Traffic illegal behavior reporting method and device, vehicle and medium

Abstract

The invention relates to the field of safe driving, and particularly discloses a traffic illegal behavior reporting method and device, a vehicle and a medium, and the method comprises the steps: obtaining discrimination data which comprises at least one of user expression data, vehicle driving data, in-vehicle voice data and in-vehicle key data; in response to the judgment that the data meets the evidence obtaining triggering condition, obtaining vehicle exterior video data of a preset historical duration; identifying the video data outside the vehicle to obtain illegal behavior information; and uploading the illegal behavior information to a reporting platform based on the current position of the vehicle. By acquiring the expression data of the user, whether traffic illegal behaviors exist or not can be judged from the emotion dimension of the driver, so that the video data outside the vehicle can be acquired in time for further recognition, illegal behavior information is effectively acquired, and the illegal behavior information is accurately uploaded to a reporting platform based on the current position of the vehicle; the method is helpful for improving the reporting efficiency and accuracy of traffic illegal behaviors and maintaining a good traffic order.

Description

Technical Field

[0001] This application relates to the field of safe driving, specifically to a method, device, vehicle, and medium for reporting traffic violations. Background Technology

[0002] When reporting traffic violations, existing dashcams or in-vehicle systems require users to manually replay, capture, identify license plates, and upload the report, a cumbersome process. Furthermore, the system cannot detect "when a traffic violation might occur or has already occurred," and cannot automatically save evidence at critical moments. Even if a collision is triggered, it only applies to accident scenarios and cannot cover non-collision violations. Summary of the Invention

[0003] In view of the above problems, this disclosure provides a method, device, vehicle, and medium for reporting traffic violations that overcomes or at least partially solves the above problems. The technical solution is as follows: A method for reporting traffic violations, characterized by comprising: acquiring discrimination data, the discrimination data including at least one of user facial expression data, vehicle driving data, in-vehicle voice data, and in-vehicle button data; in response to the discrimination data meeting the evidence collection triggering conditions, acquiring vehicle exterior video data of a preset historical duration; identifying the vehicle exterior video data to obtain violation information; and uploading the violation information to a reporting platform based on the vehicle's current location.

[0004] This application utilizes real-time collection and analysis of driver facial expression data to monitor driving behavior from an emotional state perspective, effectively identifying potential traffic violations by other vehicles within the driver's line of sight. Upon detecting abnormal emotional indicators, the system immediately triggers the onboard camera to automatically record video data of the external road environment. Intelligent algorithms then perform in-depth analysis of the video content to further confirm the existence of violations and accurately extract relevant evidence. Simultaneously, combined with vehicle positioning functionality, the system can obtain the vehicle's current location in real time and accurately upload information such as the time and location of the violation, along with video evidence, to the traffic violation reporting platform. This process not only significantly improves the efficiency of reporting traffic violations and the reliability of evidence but also provides traffic management departments with a more scientific and objective basis for enforcement, contributing to a more orderly and safer road traffic environment.

[0005] In one example, the step of obtaining vehicle exterior video data of a preset historical duration in response to the discrimination data meeting the evidence triggering condition specifically includes: determining the current emotion type of the user inside the vehicle based on the user's facial expression data; and obtaining vehicle exterior video data of a preset historical duration in response to the current emotion type being a preset emotion type.

[0006] In determining whether the data meets the evidence collection triggering conditions, this application uses the user's facial expression data to judge the user's current emotion. When the user's current emotion type matches a preset specific emotion type, the system will automatically acquire a preset historical duration of external video data. This design allows the system to keenly capture the driver's emotional reactions, such as surprise or anger, that may arise from observing traffic violations, and to quickly initiate the evidence collection process accordingly.

[0007] In one example, determining the current emotion type of a user in the vehicle based on the user's facial expression data specifically includes: determining a preset recognition model group, which at least includes a geometric rule determination model and a convolutional neural network model; inputting the user's facial expression data into the geometric rule determination model to obtain a first recognition result; when the confidence level of the first recognition result for a preset emotion type is higher than a first preset confidence threshold, the current emotion type is the preset emotion type; when the confidence level of the first recognition result for a preset emotion type is not higher than the first preset confidence threshold, inputting the user's facial expression data into the convolutional neural network model to obtain a second recognition result; when the confidence level of the second recognition result for a preset emotion type is higher than a second preset confidence threshold, the current emotion type is the preset emotion type.

[0008] Furthermore, to ensure the accuracy and robustness of emotion recognition, this application employs a multi-model fusion emotion recognition strategy. Specifically, the system first uses a geometric rule-based judgment model to perform preliminary analysis of user facial expression data. This model can quickly identify some obvious emotional features, such as upturned corners of the mouth and furrowed brows. When the preliminary analysis result indicates that the confidence level of a preset emotion type is higher than a first preset confidence threshold, the system determines the current emotion type to be that preset emotion type and triggers the video data acquisition process.

[0009] However, since geometric rule-based judgment models may have limitations in handling complex facial expressions or subtle emotional changes, this application also introduces a convolutional neural network (CNN) model as a supplement. When the output of the geometric rule-based judgment model does not meet the confidence requirements, the system automatically inputs the user's facial expression data into the CNN model for in-depth analysis. By learning from a large number of facial expression data samples, the CNN model can more accurately identify complex emotional states, such as anxiety and tension. When the confidence of the CNN model's recognition result for a preset emotion type is higher than a second preset confidence threshold, the system will also determine the current emotion type as that preset emotion type and trigger the corresponding video data acquisition process. This multi-model fusion strategy effectively improves the accuracy and reliability of emotion recognition, providing a more solid basis for subsequent judgments of traffic violations.

[0010] In one example, the step of acquiring exterior video data of a preset historical duration in response to the discrimination data meeting the evidence triggering condition specifically includes: acquiring exterior video data of a preset historical duration in response to the vehicle's speed reduction value exceeding a first acceleration threshold, or lateral acceleration exceeding a second acceleration threshold, or detection of a lateral vehicle distance below a preset distance threshold and a relative speed exceeding a preset speed threshold; and / or acquiring exterior video data of a preset historical duration in response to the user's volume increase exceeding a preset percentage threshold within a preset duration, or detection of a first type of keyword in the user's voice; and / or acquiring exterior video data of a preset historical duration in response to receiving a user actively pressing a preset button.

[0011] In addition to triggering methods based on user facial expression data, this application also provides a variety of other evidence-gathering triggering conditions. For example, when the vehicle's speed reduction value within a preset time period exceeds a first acceleration threshold, or the lateral acceleration exceeds a second acceleration threshold, or when a lateral vehicle is detected to be less than a preset distance threshold and its relative speed exceeds a preset speed threshold, the system will automatically acquire exterior video data for a preset historical time period. These conditions are mainly aimed at driving scenarios involving emergency avoidance or potential dangers, enabling timely capture of possible traffic violations. Furthermore, the system also monitors changes in the user's volume and voice content within the vehicle. When the user's volume increases by more than a preset percentage threshold within a preset time period, or when the user's voice contains specific types of keywords (such as "illegal lane change," "illegal parking," "high beams," etc.), the system will also trigger the video data acquisition process. These conditions reflect the driver's emotional reactions, such as tension and urgency, that may arise from observing dangerous situations or violations, helping the system to more comprehensively capture traffic violations. In addition, this application also supports user-initiated video data acquisition. When a user discovers a traffic violation, they only need to press a preset button, and the system can immediately acquire exterior video data for a preset historical time period. This design gives users greater autonomy, making the reporting process more flexible and convenient.

[0012] In one example, the step of identifying the external video data to obtain information on illegal behaviors specifically includes: identifying the external video data to obtain a vehicle detection frame, a lane line segmentation mask, and a drivable area mask; determining the information on illegal behaviors in the external video data based on the vehicle detection frame, the lane line segmentation mask, the drivable area mask, and preset judgment rules; the illegal behaviors include at least one of illegal lane changing, occupying the emergency lane, and driving in the wrong direction.

[0013] This application employs advanced computer vision technology when recognizing vehicle exterior video data. The system first preprocesses the video frames to improve image quality and reduce noise interference. Then, deep learning algorithms are used to detect vehicles in the video frames, generating vehicle detection boxes to accurately identify each vehicle in the video. Simultaneously, the system segments lane lines to obtain lane line segmentation masks, clearly defining road boundaries and driving directions. Furthermore, by generating drivable area masks, the system can further distinguish between drivable and non-drivable areas, providing crucial evidence for subsequent violation judgment. Based on this mask information and preset judgment rules, the system can automatically identify traffic violations in the video data, such as illegal lane changes, illegal parking, failure to yield to pedestrians, running red lights, misuse of high beams, speeding, cutting in line, and driving against traffic. These judgment rules cover various common traffic violation scenarios, ensuring the system can comprehensively and accurately capture violations.

[0014] In one example, determining the illegal behavior information in the external video data based on the vehicle detection box, lane line segmentation mask, drivable area mask, and preset judgment rules specifically includes: responding to the presence of a second type of keyword in the user's voice, determining the type of illegal behavior corresponding to the second type of keyword; determining the target judgment rule corresponding to the type of illegal behavior, and determining the illegal behavior information in the external video data based on the vehicle detection box, lane line segmentation mask, drivable area mask, and target judgment rule.

[0015] To further improve the accuracy of the system in identifying traffic violations, this application introduces a user voice interaction mechanism. Specifically, when the system detects that the user's voice contains second-type keywords (such as "crossing solid lines" or "using the emergency lane," which directly describe the violation), it immediately analyzes the violation type corresponding to that keyword. Subsequently, the system retrieves the target judgment rule matching the violation type from a preset judgment rule library. These rules may involve multi-dimensional parameters such as vehicle position, driving trajectory, and lane line relationship. Finally, the system combines visual information such as vehicle detection boxes, lane line segmentation masks, and drivable area masks with the target judgment rules to perform in-depth analysis of the external video data, thereby accurately pinpointing the specific time, location, and behavioral characteristics of the violation. This fusion processing of voice and visual information not only enhances the system's adaptability to complex traffic scenarios but also significantly improves the recall and accuracy of violation identification.

[0016] In one example, uploading the violation information to the reporting platform based on the vehicle's current location specifically includes: saving the violation information in a preset output format; matching the reporting platform based on the vehicle's current location and obtaining the reporting platform's upload protocol; and uploading the violation information based on the mapping template corresponding to the upload protocol.

[0017] In the process of uploading violation information to the reporting platform, this application first standardizes the acquired violation information and saves it in a preset output format. This format typically includes key information such as the time, location, type of violation, and video evidence to ensure the integrity and consistency of the information. Next, the system utilizes the vehicle's built-in positioning function to obtain the vehicle's current location in real time and matches the appropriate reporting platform based on the geographic location information. Different regions may use different traffic violation reporting platforms, and the system needs to automatically identify and adapt to the upload protocols of these platforms. After matching the correct reporting platform, the system further obtains the platform's upload protocol, which specifies details such as the data upload format, encryption method, and communication protocol. Finally, the system accurately uploads the standardized violation information to the reporting platform according to the mapping template corresponding to the upload protocol. This process not only automates information upload but also ensures data compatibility and security across different platforms, providing traffic management departments with timely and reliable evidence of violations.

[0018] A traffic violation reporting device includes: a discrimination data acquisition module for acquiring discrimination data, the discrimination data including at least one of user facial expression data, vehicle driving data, in-vehicle voice data, and in-vehicle button data; an evidence collection trigger judgment module for acquiring vehicle exterior video data of a preset historical duration in response to the discrimination data meeting the evidence collection trigger condition; a violation recognition module for recognizing the vehicle exterior video data to obtain violation information; and a violation upload module for uploading the violation information to a reporting platform based on the vehicle's current location.

[0019] A vehicle includes: at least one processor; and a memory communicatively connected to the at least one processor; wherein the memory stores instructions executable by the at least one processor, the instructions being executed by the at least one processor to enable the at least one processor to perform the traffic violation reporting method described in any of the above examples.

[0020] A computer-readable storage medium storing computer-executable instructions configured to perform the traffic violation reporting method described in any of the above examples.

[0021] By employing the aforementioned technical solutions, this disclosure provides a method, device, vehicle, and medium for reporting traffic violations. Through a multi-dimensional data acquisition mechanism, this application can comprehensively capture various types of information that may indicate traffic violations. Specifically, user facial expression data reflects the driver's emotional state; abnormal emotions such as anger or tension may suggest dangerous driving behavior. Vehicle driving data monitors the vehicle's driving status in real time, such as speed, acceleration, and lateral displacement, helping to detect violations such as speeding and sudden lane changes. In-vehicle voice data captures the conversation between the driver and passengers; arguments or dangerous driving commands may be associated with traffic violations. In-vehicle button data records the driver's operational behavior, such as frequent switching of lights or abnormal use of the horn, providing clues for judging violations.

[0022] When the data meets the evidence-gathering trigger conditions, the system automatically acquires a preset historical duration of external video data. This process is achieved through intelligent algorithms, which can accurately determine when to record external conditions, avoiding the storage of invalid data and improving storage efficiency. The acquired external video data will undergo professional recognition processing, utilizing advanced image recognition and computer vision technologies to accurately analyze vehicles, lane lines, and drivable areas in the video, thereby accurately obtaining information on illegal behaviors, including common violations such as crossing solid lines to change lanes, occupying emergency lanes, and driving against traffic.

[0023] Finally, based on the vehicle's current location, the system accurately uploads the violation information to the corresponding reporting platform. Through deep integration with map positioning services, the system can quickly determine the vehicle's location and match it with the appropriate reporting platform, while adhering to the platform's upload protocol to ensure smooth information transmission. This entire process automates and intelligently reports traffic violations, significantly improving efficiency and accuracy, and contributing to maintaining good traffic order.

[0024] The above description is merely an overview of the technical solution disclosed herein. In order to better understand the technical means of this disclosure and to implement it in accordance with the contents of the specification, and to make the above and other objects, features and advantages of this disclosure more apparent and understandable, specific embodiments of this disclosure are described below. Attached Figure Description

[0025] Various other advantages and benefits will become apparent to those skilled in the art upon reading the following detailed description of preferred embodiments. The accompanying drawings are for illustrative purposes only and are not intended to limit the scope of this disclosure. Furthermore, the same reference numerals denote the same parts throughout the drawings. In the drawings: Figure 1 A flowchart illustrating a method for reporting traffic violations according to an embodiment of this disclosure is shown; Figure 2 A schematic diagram of the structure of a traffic violation reporting device according to an embodiment of this disclosure is shown; Figure 3 A schematic diagram of the structure of a vehicle according to an embodiment of the present disclosure is shown. Detailed Implementation

[0026] Exemplary embodiments of the present disclosure will now be described in more detail with reference to the accompanying drawings. While exemplary embodiments of the present disclosure are shown in the drawings, it should be understood that the present disclosure may be implemented in various forms and should not be limited to the embodiments set forth herein. Rather, these embodiments are provided so that this disclosure will be thorough and complete, and will fully convey the scope of the disclosure to those skilled in the art.

[0027] The technical solutions provided by the various embodiments of this application are described in detail below with reference to the accompanying drawings.

[0028] During driving, almost every driver has encountered uncivilized driving behaviors, such as cutting in line, using the emergency lane to overtake, frequently changing lanes between multiple lanes, and interfering with vehicles traveling straight while changing lanes. These behaviors not only seriously disrupt traffic order but also easily trigger negative emotions in drivers and can even directly lead to traffic accidents. To effectively alleviate drivers' anger and anxiety caused by such behaviors, the key lies in establishing a convenient and efficient reporting mechanism that allows drivers to easily report violations with a single click, ensuring that violators are punished according to the law, thereby maintaining road fairness and safety.

[0029] However, currently available dashcams and in-vehicle intelligent systems still have significant functional limitations. Users wishing to report violations must manually replay recordings, extract video clips, identify license plate numbers, and complete the upload process step by step. This cumbersome and complex process greatly reduces users' willingness to report violations. Therefore, high-frequency violations such as cutting in line and changing lanes over solid lines are rarely effectively recorded and reported.

[0030] Furthermore, existing systems lack the intelligent perception capability to detect the timing of traffic violations, and cannot automatically save crucial evidence immediately after an incident. Although some devices have collision-triggered storage capabilities, these are primarily applicable to accident records and cannot cover violations that did not involve physical collisions, such as unauthorized lane changes or malicious cutting off of other vehicles.

[0031] While driver monitoring systems have achieved some success in identifying fatigued driving, their functionality has not yet expanded to include the correlation analysis between emotions and external risks. The system fails to capture the strong emotional reactions drivers experience when encountering dangerous driving behaviors, such as sudden anger or shock, thus missing the optimal opportunity to automatically trigger evidence preservation. This disconnect between emotion and risk limits the system's overall effectiveness in prevention and evidence collection.

[0032] Therefore, such as Figure 1 The diagram illustrates a flowchart of a traffic violation reporting method provided in one or more embodiments of this specification. This method can be applied to different types of vehicles, such as private cars, taxis, and buses. The process can be executed by a computing device in the relevant field, which can be a computing terminal installed in the vehicle or a server deployed in the cloud. When the computing device is installed in the vehicle, the entire data processing of the traffic violation reporting method provided in this application is completed on the vehicle side, ensuring user privacy and compliance. Furthermore, end-to-end deployment avoids network processing and cloud model token consumption, reducing cabin CPU, memory usage, and bandwidth consumption.

[0033] Certain input parameters or intermediate results in the process can be manually adjusted to help improve accuracy. The analysis method involved in the embodiments of this application can be implemented by a terminal device or a server. The server can be a single device or a system composed of multiple devices, i.e., a distributed server; this application does not specifically limit its implementation. For ease of understanding and description, the following embodiments all use an in-vehicle terminal as an example for detailed description.

[0034] like Figure 1 As shown in the embodiment of this application, a method for reporting traffic violations is provided, including: S101: Obtain discrimination data, wherein the discrimination data includes at least one of user facial expression data, vehicle driving data, in-vehicle voice data, and in-vehicle button data.

[0035] First, the in-vehicle terminal acquires discrimination data, which encompasses information from multiple dimensions, including user facial expression data, vehicle driving data, in-vehicle voice data, and in-vehicle button data. This discrimination data is primarily used to determine whether traffic violations have occurred. Specifically, user facial expression data uses facial recognition technology to capture subtle changes in the driver's facial expressions, such as anger, anxiety, or distraction. These emotional states are often closely related to dangerous driving behaviors. For example, when a driver displays an angry expression, it may indicate the presence of traffic violations in their vicinity, such as cutting in line or speeding.

[0036] Vehicle driving data is collected in real time by onboard sensors, including key parameters such as vehicle speed, acceleration, steering angle, and braking frequency. This data can intuitively reflect the vehicle's driving status and help the system identify evasive maneuvers such as emergency lane changes.

[0037] In-vehicle voice data is equally important, as it captures the content of conversations between the driver and passengers. Through voice recognition technology, the system can analyze keywords and emotional tendencies in the dialogue, such as accusations of dangerous driving. This information helps the system detect when a driver or passenger loses control due to traffic violations by other vehicles.

[0038] The in-car button data records the driver's actions, such as frequently switching lights and using the horn abnormally. These actions are often related to the driver's current driving state and can provide additional clues for judging traffic violations. For example, frequently switching lights may mean that the driver is reminding the vehicle in front to stop dangerous driving behavior, while abnormal use of the horn may indicate the driver's dissatisfaction or anger towards the vehicle in front that is violating the law.

[0039] User facial expression data can be captured in real time using a camera pre-installed inside the vehicle. This camera can be mounted on the dashboard directly in front of the driver to record changes in the driver's facial expressions from the optimal angle. To ensure accurate recognition of expressions under various lighting conditions, the camera can be equipped with high dynamic range imaging technology, which can automatically adjust exposure and contrast to avoid loss of facial features due to strong light or backlighting.

[0040] Vehicle driving data acquisition relies on an onboard sensor network, including but not limited to speed sensors, accelerometers, gyroscopes, and steering angle sensors. Speed ​​sensors, mounted on the wheels or driveshaft, measure vehicle speed in real time. Accelerometers monitor acceleration and deceleration, helping the system determine if dangerous behaviors such as sudden acceleration or braking are occurring. Gyroscopes and steering angle sensors work together to accurately record the vehicle's steering angle and trajectory, providing crucial data support for identifying avoidance maneuvers such as sudden braking and emergency evasion. All sensor data is transmitted in real time to the central processing unit via the onboard CAN bus, ensuring data timeliness and accuracy.

[0041] In-vehicle voice data is collected via an onboard microphone array, typically composed of multiple high-sensitivity microphones distributed throughout the vehicle to capture conversations between the driver and passengers. The microphone array employs beamforming technology to automatically focus on the direction of the sound source, effectively suppressing environmental noise interference and improving speech recognition accuracy. The system's built-in speech recognition engine, based on natural language processing technology, can convert speech into text in real time and analyze keywords and sentiment in the dialogue. For example, when it detects keywords such as "the car in front crossed the solid line" or "that person is speeding," the system immediately marks this information as potential traffic violation clues.

[0042] The recording of in-vehicle button data is accomplished through onboard button sensors installed on key operating areas such as the steering wheel, light control stalks, and horn button. Each time the driver presses a button, the sensors record information in real time, including the type of operation, the time of operation, and the frequency of operation. For example, frequently switching between high and low beams might indicate that the driver is alerting the vehicle ahead, while unusually frequent honking might suggest the driver's dissatisfaction or anger towards a vehicle violating traffic rules. This behavioral data, combined with vehicle driving data, in-vehicle voice data, and user facial expression data, forms a multi-dimensional system for identifying traffic violations.

[0043] S102: In response to the discrimination data meeting the evidence collection triggering condition, obtain vehicle exterior video data of a preset historical duration.

[0044] After obtaining the discrimination data, the in-vehicle terminal performs preliminary processing and analysis to determine whether there are potential traffic violations. This process is achieved through intelligent algorithms, which can efficiently and accurately identify abnormal data patterns that may indicate violations. Once the discrimination data meets the evidence-gathering trigger conditions, the system will automatically proceed to the next step, which is to acquire a preset historical duration of external video data (such as requesting video clips from the DVR subsystem up to the trigger time based on the trigger time), providing strong evidence for subsequent violation identification and reporting.

[0045] It should be noted that the acquisition of external video data here is based on the premise that the data meets the evidence-gathering trigger conditions, which ensures the relevance and validity of the acquired video data. The system continuously captures a continuous video stream of the external environment through the vehicle's onboard camera, and after the evidence-gathering trigger conditions are met, it extracts key segments from the continuous video stream that meet the preset historical duration requirements. This process not only reduces unnecessary data storage but also improves the efficiency of subsequent processing and analysis.

[0046] In one embodiment, when determining whether the discrimination data meets the evidence collection triggering conditions, the current emotion type of the user in the vehicle can be determined based on the user's facial expression data. If the current emotion type is a preset abnormal emotion type (such as anger, tension, etc.), the discrimination data is determined to meet the evidence collection triggering conditions. This is because abnormal emotions are often closely related to dangerous driving behavior or traffic violations. For example, the anger a driver feels due to a vehicle cutting in front of them may indicate the existence of a traffic violation.

[0047] This application utilizes user facial expression data as a key evidence trigger, enabling more timely and accurate detection of potential traffic violations. When the system determines that a user inside the vehicle is in a preset abnormal emotional state based on facial expression data, it quickly identifies that the data meets the evidence triggering conditions and then acquires a preset historical duration of external video data.

[0048] Specifically, when determining the current emotion type of a user in the vehicle based on user facial expression data, facial expression recognition technology can be used. For example, firstly, the user's facial image data is located and acquired through a face detection module; then, facial landmark detection technology is used to align and normalize the facial image to eliminate the influence of pose and scale changes; next, a pre-trained deep convolutional neural network model is used to extract high-level, discriminative expression features from the pre-processed facial image; finally, a classifier maps the expression features to preset emotion categories (such as happy, sad, angry, surprised, fearful, disgusted, and neutral) to output the final emotion recognition result.

[0049] Alternatively, a pre-trained emotion recognition model can be used. This model, trained on a large amount of facial expression image data, can accurately identify abnormal emotion types such as anger, tension, and anxiety. When the in-vehicle camera captures the driver's facial expression, the system inputs the image data into the emotion recognition model, which quickly analyzes and outputs the current emotion type. If the recognition result is a preset abnormal emotion type, the system determines that the data meets the evidence triggering conditions and immediately initiates the process of acquiring external video data.

[0050] In one embodiment, when determining the current emotion type of a user inside the vehicle, a preset recognition model group can be used. Specifically, the preset recognition model group must first be determined, which includes at least a geometric rule judgment model and a convolutional neural network model. The geometric rule judgment model is a high-confidence-priority Face Mesh geometric rule judgment model, which calculates geometric features based on 468 facial key points output by Google ML Kit. For example, when the mouth height ratio is >0.22 or the eye opening angle is >0.065, the user is considered to be in a state of fright; when the eyebrow-eye distance is <0.06 and the eye opening angle is <0.04, the user is considered to be in a state of anger. The key point indices can be set as follows: corner of mouth 61 / 291, eyelid 159 / 145 / 386 / 374, inner eyebrow 70 / 300.

[0051] The convolutional neural network model can be the TFLite lightweight CNN model. Its input is a 48×48 grayscale face image trained based on FER2013. The model structure is 3 layers of convolution + BN + Dropout + fully connected layers. Its output is the confidence score of three emotions: "anger", "fear", and "surprise". During recognition, the user's facial expression data needs to be input into the geometric rule judgment model to obtain the first recognition result. When the confidence score of the first recognition result for the preset emotion type is higher than the first preset confidence threshold (e.g., 0.7), the current emotion type is the preset emotion type. Only when the first layer does not output a high confidence result is the convolutional neural network model activated to obtain the second recognition result. When the confidence score of the second recognition result for the preset emotion type is higher than the second preset confidence threshold (e.g., 0.8), the current emotion type is the preset emotion type.

[0052] In addition to judging based on user facial expression data, the system can also conduct comprehensive analysis by integrating multi-dimensional information such as vehicle driving data, in-vehicle voice data, and in-vehicle button data. For example, when the vehicle driving data shows evasive behaviors such as sudden acceleration, sudden braking, or abnormal steering, combined with keywords accusing others of dangerous driving in the in-vehicle voice data, and operation behaviors such as frequent switching of lights or abnormal use of the horn in the in-vehicle button data, the system can more accurately determine whether there is a traffic violation and trigger the evidence collection process.

[0053] Specifically, the first evidence-gathering trigger condition may be that the vehicle's speed reduction within a preset time period exceeds a first acceleration threshold (e.g., 6 m / s²), or the lateral acceleration exceeds a second acceleration threshold (e.g., 4 m / s²), or the detected lateral vehicle distance is less than a preset distance threshold (e.g., <0.5 m), and the relative speed is greater than a preset speed threshold (e.g., >20 km / h). Meeting any one of these three conditions is considered an emergency evasive maneuver by the vehicle.

[0054] The second evidence collection trigger condition can be triggered by voice keywords, such as the user's volume inside the vehicle increasing by more than a preset percentage threshold within a preset time period (e.g., a sudden increase in volume ≥ 50%), or the detection that the user's voice contains first-type keywords (e.g., "Do you know how to drive?", "cutting in line", "changing lanes recklessly", etc., which can be configured by the user). When any one of the three conditions of the second evidence collection trigger condition is met, it is considered that the vehicle has performed an emergency avoidance action.

[0055] The third evidence collection trigger condition can be triggered by the driver's strong negative emotions. When the driver's emotion type is a preset emotion type, the third evidence collection trigger condition is considered to be met.

[0056] To enhance the accuracy of evidence collection, any two of the above three evidence collection triggering conditions can be met, and the triggering time must occur synchronously within 2 seconds (meeting the time alignment window) before starting the evidence collection process.

[0057] In addition, a fallback mechanism can be set up, that is, when the user actively triggers the process, such as setting the voice command "Now collect traffic violation evidence" or receiving the user actively pressing a preset button (at which time the user clicks the preset button on the vehicle's settings interface), the evidence collection process will be started unconditionally.

[0058] This application, by setting multiple evidence-gathering trigger conditions and a fallback mechanism, can comprehensively and flexibly address different types of traffic violation scenarios. The multiple evidence-gathering trigger conditions consider several key dimensions, including vehicle driving status, in-vehicle voice content, and driver emotional state, greatly improving the accuracy and timeliness of traffic violation judgment. For example, when a vehicle makes an emergency evasive maneuver, combined with a sudden increase in in-vehicle user volume and voice messages containing accusatory keywords, and the driver is in a preset abnormal emotional state such as anger, the system can quickly determine that a traffic violation has occurred and initiate the evidence-gathering process, acquiring external video data as strong evidence.

[0059] The fallback mechanism fully considers users' proactive needs. When a user discovers a traffic violation but the system does not automatically trigger evidence collection, the user can actively initiate the evidence collection process through voice commands or by pressing a preset button, ensuring that no important evidence of traffic violations is missed. This comprehensive evidence collection triggering method not only improves the system's intelligence level but also provides more reliable and comprehensive evidence support for reporting traffic violations, helping to maintain good traffic order and road safety.

[0060] S103: Identify the external video data to obtain information on illegal activities.

[0061] After acquiring the external video data, the system performs professional recognition and processing, utilizing advanced image recognition and computer vision technologies to analyze the video. The system identifies various traffic elements in the video, including but not limited to vehicle type, license plate number, and driving trajectory. By comparing this data with pre-stored traffic regulations, it accurately determines whether any violations exist, as well as the type and severity of the violations. This process can identify violations such as crossing solid lines to change lanes, using emergency lanes, driving against traffic, speeding, and running red lights, providing solid evidence for subsequent reports.

[0062] In one embodiment, when identifying illegal behavior information in external video data, it is necessary to identify the external video data to obtain vehicle detection frames, lane line segmentation masks, and drivable area masks; then, based on the vehicle detection frames, lane line segmentation masks, drivable area masks, and preset judgment rules, the illegal behavior information in the external video data is determined; wherein, the illegal behavior here includes illegal lane changing, illegal parking, failure to yield to pedestrians, running red lights, misuse of high beams, speeding, cutting in line, and driving against traffic, etc.

[0063] Specifically, the aforementioned illegal behavior information identification process can be completed entirely on the Android cockpit side, including illegal identification and evidence structuring, without the need for internet connectivity or cloud support. First, the YOLOPv2 model is used to reason frame by frame through the video clips. On the Android cockpit side, a single model synchronously outputs three types of information, including vehicle detection boxes, lane line segmentation masks, and drivable area masks.

[0064] The vehicle detection bounding box is used to locate illegal vehicles, serving as the input for ByteTrack tracking and trajectory construction. It can also be used to crop the license plate area. The lane line segmentation mask is used to determine lane boundaries and types, distinguishing between solid and dashed lines through post-processing (based on continuity and width), and calculating whether the vehicle's center crosses a solid line. The drivable area mask is used to determine the road structure; the emergency lane is the rightmost fixed-width area (e.g., 1.5m) within the drivable area, combined with GPS road type verification.

[0065] When constructing vehicle trajectories, the ByteTrack algorithm can be used to perform cross-frame data association based on the vehicle bounding boxes output by YOLOPv2, assigning a unique ID to each vehicle and generating continuous trajectories. During license plate recognition, the license plate region can be accurately located within the YOLOPv2 vehicle bounding box using YOLOv8n; and a CRNN+CTC model is used to recognize the 7-digit license plate. Simultaneously, to reduce computational load, the license plate of the same vehicle can be recognized only once in consecutive frames. When determining the type of violation, the violation can be determined by combining geometric and semantic rules based on the information obtained from the above recognition process.

[0066] For example, the determination of illegal lane changing over a solid line can be divided into the following four steps: Step 1: Extract the center lines of the left and right lanes from the lane segmentation results; Step 2: Obtain the center point trajectory of the target vehicle for 5 consecutive frames using ByteTrack; Step 3: Determine whether the trajectory crosses the solid line area (the solid line is determined by the continuous and unbroken feature of the lane line); Step 4: If the crossing duration is >0.5 seconds and there are no obstacles ahead in the target lane (determined by the density of the YOLOPv2 detection box), then it is determined to be illegal.

[0067] The determination of illegal use of the emergency lane can be divided into the following two steps: Step 1: Extract the rightmost edge from the drivable area mask and extend it 1.5m to the left as the emergency lane area; Step 2: Determine whether the center point of the illegal vehicle falls into this area.

[0068] The determination of wrong-way driving violations can be divided into the following three steps: Step 1: Fit the lane direction vector from the lane line segmentation results (e.g., from the bottom to the top of the image); Step 2: Calculate the vehicle movement direction vector using ByteTrack; Step 3: If the angle between the two vectors is >120°, it is determined to be wrong-way driving.

[0069] In one embodiment, to improve the speed and accuracy of identifying illegal behavior information, after detecting that the user's voice contains second-type keywords (such as "cutting in line" or "changing lanes over a solid line" and other keywords related to the type of illegal behavior), the type of illegal behavior corresponding to the second-type keywords can be determined; then the target determination rule corresponding to the type of illegal behavior can be determined, and based on the vehicle detection box, lane line segmentation mask, drivable area mask and target determination rule, the illegal behavior information in the external video data can be determined.

[0070] This application, by employing advanced image recognition and computer vision technologies combined with a user voice keyword triggering mechanism, can significantly improve the efficiency and accuracy of identifying illegal behavior information. In practical applications, when the system detects keywords related to specific illegal behaviors in a user's voice, it quickly locates the corresponding illegal behavior type and invokes the relevant target determination rules. These rules, based on key information such as vehicle detection boxes, lane line segmentation masks, and drivable area masks, can accurately determine whether illegal behaviors such as crossing solid lines to change lanes, occupying emergency lanes, or driving in the wrong direction exist in the video.

[0071] This integrated approach, combining voice keywords with image recognition, not only speeds up the identification of illegal behavior but also improves its accuracy. For example, when a user utters the keyword "cut in line," the system can immediately identify potential cutting-in behavior in the video and confirm whether the vehicle has indeed crossed the solid line to change lanes by comparing the vehicle detection frame with the lane line segmentation mask. Similarly, when a user mentions "occupying the emergency lane," the system quickly checks the drivable area mask to determine if any vehicle has illegally parked in the emergency lane.

[0072] Furthermore, this application enhances the system's adaptability to complex traffic scenarios by continuously optimizing and updating the preset judgment rules and utilizing deep learning technology to improve the performance of the image recognition model. For example, different preset recognition models are selected based on the current time and weather, ensuring stable operation and accurate identification of various traffic violations regardless of day or night, or whether it is sunny or rainy.

[0073] Finally, this efficient and accurate illegal act identification mechanism provides strong evidence support for the reporting of traffic violations. By obtaining clear and conclusive external vehicle video data and accurately identified illegal act information, relevant departments can handle traffic violations more quickly and effectively, thus maintaining good traffic order and road safety.

[0074] It should be noted that the above determination process is completed within the local video segment after being triggered, without the need for an external map or V2X. If any one or more of the above three violation types are satisfied, it is determined that an illegal act has occurred, and evidence is packaged.

[0075] After the illegal act is identified, the external vehicle video corresponding to the illegal act information can be cropped, only retaining 2 seconds before and after the occurrence of the violation, so as to save storage space resources. In addition, factors such as timestamp, GPS coordinates, vehicle speed, and violation type can be injected into the cropped external vehicle video, and it is saved in the following output format: { "violation_id": "VID20251009123456", "timestamp": "2025-10-09T12:34:56+08:00", "gps": { "lat": 39.9042, "lng": 116.4074}, "speed_kmh": 85, "violation_type": "illegal_lane_change", "license_plate": "京ADXXXXX", "plate_type": "green", "confidence": 0.92, "evidence_video_path": " / data / user / 0 / com.xxx.cockpit / files / evidence / VID20251009123456.mp4" } S104: Based on the current position of the vehicle, upload the illegal act information to the reporting platform.

[0076] After identifying traffic violations, the system uses the vehicle's built-in location tracking to obtain the vehicle's real-time location and matches it with the appropriate reporting platform based on the geographic location information. Different regions may use different traffic violation reporting platforms, and the system needs to automatically identify and adapt to the upload protocols of these platforms. After matching the correct reporting platform, the system further obtains the platform's upload protocol, which specifies details such as the data upload format, encryption method, and communication protocol. Finally, the system accurately uploads the standardized violation information to the reporting platform according to the mapping template corresponding to the upload protocol. This process not only automates the upload of information but also ensures data compatibility and security across different platforms, providing traffic management departments with timely and reliable evidence of violations.

[0077] Furthermore, to improve the accuracy and effectiveness of reports, the system also allows users to manually confirm and correct automatically identified violations. Users can view the violations identified by the system through the interactive interface of the in-vehicle terminal and make necessary additions or modifications. This human-machine collaborative approach leverages both the system's automation advantages and the user's experience and judgment, thereby improving the overall quality of reports.

[0078] In one embodiment, when uploading information about illegal activities to the reporting platform, the vehicle terminal loads the current reporting channel based on a pre-built "location-platform mapping table" and the current location. When maintaining the platform database, it is necessary to pre-configure the reporting methods for major cities and store the data format requirements for each reporting method. For example, the reporting method in Beijing is the "Beijing Traffic Police Snap and Report" WeChat mini-program; in Shenzhen, it is the "Shenzhen Traffic Police" WeChat official account's "Snap and Report" feature; in Shanghai, it is the "Shanghai Traffic Police" App; and in Chengdu, it is the "Rong e-Travel" platform. The automatic matching logic is as follows: first, obtain the vehicle's current GPS location; then, query the local reporting platform database; if a match is successful, load the corresponding platform's upload protocol (such as field format, video size requirements, watermark specifications, etc.) and display the corresponding reporting entry; otherwise, display the message "Automatic reporting is not currently supported in this region."

[0079] When reporting traffic violations, the vehicle-mounted terminal will display a preview interface after triggering, showing the violation type, license plate, video clip, and the platform to which it will be uploaded. After the user confirms with one click, the system will automatically process the video according to the current platform's upload protocol, such as compressing the video to the platform's required format (e.g., MP4, ≤20M) and adding digital watermarks (time, coordinates, etc.). It will then call the reporting platform, WeChat, WebView, or H5 page, using the violation identification JSON result as a basis to automatically fill in the license plate, time, violation type, and video, and upload it. Additionally, if the reporting platform supports HTTPS API, it will upload directly via API. Furthermore, the original video is not exported from the vehicle; only cropped and anonymized segments are exported. All operations require explicit user authorization.

[0080] In summary, the traffic violation reporting method provided in this application, through a multi-dimensional data acquisition mechanism, intelligent evidence trigger condition judgment, professional violation identification, and an automated uploading process based on vehicle location, achieves automated and intelligent reporting of traffic violations. This method not only significantly improves reporting efficiency and accuracy but also helps maintain good traffic order and ensure road safety.

[0081] Furthermore, this application has low hardware requirements for the vehicle, only requiring the installation of modules with image processing and voice recognition functions. These modules are already common in existing smart vehicles, eliminating the need for large-scale hardware upgrades. Specifically, the system primarily relies on in-vehicle cameras to collect external video data, uses in-vehicle microphones to capture user voice inside the vehicle, and then completes tasks such as image recognition, voice keyword extraction, and violation determination through a built-in processor or interaction with cloud services. This lightweight hardware requirement allows this method to be widely applied to various vehicle types, whether new or existing, enabling intelligent reporting of traffic violations through software upgrades. Simultaneously, since most computation and processing tasks are completed locally or in the cloud, it reduces the occupation of vehicle storage space, further enhancing the system's practicality and cost-effectiveness.

[0082] Furthermore, when upgrading various parameters of the recognition model deployed in vehicles, seamless upgrades can be achieved through remote update technology. When the vehicle is connected to the network, the system automatically detects whether there are new versions of the recognition model parameters on the server and compares them with the current version. Once a new version is detected, the system sends an update prompt to the user. After user confirmation, the system downloads and installs the latest model parameter package. The entire update process requires no manual user intervention and does not affect the normal use of the vehicle, ensuring that the recognition model always maintains optimal performance. At the same time, to ensure the security of the update process, the system performs strict verification and encryption on the downloaded parameter package to prevent data tampering or leakage.

[0083] In addition, such as Figure 2 As shown, Figure 2 This is a schematic diagram of a traffic violation reporting device provided in an embodiment of this application. The device includes: The discrimination data acquisition module 201 acquires discrimination data, which includes at least one of user facial expression data, vehicle driving data, in-vehicle voice data, and in-vehicle button data. The evidence collection trigger judgment module 202, in response to the judgment data meeting the evidence collection trigger condition, acquires vehicle exterior video data of a preset historical duration; The illegal behavior identification module 203 identifies the external video data to obtain illegal behavior information; The illegal behavior uploading module 204 uploads the illegal behavior information to the reporting platform based on the vehicle's current location.

[0084] Regarding the apparatus in the above embodiments, the specific manner in which each unit performs its operation has been described in detail in the embodiments related to the method, and will not be elaborated upon here.

[0085] Figure 3 This is a schematic diagram of the structure of a vehicle provided in an embodiment of this application.

[0086] For example, such as Figure 3 As shown, the vehicle includes a memory 301 and a processor 302. The memory 301 stores executable program code 3011, and the processor 302 is used to call and execute the executable program code 3011 to implement the traffic violation reporting method.

[0087] This embodiment can divide the vehicle into functional modules according to the above method example. For example, each function can be assigned to a separate module, or two or more functions can be integrated into one processing module. The integrated module can be implemented in hardware. It should be noted that the module division in this embodiment is illustrative and only represents one logical functional division. In actual implementation, there may be other division methods.

[0088] When each functional module is divided according to its corresponding function, the vehicle may include: The discrimination data acquisition module acquires discrimination data, which includes at least one of user facial expression data, vehicle driving data, in-vehicle voice data, and in-vehicle button data. The evidence collection trigger judgment module, in response to the judgment data meeting the evidence collection trigger condition, acquires vehicle exterior video data of a preset historical duration. The illegal behavior identification module identifies the external video data to obtain information on illegal behaviors; The illegal behavior uploading module uploads the illegal behavior information to the reporting platform based on the vehicle's current location.

[0089] It should be noted that all relevant content of each step involved in the above method embodiments can be referenced from the functional description of the corresponding functional module, and will not be repeated here.

[0090] The vehicle provided in this embodiment is used to execute the above-mentioned traffic violation reporting method, and therefore can achieve the same effect as the above-mentioned implementation method.

[0091] When using integrated units, the vehicle may include a processing module and a storage module. The processing module is used to control and manage the vehicle's actions. The storage module supports the vehicle in executing program code and data.

[0092] The processing module may be a processor or a controller, which can implement or execute various exemplary logic blocks, modules, and circuits as disclosed in this application. The processor may also be a combination of computing functions, such as a combination of one or more microprocessors, a combination of digital signal processing (DSP) and a microprocessor, etc., and the storage module may be a memory.

[0093] This embodiment also provides a computer-readable storage medium (including but not limited to disk storage, CD-ROM, optical storage, etc.) storing computer program code. When the computer program code is run on a computer, the computer executes the above-mentioned related method steps to realize the traffic violation reporting method provided in the above embodiment.

[0094] This embodiment also provides a computer program product that, when run on a computer, causes the computer to perform the aforementioned steps to implement the traffic violation reporting method provided in the above embodiment.

[0095] The beneficial effects of the above embodiments can be referred to the beneficial effects of the corresponding methods provided above, and will not be repeated here.

[0096] Through the above description of the embodiments, those skilled in the art will understand that, for the sake of convenience and brevity, only the division of the above functional modules is used as an example. In actual applications, the above functions can be assigned to different functional modules as needed, that is, the internal structure of the device can be divided into different functional modules to complete all or part of the functions described above.

[0097] In the 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 modules or 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 device, 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 devices or units may be electrical, mechanical, or other forms.

[0098] In the description of this disclosure, it should be understood that if the terms "upper", "lower", "front", "rear", "left" and "right" are used to indicate the orientation or positional relationship based on the orientation or positional relationship shown in the drawings, they are only for the convenience of describing the present invention and simplifying the description, and do not indicate or imply that the position or element referred to must have a specific orientation, or be constructed and operated in a specific orientation, and therefore should not be construed as a limitation of this disclosure.

[0099] It should be noted that, in this document, relational terms such as "first" and "second" are used only to distinguish one entity or operation from another, and do not necessarily require or imply any such actual relationship or order between these entities or operations. It should also be noted that the terms "comprising," "including," or any other variations thereof are intended to cover non-exclusive inclusion, such that a process, method, article, or apparatus that comprises a list of elements includes not only those elements but also other elements not expressly listed, or elements inherent to such process, method, article, or apparatus. Unless otherwise specified, an element defined by the phrase "comprising one..." does not exclude the presence of other identical elements in the process, method, article, or apparatus that includes the element.

[0100] The above are merely embodiments of this disclosure and are not intended to limit the scope of this disclosure. Various modifications and variations can be made to this disclosure by those skilled in the art. Any modifications, equivalent substitutions, improvements, etc., made within the spirit and principles of this disclosure should be included within the scope of the claims of this disclosure.

Claims

1. A method for reporting traffic violations, characterized in that, include: Acquire discrimination data, which includes at least one of user facial expression data, vehicle driving data, in-vehicle voice data, and in-vehicle button data; In response to the discrimination data meeting the evidence collection triggering condition, vehicle exterior video data of a preset historical duration is acquired; The external video data is identified to obtain information on illegal activities; Based on the vehicle's current location, the information regarding the illegal activity will be uploaded to the reporting platform.

2. The method according to claim 1, characterized in that, The step of obtaining vehicle exterior video data of a preset historical duration in response to the discrimination data satisfying the evidence collection triggering condition specifically includes: Based on the user's facial expression data, determine the current emotion type of the user in the vehicle; In response to the current emotion type being a preset emotion type, obtain vehicle exterior video data of a preset historical duration.

3. The method according to claim 2, characterized in that, Determining the current emotion type of the user in the vehicle based on the user's facial expression data specifically includes: A preset recognition model group is determined, wherein the preset recognition model group includes at least a geometric rule determination model and a convolutional neural network model; The user's facial expression data is input into the geometric rule determination model to obtain a first recognition result; When the confidence level of the first identification result for a preset emotion type is higher than the first preset confidence threshold, the current emotion type is the preset emotion type; When the confidence level of the first recognition result for the preset emotion type is not higher than the first preset confidence threshold, the user's facial expression data is input into the convolutional neural network model to obtain the second recognition result; When the confidence level of the second identification result for the preset emotion type is higher than the second preset confidence threshold, the current emotion type is the preset emotion type.

4. The method according to claim 1, characterized in that, The step of obtaining vehicle exterior video data of a preset historical duration in response to the discrimination data satisfying the evidence collection triggering condition specifically includes: In response to a vehicle speed reduction exceeding a first acceleration threshold, or a lateral acceleration exceeding a second acceleration threshold, or the detection of a lateral vehicle distance below a preset distance threshold and a relative speed exceeding a preset speed threshold within a preset time period, external video data for a preset historical time period is acquired; and / or, In response to a user's volume inside the vehicle increasing by more than a preset percentage threshold within a preset duration, or the detection of a first-type keyword in the user's voice, the system acquires external video data for a preset historical duration; and / or, In response to receiving a user's active press of a preset button, the system retrieves exterior video data for a preset historical duration.

5. The method according to claim 1, characterized in that, The process of identifying the external video data to obtain information on illegal activities specifically includes: The external video data is identified to obtain the vehicle detection box, lane line segmentation mask, and drivable area mask; Based on the vehicle detection frame, lane line segmentation mask, drivable area mask, and preset judgment rules, illegal behavior information in the external video data is determined.

6. The method according to claim 5, characterized in that, The method of determining illegal behavior information in the external video data based on vehicle detection frames, lane line segmentation masks, drivable area masks, and preset judgment rules specifically includes: In response to the presence of a second type of keyword in the user's voice, determine the type of illegal behavior corresponding to the second type of keyword; The target determination rule corresponding to the type of illegal behavior is determined, and the illegal behavior information in the external video data is determined based on the vehicle detection frame, lane line segmentation mask, drivable area mask and target determination rule.

7. The method according to claim 1, characterized in that, The process of uploading the illegal behavior information to the reporting platform based on the vehicle's current location specifically includes: Save the illegal behavior information in a preset output format; Based on the vehicle's current location, a reporting platform is matched, and the upload protocol of the reporting platform is obtained; The illegal behavior information is uploaded based on the mapping template corresponding to the upload protocol.

8. A traffic violation reporting device, characterized in that, include: The discrimination data acquisition module acquires discrimination data, which includes at least one of user facial expression data, vehicle driving data, in-vehicle voice data, and in-vehicle button data. The evidence collection trigger judgment module, in response to the judgment data meeting the evidence collection trigger condition, acquires vehicle exterior video data of a preset historical duration. The illegal behavior identification module identifies the external video data to obtain information on illegal behaviors; The illegal behavior uploading module uploads the illegal behavior information to the reporting platform based on the vehicle's current location.

9. A vehicle, characterized in that, include: At least one processor; as well as, A memory communicatively connected to the at least one processor; wherein, The memory stores instructions that can be executed by the at least one processor, which, when executed by the at least one processor, enables the at least one processor to perform the traffic violation reporting method according to any one of claims 1 to 7.

10. A computer-readable storage medium storing computer-executable instructions, characterized in that, The computer-executable instructions are configured to execute the traffic violation reporting method as described in any one of claims 1 to 7.

Images