A method, system, device and medium for determining a rear collision warning for a vehicle
Patent Information
- Application Number
- CN202610965290.6
- Authority / Receiving Office
- CN · China
- Patent Type
- Applications(China)
- Current Assignee / Owner
- Filing Date
- 2026-06-30
- Publication Date
- 2026-09-29
AI Technical Summary
[0004]本发明实施例提供一种车辆后方碰撞预警的确定方法、系统、设备及介质，以解决相关技术中传统方法仅根据目标的中心点位置进行碰撞预警，存在碰撞预警准确率低的技术问题
[0015]本发明提供的技术方案带来的有益效果包括：
Smart Images
Figure CN122830665A_ABST
Abstract
Description
Technical Field
[0001] This invention relates to the field of vehicle control technology, and in particular to a method, system, device and medium for determining rear collision warning of a vehicle. Background Technology
[0002] With the rapid development of intelligent driving technology, vehicle active safety systems have become an important feature for improving driving safety. Rear collision warning, as a key function of active safety systems, is mainly used to monitor traffic participants in the area behind the vehicle and promptly warn the driver or trigger automatic braking when a collision risk is detected, thereby effectively reducing the incidence of rear collision accidents and ensuring the safety of people and vehicles. Especially in scenarios such as changing lanes, reversing out of a parking space, or passing through intersections, accurately identifying the risk of objects crossing from behind is crucial for avoiding traffic accidents.
[0003] Existing rear collision warning technologies primarily rely on sensor devices to acquire information about targets behind the vehicle. In terms of risk assessment logic, traditional methods typically simplify rear targets to point masses, calculating collision time solely based on the target's center point position and relative velocity. However, this center point-based approach ignores parameters such as the target's geometric dimensions. When a large target causes vehicle intrusion but not the center point, false alarms are likely to occur, reducing the accuracy of rear collision warnings and increasing the accident rate. Summary of the Invention
[0004] This invention provides a method, system, device, and medium for determining rear collision warning of a vehicle, in order to solve the technical problem that traditional methods in related technologies only rely on the center point position of the target for collision warning, resulting in low accuracy of collision warning.
[0005] Firstly, a method for determining rear collision warning for vehicles is provided, including the following steps: Acquire motion information of a target behind you, including the target's size, coordinates relative to the center point, relative velocity, relative acceleration, relative yaw rate, and relative heading angle. The predicted collision time of the rear target relative to the vehicle is calculated based on the motion information of the rear target. Then, based on the motion information of the target behind, calculate the predicted coordinates of the edge points of the target behind after the predicted collision time; Whether to issue a collision warning is determined based on the predicted coordinates of the edge points and the preset collision area.
[0006] In some embodiments, calculating the predicted collision time of the rear target relative to the vehicle based on the motion information of the rear target includes: The collision distance is calculated based on the relative center point coordinates of the target behind and the vehicle's preset collision point coordinates; The collision time is predicted based on the collision distance and the relative speed of the target behind.
[0007] In some embodiments, the step of calculating the predicted coordinates of the edge points of the rear target after the predicted collision time based on the motion information of the rear target includes: The motion state of the target behind is determined based on the relative yaw rate and relative acceleration of the target behind. The motion state includes uniform linear motion and variable speed turning motion. If the target behind is moving at a constant speed in a straight line, then based on the relative velocity and relative center point coordinates of the target behind, the predicted relative center point coordinates of the target behind after the predicted collision time are calculated using a preset constant speed in a straight line motion prediction algorithm. If the target behind is in a variable speed turning motion, the predicted relative center point coordinates of the target behind are calculated by a preset variable speed turning motion prediction algorithm based on the target's relative yaw rate, relative heading angle, relative velocity, relative acceleration, and relative center point coordinates. The predicted coordinates of the edge points of the rear target after the predicted collision time are calculated based on the predicted relative center point coordinates of the rear target after the predicted collision time and the size of the rear target.
[0008] In some embodiments, determining the motion state of the rear target based on its relative yaw rate and relative acceleration includes: If the relative yaw rate of the target behind is less than the preset angular velocity and the relative acceleration is 0, then it is uniform linear motion; If the relative yaw rate of the target behind is greater than the preset angular velocity and the relative acceleration is not zero, then it is a variable speed turning motion.
[0009] In some embodiments, if the motion state of the rear target is a variable-speed turning motion, then based on the relative yaw rate, relative heading angle, relative velocity, relative acceleration, and relative center point coordinates of the rear target, the predicted relative center point coordinates of the rear target after the predicted collision time are calculated using a preset variable-speed turning motion prediction algorithm, and the method further includes: Obtain the predicted relative center point coordinates of targets behind at multiple time points and the corresponding relative center point coordinates of targets behind at multiple time points later; The adaptive factor of the rear target is calculated based on the predicted relative center point coordinates of the rear target at multiple time points and the corresponding relative center point coordinates of the rear target at multiple time points. The predicted collision time is updated based on the adaptive factor of the target behind; The predicted relative center point coordinates after the predicted collision time are updated based on the updated predicted collision time.
[0010] In some embodiments, calculating the adaptive factor of the rear target based on the predicted relative center point coordinates of the rear target at multiple time points and the corresponding relative center point coordinates of the rear target at multiple time points includes: The information sequence of the rear target is calculated based on the predicted relative center point coordinates of the rear target at multiple time points and the corresponding relative center point coordinates of the rear target at multiple time points. Calculate the predicted innovation covariance of the target based on the innovation sequence of the target, and calculate the actual innovation covariance of the target. The adaptive factor of the rear target is calculated based on the predicted information covariance and the actual information covariance of the rear target.
[0011] In some embodiments, determining whether to issue a collision warning based on the predicted coordinates of the edge points and a preset collision area includes: Determine whether the predicted coordinates of any edge point are within the preset collision area. If so, issue a collision warning.
[0012] Secondly, a vehicle rear collision warning determination system is provided, including: The acquisition module is used to acquire the motion information of the target behind, which includes the target's size, relative center point coordinates, relative velocity, relative acceleration, relative yaw rate, and relative heading angle. The first calculation module is used to calculate the predicted collision time of the rear target relative to the vehicle based on the motion information of the rear target. The second calculation module is used to calculate the predicted coordinates of the edge points of the rear target after the predicted collision time based on the motion information of the rear target. The judgment module is used to determine whether to issue a collision warning based on the predicted coordinates of the edge points and the preset collision area.
[0013] Thirdly, a computer device is provided, comprising: a memory and a processor, wherein the memory stores at least one instruction, the at least one instruction being loaded and executed by the processor to implement the aforementioned method for determining a rear collision warning for a vehicle.
[0014] Fourthly, a computer-readable storage medium is provided, the computer-readable storage medium storing computer instructions, which, when executed by a computer, cause the computer to perform the aforementioned method for determining a rear collision warning for a vehicle.
[0015] The beneficial effects of the technical solution provided by this invention include: This invention discloses a method, system, device, and medium for determining rear collision warning for vehicles. It acquires motion information of a rear target, including the target's size, coordinates relative to its center point, relative velocity, relative acceleration, relative yaw rate, and relative heading angle. Based on this motion information, it calculates the predicted collision time between the rear target and the vehicle. Then, it calculates the predicted coordinates of the target's edge points after the predicted collision time. Finally, it determines whether to issue a collision warning based on the predicted coordinates of the edge points and a preset collision area. This invention overcomes the false alarms and missed alarms caused by traditional technologies relying on center point determination by determining the edge points of the rear target for collision assessment, thus improving the accuracy and reliability of rear collision warnings. Attached Figure Description
[0016] To more clearly illustrate the technical solutions in the embodiments of the present invention, the accompanying drawings used in the description of the embodiments will be briefly introduced below. Obviously, the accompanying drawings described below are only some embodiments of the present invention. For those skilled in the art, other drawings can be obtained based on these drawings without creative effort.
[0017] Figure 1 This is a flowchart illustrating a method for determining a rear collision warning for a vehicle, as provided in an embodiment of the present invention.
[0018] Figure 2 Provided for embodiments of the present invention Figure 1 A flowchart illustrating step S2.
[0019] Figure 3 This is a schematic diagram of the structure of the vehicle and the target behind it, provided in an embodiment of the present invention.
[0020] Figure 4 Provided for embodiments of the present invention Figure 1 A flowchart illustrating step S3.
[0021] Figure 5 This is a schematic diagram of a vehicle rear collision warning determination system provided in an embodiment of the present invention.
[0022] Figure 6 This is a schematic diagram of the structure of a computer device provided in an embodiment of the present invention. Detailed Implementation
[0023] To make the objectives, technical solutions, and advantages of the embodiments of the present invention clearer, the technical solutions of the embodiments of the present invention will be clearly and completely described below with reference to the accompanying drawings. Obviously, the described embodiments are only some embodiments of the present invention, not all embodiments. Based on the embodiments of the present invention, all other embodiments obtained by those skilled in the art without creative effort are within the scope of protection of the present invention.
[0024] This invention provides a method, system, device, and medium for determining rear collision warning for vehicles, which can solve the technical problem of low accuracy in traditional methods that rely solely on the center point of the target for collision warning.
[0025] See Figure 1 As shown, this embodiment of the invention provides a method for determining a rear collision warning for a vehicle, including the following steps: S1. Obtain motion information of the target behind, the motion information of the target behind includes the size of the target behind, the coordinates of the relative center point, the relative velocity, the relative acceleration, the relative yaw rate and the relative heading angle.
[0026] In this embodiment, the acquisition of motion information of the rear target includes the size of the rear target, its coordinates relative to the center point, its relative velocity, relative acceleration, relative yaw rate, and relative heading angle, including: The vehicle acquires data on rear targets using its corner radar, rearview camera, and sensors, and obtains the motion information of the rear targets through data fusion processing. The motion information of the rear targets is real-time information, and the size of the rear targets includes their length and width. The motion information of the rear targets is relative to the vehicle, and the coordinates of the relative center point of the rear targets are coordinates in the vehicle's coordinate system. It should be noted that the rear target mentioned in this application refers to all kinds of traffic participants in the rear area, including not only motor vehicles, but also non-motor vehicles, pedestrians and other dynamic obstacles that may enter the rear area of the vehicle, so as to ensure the applicability of this method in different traffic scenarios.
[0027] S2. Calculate the predicted collision time of the rear target relative to the vehicle based on the motion information of the rear target.
[0028] See Figure 2 As shown, step S2 includes: S21. Calculate the collision distance based on the relative center point coordinates of the target behind and the preset collision point coordinates of the vehicle.
[0029] In this embodiment, calculating the collision distance based on the relative center point coordinates of the rear target and the preset collision point coordinates of the vehicle includes: The collision distance is a lateral collision distance, representing the distance between the horizontal coordinate of the relative center point of the rear target and the horizontal coordinate of the vehicle's preset collision point. Specifically, the vehicle's preset collision point is the center point of the rear axle of the vehicle. It should be noted that, see Figure 3 As shown, in the vehicle coordinate system, the direction of the front of the vehicle is the x-axis direction, the y-axis direction is the left side of the rear axle of the vehicle, and the origin is the center point of the rear axle of the vehicle. The lateral collision distance represents the distance in the y-axis direction, and the x-coordinate of the relative center point coordinate and the x-coordinate of the vehicle's preset collision point coordinate are both y-axis coordinates. The collision distance This can be expressed by the following formula:
[0030] in Represents the coordinates of the relative center point of the target behind. Represents the x-axis. Represents the length of the target behind. Represents the width of the target behind. The relative heading angle representing the target behind. This represents the width of the vehicle.
[0031] S22. Calculate and predict the collision time based on the collision distance and the relative speed of the target behind.
[0032] In this embodiment, the step of calculating the predicted collision time based on the collision distance and the relative velocity of the target behind includes: The predicted collision time This can be expressed by the following formula:
[0033] in, This represents the velocity of the target behind in the horizontal y-axis direction. This represents the sign function; if the value of y is greater than 0, then... If the value of y is less than 0, then... It is -1.
[0034] S3. Then, based on the motion information of the target behind, calculate the predicted coordinates of the edge points of the target behind after the predicted collision time.
[0035] See Figure 4 As shown, step S3 includes: S31. Determine the motion state of the target behind based on its relative yaw rate and relative acceleration. The motion state includes uniform linear motion and variable speed turning motion.
[0036] In this embodiment, determining the motion state of the rear target based on its relative yaw rate and relative acceleration includes: If the relative yaw rate of the target behind is less than the preset angular velocity and the relative acceleration is 0, then it is uniform linear motion. Optionally, if the target behind is a pedestrian, it can be directly regarded as uniform linear motion. If the relative yaw rate of the target behind is greater than the preset angular velocity and the relative acceleration is not zero, then it is a variable speed turning motion; This embodiment covers the target scenario of variable speed turning, which improves the accuracy of warnings in complex actual road conditions.
[0037] S32. If the motion state of the target behind is uniform linear motion, then based on the relative velocity and relative center point coordinates of the target behind, the predicted relative center point coordinates of the target behind after the predicted collision time are calculated by a preset uniform linear motion prediction algorithm.
[0038] In this embodiment, if the motion state of the rear target is uniform linear motion, then the calculation of the predicted relative center point coordinates of the rear target after the predicted collision time, based on the relative velocity and relative center point coordinates of the rear target, using a preset uniform linear motion prediction algorithm, includes: The predicted relative center point ordinate of the rear target after the predicted collision time. This can be expressed by the following formula:
[0039] in, This represents the velocity of the target behind in the longitudinal x-axis direction; The predicted relative center point x-coordinate of the rear target after the predicted collision time This can be expressed by the following formula:
[0040] S33. If the motion state of the target behind is a variable speed turning motion, then based on the relative yaw rate, relative heading angle, relative velocity, relative acceleration and relative center point coordinates of the target behind, the predicted relative center point coordinates of the target behind after the predicted collision time are calculated by a preset variable speed turning motion prediction algorithm.
[0041] In this embodiment, if the motion state of the rear target is a variable-speed turning motion, then based on the relative yaw rate, relative heading angle, relative velocity, relative acceleration, and relative center point coordinates of the rear target, the predicted relative center point coordinates of the rear target after the predicted collision time are calculated using a preset variable-speed turning motion prediction algorithm, including: The motion state is a variable-speed turning motion, and the predicted relative center point ordinate of the rear target after the predicted collision time is... This can be expressed by the following formula:
[0042] in, Represents the relative yaw rate of the target behind. Represents the relative acceleration of the target behind; The motion state is a variable speed turning motion, and the predicted relative center point x-coordinate of the rear target after the predicted collision time is... This can be expressed by the following formula: .
[0043] In this embodiment, if the motion state of the rear target is a variable-speed turning motion, then based on the relative yaw rate, relative heading angle, relative velocity, relative acceleration, and relative center point coordinates of the rear target, the predicted relative center point coordinates of the rear target after the predicted collision time are calculated using a preset variable-speed turning motion prediction algorithm, and the method further includes: Obtain the predicted relative center point coordinates of targets behind at multiple time points and the corresponding relative center point coordinates of targets behind at multiple time points later; Specifically, the preset uniform linear motion prediction algorithm and the preset variable speed turning motion prediction algorithm described in steps S32 and S33 are used to predict the predicted relative center point coordinates at multiple times. Then, after multiple times, the real-time relative center point coordinates of the target at multiple times are obtained by the method described in step S1.
[0044] The adaptive factor of the rear target is calculated based on the predicted relative center point coordinates of the rear target at multiple time points and the corresponding relative center point coordinates of the rear target at multiple time points.
[0045] In this embodiment, the step of calculating the adaptive factor of the rear target based on the predicted relative center point coordinates of the rear target at multiple time points and the corresponding relative center point coordinates of the rear target at multiple time points includes: The information sequence of the rear target is calculated based on the predicted relative center point coordinates of the rear target at multiple time points and the corresponding relative center point coordinates of the rear target at multiple time points later.
[0046] The information sequence of the rear target is represented by the following formula:
[0047] in, The new information sequence representing the rear target, This represents the predicted relative center point coordinates of the target behind at time k. This represents the predicted state vector at time k. This represents the relative center point coordinates of the target behind at time k.
[0048] Calculate the predicted innovation covariance of the target based on the innovation sequence of the target, and calculate the actual innovation covariance of the target.
[0049] The predicted information covariance of the rear target is expressed by the following formula:
[0050] in, The covariance of the predicted information of the target is represented by N, which represents the number of time points, specifically 10-20. The actual information covariance of the rear target is expressed by the following formula:
[0051] in, The actual information covariance representing the target at the rear. Represents the state covariance. Represents the observation matrix. This represents observation noise.
[0052] The adaptive factor of the rear target is calculated based on the predicted information covariance and the actual information covariance of the rear target.
[0053] The adaptive factor of the rear target is expressed by the following formula:
[0054] in, An adaptive factor representing the target behind. Represents the trace function.
[0055] The predicted collision time is updated based on the adaptive factor of the target behind.
[0056] If the adaptive factor of the target behind is greater than 1, it means that the predicted collision time needs to be increased. If the adaptive factor of the target behind is less than 1, it means that the predicted collision time needs to be reduced. If the adaptive factor of the target behind is equal to 1, then no changes are made; The updated predicted collision time This can be expressed by the following formula: .
[0057] The predicted relative center point coordinates after the predicted collision time are updated based on the updated predicted collision time.
[0058] S34. Calculate the predicted coordinates of the edge points of the rear target after the predicted collision time based on the predicted relative center point coordinates of the rear target after the predicted collision time and the size of the rear target.
[0059] In this embodiment, calculating the predicted coordinates of the edge points of the rear target after the predicted collision time based on the predicted relative center point coordinates of the rear target after the predicted collision time and the size of the rear target includes: Determine the edge points of the rear targets based on their category; Specifically, if the target behind is a vehicle, then four edge points are determined, see [reference]. Figure 3 As shown, the edge points are A, B, C, and D. The predicted x-coordinate of point A is expressed by the following formula:
[0060] The predicted ordinate of point A shown is expressed by the following formula:
[0061] The predicted x-coordinate of point B shown is expressed by the following formula:
[0062] The predicted ordinate of point B shown is expressed by the following formula:
[0063] The predicted x-coordinate of point C shown is expressed by the following formula:
[0064] The predicted ordinate of point C shown is expressed by the following formula:
[0065] The predicted x-coordinate of point D shown is expressed by the following formula:
[0066] The predicted ordinate of point D shown is expressed by the following formula: .
[0067] S4. Determine whether to issue a collision warning based on the predicted coordinates of the edge points and the preset collision area.
[0068] In this embodiment, determining whether to issue a collision warning based on the predicted coordinates of the edge points and the preset collision area includes: Determine whether the predicted coordinates of any edge point are within the preset collision area; if so, issue a collision warning. See Figure 3 As shown, the preset collision area is a length extending from the rear of the vehicle. Width is The rectangular region, specifically, the length of the collision region. It can be set to 0.5-5 meters, with the width being the width of the vehicle. Add 0-1.5 meters.
[0069] In summary, the present invention provides a method for determining rear collision warning for a vehicle. This method acquires the motion information of a rear target, including its size, coordinates relative to its center point, relative velocity, relative acceleration, relative yaw rate, and relative heading angle. Based on this motion information, the method calculates the predicted collision time between the rear target and the vehicle. Then, it calculates the predicted coordinates of the edge points of the rear target after the predicted collision time. Finally, it determines whether to issue a collision warning based on the predicted coordinates of the edge points and a preset collision area. This invention overcomes the false alarms and missed alarms caused by relying on center point determination in traditional technologies by determining the edge points of the rear target for collision assessment, thus improving the accuracy and reliability of rear collision warnings.
[0070] See Figure 5 As shown, this embodiment of the invention also provides a vehicle rear collision warning determination system, including: The acquisition module is used to acquire the motion information of the target behind, which includes the target's size, relative center point coordinates, relative velocity, relative acceleration, relative yaw rate, and relative heading angle. The first calculation module is used to calculate the predicted collision time of the rear target relative to the vehicle based on the motion information of the rear target. The second calculation module is used to calculate the predicted coordinates of the edge points of the rear target after the predicted collision time based on the motion information of the rear target. The judgment module is used to determine whether to issue a collision warning based on the predicted coordinates of the edge points and the preset collision area.
[0071] This invention also provides a computer device, including: a memory, a processor, and a network interface connected via a system bus. The memory stores at least one instruction, which is loaded and executed by the processor to implement all or part of the steps of the aforementioned method for determining a rear collision warning for a vehicle.
[0072] The network interface is used for network communication, such as sending assigned tasks. Those skilled in the art will understand that... Figure 6 The structure shown is merely a block diagram of a portion of the structure related to the present invention and does not constitute a limitation on the computer device to which the present invention is applied. A specific computer device may include more or fewer components than those shown in the figure, or combine certain components, or have different component arrangements.
[0073] A processor can be a CPU, or other general-purpose processors, digital signal processors (DSPs), application-specific integrated circuits (ASICs), field-programmable gate arrays (FPGAs), or other programmable logic devices, discrete gate or transistor logic devices, or discrete hardware components. A general-purpose processor can be a microprocessor, or any conventional processor. The processor is the control center of a computer device, connecting all parts of the computer device through various interfaces and lines.
[0074] Memory can be used to store computer programs and / or modules. The processor implements various functions of the computer device by running or executing the computer programs and / or modules stored in the memory, and by accessing data stored in the memory. Memory can mainly include a program storage area and a data storage area. The program storage area can store the operating system, application programs required for at least one function (such as video playback, image playback, etc.), etc.; the data storage area can store data created based on the use of the mobile phone (such as video data, image data, etc.). In addition, memory can include high-speed random access memory, and can also include non-volatile memory, such as hard disks, RAM, plug-in hard disks, SmartMedia Cards (SMC), Secure Digital (SD) cards, Flash Cards, at least one disk storage device, flash memory device, or other volatile solid-state storage devices.
[0075] In one embodiment of the invention, the processor is used to run a computer program stored in a memory to perform the following steps: Acquire motion information of a target behind you, including the target's size, coordinates relative to the center point, relative velocity, relative acceleration, relative yaw rate, and relative heading angle. The predicted collision time of the rear target relative to the vehicle is calculated based on the motion information of the rear target. Then, based on the motion information of the target behind, calculate the predicted coordinates of the edge points of the target behind after the predicted collision time; Whether to issue a collision warning is determined based on the predicted coordinates of the edge points and the preset collision area.
[0076] In some embodiments, calculating the predicted collision time of the rear target relative to the vehicle based on the motion information of the rear target includes: The collision distance is calculated based on the relative center point coordinates of the target behind and the vehicle's preset collision point coordinates; The collision time is predicted based on the collision distance and the relative speed of the target behind.
[0077] In some embodiments, the step of calculating the predicted coordinates of the edge points of the rear target after the predicted collision time based on the motion information of the rear target includes: The motion state of the target behind is determined based on the relative yaw rate and relative acceleration of the target behind. The motion state includes uniform linear motion and variable speed turning motion. If the target behind is moving at a constant speed in a straight line, then based on the relative velocity and relative center point coordinates of the target behind, the predicted relative center point coordinates of the target behind after the predicted collision time are calculated using a preset constant speed in a straight line motion prediction algorithm. If the target behind is in a variable speed turning motion, the predicted relative center point coordinates of the target behind are calculated by a preset variable speed turning motion prediction algorithm based on the target's relative yaw rate, relative heading angle, relative velocity, relative acceleration, and relative center point coordinates. The predicted coordinates of the edge points of the rear target after the predicted collision time are calculated based on the predicted relative center point coordinates of the rear target after the predicted collision time and the size of the rear target.
[0078] In some embodiments, determining the motion state of the rear target based on its relative yaw rate and relative acceleration includes: If the relative yaw rate of the target behind is less than the preset angular velocity and the relative acceleration is 0, then it is uniform linear motion; If the relative yaw rate of the target behind is greater than the preset angular velocity and the relative acceleration is not zero, then it is a variable speed turning motion.
[0079] In some embodiments, if the motion state of the rear target is a variable-speed turning motion, then based on the relative yaw rate, relative heading angle, relative velocity, relative acceleration, and relative center point coordinates of the rear target, the predicted relative center point coordinates of the rear target after the predicted collision time are calculated using a preset variable-speed turning motion prediction algorithm, and the method further includes: Obtain the predicted relative center point coordinates of targets behind at multiple time points and the corresponding relative center point coordinates of targets behind at multiple time points later; The adaptive factor of the rear target is calculated based on the predicted relative center point coordinates of the rear target at multiple time points and the corresponding relative center point coordinates of the rear target at multiple time points. The predicted collision time is updated based on the adaptive factor of the target behind; The predicted relative center point coordinates after the predicted collision time are updated based on the updated predicted collision time.
[0080] In some embodiments, calculating the adaptive factor of the rear target based on the predicted relative center point coordinates of the rear target at multiple time points and the corresponding relative center point coordinates of the rear target at multiple time points includes: The information sequence of the rear target is calculated based on the predicted relative center point coordinates of the rear target at multiple time points and the corresponding relative center point coordinates of the rear target at multiple time points. Calculate the predicted innovation covariance of the target based on the innovation sequence of the target, and calculate the actual innovation covariance of the target. The adaptive factor of the rear target is calculated based on the predicted information covariance and the actual information covariance of the rear target.
[0081] In some embodiments, determining whether to issue a collision warning based on the predicted coordinates of the edge points and a preset collision area includes: Determine whether the predicted coordinates of any edge point are within the preset collision area. If so, issue a collision warning.
[0082] This invention also provides a computer-readable storage medium storing a computer program thereon, which, when executed by a processor, implements all or part of the steps of the aforementioned method for determining a rear collision warning for a vehicle.
[0083] The embodiments of the present invention can implement all or part of the aforementioned processes, or they can be accomplished by a computer program instructing related hardware. The computer program can be stored in a computer-readable storage medium, and when executed by a processor, it can implement the steps of the various methods described above. The computer program includes computer program code, which can be in the form of source code, object code, executable files, or certain intermediate forms. The computer-readable medium can include: any entity or device capable of carrying computer program code, recording media, USB flash drives, portable hard drives, magnetic disks, optical disks, computer memory, read-only memory (ROM), random access memory (RAM), electrical carrier signals, telecommunication signals, and software distribution media, etc. It should be noted that the content included in the computer-readable medium can be appropriately added to or subtracted according to the requirements of legislation and patent practice in the jurisdiction. For example, in some jurisdictions, according to legislation and patent practice, computer-readable media do not include electrical carrier signals and telecommunication signals.
[0084] Those skilled in the art will understand that embodiments of the present invention can be provided as methods, systems, servers, or computer program products. Therefore, the present invention can take the form of a completely hardware embodiment, a completely software embodiment, or an embodiment combining software and hardware aspects. Furthermore, the present invention can take the form of a computer program product embodied on one or more computer-usable storage media (including, but not limited to, disk storage and optical storage) containing computer-usable program code.
[0085] It should be noted that, in this document, the terms "comprising," "including," or any other variations thereof are intended to cover non-exclusive inclusion, such that a process, method, article, or system that comprises a list of elements includes not only those elements but also other elements not expressly listed, or elements inherent to such a process, method, article, or system. 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 system that includes that element.
[0086] The serial numbers in the above embodiments of the present invention are for descriptive purposes only and do not represent the superiority or inferiority of the embodiments.
[0087] This invention is described with reference to flowchart illustrations and / or block diagrams of methods, apparatus (systems), and computer program products according to embodiments of the invention. It will be understood that each block of the flowchart illustrations and / or block diagrams, and combinations of blocks in the flowchart illustrations and / or block diagrams, can be implemented by computer program instructions. These computer program instructions can be provided to a processor of a general-purpose computer, special-purpose computer, embedded processor, or other programmable data processing apparatus to produce a machine, such that the instructions, which execute via the processor of the computer or other programmable data processing apparatus, generate instructions for implementing the flowchart illustrations and / or block diagrams. Figure 1 One or more processes and / or boxes Figure 1 A device that provides the functions specified in one or more boxes.
[0088] The above description is merely a specific embodiment of the present invention, enabling those skilled in the art to understand or implement the invention. Various modifications to these embodiments will be readily apparent to those skilled in the art, and the general principles defined herein may be implemented in other embodiments without departing from the spirit or scope of the invention. Therefore, the present invention is not to be limited to the embodiments shown herein, but is to be accorded the widest scope consistent with the principles and novel features of the invention herein.
Claims
1. A method for determining a rear collision warning for a vehicle, characterized in that, Includes the following steps: Acquire motion information of a target behind you, including the target's size, coordinates relative to the center point, relative velocity, relative acceleration, relative yaw rate, and relative heading angle. The predicted collision time of the rear target relative to the vehicle is calculated based on the motion information of the rear target. Then, based on the motion information of the target behind, calculate the predicted coordinates of the edge points of the target behind after the predicted collision time; Whether to issue a collision warning is determined based on the predicted coordinates of the edge points and the preset collision area.
2. The method for determining a rear collision warning for a vehicle according to claim 1, characterized in that, The step of calculating the predicted collision time of the rear target relative to the vehicle based on the motion information of the rear target includes: The collision distance is calculated based on the relative center point coordinates of the target behind and the vehicle's preset collision point coordinates; The collision time is predicted based on the collision distance and the relative speed of the target behind.
3. The method for determining a rear collision warning for a vehicle according to claim 1, characterized in that, The step of calculating the predicted coordinates of the edge points of the rear target after the predicted collision time based on the motion information of the rear target includes: The motion state of the target behind is determined based on the relative yaw rate and relative acceleration of the target behind. The motion state includes uniform linear motion and variable speed turning motion. If the target behind is moving at a constant speed in a straight line, then based on the relative velocity and relative center point coordinates of the target behind, the predicted relative center point coordinates of the target behind after the predicted collision time are calculated using a preset constant speed in a straight line motion prediction algorithm. If the target behind is in a variable speed turning motion, the predicted relative center point coordinates of the target behind are calculated by a preset variable speed turning motion prediction algorithm based on the target's relative yaw rate, relative heading angle, relative velocity, relative acceleration, and relative center point coordinates. The predicted coordinates of the edge points of the rear target after the predicted collision time are calculated based on the predicted relative center point coordinates of the rear target after the predicted collision time and the size of the rear target.
4. The method for determining a rear collision warning for a vehicle according to claim 3, characterized in that, The step of determining the motion state of the target behind based on the relative yaw rate and relative acceleration includes: If the relative yaw rate of the target behind is less than the preset angular velocity and the relative acceleration is 0, then it is uniform linear motion; If the relative yaw rate of the target behind is greater than the preset angular velocity and the relative acceleration is not zero, then it is a variable speed turning motion.
5. The method for determining a rear collision warning for a vehicle according to claim 3, characterized in that, If the motion state of the rear target is a variable-speed turning motion, then based on the relative yaw rate, relative heading angle, relative velocity, relative acceleration, and relative center point coordinates of the rear target, the predicted relative center point coordinates of the rear target after the predicted collision time are calculated using a preset variable-speed turning motion prediction algorithm, and the method further includes: Obtain the predicted relative center point coordinates of targets behind at multiple time points and the corresponding relative center point coordinates of targets behind at multiple time points later; The adaptive factor of the rear target is calculated based on the predicted relative center point coordinates of the rear target at multiple time points and the corresponding relative center point coordinates of the rear target at multiple time points. The predicted collision time is updated based on the adaptive factor of the target behind; The predicted relative center point coordinates are updated based on the updated predicted collision time.
6. The method for determining a rear collision warning for a vehicle according to claim 5, characterized in that, The step of calculating the adaptive factor of the rear target based on the predicted relative center point coordinates of the rear target at multiple time points and the corresponding relative center point coordinates of the rear target at multiple time points includes: The information sequence of the rear target is calculated based on the predicted relative center point coordinates of the rear target at multiple time points and the corresponding relative center point coordinates of the rear target at multiple time points. Calculate the predicted innovation covariance of the target based on the innovation sequence of the target, and calculate the actual innovation covariance of the target. The adaptive factor of the rear target is calculated based on the predicted information covariance and the actual information covariance of the rear target.
7. The method for determining a rear collision warning for a vehicle according to claim 1, characterized in that, The step of determining whether to issue a collision warning based on the predicted coordinates of the edge points and the preset collision area includes: Determine whether the predicted coordinates of any edge point are within the preset collision area. If so, issue a collision warning.
8. A vehicle rear collision warning determination system, characterized in that, include: The acquisition module is used to acquire the motion information of the target behind, which includes the target's size, relative center point coordinates, relative velocity, relative acceleration, relative yaw rate, and relative heading angle. The first calculation module is used to calculate the predicted collision time of the rear target relative to the vehicle based on the motion information of the rear target. The second calculation module is used to calculate the predicted coordinates of the edge points of the rear target after the predicted collision time based on the motion information of the rear target. The judgment module is used to determine whether to issue a collision warning based on the predicted coordinates of the edge points and the preset collision area.
9. A computer device, characterized in that, include: A memory and a processor, wherein the memory stores at least one instruction, which is loaded and executed by the processor to implement a method for determining a rear collision warning for a vehicle according to any one of claims 1 to 7.
10. A computer-readable storage medium, characterized in that: The computer-readable storage medium stores computer instructions that, when executed by a computer, cause the computer to perform a method for determining a rear collision warning for a vehicle according to any one of claims 1 to 7.