Driving behavior reporting method and device based on vehicle-mounted perception data and vehicle-mounted terminal

Abstract

The application provides a driving behavior reporting method and device based on vehicle-mounted sensing data and a vehicle-mounted terminal, and relates to the technical field of information processing. The method comprises the following steps: acquiring video data and environmental sensing data in a preset range of a driving vehicle collected by a vehicle-mounted camera and a radar sensor; identifying whether a target vehicle with a rule-breaking driving behavior exists in the preset range of the driving vehicle according to the video data and the environmental sensing data; generating a rule-breaking prompt information if the target vehicle with the rule-breaking driving behavior is identified; and uploading target video data corresponding to the rule-breaking driving behavior of the target vehicle to a traffic supervision platform in response to a confirmation operation of a user on the rule-breaking prompt information. The application effectively utilizes the sensing data of the vehicle to realize the reporting of the rule-breaking driving behavior and expands the coverage of law enforcement.

Description

Technical Field

[0001] This application relates to the field of information processing technology, and more specifically, to a method, device, and vehicle terminal for reporting driving behavior based on vehicle-mounted perception data. Background Technology

[0002] With the continuous increase in road traffic flow, various illegal driving behaviors occur frequently, seriously affecting road traffic safety and easily causing traffic accidents. Relying solely on a limited number of traffic police officers for enforcement and road cameras for capture is limited in scope and inefficient, making it difficult to achieve full-time, full-area supervision.

[0003] Currently, it is common for drivers to use their mobile phones to record videos to report traffic violations. However, this method relies on the driver's subjective ability to identify violations, which can easily lead to safety hazards caused by the driver being distracted while filming. Moreover, the video data is often invalid due to insufficient shooting angle, clarity, and lack of accurate time, location, and other key information. Summary of the Invention

[0004] The purpose of this application is to address the shortcomings of the prior art by providing a method, device, and vehicle terminal for reporting driving behavior based on vehicle perception data, so as to effectively utilize vehicle perception data to report illegal driving behavior and expand the scope of law enforcement.

[0005] To achieve the above objectives, the technical solutions adopted in the embodiments of this application are as follows: In a first aspect, embodiments of this application provide a method for reporting driving behavior based on vehicle-mounted perception data, applied to an in-vehicle terminal, the method comprising: Acquire video data and environmental perception data within a preset range of the driving vehicle collected by in-vehicle cameras and radar sensors; Based on the video data and the environmental perception data, identify whether there are target vehicles with illegal driving behavior within a preset range of the driving vehicle; If a target vehicle exhibiting the aforementioned illegal driving behavior is identified, a violation notification message is generated. In response to the user's confirmation of the violation notification, the target video data corresponding to the violation of the target vehicle is uploaded to the traffic monitoring platform.

[0006] Optionally, identifying whether a target vehicle with illegal driving behavior exists within a preset range of the driving vehicle based on the video data and the environmental perception data includes: The video data is used to identify the initial vehicle that made contact with the target lane boundary line and the duration of contact with the target lane boundary line. If the duration of contact with the target lane boundary line exceeds a preset duration, the initial vehicle is determined to be the target vehicle that is driving over the line.

[0007] Optionally, identifying whether a target vehicle with illegal driving behavior exists within a preset range of the driving vehicle based on the video data and the environmental perception data includes: The video data is used to identify the initial vehicle in the intersection's guide lane and the turn signal status of the initial vehicle. Based on the environmental perception data, the number of lane lines that the initial vehicle crosses laterally and the direction of crossing are determined; If the turn signal status and crossing direction of the initial vehicle do not meet the preset status conditions, and the number of lane lines crossed laterally is greater than or equal to a preset number threshold, the initial vehicle is determined to be the target vehicle for cutting in and changing lanes.

[0008] Optionally, identifying whether a target vehicle with illegal driving behavior exists within a preset range of the driving vehicle based on the video data and the environmental perception data includes: The video data is used to determine the driving lanes of other vehicles; The driving speed of the other vehicles is determined based on the environmental perception data; Based on the speed limit of the lane in which the other vehicles are traveling and the speed of the other vehicles, the target vehicle with speeding or low-speed lane occupation behavior is identified.

[0009] Optionally, identifying whether a target vehicle with illegal driving behavior exists within a preset range of the driving vehicle based on the video data and the environmental perception data includes: The traffic light status and stop line position at the intersection are determined using the video data. Based on the environmental perception data, it is determined that a vehicle whose front wheels have crossed the stop line and is in motion when the traffic light at the intersection is red is the target vehicle for running a red light.

[0010] Optionally, if a target vehicle exhibiting the aforementioned illegal driving behavior is identified, generating a violation warning message includes: If a target vehicle with the aforementioned illegal driving behavior is identified, the violation warning information is generated and displayed according to the driving status of the vehicle, using a prompting method that matches the driving status.

[0011] Optionally, the method further includes: In response to a user triggering the in-vehicle reporting button after recognizing a violation of driving rules, video data of a preset duration before and after the user triggers the in-vehicle reporting button is obtained from the video data captured by the in-vehicle camera and uploaded to the traffic monitoring platform.

[0012] Optionally, the step of responding to the user's confirmation of the violation notification by uploading the target video data corresponding to the target vehicle's illegal driving behavior to the traffic monitoring platform includes: In response to the user's confirmation of the violation notification, the target video data corresponding to the violation of the target vehicle is uploaded to the mobile terminal bound to the vehicle terminal. The mobile terminal then blurs the non-target vehicles and pedestrians in the target video data and uploads the blurred target video data to the traffic monitoring platform.

[0013] Secondly, embodiments of this application also provide a driving behavior reporting device based on vehicle-mounted perception data, applied to an in-vehicle terminal, the device comprising: The data acquisition module is used to acquire video data and environmental perception data within a preset range of the driving vehicle collected by the vehicle-mounted camera and radar sensor; The vehicle recognition module is used to identify, based on the video data and the environmental perception data, whether there is a target vehicle with illegal driving behavior within a preset range of the driving vehicle; The information prompt module is used to generate violation prompt information if a target vehicle with the aforementioned illegal driving behavior is identified; The video reporting module is used to respond to the user's confirmation of the violation prompt information and upload the target video data corresponding to the target vehicle's illegal driving behavior to the traffic monitoring platform.

[0014] Optionally, the vehicle recognition module is specifically used to identify the initial vehicle that contacts the target lane boundary line and the duration of contact with the target lane boundary line based on the video data; if the duration of contact with the target lane boundary line exceeds a preset duration, the initial vehicle is determined to be the target vehicle that is driving over the line.

[0015] Optionally, the vehicle recognition module is specifically used to identify an initial vehicle in the intersection's guide lane and the turn signal status of the initial vehicle based on the video data; determine the number and direction of lane lines crossed laterally by the initial vehicle based on the environmental perception data; if the turn signal status and crossing direction of the initial vehicle do not meet preset conditions, and the number of lane lines crossed laterally is greater than or equal to a preset threshold, determine that the initial vehicle is a target vehicle that cuts in or changes lanes.

[0016] Optionally, the vehicle recognition module is specifically used to determine the driving lanes of other vehicles through the video data; determine the driving speed of the other vehicles based on the environmental perception data; and determine target vehicles with speeding or low-speed lane-occupancy behavior based on the speed limit of the driving lanes of the other vehicles and the driving speed of the other vehicles.

[0017] Optionally, the vehicle recognition module is specifically used to determine the traffic light status and stop line position at the intersection through the video data; and to determine, through the environmental perception data, that a vehicle whose front wheels have crossed the stop line and is in motion when the traffic light at the intersection is red is a target vehicle that has run a red light.

[0018] Optionally, the information prompting module is specifically used to generate and display the violation prompt information based on the driving status of the vehicle and a prompting method that matches the driving status if a target vehicle with the violation driving behavior is identified.

[0019] Optionally, the video reporting module is also used to respond to the user's triggering operation of the in-vehicle reporting button after recognizing the illegal driving behavior, and to obtain video data of a preset duration before and after the user triggers the in-vehicle reporting button from the video data captured by the in-vehicle camera and upload it to the traffic supervision platform.

[0020] Optionally, the video reporting module is specifically used to respond to the user's confirmation operation of the violation prompt information, and upload the target video data corresponding to the violation driving behavior of the target vehicle to the mobile terminal bound to the vehicle terminal, so that the mobile terminal blurs the non-target vehicles and pedestrians in the target video data, and then uploads the blurred target video data to the traffic monitoring platform through the mobile terminal.

[0021] Thirdly, embodiments of this application also provide an in-vehicle terminal, including: a processor, a storage medium, and a bus. The storage medium stores program instructions executable by the processor. When the in-vehicle terminal is running, the processor communicates with the storage medium via the bus, and the processor executes the program instructions to perform the steps of the driving behavior reporting method based on in-vehicle perception data as described in any of the first aspects.

[0022] Fourthly, embodiments of this application also provide a computer-readable storage medium storing a computer program, which, when executed by a processor, performs the steps of the driving behavior reporting method based on vehicle perception data as described in any of the first aspects.

[0023] The beneficial effects of this application are: The driving behavior reporting method, device, and vehicle terminal provided in this application, based on vehicle-mounted perception data, combine video data and environmental perception data collected by existing cameras and radar sensors in intelligent driving vehicles on the market to identify and report illegal driving behaviors. Forming a mobile "electronic police" network, it can efficiently assist traffic management departments in detecting and promptly resolving traffic violations, better maintaining public transportation safety, and greatly expanding the scope of law enforcement. Furthermore, it allows users to choose whether to report violations while ensuring driving safety, giving users full choice and control. Attached Figure Description

[0024] To more clearly illustrate the technical solutions of the embodiments of this application, the accompanying drawings used in the embodiments will be briefly introduced below. It should be understood that the following drawings only show some embodiments of this application and should not be regarded as a limitation of the scope. For those skilled in the art, other related drawings can be obtained based on these drawings without creative effort.

[0025] Figure 1 A system architecture diagram of the driving behavior reporting system provided in this application embodiment; Figure 2 A flowchart illustrating the driving behavior reporting method based on vehicle perception data provided in this application embodiment. Figure 1 ; Figure 3 A flowchart illustrating the driving behavior reporting method based on vehicle perception data provided in this application embodiment. Figure 2 ; Figure 4 A flowchart illustrating the driving behavior reporting method based on vehicle perception data provided in this application embodiment. Figure 3 ; Figure 5 A flowchart illustrating the driving behavior reporting method based on vehicle perception data provided in this application embodiment. Figure 4 ; Figure 6 A flowchart illustrating the driving behavior reporting method based on vehicle perception data provided in this application embodiment. Figure 5 ; Figure 7 This is a schematic diagram of the structure of a driving behavior reporting device based on vehicle-mounted perception data provided in an embodiment of this application; Figure 8 This is a schematic diagram of the vehicle-mounted terminal provided in an embodiment of this application. Detailed Implementation

[0026] To make the objectives, technical solutions, and advantages of the embodiments of this application clearer, the technical solutions of the embodiments of this application will be clearly and completely described below with reference to the accompanying drawings. Obviously, the described embodiments are some embodiments of this application, but not all embodiments.

[0027] Therefore, the following detailed description of the embodiments of this application provided in the accompanying drawings is not intended to limit the scope of the claimed application, but merely to illustrate selected embodiments of the application. All other embodiments obtained by those skilled in the art based on the embodiments of this application without inventive effort are within the scope of protection of this application.

[0028] Furthermore, the terms "first," "second," etc., used in the specification, claims, and accompanying drawings of this application are used to distinguish similar objects and are not necessarily used to describe a specific order or sequence. It should be understood that such data can be interchanged where appropriate so that the embodiments of this application described herein can be implemented in orders other than those illustrated or described herein. Additionally, the terms "comprising" and "having," and any variations thereof, are intended to cover a non-exclusive inclusion; for example, a process, method, system, product, or apparatus that comprises a series of steps or units is not necessarily limited to those steps or units explicitly listed, but may include other steps or units not explicitly listed or inherent to such processes, methods, products, or apparatus.

[0029] It should be noted that, where there is no conflict, the features in the embodiments of this application can be combined with each other.

[0030] The driving behavior reporting method based on vehicle-mounted perception data provided in this application is applied to an in-vehicle terminal, which can be an electronic device, a computer device, or a server. The in-vehicle terminal provides a vehicle display screen for users to view violation information. Users can then view the violation information on the vehicle display screen and decide whether to report it. If the user confirms the report, the video data of the illegal driving is uploaded to the traffic monitoring platform.

[0031] The following is an introduction to the driving behavior reporting system used in this application. Figure 1 The system architecture diagram of the driving behavior reporting system provided in the embodiments of this application is as follows: Figure 1 As shown, the driving behavior reporting system may include at least: an in-vehicle subsystem and a traffic monitoring platform.

[0032] The vehicle-mounted subsystem may include: a perception data acquisition module, a violation driving behavior judgment module, a human-machine interaction module, and a storage module. The violation driving behavior judgment module, human-machine interaction module, and storage module may be integrated into the vehicle-mounted terminal.

[0033] The perception data acquisition module includes onboard cameras and radar sensors, used to collect real-time video data and environmental perception data around the driving vehicle. The onboard cameras may include at least a forward-facing camera and a surround-view camera, used to capture images and videos of the driving status of surrounding vehicles. These images and videos are linked to the acquisition time and location; the acquisition time is provided by the onboard clock module, and the acquisition location is provided by the Global Navigation Satellite System (GNSS). The radar sensors are used to assist in collecting data such as the distance, speed, and trajectory of surrounding vehicles, providing supplementary evidence for judging illegal driving behavior.

[0034] The illegal driving behavior judgment module is connected to the perception data acquisition module. It receives image and video data and environmental perception data, performs calculations and analysis on the data to determine the driving behavior of surrounding vehicles, and matches this data with preset illegal driving behaviors to determine if any illegal driving behavior exists. Preset illegal driving behaviors may include, but are not limited to, speeding, illegal parking, illegal lane changing, driving against traffic, and objects falling from the road. If a violation is found, a violation warning message is sent to the user. After the user responds to and confirms the violation warning message, the illegal driving behavior is identified as a target reporting event, and the corresponding image and video data is packaged, processed, and stored in the storage module.

[0035] The human-computer interaction module consists of physical buttons (hard switches) and an in-vehicle central control screen (soft switches and prompt interface). The physical buttons should be self-resetting and used to allow users to trigger a manual reporting command when they subjectively identify illegal driving behavior. The in-vehicle central control screen is used to issue a warning to the user through the in-vehicle display screen and voice broadcaster when the illegal driving behavior judgment module identifies illegal driving behavior, so that the user can decide whether to report it through the in-vehicle central control screen.

[0036] In some embodiments, such as Figure 1 As shown, the driving behavior reporting system may also include a mobile terminal, which has a mobile terminal video management APP installed on it. The APP consists of a communication module, an authentication module, a directory display and reporting confirmation interface, a data management module, and an encrypted upload module.

[0037] The communication module is used to establish a wireless communication connection (such as Bluetooth, Wi-Fi, 4G / 5G) with the vehicle terminal system and to receive data packets transmitted by the vehicle terminal system.

[0038] The authentication module is used for user identity verification, including facial recognition or fingerprint recognition. When a user makes a report, the user's identity information needs to be verified to ensure that the information of the reporter is true and reliable.

[0039] The directory display and report confirmation interface is used to receive and display the directory information of the evidence package, and provides a one-click report function button for users to initiate a report request after confirmation.

[0040] The data management module is used to store, view, and edit the received packaged data (such as cropping invalid video clips); at the same time, the data management module also records the reporting history information, including the reporting time, reporting type, processing progress, etc., for users to query.

[0041] The encrypted upload module encrypts the data packets transmitted between the vehicle and the mobile app, as well as the reporting requests and data packets transmitted between the mobile app and the traffic monitoring platform's reporting portal. After a user triggers the one-click reporting function, the encrypted data packets are automatically uploaded to the pre-set reporting portal on the traffic monitoring platform, completing the report of the illegal driving behavior. Before uploading the video evidence package, the mobile app automatically blurs and masks the faces of other unrelated vehicles and pedestrians in the video, excluding the target vehicle and the user's own vehicle.

[0042] The following describes the specific implementation of the driving behavior reporting method based on vehicle perception data applied to vehicle terminals, with reference to the embodiments.

[0043] Figure 2 A flowchart illustrating the driving behavior reporting method based on vehicle perception data provided in this application embodiment. Figure 1 ,like Figure 2 As shown, the method may include: S101. Acquire video data and environmental perception data within a preset range of the driving vehicle collected by the vehicle-mounted camera and radar sensor.

[0044] In this embodiment, the vehicle-mounted camera may include at least a forward-facing camera and a surround-view camera. The forward-facing camera covers a preset area in front of the vehicle, with a horizontal field of view generally greater than or equal to 120°, and can completely capture vehicles in adjacent lanes and oncoming lanes. The surround-view camera can be set around the vehicle to cover a preset area around the driver's vehicle, and is used to identify lateral or rearward violations such as cutting in, reversing, and sudden stopping.

[0045] Radar sensors can be millimeter-wave radar, ultrasonic radar, or other types. The radar point cloud data collected by the radar sensors can be mapped to the vehicle's coordinate system after coordinate system transformation. This radar point cloud data serves as environmental perception data, allowing the determination of distances, speeds, and trajectories between the vehicle and surrounding vehicles.

[0046] In some embodiments, video data and environmental perception data collected by vehicle cameras and radar sensors need to be time-aligned.

[0047] S102. Based on video data and environmental perception data, identify whether there are target vehicles with illegal driving behavior within a preset range of the driving vehicle.

[0048] In this embodiment, a standardized violation judgment database is pre-established, which covers common traffic violation types and clearly defines the judgment conditions for various illegal driving behaviors.

[0049] For video data, a multi-target tracking algorithm is used to track surrounding vehicles across frames, constructing a continuous motion trajectory sequence of the surrounding vehicles. Ground markings are identified through image semantic segmentation, and the distance between the center point of the vehicle's bounding box and the nearest marking is calculated using a projection transformation model. Furthermore, the turn signal status of surrounding vehicles can be determined using video data, and the speed and trajectory of surrounding vehicles can be determined using environmental perception data.

[0050] By combining the distance between the center point of the vehicle's boundary frame and the nearest lane marking, the status of the turn signal, the operating speed, and the operating trajectory with the judgment conditions for various illegal driving behaviors, the target vehicle with illegal driving behavior is identified.

[0051] It should be noted that after marking each surrounding vehicle using video data, the environmental perception data of each surrounding vehicle can be determined from the environmental perception data based on the time alignment of the video data and the environmental perception data. This allows the data such as the distance between the center point of the vehicle bounding box of each surrounding vehicle and the nearest lane marking, the turn signal status, the running speed, and the running trajectory to be bound together.

[0052] S103. If a target vehicle with the aforementioned illegal driving behavior is identified, a violation warning message is generated.

[0053] In this embodiment, if a target vehicle with the aforementioned illegal driving behavior is identified, trajectory prompt information is generated. The violation prompt information may include at least: the type of illegal driving behavior and the approximate location of the target vehicle. The violation prompt information is sent to the user through the prompt module on the vehicle.

[0054] The violation notice can be broadcast through the vehicle's voice broadcaster, displayed on the vehicle's central control screen, or broadcast and displayed through a combination of the voice broadcaster and the central control screen.

[0055] S104. In response to the user's confirmation of the violation notification, upload the target video data corresponding to the violation of the target vehicle to the traffic monitoring platform.

[0056] In this embodiment, users are given full choice and control, allowing them to decide whether to report illegal driving behavior. After sending a violation notification to the user, it is determined whether a confirmation report is received from the user within a preset time. If a confirmation report is received, target video data of a preset duration before and after the illegal driving behavior is extracted from the video data, and uploaded to the reporting portal of the traffic monitoring platform along with information such as time and location. For example, target video data between 30 seconds before and 10 seconds after the illegal driving behavior, as well as data on vehicles driving in the wrong direction, can be extracted and packaged.

[0057] In some embodiments, the system may determine whether a user has reported a violation of driving rules in response to a user's voice confirmation.

[0058] In other embodiments, the system can determine whether a user has reported a violation of driving rules in response to a user's triggering action via a reporting control on the central control screen.

[0059] Furthermore, if the user does not confirm the report within the preset time, the target video data will not be extracted from the video data, and a report record cannot be generated.

[0060] The driving behavior reporting method based on vehicle-mounted perception data provided in the above embodiments combines video data and environmental perception data collected by existing cameras and radar sensors in intelligent driving vehicles on the market to identify and report illegal driving behaviors. This forms a mobile "electronic police" network, which can efficiently assist traffic management departments in detecting and promptly resolving traffic violations, better maintaining public transportation safety, and greatly expanding the scope of law enforcement. Furthermore, it allows users to choose whether to report violations while ensuring driving safety, giving users full choice and control.

[0061] In one possible implementation, Figure 3 A flowchart illustrating the driving behavior reporting method based on vehicle perception data provided in this application embodiment. Figure 2 ,like Figure 3 As shown, the process of identifying whether a target vehicle within a preset range exhibits illegal driving behavior based on video data and environmental perception data in step S102 may include: S201. Identify the initial vehicle that contacts the target lane boundary line and the duration of contact with the target lane boundary line based on video data.

[0062] In this embodiment, the vehicle's camera continuously captures road video and performs pixel-level analysis on each frame of the image using a built-in lane line segmentation model to identify the target lane boundary line in each frame of the image. The target lane boundary line can be a double yellow line or a white solid line.

[0063] A vehicle recognition model is used to identify vehicles in each frame of the image, and the identified vehicles are marked with rectangular boxes, with each vehicle assigned a temporary label.

[0064] The geometric relationship between the bounding box of each vehicle and the identified target lane boundary line is calculated, and vehicles whose bounding box edges have pixel-level contact or overlap with the target lane boundary line are identified as initial vehicles.

[0065] The initial vehicle's operating status in the video data is continuously monitored to determine the time when the initial vehicle contacts the target lane boundary line and the time when it stops contacting the target lane boundary line, so as to calculate the duration of the initial vehicle's contact with the target lane boundary line.

[0066] S202. If the time spent in contact with the target lane boundary line exceeds the preset time, the initial vehicle is determined to be the target vehicle that is driving on the line.

[0067] In this embodiment, it is determined whether the duration of the initial vehicle's contact with the target lane boundary line exceeds a preset time. If the duration exceeds the preset time, the initial vehicle's illegal driving behavior is determined to be driving over the line, and the initial vehicle is marked as the target vehicle for illegal driving. If the duration does not exceed the preset time, the initial vehicle is determined not to have engaged in illegal driving behavior.

[0068] In another possible implementation Figure 4 A flowchart illustrating the driving behavior reporting method based on vehicle perception data provided in this application embodiment. Figure 3 ,like Figure 4 As shown, the process of identifying whether a target vehicle within a preset range exhibits illegal driving behavior based on video data and environmental perception data in step S102 may include: S301. Identify the initial vehicle in the intersection's guiding lane and the initial vehicle's turn signal status based on video data.

[0069] In this embodiment, the intersection guide lane refers to a dedicated lane marked in white at the entrance of a level intersection to guide vehicles to travel in a designated direction. It is a lane of limited length located before the stop line at the intersection, and vehicles are prohibited from changing lanes arbitrarily after entering this area.

[0070] In some embodiments, lane lines on the road surface are identified using video data, and when the lane lines change from dashed lines to continuous solid lines, it is determined that the vehicle has entered the intersection guide lane.

[0071] In other embodiments, lane lines and directional arrow patterns on the road surface are identified based on video data to determine whether an intersection guide lane has been entered. The intersection guide lane has directional arrow patterns such as left turn, straight, right turn, and straight and right turn.

[0072] In other embodiments, it can be determined whether an intersection guide lane has been entered based on high-precision map data.

[0073] After determining the direction lane for entering the intersection, the initial vehicles in the direction lane of the intersection in the video data are identified and marked to determine the original direction lane of each initial vehicle. The turn signal status of each initial vehicle is continuously monitored from the video data. The turn signal status is used to indicate the on / off status of the left and right turn signals of each initial vehicle.

[0074] S302. Based on environmental perception data, determine the number of lane lines that the initial vehicle will cross laterally and the direction of crossing.

[0075] In this embodiment, environmental perception data is used to determine whether the lateral speed of each initial vehicle is greater than a preset speed. If the lateral speed is greater than the preset speed, it means that the initial vehicle may be changing lanes. By combining environmental perception data with video data, it is determined whether each initial vehicle has entered the target direction lane from the original direction lane. If each initial vehicle has entered the target direction lane from the original direction lane, the number of lane lines crossed laterally by the initial vehicle is determined.

[0076] The crossing direction is determined based on the positional relationship between the original guiding vehicle and the target guiding lane.

[0077] S303. If the turn signal status and crossing direction of the initial vehicle do not meet the preset status conditions, and the number of lane lines crossed laterally is greater than or equal to the preset number threshold, the initial vehicle is determined to be the target vehicle for cutting in and changing lanes.

[0078] In this embodiment, a legal lane change within the intersection's guide lane requires activating the turn signal in the corresponding direction before the lane change. If the initial vehicle fails to activate its turn signal during the lane change, or if the activated turn signal is inconsistent with the crossing direction, or if the distance between the activated turn signal position and the intersection stop line is less than a preset distance, it is determined that the initial vehicle's turn signal status and crossing direction do not meet the preset status conditions. Based on this, if the number of lane lines crossed laterally is greater than or equal to a preset number threshold, the initial vehicle's illegal driving behavior is determined to be cutting in, and the initial vehicle is marked as the target vehicle for illegal driving; otherwise, it is determined that the initial vehicle does not have illegal driving behavior.

[0079] In another possible implementation Figure 5 A flowchart illustrating the driving behavior reporting method based on vehicle perception data provided in this application embodiment. Figure 4 ,like Figure 5 As shown, the process of identifying whether a target vehicle within a preset range exhibits illegal driving behavior based on video data and environmental perception data in step S102 may include: S401. Determine the driving lanes of other vehicles using video data.

[0080] S402. Determine the speed of other vehicles based on environmental perception data.

[0081] S403. Based on the speed limits of other vehicles' driving lanes and the speeds of other vehicles, identify target vehicles that are speeding or occupying lanes at low speeds.

[0082] In this embodiment, the video data is analyzed at the pixel level to accurately identify the dividing lines of each driving lane and determine the vehicles located in each driving lane, and each vehicle in each driving lane is marked.

[0083] The system calculates the speed of each vehicle based on environmental perception data in each lane, and determines the speed limit of each lane by using traffic signs in high-precision maps or video data. When the speed of a vehicle exceeds the maximum speed limit of the corresponding lane, the vehicle is identified as speeding and marked as the target vehicle for the violation.

[0084] When a vehicle's speed is less than the minimum speed limit for the corresponding lane, the vehicle's illegal driving behavior is determined to be low-speed lane occupation, and the vehicle is marked as the target vehicle for illegal driving.

[0085] In another possible implementation Figure 6 A flowchart illustrating the driving behavior reporting method based on vehicle perception data provided in this application embodiment. Figure 5 ,like Figure 6 As shown, the process of identifying whether a target vehicle within a preset range exhibits illegal driving behavior based on video data and environmental perception data in step S102 may include: S501. Determine the status of traffic lights and the position of stop lines at intersections using video data.

[0086] S502. Based on environmental perception data, a vehicle whose front wheels have crossed the stop line and is in motion when the traffic light at an intersection is red is identified as a target vehicle that has committed the act of running a red light.

[0087] In this embodiment, the video data collected by the forward-facing camera of the driving vehicle is identified to determine the traffic light image area in the video data, and the color of the traffic lights in each direction is determined by a dedicated CNN model to determine the traffic status in each direction.

[0088] The lane detection model is used to identify horizontal white solid lines as stop lines in video data. By transforming the coordinate system, the pixel positions of the stop lines in the image are converted to their precise positions in the real-world coordinate system.

[0089] If the traffic light is red, vehicles approaching the stop line are identified using environmental perception data. By using video data and environmental perception data, it is monitored in real time to see if the front wheels of vehicles approaching the stop line have crossed the stop line and are still moving. If so, the vehicle's illegal driving behavior is determined to be running a red light, and the vehicle is marked as a target vehicle with illegal driving behavior.

[0090] In some embodiments, the driving direction of the vehicle is determined based on environmental perception data. If the vehicle's direction is the direction corresponding to the red light, the illegal driving behavior of the vehicle is determined to be running a red light.

[0091] The above embodiments provide a driving behavior reporting method based on vehicle perception data, which identifies illegal driving behavior of vehicles through video data and environmental perception data, thereby improving the accuracy of illegal driving behavior identification.

[0092] In some embodiments, in addition to the aforementioned illegal driving behaviors, illegal driving behaviors such as illegal parking, driving against traffic, and falling objects can also be identified based on video data and environmental perception data. This embodiment will not provide further explanation in this regard.

[0093] In one possible implementation, the process of generating a violation warning message if the target vehicle with the aforementioned illegal driving behavior is identified in step S103 may include: If a target vehicle with illegal driving behavior is identified, a violation warning message will be generated and displayed based on the driving status of the vehicle, using a prompting method that matches the driving status.

[0094] In this embodiment, a tiered prompting strategy is adopted to avoid interfering with the user's attention. The prompting level can be determined based on the driving status of the vehicle. For example, if the vehicle is driving at low speed, a level one prompt is used; if the vehicle is driving at high speed, a level two prompt is used. If the current driving section is unobstructed, a level one prompt is used; if the current driving section is congested, a level two prompt is used. If the user is not looking at the central control screen, a level one prompt is used; if the user's gaze is on the central control screen, a level two prompt is used. The central control screen needs to have a gaze detection mechanism.

[0095] The first-level prompt method is a lightweight and unobstructed prompt, which pops up a small icon in the corner of the central control screen, such as "Violation detected", accompanied by a slight sound prompt, such as a short "beep" or "The vehicle on the left has illegally cut in, please give way", without forcing interaction and without obstructing the driver's view.

[0096] The secondary prompt mode is a full prompt mode, automatically unfolding a simple card-style pop-up window on the central control screen. The pop-up window is located at the edge of the screen and does not obstruct navigation or key driving information. The pop-up window content includes: the type of violation such as "cutting in" or "driving over the line", a thumbnail of the violating vehicle (automatically captured), the time of occurrence, and the location.

[0097] When the driver clicks the prompt card, a pop-up window appears on the instrument panel asking "Report?" with a yes or no option, requesting user confirmation. The interface design follows the principles of "minimal operation, undoability, and supplementability." The interface content includes: a view of the violating vehicle, a preview of a photo or short video automatically captured by the central display system of the moment of the violation, a red-framed mark on the violating vehicle, the automatic identification result of the violation, and the type of violation determined by the system. Compliant vehicles are automatically blurred, and the driver can manually modify the violation type; for example, if the system misjudges it as "crossing the line," the driver can change it to "normal lane change." Reporting options include: confirm report, cancel report, and view details (including trajectory, speed, and other data). After the user selects "confirm report," the confirmation instruction is sent to the illegal driving behavior judgment module. If the driver does not select anything within 1 minute, the driver is considered to have chosen not to report.

[0098] The driving behavior reporting method based on vehicle perception data provided in the above embodiments generates and displays violation notification information using a prompting method that matches the driving status, so as to achieve violation notification without interfering with the user's driving and ensure driving safety.

[0099] In one possible implementation, the method may further include: In response to a user's triggering of the in-vehicle reporting button after identifying a violation of driving rules, the system retrieves video data from the in-vehicle camera, including video data of a preset duration before and after the user triggers the reporting button, and uploads it to the traffic monitoring platform.

[0100] In this embodiment, when a user discovers a vehicle ahead engaging in illegal driving behavior, such as a truck with loosely secured cargo, dropping cargo, changing lanes without using turn signals, continuously overtaking, suddenly stopping in the fast lane, reversing, or driving against traffic, the user can manually trigger a report by pressing a physical switch or a soft switch on the vehicle's central control screen. Upon triggering, the illegal driving behavior judgment module immediately saves multiple video feeds or a single video feed from the selected direction for the period 30 seconds before and 10 seconds after the switch is pressed.

[0101] The driving behavior reporting method based on vehicle perception data provided in the above embodiments enables users to actively report illegal driving behaviors through the vehicle reporting button.

[0102] In one possible implementation, the process of S104, which responds to the user's confirmation of the violation notification and uploads the target video data corresponding to the violation of the target vehicle to the traffic monitoring platform, may include: In response to the user's confirmation of the violation notification, the target video data corresponding to the violation of the target vehicle is uploaded to the mobile terminal bound to the vehicle terminal. The mobile terminal then blurs the non-target vehicles and pedestrians in the target video data and uploads the blurred target video data to the traffic monitoring platform.

[0103] In this embodiment, the system can be manually triggered by the user or automatically identified by the user-confirmed report of illegal driving. The system processes the target video clips according to the technical standards required by the traffic supervision platform, such as video file format and data structure, and redacts the normal driving vehicles. At the same time, it binds the video clips with information such as time, location, license plate number, VIN code, and violation type code, and encrypts and packages them into an evidence package, which is then temporarily stored in the protected partition of the vehicle's storage device.

[0104] After completing the driving task, the user opens the mobile app. The app automatically syncs a new list of evidence packages from the vehicle's infotainment system via Bluetooth / 4G / Wi-Fi. The user can preview videos by clicking on the list. The evidence packages are transmitted via a secure channel to the mobile app linked to the vehicle's subsystem for playback. The app automatically blurs license plates of other vehicles and pedestrians. For each evidence package, the user must manually select and confirm it, then click the "One-Click Report" switch to report it. The app verifies the user's identity using fingerprint or facial recognition. Once confirmed, the app uploads the evidence package to the designated traffic monitoring platform of the traffic management department via an encrypted network.

[0105] Furthermore, the app receives feedback from the traffic monitoring platform regarding the processing status of reported information, and users can click to view the progress of their reported information processing.

[0106] The driving behavior reporting method based on vehicle perception data provided in the above embodiments adopts the "vehicle-side storage-manual confirmation-encrypted upload" mode. From the physical switch to the final upload, the driver is given control over the entire chain, eliminating the privacy and information security risks that automatic upload may bring, realizing local data encryption and transmission encryption, and strictly adhering to the bottom line of information security.

[0107] This application utilizes a vehicle-mounted fixed camera to capture stable, professional-looking footage, automatically binding precise time and location information to form a complete chain of evidence that meets the requirements. This significantly increases the acceptance rate of reports, encourages professional drivers to become "traffic safety assistants," and creates a new pattern of "collective prevention and control" in traffic governance. It effectively deters illegal driving behaviors and improves road safety. The system design fully complies with relevant laws and regulations such as the Personal Information Protection Law, and ensures the legality and compliance of reporting behavior through privacy masking and selective reporting.

[0108] Based on the above method embodiments, this application also provides a driving behavior reporting device based on vehicle perception data, which is applied to vehicle terminals. Figure 7 This is a schematic diagram of the structure of the driving behavior reporting device based on vehicle perception data provided in the embodiments of this application, as shown below. Figure 7 As shown, the device may include: Data acquisition module 601 is used to acquire video data and environmental perception data within a preset range of the driving vehicle collected by the vehicle-mounted camera and radar sensor; The vehicle recognition module 602 is used to identify whether a target vehicle with illegal driving behavior is within a preset range based on video data and environmental perception data. Information prompt module 603 is used to generate violation prompt information if a target vehicle with illegal driving behavior is identified; The video reporting module 604 is used to respond to the user's confirmation of the violation prompt information and upload the target video data corresponding to the violation driving behavior of the target vehicle to the traffic monitoring platform.

[0109] Optionally, the vehicle recognition module 602 is specifically used to identify the initial vehicle that has contacted the target lane boundary line and the duration of contact with the target lane boundary line based on video data; if the duration of contact with the target lane boundary line exceeds a preset duration, the initial vehicle is determined to be the target vehicle that has been driving over the line.

[0110] Optionally, the vehicle recognition module 602 is specifically used to identify the initial vehicle in the intersection's guide lane and the initial vehicle's turn signal status based on video data; determine the number and direction of lane lines crossed laterally by the initial vehicle based on environmental perception data; if the initial vehicle's turn signal status and crossing direction do not meet preset conditions, and the number of lane lines crossed laterally is greater than or equal to a preset threshold, determine that the initial vehicle is the target vehicle for cutting in and changing lanes.

[0111] Optionally, the vehicle recognition module 602 is specifically used to determine the driving lane of other vehicles through video data; determine the driving speed of other vehicles based on environmental perception data; and determine the target vehicle with speeding or low-speed lane-occupancy behavior based on the speed limit of the driving lane of other vehicles and the driving speed of other vehicles.

[0112] Optionally, the vehicle recognition module 602 is specifically used to determine the traffic light status and stop line position at the intersection through video data; and to determine, through environmental perception data, that a vehicle whose front wheels have crossed the stop line and is in motion when the traffic light at the intersection is red is the target vehicle for running a red light.

[0113] Optionally, the information prompting module 603 is specifically used to generate and display violation prompt information based on the driving status of the target vehicle and a prompting method that matches the driving status if a target vehicle with illegal driving behavior is identified.

[0114] Optionally, the video reporting module 604 is also used to respond to the user's triggering operation of the in-vehicle reporting button after recognizing the illegal driving behavior, and to obtain video data of a preset duration before and after the user triggers the in-vehicle reporting button from the video data captured by the in-vehicle camera and upload it to the traffic supervision platform.

[0115] Optionally, the video reporting module 604 is specifically used to respond to the user's confirmation operation of the violation prompt information, and upload the target video data corresponding to the violation driving behavior of the target vehicle to the mobile terminal bound to the vehicle terminal, so that the mobile terminal can blur the non-target vehicles and pedestrians in the target video data, and then upload the blurred target video data to the traffic supervision platform through the mobile terminal.

[0116] The above-described device is used to execute the method provided in the foregoing embodiments, and its implementation principle and technical effect are similar, so they will not be described again here.

[0117] These modules can be one or more integrated circuits configured to implement the above methods, such as one or more Application Specific Integrated Circuits (ASICs), one or more microprocessors, or one or more Field Programmable Gate Arrays (FPGAs). Alternatively, when a module is implemented using processing element scheduler code, the processing element can be a general-purpose processor, such as a Central Processing Unit (CPU) or other processor capable of calling program code. Furthermore, these modules can be integrated together as a system-on-a-chip (SOC).

[0118] Figure 8 This is a schematic diagram of the vehicle-mounted terminal provided in the embodiments of this application, as shown below. Figure 8As shown, the vehicle-mounted terminal 700 may include a processor 701, a storage medium 702, and a bus. The storage medium 702 stores program instructions executable by the processor 701. When the vehicle-mounted terminal 700 is running, the processor 701 communicates with the storage medium 702 via the bus, and the processor 701 executes the program instructions to perform the above-described method embodiment. The specific implementation and technical effects are similar and will not be described in detail here.

[0119] Optionally, this application also provides a computer-readable storage medium storing a computer program, which is executed by a processor to perform the above-described method embodiments.

[0120] In the several embodiments provided in this application, it should be understood that the disclosed apparatus and methods can be implemented in other ways. For example, the apparatus embodiments described above are merely illustrative; for instance, the division of units is only a logical functional division, and in actual implementation, there may be other division methods. For example, multiple units or components may be combined or integrated into another system, or some features may be ignored or not executed. Furthermore, the coupling or direct coupling or communication connection shown or discussed may be through some interfaces; the indirect coupling or communication connection between apparatuses or units may be electrical, mechanical, or other forms.

[0121] The units described as separate components may or may not be physically separate. The components shown as units may or may not be physical units; that is, they may be located in one place or distributed across multiple network units. Some or all of the units can be selected to achieve the purpose of this embodiment according to actual needs.

[0122] Furthermore, the functional units in the various embodiments of this application can be integrated into one processing unit, or each unit can exist physically separately, or two or more units can be integrated into one unit. The integrated unit can be implemented in hardware or in a combination of hardware and software functional units.

[0123] The integrated units implemented as software functional units described above can be stored in a computer-readable storage medium. These software functional units, stored in a storage medium, include several instructions to cause a computer device (which may be a personal computer, server, or network device, etc.) or processor to execute some steps of the methods described in the various embodiments of this application. The aforementioned storage medium includes various media capable of storing program code, such as USB flash drives, portable hard drives, read-only memory (ROM), random access memory (RAM), magnetic disks, or optical disks.

[0124] The above are merely specific embodiments of this application, but the scope of protection of this application is not limited thereto. Any variations or substitutions that can be easily conceived by those skilled in the art within the scope of the technology disclosed in this application should be included within the scope of protection of this application. Therefore, the scope of protection of this application should be determined by the scope of the claims.

Claims

1. A method for reporting driving behavior based on vehicle-mounted perception data, characterized in that, Applied to vehicle-mounted terminals, the method includes: Acquire video data and environmental perception data within a preset range of the driving vehicle collected by in-vehicle cameras and radar sensors; Based on the video data and the environmental perception data, identify whether there are target vehicles with illegal driving behavior within a preset range of the driving vehicle; If a target vehicle exhibiting the aforementioned illegal driving behavior is identified, a violation notification message is generated. In response to the user's confirmation of the violation notification, the target video data corresponding to the violation of the target vehicle is uploaded to the traffic monitoring platform.

2. The method as described in claim 1, characterized in that, The step of identifying whether a target vehicle with illegal driving behavior is within a preset range of the driving vehicle based on the video data and the environmental perception data includes: The video data is used to identify the initial vehicle that made contact with the target lane boundary line and the duration of contact with the target lane boundary line. If the duration of contact with the target lane boundary line exceeds a preset duration, the initial vehicle is determined to be the target vehicle that is driving over the line.

3. The method as described in claim 1, characterized in that, The step of identifying whether a target vehicle with illegal driving behavior is within a preset range of the driving vehicle based on the video data and the environmental perception data includes: The video data is used to identify the initial vehicle in the intersection's guide lane and the turn signal status of the initial vehicle. Based on the environmental perception data, the number of lane lines that the initial vehicle crosses laterally and the direction of crossing are determined; If the turn signal status and crossing direction of the initial vehicle do not meet the preset status conditions, and the number of lane lines crossed laterally is greater than or equal to a preset number threshold, the initial vehicle is determined to be the target vehicle for cutting in and changing lanes.

4. The method as described in claim 1, characterized in that, The step of identifying whether a target vehicle with illegal driving behavior is within a preset range of the driving vehicle based on the video data and the environmental perception data includes: The video data is used to determine the driving lanes of other vehicles; The driving speed of the other vehicles is determined based on the environmental perception data; Based on the speed limit of the lane in which the other vehicles are traveling and the speed of the other vehicles, the target vehicle with speeding or low-speed lane occupation behavior is identified.

5. The method as described in claim 1, characterized in that, The step of identifying whether a target vehicle with illegal driving behavior is within a preset range of the driving vehicle based on the video data and the environmental perception data includes: The traffic light status and stop line position at the intersection are determined using the video data. Based on the environmental perception data, it is determined that a vehicle whose front wheels have crossed the stop line and is in motion when the traffic light at the intersection is red is the target vehicle for running a red light.

6. The method as described in claim 1, characterized in that, If a target vehicle exhibiting the aforementioned illegal driving behavior is identified, a violation notification message is generated, including: If a target vehicle with the aforementioned illegal driving behavior is identified, the violation warning information is generated and displayed according to the driving status of the vehicle, using a prompting method that matches the driving status.

7. The method as described in claim 1, characterized in that, The method further includes: In response to a user triggering the in-vehicle reporting button after recognizing a violation of driving rules, video data of a preset duration before and after the user triggers the in-vehicle reporting button is obtained from the video data captured by the in-vehicle camera and uploaded to the traffic monitoring platform.

8. The method as described in claim 1, characterized in that, The step of responding to the user's confirmation of the violation notification information by uploading the target video data corresponding to the target vehicle's illegal driving behavior to the traffic monitoring platform includes: In response to the user's confirmation of the violation notification, the target video data corresponding to the violation of the target vehicle is uploaded to the mobile terminal bound to the vehicle terminal. The mobile terminal then blurs the non-target vehicles and pedestrians in the target video data and uploads the blurred target video data to the traffic monitoring platform.

9. A driving behavior reporting device based on vehicle-mounted perception data, characterized in that, The device, applied to an in-vehicle terminal, includes: The data acquisition module is used to acquire video data and environmental perception data within a preset range of the driving vehicle collected by the vehicle-mounted camera and radar sensor; The vehicle recognition module is used to identify, based on the video data and the environmental perception data, whether there is a target vehicle with illegal driving behavior within a preset range of the driving vehicle; The information prompt module is used to generate violation prompt information if a target vehicle with the aforementioned illegal driving behavior is identified; The video reporting module is used to respond to the user's confirmation of the violation prompt information and upload the target video data corresponding to the target vehicle's illegal driving behavior to the traffic monitoring platform.

10. A vehicle-mounted terminal, characterized in that, include: The system includes a processor, a storage medium, and a bus. The storage medium stores program instructions executable by the processor. When the vehicle terminal is running, the processor communicates with the storage medium via the bus. The processor executes the program instructions to perform the steps of the driving behavior reporting method based on vehicle perception data as described in any one of claims 1 to 8.

Images