Vehicle trajectory prediction method and device based on YTS and electronic equipment

Abstract

This application provides a vehicle trajectory prediction method, device, and electronic device based on YTS, relating to the field of system control technology, and solves the technical problem of low accuracy in predicting the trajectory of a vehicle ahead. The method includes: acquiring vehicle driving video data of a target vehicle, and identifying the vehicle type, model, and several corresponding drivers based on the vehicle driving video data; determining the driving time corresponding to the target vehicle in the vehicle driving video data, and matching the target driving time for each driver within the driving time; and analyzing the driving habit data corresponding to each driver through the YTS system based on the target driving time and vehicle driving video data for each driver; the driving habit data includes driving habit route, driving habit time, and driving habit lane.

Description

Technical Field

[0001] This application relates to the field of system control technology, and in particular to a vehicle trajectory prediction method, device, and electronic device based on YTS. Background Technology

[0002] Currently, in-vehicle terminals can identify whether the vehicle ahead has its lights on based on images captured by image acquisition equipment, and then determine whether the vehicle ahead is about to slow down based on whether its lights are on. However, judging whether a vehicle ahead is about to slow down solely based on its lights only indicates that the vehicle is slowing down by braking, and cannot determine the specific driving conditions such as the vehicle's trajectory, resulting in low accuracy in predicting the vehicle's upcoming trajectory. Summary of the Invention

[0003] The purpose of this invention is to provide a vehicle trajectory prediction method, device, and electronic device based on YTS, so as to solve the technical problem of low accuracy in predicting the trajectory of the vehicle ahead.

[0004] Firstly, this application provides a vehicle trajectory prediction method based on YTS, applied to an in-vehicle terminal, the method comprising:

[0005] Acquire vehicle driving video data of the target vehicle, and identify the vehicle type, vehicle model and several driving users corresponding to the target vehicle based on the vehicle driving video data;

[0006] Based on the vehicle driving video data, determine the driving time corresponding to the target vehicle in the vehicle driving video data, and match the target driving time of the target vehicle for each driver in the driving time.

[0007] Based on the target driving time and vehicle driving video data corresponding to each driver user, the YTS system analyzes the driving habit data corresponding to each driver user; the driving habit data includes driving habit route, driving habit time and driving habit lane.

[0008] The system determines the vehicle currently traveling in front of its own vehicle terminal from the vehicle's dashcam data, and determines whether the vehicle in front exists from among multiple target vehicles. If the vehicle in front exists, the system determines the target driving habit data of several target drivers corresponding to the vehicle in front from the driving habit data corresponding to the multiple target vehicles.

[0009] Based on the video data of the vehicle in front in the dashcam, the target driving habit data of each target driver is matched with the current driving habit data corresponding to the video data of the vehicle in front, and the current target driver currently driving the vehicle in front is determined from the plurality of target drivers according to the matching results.

[0010] Based on the target driving habit route, target driving habit time, and target driving habit lane corresponding to the current target driving user, the future driving trajectory of the vehicle ahead on the road is predicted to obtain the vehicle trajectory prediction result.

[0011] In one possible implementation, the on-board terminal is equipped with an infrared temperature detector; it also includes:

[0012] The infrared temperature detector detects the tire temperature of the vehicle in front, corresponding to its own vehicle terminal.

[0013] Determine the temperature difference between the tire temperature and the current ambient temperature; wherein, the current ambient temperature is the temperature of the environment in which the vehicle terminal is located;

[0014] Determine whether the temperature difference exceeds a specified temperature difference threshold;

[0015] If the temperature difference exceeds the specified temperature difference threshold, it is determined that the vehicle in front is currently in a state of fatigue driving, and the driving direction and / or driving speed of the vehicle terminal are controlled to be changed so as to increase the vehicle distance between the vehicle terminal and the vehicle in front.

[0016] The vehicle information interaction content between the vehicle terminal and the vehicle ahead is determined by the latest driving direction and speed after the change, the tire temperature of the vehicle ahead, and the temperature difference. The vehicle information interaction content is then sent to the terminal corresponding to the vehicle ahead.

[0017] In one possible implementation,

[0018] The control to change the driving direction and / or speed of the vehicle-mounted terminal includes:

[0019] Based on the vehicle trajectory prediction results and the fatigue driving state, the vehicle's own on-board terminal's driving trajectory is changed, so that the on-board terminal changes from being behind the vehicle in front to being to the side of the vehicle in front. While the on-board terminal is to the side of the vehicle in front, its driving speed is increased, so that the on-board terminal is in front of the vehicle in front and the distance between them increases; or...

[0020] Based on the vehicle trajectory prediction results and the fatigue driving state, the vehicle terminal's driving speed is reduced so that the vehicle terminal is behind the vehicle in front and the distance between the two vehicles is greater than a specified distance.

[0021] In one possible implementation, the vehicle-mounted terminal is further equipped with an image acquisition device; the method also includes:

[0022] The image acquisition device acquires driving video data of the vehicle in front, and identifies the target vehicle type of the vehicle in front based on the driving video data;

[0023] Retrieve the vehicle performance of the target vehicle type; wherein the vehicle performance includes at least one of acceleration performance, braking performance, and maximum vehicle performance threshold;

[0024] Based on the vehicle performance analysis, the maximum drivable speed, maximum acceleration, and maximum deceleration of the vehicle ahead are determined.

[0025] Based on the driving video data, the AI ​​system analyzes the driving habits of the first user corresponding to the vehicle in front;

[0026] The driving habits, maximum drivable speed, maximum acceleration, and maximum deceleration are bound to the license plate number of the vehicle ahead to generate comprehensive driving analysis data for the vehicle ahead. This comprehensive driving analysis data is then sent to the platform server, allowing multiple second-user vehicle terminals to obtain the comprehensive driving analysis data corresponding to the vehicle ahead through the platform server. The platform server stores comprehensive driving analysis data for multiple vehicles, including the vehicle ahead.

[0027] In response to a correction request from the second target user regarding the comprehensive driving analysis data in the platform server, the comprehensive driving analysis data is corrected according to the data in the correction request to obtain real-time comprehensive driving data, so that the comprehensive driving analysis data in the platform server is updated in real time.

[0028] The system obtains comprehensive real-time driving data for multiple vehicles from the platform server, and controls the driving direction and speed of its own vehicle terminal based on the driving habits, maximum driving speed, maximum acceleration, and maximum deceleration of each vehicle in the comprehensive real-time driving data.

[0029] In one possible implementation, based on the driving habits and maximum drivable speed of each vehicle in the comprehensive real-time driving data, the driving direction and speed of the vehicle's own onboard terminal are controlled, including:

[0030] Based on the vehicle's deviation from the lane center position error in the aforementioned driving habits, the driving direction of the vehicle-mounted terminal is controlled using the following formula: θs = Kp × e ( t )+ Ki + ;in, θs It's the steering angle. e(t) It is the positional error of the vehicle deviating from the center of the lane. Kp It's about proportion. Ki It's an integral. Kd These are differential coefficients;

[0031] The vehicle's own speed is controlled according to the maximum drivable speed: Vself(t) = Vfront(t) + Kp × (Dsafe - Dcurrent); where Vself(t) is the target speed of the vehicle's own speed, Vfront(t) is the maximum drivable speed of the vehicle in front, Kp is the proportional coefficient, Dsafe is the set safe distance, and Dcurrent is the current distance to the vehicle in front.

[0032] In one possible implementation, the step of analyzing the driving habits of the first user corresponding to the vehicle ahead using an AI system based on the driving video data includes:

[0033] The time interval between two frames is calculated based on the timestamp difference in the corresponding video frames of the driving video data. Based on the time interval, an object detection algorithm is used to identify the change data of the vehicle position between the vehicle in front and the vehicle terminal itself, and the first speed of the vehicle in front is determined based on the change data of the vehicle position.

[0034] The first acceleration or first deceleration of the vehicle ahead is determined based on the change data of the first speed over a continuous time period.

[0035] Based on the driving video data, the positions of the vehicles in front and the vehicle's own on-board terminal are tracked using computer vision processing. The distance between the vehicle in front and the vehicle's own on-board terminal is calculated over time using the formula R=ΔDfront / ΔT. Here, R represents the rate of change of distance from the vehicle in front, ΔDfront is the amount of change in distance from the vehicle in front, and ΔT is the time period during which the change occurs.

[0036] Based on the first speed, the first acceleration or the first deceleration, and the distance change over time, the AI ​​system analyzes the driving habit data of the first user corresponding to the vehicle ahead using the following formula: S = w1 × Vs + w2 × As + w3 × Rs; where S is the total driving habit data, w1, w2, and w3 are weighting coefficients, Vs is the first speed, As is the first acceleration or the first deceleration, and Rs is the distance change over time.

[0037] In one possible implementation, the step of binding the driving habits, the maximum drivable speed, the maximum acceleration, and the maximum deceleration with the license plate number of the vehicle ahead to generate comprehensive driving analysis data for the vehicle ahead includes:

[0038] Based on the driving habits, the maximum drivable speed, the maximum acceleration, and the maximum deceleration, comprehensive driving analysis data for the vehicle ahead is generated using the following formula: Statal = w1 × Vs + w2 × As + w3 × Rs + w4 × Vmax + w5 × Amax - w6 × |Amin|; where Statal is the comprehensive driving analysis data; w1, w2, w3, w4, w5, and w6 are the weighting coefficients of each indicator, Vs is the driving speed, As is the acceleration, Rs is the rate of change of distance between the vehicle ahead and the vehicle's own onboard terminal, Vmax is the maximum permissible speed, Amax is the maximum acceleration, and Amin is the maximum deceleration.

[0039] Secondly, this application provides a vehicle trajectory prediction device based on YTS, applied to an in-vehicle terminal, wherein the in-vehicle terminal is equipped with an infrared temperature detector; the device includes:

[0040] The identification module is used to acquire vehicle driving video data of the target vehicle, and identify the vehicle type, vehicle model and several driving users corresponding to the target vehicle based on the vehicle driving video data.

[0041] The matching module is used to determine the driving time corresponding to the target vehicle in the vehicle driving video data based on the vehicle driving video data, and to match the target driving time of the target vehicle for each driver in the driving time.

[0042] The analysis module is used to analyze the driving habit data of each driver user based on the target driving time and the vehicle driving video data, through the YTS system; the driving habit data includes driving habit route, driving habit time and driving habit lane;

[0043] The first determining module is used to determine the vehicle currently driving in front of the vehicle terminal from the driving recorder of its own vehicle terminal, and to determine whether the vehicle in front exists from a plurality of target vehicles. If the vehicle in front exists, the module determines the target driving habit data of a plurality of target driving users corresponding to the vehicle in front from the driving habit data corresponding to the plurality of target vehicles.

[0044] The second determining module is used to match the target driving habit data of each target driver with the corresponding current driving habit data in the video data of the vehicle in front, based on the video data of the vehicle in front in the dashcam, and determine the current target driver currently driving the vehicle in front from the plurality of target drivers according to the matching result.

[0045] The prediction module is used to predict the future driving trajectory of the vehicle ahead on the road based on the target driving habit route, target driving habit time and target driving habit lane corresponding to the current target driving user, and obtain the vehicle trajectory prediction result.

[0046] Thirdly, this application also provides an electronic device, including a memory and a processor, wherein the memory stores a computer program that can run on the processor, and the processor executes the computer program to implement the method described in the first aspect above.

[0047] Fourthly, this application also provides a computer-readable storage medium storing computer-executable instructions that, when invoked and executed by a processor, cause the processor to perform the method described in the first aspect above.

[0048] This application brings the following beneficial effects:

[0049] This application provides a vehicle trajectory prediction method, device, and electronic device based on YTS, capable of acquiring vehicle driving video data of a target vehicle, and identifying the vehicle type, model, and several corresponding drivers of the target vehicle based on the vehicle driving video data; determining the driving time corresponding to the target vehicle in the vehicle driving video data, and matching the target driving time of the target vehicle for each driver within the driving time; and analyzing the driving habit data corresponding to each driver through the YTS system based on the target driving time corresponding to each driver and the vehicle driving video data; the driving habit... The habitual data includes driving habit routes, driving habit times, and driving habit lanes. It identifies the vehicle currently ahead of its own vehicle's dashcam data and determines whether the vehicle ahead exists from a pool of target vehicles. If the vehicle ahead exists, it identifies the target driving habit data of several target drivers corresponding to that vehicle from the driving habit data corresponding to the multiple target vehicles. Based on the video data of the vehicle ahead in the dashcam, it matches the target driving habit data of each target driver with the corresponding current driving habit data in the video data of the vehicle ahead, and determines the target driving habit data of several target drivers based on the matching results. The system identifies the current target driver of the vehicle ahead; based on the target driver's preferred route, preferred driving time, and preferred lane, it predicts the future trajectory of the vehicle ahead on the road, obtaining a vehicle trajectory prediction result. In this scheme, video data is used to determine the vehicle's driving situation within a specific time period, and this information is matched with the known preferred driving times of various drivers. This process helps narrow down the range of potential drivers. The system identifies the vehicle ahead in the dashcam video of the current vehicle and determines whether it belongs to the previously collected target vehicle database. Once it confirms that the vehicle ahead is one of the target vehicles, the system will attempt to... The system matches previously collected data on the driving habits of the vehicle's drivers with the currently observed driving behavior. Based on the degree of matching between the driving habit data and real-time video data, the system can infer which driver is most likely currently driving the vehicle ahead. Finally, based on the determined driver's driving habit data (such as preferred driving routes, times, and lanes), combined with real-time traffic conditions, the system predicts the driving trajectory of the vehicle ahead over a period of time. The system not only considers the physical characteristics of the vehicle itself but also deeply analyzes the specific driver's behavioral habits. This method makes the prediction of the upcoming driving trajectory of the vehicle ahead more accurate and solves the technical problem of low accuracy in predicting the upcoming driving trajectory of the vehicle ahead.

[0050] To make the above-mentioned objectives, features and advantages of this application more apparent and understandable, preferred embodiments are described below in detail with reference to the accompanying drawings. Attached Figure Description

[0051] To more clearly illustrate the technical solutions in the specific embodiments of this application or the prior art, the drawings used in the description of the specific embodiments or the prior art will be briefly introduced below. Obviously, the drawings described below are some embodiments of this application. For those skilled in the art, other drawings can be obtained from these drawings without creative effort.

[0052] Figure 1 A flowchart illustrating the YTS-based vehicle trajectory prediction method provided in this application embodiment;

[0053] Figure 2 Another flowchart illustrating the YTS-based vehicle trajectory prediction method provided in this application embodiment;

[0054] Figure 3 A schematic diagram of the structure of a YTS-based vehicle trajectory prediction device provided in an embodiment of this application;

[0055] Figure 4 A schematic diagram of the structure of an electronic device provided in an embodiment of this application is shown. Detailed Implementation

[0056] To make the objectives, technical solutions, and advantages of the embodiments of this application clearer, the technical solutions of this application will be clearly and completely described below with reference to the accompanying drawings. Obviously, the described embodiments are only some embodiments of this application, not all embodiments. Based on the embodiments of this application, all other embodiments obtained by those skilled in the art without creative effort are within the scope of protection of this application.

[0057] The terms "comprising" and "having," and any variations thereof, used in the embodiments of this application, are intended to cover non-exclusive inclusion. For example, a process, method, system, product, or device that includes a series of steps or units is not limited to the steps or units listed, but may optionally include other steps or units not listed, or may optionally include other steps or units inherent to these processes, methods, products, or devices.

[0058] Currently, the accuracy of predicting the trajectory of vehicles ahead is relatively low. Therefore, this application provides a vehicle trajectory prediction method, device, and electronic device based on YTS (Yet-Time Trajectory Theory), which can solve the technical problem of poor automatic driving control performance.

[0059] The embodiments of the present invention will be further described below with reference to the accompanying drawings.

[0060] Figure 1 This is a flowchart illustrating a YTS-based vehicle trajectory prediction method provided in an embodiment of this application. The method is applied to an in-vehicle terminal. Figure 1 As shown, the method includes:

[0061] Step S101: Obtain vehicle driving video data of the target vehicle, and identify the vehicle type, vehicle model and several driving users corresponding to the target vehicle based on the vehicle driving video data.

[0062] For example, the collected video data is transmitted to a data center or cloud server for storage via wireless network (such as 4G / 5G) or wired connection. The uploaded video data undergoes preprocessing, including but not limited to cropping, rotating, and adjusting brightness and contrast, to improve the accuracy of subsequent recognition. Noise removal and image stabilization techniques may be needed to optimize video quality. Computer vision techniques and machine learning algorithms are used to analyze the preprocessed video frames to identify the vehicle type (such as sedan, SUV, truck, etc.) and model. The driver's facial features or other biometric information (such as fingerprints, voice, etc.) is captured by an in-vehicle camera and compared with existing user information in a database. Facial recognition algorithms or other biometric technologies are used to ensure the accuracy and reliability of the recognition.

[0063] Step S102: Determine the driving time corresponding to the target vehicle in the vehicle driving video data based on the vehicle driving video data, and match the target driving time of the target vehicle for each driver in the driving time.

[0064] For example, precise timestamps are added to video data, typically achieved by synchronizing video recording equipment and GPS devices to ensure each frame has corresponding time information. Computer vision techniques (such as background subtraction and optical flow) or sensor data (such as vehicle speed sensors) are used to identify the specific moments when the vehicle starts and stops moving, thus determining the entire travel time. This step requires accurately capturing changes in the vehicle's state, such as from stationary to moving, or from moving to stationary. Facial recognition and behavioral feature analysis are used to identify different drivers within the travel time. For each identified driver, the travel time is segmented and labeled according to the time period in which they appear, determining the specific target travel time for each user.

[0065] Step S103: Based on the target driving time and vehicle driving video data corresponding to each driver user, analyze the driving habit data corresponding to each driver user through the YTS system.

[0066] As one possible implementation, driving habit data includes driving habit routes, driving habit times, and driving habit lanes.

[0067] In practical applications, YTS (Unity TV Service) refers to the Unity visualization rendering service system. Unity is a real-time 3D interactive content creation and operation platform, enabling creators in fields such as game development, art, architecture, automotive design, and film to turn their ideas into reality. The platform provides a complete software solution for creating, operating, and monetizing any real-time interactive 2D and 3D content, supporting platforms including mobile phones, tablets, PCs, game consoles, augmented reality, and virtual reality devices. The YTS engine is an intelligent engine system that deeply integrates AI algorithms, physical simulation, and 3D digital rendering technology, specifically designed for next-generation intelligent vehicles. Its core objective is to drive comprehensive upgrades in areas such as autonomous driving, vehicle-road collaboration, and intelligent interaction through high-precision simulation, real-time decision optimization, and cross-domain collaboration capabilities, building an integrated intelligent transportation ecosystem encompassing "people-vehicle-road-cloud."

[0068] Step S104: Determine the vehicle currently driving in front of the vehicle from the dashcam of the vehicle terminal, and determine whether there is a vehicle in front from multiple target vehicles. If there is a vehicle in front, determine the target driving habit data of several target drivers corresponding to the vehicle in front from the driving habit data of multiple target vehicles.

[0069] Computer vision techniques (such as deep learning-based object detection algorithms) are used to analyze preprocessed video frames to identify and locate all vehicles currently in front of the in-vehicle terminal. Tracking algorithms (such as Kalman filters or optical flow methods) are used to continuously track the positional changes of these vehicles in consecutive frames, ensuring stable and accurate identification of vehicles ahead. License plate recognition technology or other unique vehicle features (such as vehicle color, shape, etc.) are used to generate a unique identifier for each detected vehicle ahead. These identifiers are compared with a known "target vehicle" database to check for matches. This step requires access to a database containing information on multiple target vehicles (including but not limited to license plate numbers, vehicle models, etc.) and their corresponding driver and driving habit data. If a vehicle ahead is confirmed to exist in the target vehicle database, the driving habit data of the target driver corresponding to that vehicle is retrieved from the database based on its unique identifier. This driving habit data may include, but is not limited to, average speed, frequency of emergency braking, acceleration patterns, lane change frequency, etc. The retrieved driving habit data is analyzed, combined with current road conditions and other environmental factors, to assess the behavioral patterns and potential risks of the vehicles ahead. Based on the analysis results, the system can provide drivers with early warning information (such as risk warnings of vehicles suddenly slowing down ahead), route optimization suggestions, or other information services that help improve driving safety and efficiency.

[0070] Step S105: Based on the video data of the vehicle in front in the dashcam, match the target driving habit data of each target driver with the corresponding current driving habit data in the video data of the vehicle in front, and determine the current target driver of the vehicle in front from several target drivers according to the matching results.

[0071] For example, computer vision techniques (such as deep learning algorithms) are used to identify and locate vehicles ahead from video frames. Object tracking techniques (such as Kalman filters or optical flow methods) are applied to continuously track the positions of these vehicles in consecutive frames to ensure accurate identification. Based on the behavioral patterns of the vehicles ahead, relevant driving habit features are extracted from the video data. This may include, but is not limited to, changes in vehicle speed, acceleration patterns, lane change frequency, and sudden braking situations. A behavioral model of the current driving habits of the vehicle is constructed for each segment of video data. Based on the unique identifier of the vehicles ahead obtained in the previous steps, the driving habit data of all potential target drivers is retrieved from the database. The driving habit features extracted from the front-end vehicle video data are compared and matched with the retrieved driving habit data of each target driver. For example, machine learning or statistical methods can be used to quantify the similarity between the two, such as calculating Euclidean distance, cosine similarity, or other suitable metrics. Based on the matching results obtained in the previous step, the closest match is found. That is, the target driver with the highest similarity score is identified as the user currently driving the vehicle ahead. If there are multiple users with high similarity scores, further filtering can be performed based on other auxiliary information (such as timestamps, geographical locations, etc.).

[0072] Step S106: Based on the target driving habit route, target driving habit time and target driving habit lane corresponding to the current target driving user, predict the future driving trajectory of the vehicle in front on the road, and obtain the vehicle trajectory prediction result.

[0073] In this embodiment, the system determines the vehicle's driving status within a specific time period using video data and matches this information with the known driving habits of various drivers. This process helps narrow down the range of potential drivers. The system identifies the vehicle ahead in the dashcam video of the current vehicle and determines whether it belongs to the previously collected target vehicle database. Once the vehicle ahead is confirmed to be one of the target vehicles, the system attempts to match the previously collected driving habit data of the driver of that vehicle with the currently observed driving behavior. Based on the degree of matching between the driving habit data and the real-time video data, the system can infer which driver is most likely currently driving the vehicle ahead. Finally, based on the determined driving habit data of the driver (such as preferred driving routes, times, and lanes), combined with real-time traffic conditions, the system predicts the driving trajectory of the vehicle ahead over a future period. The system not only considers the physical characteristics of the vehicle itself but also deeply analyzes the specific driver's behavioral habits. This method provides a more accurate prediction of the upcoming driving trajectory of the vehicle ahead, solving the technical problem of low accuracy in predicting the upcoming driving trajectory of the vehicle ahead.

[0074] In some embodiments, the aforementioned vehicle-mounted terminal is equipped with an infrared temperature detector (such as an infrared probe). Figure 2 As shown, the method may also include the following steps:

[0075] Step S110: Detect the tire temperature of the vehicle in front corresponding to its own vehicle terminal using an infrared temperature detector.

[0076] As one possible implementation, sensors (such as cameras or radar) on the vehicle's own terminal are used to identify and lock onto the position of the vehicle ahead. Once the position of the vehicle ahead is determined, the system adjusts the orientation of the infrared temperature detector so that it is accurately pointed at the tires of the target vehicle. The infrared temperature detector begins to operate, measuring the surface temperature of the tires by detecting the infrared radiation emitted by them. During this process, the system continuously collects data and adjusts the probe angle as needed to obtain the most accurate reading. For data analysis and processing, the collected data is transmitted to the onboard computer for analysis. Specific algorithms are used to process this data, calculate the actual temperature value of the tires, and assess whether it exceeds a safety threshold.

[0077] Step S120: Determine the temperature difference between the tire temperature and the current ambient temperature.

[0078] The current ambient temperature refers to the temperature of the environment in which the vehicle's onboard terminal is located. The onboard terminal is equipped with an ambient temperature sensor to monitor the air temperature around the vehicle in real time. This sensor continuously collects data and sends the results to the onboard computer for processing. For tire temperature detection, an infrared temperature detector is used to measure the surface temperature of the tires of the vehicle in front in a non-contact manner. The infrared temperature detector needs to be accurately positioned and focused on the tire location to ensure the representativeness of the collected data. Since ambient temperature and tire temperature may be measured at different times, the system must ensure the accuracy of the data within the same time period. Slight time synchronization adjustments or the impact of brief delays may be necessary. Specifically, the temperature difference calculation process compares the tire temperature data obtained from the infrared temperature detector with the data provided by the ambient temperature sensor. The calculation formula is: Temperature Difference = Tire Temperature - Ambient Temperature. The obtained temperature difference is then analyzed to determine if it exceeds a preset safety range. If the temperature difference exceeds a threshold, it indicates a potential risk of tire overheating, requiring further attention or intervention.

[0079] Step S130: Determine whether the temperature difference exceeds the specified temperature difference threshold.

[0080] In one possible implementation, firstly, a reasonable temperature difference threshold is set based on the vehicle manufacturer's recommendations or industry standards. This threshold is used to determine whether the difference between tire temperature and ambient temperature is within a safe range. This threshold is stored in the vehicle's onboard computer as a standard for subsequent comparisons. The current ambient temperature is acquired using an ambient temperature sensor, and the tire surface temperature is measured using an infrared temperature detector. Accuracy and precision are ensured during data acquisition to avoid errors caused by external factors (such as weather, road conditions, etc.). Using the data obtained above, the actual temperature difference is calculated according to the formula: Temperature Difference = Tire Temperature - Ambient Temperature. Then, the calculated temperature difference is compared with the preset temperature difference threshold. If the temperature difference is less than or equal to the set threshold, the current tire temperature is considered to be within the normal range, and no special action is required. If the temperature difference exceeds the set threshold, the process proceeds to the next step.

[0081] In step S140, if the temperature difference exceeds the specified temperature difference threshold, it is determined that the vehicle in front is currently in a state of fatigue driving, and the driving direction and / or driving speed of the vehicle terminal are controlled to change so as to increase the distance between the vehicle terminal and the vehicle in front.

[0082] By monitoring the tire temperature of the vehicle ahead and determining whether the temperature difference between the tire temperature and the current ambient temperature exceeds a specified temperature difference threshold, the larger the temperature difference indicates that the vehicle ahead has been driving for a longer period of time. This allows for the determination of whether the vehicle ahead is in a state of fatigue due to prolonged driving, thus enabling data detection of the fatigue level of the vehicle ahead.

[0083] As an optional implementation, step S140, which controls the change of the vehicle-mounted terminal's driving direction and / or speed, may specifically include the following steps: Based on the vehicle trajectory prediction results and fatigue driving status, control the change of the vehicle-mounted terminal's driving trajectory so that it changes from being behind the vehicle in front to being to the side of the vehicle in front. While the vehicle-mounted terminal is to the side of the vehicle in front, control the increase of its driving speed so that it is in front of the vehicle in front and the distance between them increases. This processing method allows for more efficient control of maintaining a safe relative position and distance between the vehicle-mounted terminal and the vehicle in front.

[0084] As an alternative implementation, step S140, which controls the change of the vehicle-mounted terminal's driving direction and / or speed, may specifically include the following steps: Based on the vehicle trajectory prediction results and fatigue driving status, control the vehicle-mounted terminal's speed to decrease, so that the vehicle-mounted terminal is positioned behind the vehicle in front and the distance between them is greater than a specified distance. This approach allows for more precise and efficient control of maintaining a safe relative distance between the vehicle-mounted terminal and the vehicle in front.

[0085] Step S150: The vehicle information interaction content between the vehicle terminal and the vehicle in front is determined by the latest driving direction and speed corresponding to the changes of the vehicle terminal, the tire temperature of the vehicle in front and the temperature difference. The vehicle information interaction content is then sent to the corresponding terminal of the vehicle in front.

[0086] In existing technologies, judging whether a vehicle ahead is about to slow down is based solely on the vehicle's lights. This method cannot determine if the vehicle ahead is slowing down due to other reasons, such as fatigue. These factors can affect the control of one's own vehicle, resulting in poor automatic driving control.

[0087] In this embodiment, by monitoring the tire temperature of the vehicle ahead and determining whether the temperature difference between the tire temperature and the current ambient temperature exceeds a specified temperature difference threshold, the larger the temperature difference indicates that the vehicle ahead has been driving for a longer period of time. This allows the system to determine whether the vehicle ahead is in a state of fatigue due to prolonged driving, thus enabling data detection of the fatigue level of the vehicle ahead. Based on this, the system adjusts its own vehicle's driving direction and / or speed to increase the safe distance from the vehicle ahead. When the system determines that the vehicle ahead may pose a risk of fatigue driving, it can automatically adjust the vehicle's speed or lane, achieving early warning and proactive avoidance of dangerous situations. This realizes intelligent early warning and proactive risk avoidance for the vehicle's autonomous driving control, improving the effectiveness of automatic driving control.

[0088] Furthermore, by detecting changes in the tire temperature of vehicles ahead, the system can infer their driving status, particularly identifying potential instability caused by driver fatigue, thus allowing for proactive measures to prevent rear-end collisions. Moreover, it enables monitoring and response to the surrounding environment without requiring additional driver intervention, reducing the driver's workload.

[0089] In some embodiments, the vehicle-mounted terminal is further equipped with an image acquisition device; the method may also include the following steps:

[0090] Step S210: Acquire driving video data of the vehicle in front using an image acquisition device, and identify the target vehicle type of the vehicle in front based on the driving video data;

[0091] Step S220: Retrieve vehicle performance data for the target vehicle type; wherein, vehicle performance data includes at least one of acceleration performance, braking performance, and maximum vehicle performance threshold.

[0092] Step S230: Analyze the maximum drivable speed, maximum acceleration, and maximum deceleration of the vehicle in front based on vehicle performance analysis;

[0093] Step S240: Based on the driving video data, the AI ​​system analyzes the driving habits of the first user for the vehicle in front.

[0094] Step S250: Bind driving habits, maximum drivable speed, maximum acceleration, and maximum deceleration to the license plate number of the vehicle in front to generate comprehensive driving analysis data for the vehicle in front. Send the comprehensive driving analysis data to the platform server so that multiple second users' own vehicle terminals can obtain the comprehensive driving analysis data corresponding to the vehicle in front through the platform server. The platform server stores comprehensive driving analysis data corresponding to multiple vehicles including the vehicle in front.

[0095] Step S260: In response to the second target user's request for correction of the comprehensive driving analysis data in the platform server, the comprehensive driving analysis data is corrected according to the data in the correction request to obtain real-time comprehensive driving data so that the comprehensive driving analysis data in the platform server is updated in real time.

[0096] Step S270: Obtain comprehensive real-time driving data for multiple vehicles from the platform server, and control the driving direction and speed of the vehicle terminal based on the driving habits, maximum driving speed, maximum acceleration and maximum deceleration of each vehicle in the comprehensive real-time driving data.

[0097] By monitoring vehicles ahead in real time through image acquisition equipment and identifying the target vehicle type and its performance (acceleration, braking performance, etc.) based on driving video data, combined with AI system analysis of the first user's driving habits, the system can predict the behavior patterns of vehicles ahead and take measures in advance to avoid potential accidents. For example, when it detects that a vehicle ahead may suddenly decelerate, the system can automatically adjust its speed or change lanes to maintain a safe distance.

[0098] Furthermore, by generating comprehensive driving analysis data for each vehicle ahead, including its driving habits, maximum speed, acceleration, and deceleration, and binding it to the license plate number, this not only helps to gain a deeper understanding of the behavior patterns of specific vehicles, but also provides early warning information to other users, helping them make more informed driving decisions.

[0099] Furthermore, by enabling second users (i.e., other drivers) to request corrections to the comprehensive driving analysis data on the platform's server, the accuracy and real-time nature of the data are ensured. This mechanism allows all users to benefit from the latest and most accurate information, achieving a dynamic update and correction mechanism, and further enhancing the system's practical value.

[0100] In some embodiments, the above-mentioned control of the driving direction and speed of the vehicle terminal based on the driving habits and maximum drivable speed of each vehicle in the comprehensive real-time driving data may specifically include the following steps:

[0101] Based on the vehicle's deviation from the lane center position error according to driving habits, the driving direction of its own vehicle terminal is controlled by the following formula: θs = Kp × e ( t )+ Ki + ;in, θs It's the steering angle. e ( t This represents the positional error of the vehicle deviating from the center of the lane. Kp It's about proportion. Ki It's an integral. Kd These are differential coefficients;

[0102] The vehicle's onboard terminal controls its own speed based on the maximum drivable speed. Vself ( t )= Vfront ( t )+ Kp ×( Dsafe - Dcurrent );in, Vself ( t () is the target speed of its own vehicle terminal. Vfront ( t () is the maximum speed that the vehicle in front can travel. Kp It is a proportionality coefficient. Dsafe It is the set safe distance. Dcurrent It represents the current distance to the vehicle in front.

[0103] In this embodiment of the application, the vehicle control method using the above formula makes the control of the vehicle terminal's driving direction and speed more precise.

[0104] In some embodiments, the above-mentioned analysis of the driving habits of the first user corresponding to the vehicle ahead based on driving video data using an AI system may specifically include the following steps:

[0105] The time interval between two frames is calculated based on the timestamp difference in the corresponding video frames of the driving video data. Based on the time interval, an object detection algorithm is used to identify the change data of vehicle position between the vehicle in front and its own vehicle terminal, and the first speed of the vehicle in front is determined based on the change data of vehicle position.

[0106] Determine the first acceleration or first deceleration of the vehicle ahead based on the change data of the first speed over a continuous time period;

[0107] Based on driving video data, the system uses computer vision processing to track the positions of vehicles ahead and behind the vehicle's own onboard terminal, and then uses a formula... R =Δ Dfront / ΔT Calculate the data on how the distance between the vehicle ahead and the vehicle's own onboard terminal changes over time; among which... R Δ represents the rate of change of distance from the vehicle in front. Dfront It is the change in distance from the vehicle in front, Δ T It refers to the time period during which the change occurred;

[0108] Based on the data of the first speed, first acceleration or first deceleration, and the change of distance over time, the AI ​​system analyzes the driving habit data of the first user regarding the vehicle ahead using the following formula: S = w 1× Vs + w 2× As + w 3× Rs; in, S It's overall driving habit data. w 1, w 2, w 3 is the weighting coefficient. Vs It is the first speed. As This is the first acceleration or the first deceleration. Rs This data shows how distance changes over time.

[0109] In this embodiment of the application, the calculation method using the above formula makes the data on the driving habits of the first user for the vehicle in front more comprehensive and accurate.

[0110] In some embodiments, the above-mentioned binding of driving habits, maximum drivable speed, maximum acceleration, and maximum deceleration with the license plate number of the vehicle in front generates comprehensive driving analysis data for the vehicle in front. Specifically, this may include the following steps:

[0111] Based on driving habits, maximum drivable speed, maximum acceleration, and maximum deceleration, comprehensive driving analysis data for the vehicle ahead is generated using the following formula: Stotal =w 1× Vs + w 2× As + w 3× Rs + w 4× Vmax + w 5× Amax - w 6×∣ Amin |; among which, Stotal It is comprehensive driving analysis data; w 1. w 2. w 3. w 4. w 5 and w 6 represents the weighting coefficients of each indicator. Vs For driving speed, As Acceleration, Rs Rate of change of distance between the vehicle ahead and its own onboard terminal Vmax It is the maximum permissible speed. Amax It is to accelerate to the maximum extent. Amin That is the maximum deceleration.

[0112] In this embodiment of the application, the calculation method using the above formula makes the generated comprehensive driving analysis data for the vehicle ahead more comprehensive and accurate.

[0113] Figure 3 A schematic diagram of a vehicle trajectory prediction device based on YTS is provided. This device can be applied to its own in-vehicle terminal. Figure 3 As shown, the YTS-based vehicle trajectory prediction device 300 includes:

[0114] The identification module 301 is used to acquire vehicle driving video data of the target vehicle, and identify the vehicle type, vehicle model and several driving users corresponding to the target vehicle based on the vehicle driving video data.

[0115] The matching module 302 is used to determine the driving time corresponding to the target vehicle in the vehicle driving video data based on the vehicle driving video data, and to match the target driving time of the target vehicle for each driver in the driving time.

[0116] Analysis module 303 is used to analyze the driving habit data of each driver user based on the target driving time and vehicle driving video data corresponding to each driver user through the YTS system; the driving habit data includes driving habit route, driving habit time and driving habit lane;

[0117] The first determining module 304 is used to determine the vehicle currently driving in front of the vehicle terminal from the driving recorder of its own vehicle terminal, and to determine whether the vehicle in front exists from a plurality of target vehicles. If the vehicle in front exists, the target driving habit data of a plurality of target driving users corresponding to the vehicle in front is determined from the driving habit data corresponding to the plurality of target vehicles.

[0118] The second determining module 305 is used to match the target driving habit data of each target driver with the corresponding current driving habit data in the video data of the vehicle in front based on the video data of the vehicle in front in the dashcam, and determine the current target driver currently driving the vehicle in front from the plurality of target drivers according to the matching result.

[0119] The prediction module 306 is used to predict the future driving trajectory of the vehicle ahead on the road based on the target driving habit route, target driving habit time and target driving habit lane corresponding to the current target driving user, and obtain the vehicle trajectory prediction result.

[0120] The YTS-based vehicle trajectory prediction device provided in this application has the same technical features as the YTS-based vehicle trajectory prediction method provided in the above embodiments, so it can also solve the same technical problems and achieve the same technical effects.

[0121] An electronic device provided in this application embodiment, such as Figure 4 As shown, the electronic device 400 includes a processor 402 and a memory 401. The memory stores a computer program that can run on the processor. When the processor executes the computer program, it implements the steps of the method provided in the above embodiments.

[0122] See Figure 4 The electronic device also includes a bus 403 and a communication interface 404. The processor 402, the communication interface 404 and the memory 401 are connected through the bus 403. The processor 402 is used to execute executable modules, such as computer programs, stored in the memory 401.

[0123] The memory 401 may include high-speed random access memory (RAM) or non-volatile memory, such as at least one disk storage device. Communication between this system network element and at least one other network element is achieved through at least one communication interface 404 (which can be wired or wireless), such as the Internet, wide area network, local area network, or metropolitan area network.

[0124] Bus 403 can be an ISA bus, PCI bus, or EISA bus, etc. The bus can be divided into address bus, data bus, control bus, etc. For ease of representation, Figure 4 The symbol is represented by a single double-headed arrow, but this does not mean that there is only one bus or one type of bus.

[0125] The memory 401 is used to store programs. After receiving an execution instruction, the processor 402 executes the program. The method executed by the apparatus defined by the process disclosed in any of the preceding embodiments of this application can be applied to the processor 402 or implemented by the processor 402.

[0126] Processor 402 may be an integrated circuit chip with signal processing capabilities. In implementation, each step of the above method can be completed by the integrated logic circuitry in the hardware of processor 402 or by instructions in software form. The processor 402 can be a general-purpose processor, including a Central Processing Unit (CPU), a Network Processor (NP), etc.; it can also be a Digital Signal Processor (DSP), an Application Specific Integrated Circuit (ASIC), a Field-Programmable Gate Array (FPGA), or other programmable logic devices, discrete gate or transistor logic devices, or discrete hardware components. It can implement or execute the methods, steps, and logic block diagrams disclosed in the embodiments of this application. The general-purpose processor can be a microprocessor or any conventional processor. The steps of the methods disclosed in the embodiments of this application can be directly manifested as execution by a hardware decoding processor, or execution by a combination of hardware and software modules in the decoding processor. The software module can reside in a mature storage medium in the field, such as random access memory, flash memory, read-only memory, programmable read-only memory, electrically erasable programmable memory, or registers. This storage medium is located in memory 401, and processor 402 reads the information from memory 401 and, in conjunction with its hardware, completes the steps of the above method.

[0127] Corresponding to the above-described YTS-based vehicle trajectory prediction method, this application also provides a computer-readable storage medium storing computer-executable instructions. When called and executed by a processor, the computer-executable instructions cause the processor to perform the steps of the above-described YTS-based vehicle trajectory prediction method.

[0128] The YTS-based vehicle trajectory prediction device provided in this application embodiment can be specific hardware on a device or software or firmware installed on the device. The implementation principle and technical effects of the device provided in this application embodiment are the same as those in the foregoing method embodiments. For the sake of brevity, any parts not mentioned in the device embodiment can be referred to the corresponding content in the foregoing method embodiments. Those skilled in the art will clearly understand that, for the sake of convenience and brevity, the specific working processes of the systems, devices, and units described above can all be referred to the corresponding processes in the above method embodiments, and will not be repeated here.

[0129] In the embodiments provided in this application, it should be understood that the disclosed apparatus and methods can be implemented in other ways. The apparatus embodiments described above are merely illustrative. For example, the division of units is only a logical functional division, and in actual implementation, there may be other division methods. Furthermore, multiple units or components may be combined or integrated into another system, or some features may be ignored or not executed. Additionally, the displayed or discussed mutual couplings, direct couplings, or communication connections may be through some communication interfaces; indirect couplings or communication connections between devices or units may be electrical, mechanical, or other forms.

[0130] For example, the flowcharts and block diagrams in the accompanying drawings illustrate the architecture, functionality, and operation of possible implementations of apparatus, methods, and computer program products according to various embodiments of this application. In this regard, each block in a flowchart or block diagram may represent a module, segment, or portion of code containing one or more executable instructions for implementing a specified logical function. It should also be noted that in some alternative implementations, the functions marked in the blocks may occur in a different order than those marked in the drawings. For example, two consecutive blocks may actually be executed substantially in parallel, and they may sometimes be executed in reverse order, depending on the functions involved. It should also be noted that each block in a block diagram and / or flowchart, and combinations of blocks in block diagrams and / or flowcharts, can be implemented using a dedicated hardware-based system that performs the specified function or action, or using a combination of dedicated hardware and computer instructions.

[0131] 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.

[0132] In addition, the functional units in the embodiments provided in 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.

[0133] If the aforementioned functions are implemented as software functional units and sold or used as independent products, they can be stored in a computer-readable storage medium. Based on this understanding, the technical solution of this application, in essence, or the part that contributes to the prior art, or a portion of the technical solution, can be embodied in the form of a software product. This computer software product is stored in a storage medium and includes several instructions to cause a computer device (which may be a personal computer, server, or network device, etc.) to execute all or part of the steps of the YTS-based vehicle trajectory prediction method 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.

[0134] It should be noted that similar labels and letters in the following figures indicate similar items. Therefore, once an item is defined in one figure, it does not need to be further defined and explained in subsequent figures. In addition, the terms "first", "second", "third", etc. are used only to distinguish descriptions and should not be construed as indicating or implying relative importance.

[0135] Finally, it should be noted that the above-described embodiments are merely specific implementations of this application, used to illustrate the technical solutions of this application, and not to limit them. The protection scope of this application is not limited thereto. Although this application has been described in detail with reference to the foregoing embodiments, those skilled in the art should understand that any person skilled in the art can still modify or easily conceive of changes to the technical solutions described in the foregoing embodiments, or make equivalent substitutions for some of the technical features, within the scope of the technology disclosed in this application; and these modifications, changes, or substitutions do not cause the essence of the corresponding technical solutions to deviate from the scope of the technical solutions of the embodiments of this application. All should be covered within the protection scope of this application. Therefore, the protection scope of this application should be determined by the protection scope of the claims.

Claims

1. A vehicle trajectory prediction method based on YTS, characterized in that, Applied to vehicle-mounted terminals, the method includes: Acquire vehicle driving video data of the target vehicle, and identify the vehicle type, vehicle model and several driving users corresponding to the target vehicle based on the vehicle driving video data; Based on the vehicle driving video data, determine the driving time corresponding to the target vehicle in the vehicle driving video data, and match the target driving time of the target vehicle for each driver in the driving time. Based on the target driving time and vehicle driving video data corresponding to each driver user, the YTS system analyzes the driving habit data corresponding to each driver user; the driving habit data includes driving habit route, driving habit time and driving habit lane. The system determines the vehicle currently traveling in front of its own vehicle terminal from the vehicle's dashcam data, and determines whether the vehicle in front exists from among multiple target vehicles. If the vehicle in front exists, the system determines the target driving habit data of several target drivers corresponding to the vehicle in front from the driving habit data corresponding to the multiple target vehicles. Based on the video data of the vehicle in front in the dashcam, the target driving habit data of each target driver is matched with the current driving habit data corresponding to the video data of the vehicle in front, and the current target driver currently driving the vehicle in front is determined from the plurality of target drivers according to the matching results. Based on the target driving habit route, target driving habit time, and target driving habit lane corresponding to the current target driving user, the future driving trajectory of the vehicle ahead on the road is predicted to obtain the vehicle trajectory prediction result.

2. The method according to claim 1, characterized in that, The vehicle-mounted terminal is equipped with an infrared temperature detector; it also includes: The infrared temperature detector detects the tire temperature of the vehicle in front, corresponding to its own vehicle terminal. Determine the temperature difference between the tire temperature and the current ambient temperature; wherein, the current ambient temperature is the temperature of the environment in which the vehicle terminal is located; Determine whether the temperature difference exceeds a specified temperature difference threshold; If the temperature difference exceeds the specified temperature difference threshold, it is determined that the vehicle in front is currently in a state of fatigue driving, and the driving direction and / or driving speed of the vehicle terminal are controlled to be changed so as to increase the vehicle distance between the vehicle terminal and the vehicle in front. The vehicle information interaction content between the vehicle terminal and the vehicle ahead is determined by the latest driving direction and speed after the change, the tire temperature of the vehicle ahead, and the temperature difference. The vehicle information interaction content is then sent to the terminal corresponding to the vehicle ahead.

3. The method according to claim 2, characterized in that, The control to change the driving direction and / or speed of the vehicle-mounted terminal includes: Based on the vehicle trajectory prediction results and the fatigue driving state, the vehicle's own on-board terminal's driving trajectory is changed, so that the on-board terminal changes from being behind the vehicle in front to being to the side of the vehicle in front. While the on-board terminal is to the side of the vehicle in front, its driving speed is increased, so that the on-board terminal is in front of the vehicle in front and the distance between them increases; or... Based on the vehicle trajectory prediction results and the fatigue driving state, the vehicle terminal's driving speed is reduced so that the vehicle terminal is behind the vehicle in front and the distance between the two vehicles is greater than a specified distance.

4. The method according to claim 2, characterized in that, The vehicle-mounted terminal is also equipped with an image acquisition device; the method further includes: The image acquisition device acquires driving video data of the vehicle in front, and identifies the target vehicle type of the vehicle in front based on the driving video data; Retrieve the vehicle performance of the target vehicle type; wherein the vehicle performance includes at least one of acceleration performance, braking performance, and maximum vehicle performance threshold; Based on the vehicle performance analysis, the maximum drivable speed, maximum acceleration, and maximum deceleration of the vehicle ahead are determined. Based on the driving video data, the AI ​​system analyzes the driving habits of the first user corresponding to the vehicle in front; The driving habits, maximum drivable speed, maximum acceleration, and maximum deceleration are bound to the license plate number of the vehicle ahead to generate comprehensive driving analysis data for the vehicle ahead. This comprehensive driving analysis data is then sent to the platform server, allowing multiple second-user vehicle terminals to obtain the comprehensive driving analysis data corresponding to the vehicle ahead through the platform server. The platform server stores comprehensive driving analysis data for multiple vehicles, including the vehicle ahead. In response to a correction request from the second target user regarding the comprehensive driving analysis data in the platform server, the comprehensive driving analysis data is corrected according to the data in the correction request to obtain real-time comprehensive driving data, so that the comprehensive driving analysis data in the platform server is updated in real time. The system obtains comprehensive real-time driving data for multiple vehicles from the platform server, and controls the driving direction and speed of its own vehicle terminal based on the driving habits, maximum driving speed, maximum acceleration, and maximum deceleration of each vehicle in the comprehensive real-time driving data.

5. The method according to claim 4, characterized in that, Based on the driving habits and maximum drivable speed of each vehicle in the comprehensive real-time driving data, the driving direction and speed of the vehicle's own onboard terminal are controlled, including: Based on the vehicle's deviation from the lane center position error in the aforementioned driving habits, the driving direction of the vehicle-mounted terminal is controlled using the following formula: θs = Kp × e ( t )+ Ki + ;in, θs It's the steering angle. e ( t This represents the positional error of the vehicle deviating from the center of the lane. Kp It's about proportion. Ki It's an integral. Kd These are differential coefficients; The vehicle's speed is controlled by the following formula based on the maximum drivable speed: Vself ( t )= Vfront ( t )+ Kp ×( Dsafe - Dcurrent );in, Vself ( t The target speed of the vehicle's own onboard terminal is ). Vfront ( t () is the maximum drivable speed of the vehicle ahead. Kp It is a proportionality coefficient. Dsafe It is the set safe distance. Dcurrent It represents the current distance to the vehicle in front.

6. The method according to claim 4, characterized in that, The step of analyzing the driving habits of the first user corresponding to the vehicle ahead using the AI ​​system based on the driving video data includes: The time interval between two frames is calculated based on the timestamp difference in the corresponding video frames of the driving video data. Based on the time interval, an object detection algorithm is used to identify the change data of the vehicle position between the vehicle in front and the vehicle terminal itself, and the first speed of the vehicle in front is determined based on the change data of the vehicle position. The first acceleration or first deceleration of the vehicle ahead is determined based on the change data of the first speed over a continuous time period. Based on the driving video data, the positions of the vehicles in front and the vehicle's own onboard terminal are tracked using computer vision processing, and then calculated using a formula. R =Δ Dfront / ΔT Calculate the distance between the vehicle ahead and the vehicle's own onboard terminal as a function of time; wherein, R Δ represents the rate of change of distance from the vehicle in front. Dfront It is the change in distance from the vehicle in front, Δ T It refers to the time period during which the change occurred; Based on the first speed, the first acceleration or deceleration, and the distance changing over time, the AI ​​system analyzes the driving habit data of the first user corresponding to the vehicle ahead using the following formula: S = w 1× Vs + w 2× As + w 3× Rs; in, S It's overall driving habit data. w 1, w 2, w 3 is the weighting coefficient. Vs It is the first speed. As The first acceleration or the first deceleration, Rs This refers to the data showing how the distance changes over time.

7. The method according to claim 4, characterized in that, The process of binding the driving habits, the maximum drivable speed, the maximum acceleration, and the maximum deceleration with the license plate number of the vehicle ahead to generate comprehensive driving analysis data for the vehicle ahead includes: Based on the driving habits, the maximum drivable speed, the maximum acceleration, and the maximum deceleration, comprehensive driving analysis data for the vehicle ahead is generated using the following formula: Stotal = w 1× Vs + w 2× As + w 3× Rs + w 4× Vmax + w 5× Amax - w 6×∣ Amin |; among which, Stotal It is comprehensive driving analysis data; w 1. w 2. w 3. w 4. w 5 and w 6 represents the weighting coefficients of each indicator. Vs For driving speed, As Acceleration Rs The rate of change of distance between the vehicle ahead and the vehicle's own onboard terminal. Vmax It is the maximum permissible speed. Amax It is to accelerate to the maximum extent. Amin That is the maximum deceleration.

8. A vehicle trajectory prediction device based on YTS, characterized in that, Applied to in-vehicle terminals, the in-vehicle terminal itself is equipped with an infrared temperature detector; the device includes: The identification module is used to acquire vehicle driving video data of the target vehicle, and identify the vehicle type, vehicle model and several driving users corresponding to the target vehicle based on the vehicle driving video data. The matching module is used to determine the driving time corresponding to the target vehicle in the vehicle driving video data based on the vehicle driving video data, and to match the target driving time of the target vehicle for each driver in the driving time. The analysis module is used to analyze the driving habit data of each driver user based on the target driving time and the vehicle driving video data, through the YTS system; the driving habit data includes driving habit route, driving habit time and driving habit lane; The first determining module is used to determine the vehicle currently driving in front of the vehicle terminal from the driving recorder of its own vehicle terminal, and to determine whether the vehicle in front exists from a plurality of target vehicles. If the vehicle in front exists, the module determines the target driving habit data of a plurality of target driving users corresponding to the vehicle in front from the driving habit data corresponding to the plurality of target vehicles. The second determining module is used to match the target driving habit data of each target driver with the corresponding current driving habit data in the video data of the vehicle in front, based on the video data of the vehicle in front in the dashcam, and determine the current target driver currently driving the vehicle in front from the plurality of target drivers according to the matching result. The prediction module is used to predict the future driving trajectory of the vehicle ahead on the road based on the target driving habit route, target driving habit time and target driving habit lane corresponding to the current target driving user, and obtain the vehicle trajectory prediction result.

9. An electronic device comprising a memory and a processor, wherein the memory stores a computer program executable on the processor, characterized in that, When the processor executes the computer program, it implements the steps of the method described in any one of claims 1 to 7.

10. A computer-readable storage medium, characterized in that, The computer-readable storage medium stores computer-executable instructions that, when invoked and executed by a processor, cause the processor to perform the method according to any one of claims 1 to 7.

Images