of that pedestrian are within the vehicle boundary interval; if so, determining the candidate focus distance of that pedestrian based on the candidate gaze and gesture focuses; and then determining whether the candidate gaze and gesture focuses of that pedestrian are the target gaze and gesture focuses based on the candidate focus distance and the preset focus distance threshold. This improves the target focus determination mechanism. The above scheme, by introducing candidate focus distance and comparing it with the preset focus distance threshold to determine the target gaze and gesture focuses, improves the accuracy of the determined target gaze and gesture focuses.

[0101] During vehicle inspection and diagnosis, the gaze and gesture focus of people outside the vehicle (such as pedestrians or bystanders) can provide important indicative information. Traditional methods often rely on in-vehicle sensors and diagnostic tools, neglecting the gaze and gesture information of people outside the vehicle. By combining this information, abnormal vehicle conditions can be located and diagnosed more accurately.

[0102] The vehicle anomaly area determination scheme provided in this invention can be implemented through a vehicle detection system. This scheme achieves rapid localization of vehicle anomaly areas by analyzing the target gaze focus and target gesture focus of pedestrians outside the vehicle (i.e., target pedestrians), quickly identifying potential vehicle anomaly areas; it improves detection accuracy by combining the gaze and gesture information of multiple pedestrians outside the vehicle, reducing false alarms and increasing detection accuracy; and it comprehensively considers distance and time factors by analyzing the combined angle of gaze and gaze time to determine key areas of focus.

[0103] Based on the above technical solutions, the vehicle abnormality area determination method provided by the embodiments of the present invention can be applied to scenarios where it is necessary to determine whether a vehicle's tires are abnormal or faulty.

[0104] Example 3

[0105] Figure 3 This is a schematic diagram of a vehicle abnormal area determination device provided in Embodiment 3 of the present invention. This embodiment is applicable to the determination of abnormal areas in a vehicle. The method can be executed by a vehicle abnormal area determination device, which can be implemented in software and / or hardware and can be configured in an electronic device that carries the function of determining vehicle abnormal areas.

[0106] like Figure 3 As shown, the device includes: a focus determination module 310, a target pedestrian determination module 320, an anomaly area center determination module 330, a target data determination module 340, and an anomaly area determination module 350. Among them,

[0107] The focus determination module 310 is used to acquire a video of the current vehicle's environment and determine the candidate gaze focus and candidate gesture focus of the candidate pedestrians around the current vehicle from the initial vehicle environment image in the video.

[0108] The target pedestrian determination module 320 is used to select a target gaze focus and a target gesture focus from the candidate gaze focus and the candidate gesture focus based on the candidate gaze focus, the candidate gesture focus, the vehicle boundary interval and a preset focus distance threshold, and to take the candidate pedestrians corresponding to the target gaze focus and the target gesture focus as the target pedestrians;

[0109] The abnormal area center determination module 330 is used to determine the number of pedestrians of the target pedestrian, and when the number of pedestrians reaches a preset pedestrian number threshold, to determine the abnormal area center of the current vehicle based on the target gaze focus and target gesture focus of each target pedestrian.

[0110] The target data determination module 340 is used to determine the candidate gaze time and candidate line-of-sight angle of each of the target pedestrians based on the vehicle environment video, and to determine the target gaze duration based on each of the candidate gaze times and the target line-of-sight angle based on each of the candidate line-of-sight angles.

[0111] The abnormal region determination module 350 is used to determine the radius of the abnormal region based on the number of pedestrians, the target gaze duration and the target line of sight angle, and to determine the vehicle abnormal region of the current vehicle based on the radius of the abnormal region and the center of the abnormal region.

[0112] This invention provides a scheme for determining abnormal vehicle regions. It involves acquiring a video of the current vehicle's environment and determining candidate gaze points and candidate gesture points of pedestrians around the vehicle from the initial vehicle environment image within the video. Based on these candidate gaze points, candidate gesture points, vehicle boundary intervals, and a preset focus distance threshold, target gaze points and target gesture points are selected from the candidate gaze points and candidate gesture points, and the candidate pedestrians corresponding to these target gaze points and target gesture points are designated as target pedestrians. The number of target pedestrians is determined, and when the number of pedestrians reaches a preset pedestrian number threshold, the center of the abnormal region of the current vehicle is determined based on the target gaze points and target gesture points of each target pedestrian. Based on the vehicle environment video, the candidate gaze time and candidate line-of-sight angle of each target pedestrian are determined, and the target gaze duration and target line-of-sight angle are determined based on the candidate gaze time and candidate line-of-sight angle, respectively. Finally, the radius of the abnormal region is determined based on the number of pedestrians, the target gaze duration, and the target line-of-sight angle, and the abnormal region of the current vehicle is determined based on the radius and the center of the abnormal region. The above-mentioned scheme, by introducing candidate gaze focus and candidate gesture focus of candidate pedestrians, determines the abnormal vehicle area, realizing the identification of abnormal vehicle areas based on the actions of pedestrians around the vehicle, thus achieving rapid location of abnormal vehicle areas and improving the efficiency of identifying abnormal vehicle areas. At the same time, by introducing a preset threshold for the number of pedestrians, it realizes the use of multiple target gaze focus and target gesture focus, and comprehensively considers the factors of target gaze duration and target line of sight angle, improving the accuracy and reliability of the identified abnormal vehicle areas. Furthermore, by analyzing the behavioral data of people outside the vehicle, it enhances the human-computer interaction capability.

[0113] Optionally, the target pedestrian determination module 320 includes:

[0114] The focus determination unit is used to determine, for any candidate pedestrian, whether the candidate gaze focus and the candidate gesture focus of the candidate pedestrian are both within the vehicle boundary interval;

[0115] The candidate focus distance determination unit is used to determine the candidate focus distance of the candidate pedestrian based on the candidate gaze focus and the candidate gesture focus if the pedestrian is present.

[0116] The target focus determination unit is used to determine whether the candidate gaze focus and the candidate gesture focus of the candidate pedestrian are the target gaze focus and the target gesture focus, based on the candidate focus distance and the preset focus distance threshold.

[0117] Optional, the target focus determination unit is specifically used for:

[0118] If the candidate focus distance is less than or equal to the preset focus distance threshold, then the candidate gaze focus and the candidate gesture focus of the candidate pedestrian are determined as the target gaze focus and the target gesture focus;

[0119] If the distance between the candidate focus points is greater than the preset focus distance threshold, then the candidate gaze focus and the candidate gesture focus of the candidate pedestrian are prohibited from being used as the target gaze focus and the target gesture focus.

[0120] Optionally, the abnormal region center determination module 330 includes:

[0121] A weight determination unit is used to determine the gaze weight of the target gaze focus and the gesture weight of the target gesture focus;

[0122] An abnormal region center determination unit is used to determine the abnormal region center of the current vehicle based on the gaze weight, the target gaze focus, the gesture weight, and the target gesture focus.

[0123] Optionally, the target data determination module 340 includes:

[0124] The reference gaze focus determination unit is used to track and monitor the target pedestrian based on the vehicle environment video, and determine the reference gaze focus of each target pedestrian in each reference vehicle environment image in the vehicle environment video;

[0125] The candidate gaze time determination unit is used to determine whether each of the reference gaze focal points is within a preset gaze focal point range, and to determine the candidate gaze time of each of the target pedestrians based on the determination result.

[0126] Optionally, the target data determination module 340 includes:

[0127] A gaze intersection time determination unit is used to determine the gaze intersection time of the target pedestrians based on the candidate gaze times of each target pedestrian;

[0128] The target gaze duration determination unit is used to determine the target gaze duration based on the gaze intersection time.

[0129] Optionally, the target data determination module 340 includes:

[0130] An intersection image determination unit is used to determine an intersection vehicle environment image from the vehicle environment video based on the gaze intersection time;

[0131] The candidate gaze angle determination unit is used to determine the candidate gaze angle between each target pedestrian in the intersection vehicle environment image based on the intersection gaze focus of each target pedestrian in the intersection vehicle environment image;

[0132] Correspondingly, the target data determination module 340 also includes:

[0133] The target line-of-sight angle determination unit is used to compare the candidate line-of-sight angles and take the largest candidate line-of-sight angle as the target line-of-sight angle.

[0134] The vehicle abnormal area determination device provided in the embodiments of the present invention can execute the vehicle abnormal area determination method provided in any embodiment of the present invention, and has the corresponding functional modules and beneficial effects for executing each vehicle abnormal area determination method.

[0135] The technical solution of this invention involves the collection, storage, use, processing, transmission, provision, and disclosure of vehicle environment videos, vehicle boundary intervals, and preset focus distance thresholds, all of which comply with relevant laws and regulations and do not violate public order and good morals.

[0136] Example 4

[0137] Figure 4 This is a schematic diagram of an electronic device for implementing a method for determining abnormal vehicle areas, provided in Embodiment 4 of the present invention. The electronic device 410 is intended to represent various forms of digital computers, such as laptop computers, desktop computers, workstations, personal digital assistants, servers, blade servers, mainframe computers, and other suitable computers. The electronic device may also represent various forms of mobile devices, such as personal digital processors, cellular phones, smartphones, wearable devices (e.g., helmets, glasses, watches, etc.), and other similar computing devices. The components shown herein, their connections and relationships, and their functions are merely illustrative and are not intended to limit the implementation of the invention described and / or claimed herein.

[0138] like Figure 4As shown, the electronic device 410 includes at least one processor 411 and a memory, such as a read-only memory (ROM) 412 or a random access memory (RAM) 413, communicatively connected to the at least one processor 411. The memory stores computer programs executable by the at least one processor. The processor 411 can perform various appropriate actions and processes based on the computer program stored in the ROM 412 or loaded from storage unit 418 into the RAM 413. The RAM 413 may also store various programs and data required for the operation of the electronic device 410. The processor 411, ROM 412, and RAM 413 are interconnected via a bus 414. An input / output (I / O) interface 415 is also connected to the bus 414.

[0139] Multiple components in electronic device 410 are connected to I / O interface 415, including: input unit 416, such as keyboard, mouse, etc.; output unit 417, such as various types of displays, speakers, etc.; storage unit 418, such as disk, optical disk, etc.; and communication unit 419, such as network card, modem, wireless transceiver, etc. Communication unit 419 allows electronic device 410 to exchange information / data with other devices through computer networks such as the Internet and / or various telecommunications networks.

[0140] Processor 411 can be a variety of general-purpose and / or special-purpose processing components with processing and computing capabilities. Some examples of processor 411 include, but are not limited to, a central processing unit (CPU), a graphics processing unit (GPU), various special-purpose artificial intelligence (AI) computing chips, various processors running machine learning model algorithms, a digital signal processor (DSP), and any suitable processor, controller, microcontroller, etc. Processor 411 performs the various methods and processes described above, such as the vehicle anomaly area determination method.

[0141] In some embodiments, the vehicle anomaly area determination method may be implemented as a computer program tangibly contained in a computer-readable storage medium, such as storage unit 418. In some embodiments, part or all of the computer program may be loaded and / or installed on electronic device 410 via ROM 412 and / or communication unit 419. When the computer program is loaded into RAM 413 and executed by processor 411, one or more steps of the vehicle anomaly area determination method described above may be performed. Alternatively, in other embodiments, processor 411 may be configured to perform the vehicle anomaly area determination method by any other suitable means (e.g., by means of firmware).

[0142] Various embodiments of the systems and techniques described above herein can be implemented in digital electronic circuit systems, integrated circuit systems, field-programmable gate arrays (FPGAs), application-specific integrated circuits (ASICs), application-specific standard products (ASSPs), systems-on-a-chip (SoCs), payload-programmable logic devices (CPLDs), computer hardware, firmware, software, and / or combinations thereof. These various embodiments may include implementations in one or more computer programs that can be executed and / or interpreted on a programmable system including at least one programmable processor, which may be a dedicated or general-purpose programmable processor, capable of receiving data and instructions from a storage system, at least one input device, and at least one output device, and transmitting data and instructions to the storage system, the at least one input device, and the at least one output device.

[0143] Computer programs used to implement the methods of the present invention may be written in any combination of one or more programming languages. These computer programs may be provided to a processor of a general-purpose computer, a special-purpose computer, or other programmable data processing device, such that when executed by the processor, the computer programs cause the functions / operations specified in the flowcharts and / or block diagrams to be performed. The computer programs may be executed entirely on a machine, partially on a machine, or as a standalone software package, partially on a machine and partially on a remote machine, or entirely on a remote machine or server.

[0144] In the context of this invention, a computer-readable storage medium can be a tangible medium that may contain or store a computer program for use by or in conjunction with an instruction execution system, apparatus, or device. A computer-readable storage medium may include, but is not limited to, electronic, magnetic, optical, electromagnetic, infrared, or semiconductor systems, apparatus, or devices, or any suitable combination thereof. Alternatively, a computer-readable storage medium may be a machine-readable signal medium. More specific examples of machine-readable storage media include electrical connections based on one or more wires, portable computer disks, hard disks, random access memory (RAM), read-only memory (ROM), erasable programmable read-only memory (EPROM or flash memory), optical fibers, portable compact disk read-only memory (CD-ROM), optical storage devices, magnetic storage devices, or any suitable combination thereof.

[0145] To provide interaction with a user, the systems and techniques described herein can be implemented on an electronic device having: a display device for displaying information to the user (e.g., a CRT (cathode ray tube) or LCD (liquid crystal display) monitor); and a keyboard and pointing device (e.g., a mouse or trackball) through which the user provides input to the electronic device. Other types of devices can also be used to provide interaction with the user; for example, feedback provided to the user can be any form of sensory feedback (e.g., visual feedback, auditory feedback, or tactile feedback); and input from the user can be received in any form (including sound input, voice input, or tactile input).

[0146] The systems and technologies described herein can be implemented in computing systems that include backend components (e.g., as data servers), or computing systems that include middleware components (e.g., application servers), or computing systems that include frontend components (e.g., user computers with graphical user interfaces or web browsers through which users can interact with implementations of the systems and technologies described herein), or any combination of such backend, middleware, or frontend components. The components of the system can be interconnected via digital data communication of any form or medium (e.g., communication networks). Examples of communication networks include local area networks (LANs), wide area networks (WANs), blockchain networks, and the Internet.

[0147] A computing system can include clients and servers. Clients and servers are generally located far apart and typically interact through communication networks. The client-server relationship is created by computer programs running on the respective computers and having a client-server relationship with each other. The server can be a cloud server, also known as a cloud computing server or cloud host, which is a hosting product within the cloud computing service system to address the shortcomings of traditional physical hosts and VPS services, such as high management difficulty and weak business scalability.

[0148] It should be understood that the various forms of processes shown above can be used, with steps reordered, added, or deleted. For example, the steps described in this invention can be executed in parallel, sequentially, or in different orders, as long as the desired result of the technical solution of this invention can be achieved, and this is not limited herein.

[0149] The specific embodiments described above do not constitute a limitation on the scope of protection of this invention. Those skilled in the art should understand that various modifications, combinations, sub-combinations, and substitutions can be made according to design requirements and other factors. Any modifications, equivalent substitutions, and improvements made within the spirit and principles of this invention should be included within the scope of protection of this invention.

Claims

1. A vehicle abnormal region determination method characterized by comprising: The method comprises the following steps: acquiring a vehicle environment video of a current vehicle, and determining candidate gaze focal points and candidate gesture focal points of candidate pedestrians around the current vehicle from an initial vehicle environment image in the vehicle environment video; selecting target gaze focal points and target gesture focal points from the candidate gaze focal points and the candidate gesture focal points according to the candidate gaze focal points, the candidate gesture focal points, a vehicle boundary interval and a preset focal point distance threshold, and taking candidate pedestrians corresponding to the target gaze focal points and the target gesture focal points as target pedestrians; determining a pedestrian quantity of the target pedestrians, and determining an abnormal region center of the current vehicle according to target gaze focal points and target gesture focal points of each target pedestrian when the pedestrian quantity reaches a preset pedestrian quantity threshold; determining candidate gaze times and candidate visual line included angles of each target pedestrian based on the vehicle environment video, and determining a target gaze time length based on each candidate gaze time and determining a target visual line included angle based on each candidate visual line included angle; determining an abnormal region radius according to the pedestrian quantity, the target gaze time length and the target visual line included angle, and determining a vehicle abnormal region of the current vehicle based on the abnormal region radius and the abnormal region center.

2. The method of claim 1, wherein, The step of selecting the target gaze focal points and the target gesture focal points from the candidate gaze focal points and the candidate gesture focal points according to the candidate gaze focal points, the candidate gesture focal points, the vehicle boundary interval and the preset focal point distance threshold comprises the following steps: determining whether the candidate gaze focal points and the candidate gesture focal points of any candidate pedestrian are both within the vehicle boundary interval; if yes, determining a candidate focal point distance of the candidate pedestrian according to the candidate gaze focal points and the candidate gesture focal points; determining whether the candidate gaze focal points and the candidate gesture focal points of the candidate pedestrian are target gaze focal points and target gesture focal points according to the candidate focal point distance and the preset focal point distance threshold.

3. The method of claim 2, wherein, The step of determining whether the candidate gaze focal points and the candidate gesture focal points of the candidate pedestrian are target gaze focal points and target gesture focal points according to the candidate focal point distance and the preset focal point distance threshold comprises the following steps: if the candidate focal point distance is less than or equal to the preset focal point distance threshold, determining that the candidate gaze focal points and the candidate gesture focal points of the candidate pedestrian are target gaze focal points and target gesture focal points; if the candidate focal point distance is greater than the preset focal point distance threshold, prohibiting the candidate gaze focal points and the candidate gesture focal points of the candidate pedestrian from being taken as target gaze focal points and target gesture focal points.

4. The method of claim 1, wherein, The step of determining the abnormal region center of the current vehicle according to the target gaze focal points and the target gesture focal points of each target pedestrian comprises the following steps: determining a gaze weight of the target gaze focal points and a gesture weight of the target gesture focal points; determining the abnormal region center of the current vehicle according to the gaze weight, the target gaze focal points, the gesture weight and the target gesture focal points.

5. The method of claim 1, wherein, The step of determining the candidate gaze times of each target pedestrian based on the vehicle environment video comprises the following steps: tracking and monitoring the target pedestrians based on the vehicle environment video, determining reference gaze focal points of the target pedestrians in each reference vehicle environment image in the vehicle environment video; determining whether each of the reference gaze focal points is in a preset gaze focal point interval, and determining candidate gaze times of the target pedestrians according to a determination result.

6. The method of claim 5, wherein, The target gaze time is determined based on the candidate gaze times, including: determining a gaze intersection time of the target pedestrians according to the candidate gaze times of the target pedestrians; determining the target gaze time according to the gaze intersection time.

7. The method of claim 6, wherein, The candidate visual line angles of the target pedestrians are determined, including: determining an intersection vehicle environment image from the vehicle environment video according to the gaze intersection time; determining candidate visual line angles between the target pedestrians in the intersection vehicle environment image according to intersection gaze focal points of the target pedestrians in the intersection vehicle environment image; Correspondingly, the target visual line angle is determined based on the candidate visual line angles, including: comparing each of the candidate visual line angles, and taking the largest candidate visual line angle as the target visual line angle.

8. A vehicle abnormal region determination apparatus characterized by comprising: including: a focal point determination module configured to obtain a vehicle environment video of a current vehicle, and determine candidate gaze focal points and candidate gesture focal points of candidate pedestrians around the current vehicle from an initial vehicle environment image in the vehicle environment video; a target pedestrian determination module configured to select target gaze focal points and target gesture focal points from the candidate gaze focal points and the candidate gesture focal points according to the candidate gaze focal points, the candidate gesture focal points, a vehicle boundary interval, and a preset focal point distance threshold, and take candidate pedestrians corresponding to the target gaze focal points and the target gesture focal points as target pedestrians; an abnormal area center determination module configured to determine a pedestrian quantity of the target pedestrians, and determine an abnormal area center of the current vehicle according to target gaze focal points and target gesture focal points of the target pedestrians when the pedestrian quantity reaches a preset pedestrian quantity threshold; a target data determination module configured to determine candidate gaze times and candidate visual line angles of the target pedestrians based on the vehicle environment video, determine a target gaze time based on the candidate gaze times, and determine a target visual line angle based on the candidate visual line angles; an abnormal area determination module configured to determine an abnormal area radius according to the pedestrian quantity, the target gaze time, and the target visual line angle, and determine a vehicle abnormal area of the current vehicle based on the abnormal area radius and the abnormal area center.

9. An electronic device, comprising: including: one or more processors; a memory configured to store one or more programs; when the one or more programs are executed by the one or more processors, the one or more processors implement a vehicle abnormal area determination method according to any one of claims 1-7.

10. A computer-readable storage medium having stored thereon a computer program, characterized in that, The program is executed by the processor to implement a vehicle abnormal area determination method according to any one of claims 1-7.

Images