A vehicle anti-collision control method, system, device and storage medium

Abstract

The application relates to the technical field of automobiles and discloses an automobile anti-collision control method, system, device and storage medium. In the application, firstly, whether a barrier needs to start a warning is judged according to the driving state between the vehicle and the barrier, if the starting warning condition is reached, a to-be-monitored object is obtained through coarse screening based on the relative distance of the vehicle, and the to-be-monitored object is numbered, and then secondary refinement is carried out on the to-be-monitored object under the influence of factors such as acceleration, so as to judge whether a warning signal is sent. Not only can the barrier closest to the vehicle be subjected to priority anti-collision analysis based on the number, but also the total number of target barriers can be reduced to achieve data lightening, improve the identification rate and reduce the false alarm rate of the warning.

Description

Technical Field

[0001] This invention relates to the field of automotive technology, and in particular to an automotive collision avoidance control method, system, device, and storage medium. Background Technology

[0002] With the increasing prevalence of automobiles, the number of cars on the road is growing, leading to a greater demand for overtaking. Surveys show that approximately 60% to 70% of traffic accidents are caused by vehicle collisions. Therefore, effectively avoiding or reducing vehicle collisions is crucial to reducing traffic accidents and minimizing personal injury and economic losses. To reduce or avoid vehicle collisions and improve driving safety, automotive safety systems have become a hot research topic for various research institutions.

[0003] However, current automotive collision avoidance devices are too slow to detect obstacles, making it difficult to achieve real-time detection on in-vehicle equipment. Collision avoidance devices that can meet real-time requirements generally have low accuracy and a high false alarm rate. Summary of the Invention

[0004] The purpose of this invention is to provide a method, system, device, and storage medium for automotive collision avoidance control, in order to improve the aforementioned problems. To achieve the above objective, the technical solution adopted by this invention is as follows:

[0005] In a first aspect, this application provides a vehicle collision avoidance control method, comprising:

[0006] The current vehicle driving image sequence is acquired, and the SURF algorithm is used to detect feature points and determine candidate feature points.

[0007] The optical flow method based on feature matching tracks the positions of the candidate feature points, calculates the motion vector of each candidate feature point, and estimates the camera motion path.

[0008] The camera motion path is smoothed using the Kalman filter algorithm, and driving images are output based on time series arrangement.

[0009] Based on each movable object in each driving image, it is determined whether the activation warning condition is met; if the activation warning condition is met, it is identified as an obstacle, and the obstacles are numbered in ascending order from the nearest to the farthest from the current vehicle; the activation warning condition is a warning distance describing the obstacle in front of the vehicle that may cause obstruction to the vehicle's movement.

[0010] Based on the obstacle corresponding to the smallest number, travel data and braking data are obtained. The travel data is the driving speed and acceleration of the current vehicle and the obstacle. The braking data includes the distance between the current vehicle and the obstacle, braking reaction time, and braking coordination time.

[0011] The collision warning level is determined based on the travel data and the braking data, and vehicle collision avoidance control is performed according to the collision warning level.

[0012] Secondly, this application provides an automotive collision avoidance control system, including modules for executing the above-described automotive collision avoidance control method. The modules include a first acquisition module, a tracking module, an output module, a judgment module, a second acquisition module, and a warning module, wherein:

[0013] The first acquisition module is used to acquire the current vehicle driving image sequence and use the SURF algorithm to detect feature points and determine candidate feature points.

[0014] Tracking module: used to track the positions of the candidate feature points using optical flow based on feature matching, calculate the motion vector of each candidate feature point, and estimate the camera motion path;

[0015] Output module: used to smooth the camera motion path based on the Kalman filter algorithm and output driving images arranged in time series;

[0016] Judgment module: used to determine whether the activation warning condition is met for each movable object in each driving image; if the activation warning condition is met, it is identified as an obstacle, and the obstacles are numbered in ascending order from the current vehicle to the farthest; the activation warning condition is a warning distance describing the obstacle in front of the vehicle that may cause obstruction to the vehicle's movement;

[0017] The second acquisition module is used to acquire travel data and braking data based on the obstacle corresponding to the smallest number. The travel data is the driving speed and acceleration of the current vehicle and the obstacle. The braking data includes the distance between the current vehicle and the obstacle, braking reaction time, and braking coordination time.

[0018] Warning module: used to determine the collision warning level based on the travel data and the braking data, and to perform vehicle collision avoidance control according to the collision warning level.

[0019] Thirdly, this application also provides an automotive collision avoidance control device, comprising:

[0020] Memory, used to store computer programs;

[0021] A processor is used to implement the steps of the above-described vehicle collision avoidance control method when executing the computer program.

[0022] Fourthly, this application also provides a storage medium storing a computer program, which, when executed by a processor, implements the steps of the above-described vehicle collision avoidance control method.

[0023] The beneficial effects of this invention are as follows:

[0024] In this invention, the driving status between the vehicle and the obstacle is first assessed to determine whether an obstacle warrants a warning. If the warning conditions are met, a coarse screening based on the relative distance to the vehicle is performed to identify and number the objects to be monitored. Then, considering factors such as acceleration, the objects to be monitored are further refined to determine whether a warning signal should be issued. This method not only prioritizes collision avoidance analysis based on the number of obstacles closest to the vehicle but also reduces the total number of target obstacles detected, achieving data lightweighting, improving recognition speed, and reducing false alarm rates.

[0025] Furthermore, this invention employs adaptive dynamic threshold warning distance and warning collision time for collision analysis based on different objects to be detected. It also considers the impact of factors such as road surface friction coefficient and driver characteristics of different driving styles on safe following distances in road driving scenarios. This overcomes the shortcomings of traditional methods that use fixed collision time thresholds and fixed collision safety distances for warnings. The dynamic threshold warning distance meets personalized needs, accurately limits the obstacle recognition range, reduces false alarm rates, and improves the output rate of the final collision avoidance analysis results.

[0026] Secondly, during image acquisition, road bumps and vehicle vibrations can cause image frame blurring. This invention performs anti-shake preprocessing on the current vehicle driving image sequence and uses an optical flow tracking algorithm to perform motion compensation frame-by-frame on the acquired driving image sequence. This significantly improves stability and computation speed, thereby increasing the accuracy of moving target detection.

[0027] Other features and advantages of the invention will be set forth in the following description, and will be apparent in part from the description, or may be learned by practicing embodiments of the invention. The objects and other advantages of the invention may be realized and obtained by means of the structures particularly pointed out in the written description, claims, and drawings. Attached Figure Description

[0028] Figure 1 This is a block diagram of the vehicle collision avoidance control method in this embodiment;

[0029] Figure 2 This is a block diagram of the vehicle collision avoidance control system in this embodiment;

[0030] Figure 3 This is a schematic diagram of the vehicle collision avoidance control device in this embodiment.

[0031] In the diagram: 710 - First acquisition module; 711 - Tracking module; 712 - Output module; 720 - Judgment module; 721 - First classification unit; 722 - First judgment unit; 723 - Second judgment unit; 724 - Second classification unit; 725 - Third judgment unit; 7251 - Input unit; 7252 - Acquisition subunit; 7253 - First calculation unit; 730 - Second acquisition module; 740 - Early warning module; 741 - Second calculation unit; 742 - Third calculation unit; 743 - Fourth calculation unit; 744 - Fourth judgment unit; 800 - Vehicle collision avoidance control device; 801 - Processor; 802 - Memory; 803 - Multimedia component; 804 - I / O interface; 805 - Communication component. Detailed Implementation

[0032] 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, not all, of the embodiments of the present invention. The components of the embodiments of the present invention described and shown in the accompanying drawings can generally be arranged and designed in various different configurations. Therefore, the following detailed description of the embodiments of the present invention provided in the accompanying drawings is not intended to limit the scope of the claimed invention, but merely to illustrate selected embodiments of the invention. All other embodiments obtained by those skilled in the art based on the embodiments of the present invention without inventive effort are within the scope of protection of the present invention.

[0033] It should be noted that similar reference numerals 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. Furthermore, in the description of this invention, terms such as "first," "second," etc., are used only to distinguish descriptions and should not be construed as indicating or implying relative importance.

[0034] Example 1:

[0035] This embodiment provides a vehicle collision avoidance control method, see [link to documentation]. Figure 1 The figure shows that the method includes steps S1, S2, S3, S4, S5 and S6.

[0036] Step S1: Obtain the current vehicle driving image sequence and use the SURF algorithm to detect feature points and determine candidate feature points.

[0037] Understandably, in this step, a camera acquisition device is installed in the vehicle to acquire real-time driving images of the vicinity of the vehicle based on time series data. Then, frame-by-frame preprocessing using convolutional neural network algorithms and gradient threshold image sharpness evaluation algorithms is performed to improve image quality, resulting in driving images that enhance obstacle recognition and improve the accuracy of subsequent obstacle classification. However, during image acquisition, road bumps and vehicle vibrations can cause image frame blurring, significantly impacting the accuracy of image recognition. To address this issue, this invention performs anti-shake preprocessing on the current vehicle driving image sequence. In this step, the SURF algorithm is used to represent the change of surrounding pixels in each frame of driving image with the determinant value of the Hessian matrix, and feature point detection is performed using the determinant value of the fixed scale. Then, local extrema are obtained by solving the determinant of the Hessian matrix. Each local extrema, together with the other 8 neighboring points in the same layer, and the 9 points in the upper and lower layers, forms a 3×3×3 three-dimensional region. When the local extrema is the maximum (or minimum) point in this three-dimensional region, it is a candidate feature point.

[0038] Step S2: Track the positions of the candidate feature points using optical flow based on feature matching, calculate the motion vector of each candidate feature point, and estimate the camera motion path.

[0039] Step S3: Smooth the camera motion path based on the Kalman filter algorithm and output the driving image.

[0040] In the above-mentioned image stabilization preprocessing, the optical flow tracking algorithm is used to perform motion compensation frame by frame on the acquired driving image sequence, which greatly improves the stability and calculation speed, and improves the accuracy of moving obstacle detection and target recognition.

[0041] Step S4: Determine whether the warning activation condition is met for each movable object in each driving image; if the warning activation condition is met, it is identified as an obstacle, and the obstacles are numbered in ascending order from the nearest to the farthest from the current vehicle; the warning activation condition describes the warning distance that the obstacle in front of the vehicle may cause obstruction to the vehicle's movement.

[0042] Understandably, in this step, movable objects in the driving image are coarsely screened according to the conditions for activating the warning, and potential obstacles that require the activation of the collision avoidance warning are identified. The potential obstacles are then numbered in ascending order according to their distance from the current vehicle. The smaller the number, the closer the distance and the more likely a collision is to occur. This facilitates subsequent optimization of the collision avoidance analysis of the corresponding obstacles based on the number size, reducing the total number of target obstacles monitored to achieve data lightweighting and improve the recognition rate.

[0043] In detail, the warning safety distance or warning time corresponding to different travel speeds of obstacles are different, and warning based on a fixed collision time will cause a high false alarm rate. To solve this problem, step S4 includes steps S41, S42, S43, S44 and S45.

[0044] Step S41: Based on the driving images, perform identification and classification to obtain sets of vehicles traveling in the same direction and sets of vehicles traveling in opposite directions.

[0045] Understandably, in this step, each element in the driving image is categorized as either traveling in the same or opposite direction. For example, the front and rear of the car are respectively determined as traveling in opposite directions and traveling in the same direction. All elements traveling in the same direction are grouped into the same-direction travel set, and all elements traveling in opposite directions are grouped into the opposite-direction travel set.

[0046] Step S42: Determine whether each first element in the same direction driving set is in the same lane as the current vehicle. If the first element is in the same lane as the current vehicle, it is the first monitoring object.

[0047] Understandably, in this step, if the first element traveling in the same direction is in the same lane as the current vehicle, and a collision is likely to occur, it will be selected as the first object to be monitored, and the remaining vehicles will be filtered out.

[0048] Step S43: Based on each second element in the set of vehicles traveling in opposite directions, determine whether it is in an adjacent lane or the same lane as the current vehicle. If the second element is in an adjacent lane or the same lane as the current vehicle, it is the first monitoring target, and the remaining vehicles are filtered out.

[0049] Understandably, in this step, if a second element traveling in the opposite direction is in the same lane or adjacent lane as the current vehicle, and a collision is likely to occur, it will be selected as the first target to be monitored, while the remaining vehicles will be filtered out.

[0050] Step S44: Classify the first monitored object and the preset classification conditions to obtain a second monitored object set. The preset classification conditions are the average driving speed classification threshold.

[0051] Understandably, in this step, it is assumed that the first monitored object is divided into three categories of second monitored objects: pedestrians, bicycles, and motor vehicles, based on three different speed levels (i.e., preset classification conditions).

[0052] Step S45: Based on each second object to be monitored in the second set of objects to be monitored and its corresponding preset warning distance, a judgment is made. The preset warning distance refers to the maximum safe distance for an obstacle to enter the collision avoidance monitoring field. If the second object to be monitored is within the corresponding preset warning distance, it is determined to be an obstacle.

[0053] Understandably, in this step, in actual driving scenarios, drivers tend to maintain a relatively short distance from obstacles such as vehicles, pedestrians, and bicycles. Using a fixed safe distance for warnings would excessively interfere with normal driving and result in low accuracy. Therefore, this invention uses a dynamic threshold warning distance (i.e., a preset warning distance corresponding to the second monitored object) to assess risk for different second monitored objects, filtering out obstacles with a high probability of collision. Then, each type of obstacle (such as a pedestrian) is numbered in ascending order based on its distance from the current vehicle.

[0054] Furthermore, the calculation method for the aforementioned preset warning distance includes steps S451, S452, and S453.

[0055] Step S451: Determine a first feature parameter for each of the second objects to be monitored, wherein the first feature parameter is the average moving speed and average deceleration corresponding to each type of obstacle.

[0056] Understandably, in this step, the current vehicle can receive the first feature parameters sent by the second monitored object via the Internet, or calculate the first feature parameters of the second monitored object using the cross ratio law under projection based on images collected in two adjacent time periods.

[0057] Step S452: Obtain the second feature parameter and the third feature parameter. The second feature parameter is the current vehicle speed, deceleration, driver braking response characteristic coefficient, and preset safe travel time. The third feature parameter is the influence coefficient of the current road on the vehicle braking distance.

[0058] Understandably, in this step, driving speed and deceleration are collected through various sensors. Simultaneously, the driver can customize the input of the remaining data via various input devices according to their own needs, or obtain it from historical data of the vehicle; there are no specific restrictions. It should be noted that the driver braking reaction characteristic coefficient in this step is a characteristic coefficient based on the speed of each driver's reaction to an emergency, adjusted according to different driving styles, ranging from 0.25 to 1.00. The preset safe travel time refers to the maximum time required for the driver to react in an emergency. The influence coefficient of the current road on the vehicle's braking distance refers to the value determined by the corresponding friction coefficient based on the impact of different road surface roughness on the safe following distance. The specific classification description of the corresponding road surface conditions and the corresponding friction coefficient values ​​can be found in the road surface friction meteorological index table for appropriate settings. For example, the influence coefficient of the current road on the vehicle's braking distance is 1 for normal road surfaces with normal temperature, dryness, and no impurities, while it is generally 0.3 for the worst road surface conditions, such as icy roads.

[0059] Step S453: Calculate the preset warning distance based on the first feature parameter, the second feature parameter and the third feature parameter.

[0060] It is understandable that in this step, the preset warning distance is calculated according to formulas (1) and (2):

[0061]

[0062]

[0063] Where: L is the preset warning distance; V h and V q These represent the current vehicle speed and the obstacle speed, respectively; a h and a q λ represents the deceleration of the current vehicle and the obstacle, respectively; λ is the driver's braking response characteristic coefficient; T is the preset safe travel time; θ is the influence coefficient of the current road on the vehicle's braking distance; and μ is the estimated friction coefficient for different road surface conditions, where μ min The friction coefficient of the abnormal road surface, μ n f(μ) represents the friction coefficient under normal road surface conditions, where normal road surface conditions refer to a road surface at room temperature, dry, and free of impurities; min f(μ) represents the adhesion coefficient of the abnormal road surface. n f(μ) represents the adhesion coefficient of a normal road surface. θ represents the influence of road conditions on the safe following distance, determined by the friction coefficient μ. For example, for a normal road surface at room temperature, dry, and free of impurities, f(μ) is taken as f(μ). n =1, the friction coefficient under the worst road conditions, such as road icing, is taken as f(μ) = 1, based on relevant research results. min=0.3 etc. In this invention, the road driving scenario is considered, taking into account the influence of road surface friction coefficient and the characteristics of drivers with different driving styles on safe following distance, so as to meet the dynamic threshold warning distance that meets personalized needs and improve the output rate of the final collision avoidance analysis results.

[0064] Step S5: Obtain travel data and braking data based on the obstacle corresponding to the smallest number. The travel data is the travel speed and acceleration of the current vehicle and the obstacle. The braking data includes the distance between the current vehicle and the obstacle, braking reaction time, and braking coordination time.

[0065] It is understood that in this step, the aforementioned braking reaction time is the time difference between when the driver discovers an emergency and takes corresponding action, and the braking coordination time is the time difference between when the vehicle receives the driver's braking action and when it initiates emergency braking.

[0066] Step S6: Determine the collision warning level based on the travel data and the braking data, and perform vehicle collision avoidance control according to the collision warning level.

[0067] Understandably, in this step, the collision time is obtained based on the ratio of the distance between the current vehicle and the obstacle to the relative speed of the current vehicle relative to the obstacle. The corresponding collision warning level is then determined based on the collision time. When the collision warning level is high-risk, a warning signal is issued, and corresponding measures are taken to prevent a collision.

[0068] Further, step S6 includes steps S61, S62, S63 and S64.

[0069] Step S61: Calculate the relative distance based on the travel data and the braking data.

[0070] Understandably, in this step, the relative distance is calculated according to formula (3):

[0071]

[0072] Where: D is the relative distance between the current vehicle and the obstacle; V h and V q These represent the current vehicle speed and the obstacle speed, respectively; a h and a q These represent the decelerations of the current vehicle and the obstacle, respectively; T a and T b These are braking reaction time and braking coordination time, respectively.

[0073] Step S62: Determine whether the relative distance is within the preset pursuit distance, where the preset pursuit distance is the preset maximum safe distance between adjacent vehicles and obstacles; if the relative distance is within the preset pursuit distance, calculate the relative speed and relative acceleration of the current vehicle and the obstacle based on the travel data.

[0074] Step S63: Calculate the collision time and collision time threshold based on the relative velocity, the relative acceleration and the distance.

[0075] Understandably, in this step, the collision time is calculated according to formula (4), and the collision time threshold is calculated according to formula (5):

[0076]

[0077]

[0078] Wherein: T r and T m These represent the collision time and the collision time threshold, respectively; V is the relative velocity; T... a denoted as braking reaction time; 'a' as relative acceleration; and 'H' as the distance between the current vehicle and the obstacle.

[0079] Step S64: Determine whether the collision time is less than the collision time threshold. If the collision time is less than the collision time threshold, issue a warning signal.

[0080] This invention considers the impact of acceleration on collision time, thereby allowing for the reasonable setting of collision time thresholds to improve the effectiveness of the warning algorithm and ensure that the vehicle collision avoidance warning system can both assist the driver in safe driving and not affect the driver's driving experience.

[0081] Example 2:

[0082] Please refer to Figure 2 , Figure 2 The image shows a vehicle collision avoidance control system according to this embodiment. The vehicle collision avoidance control system includes a first acquisition module 710, a tracking module 711, an output module 712, a judgment module 720, a second acquisition module 730, and a warning module 740, wherein:

[0083] First acquisition module 710: used to acquire the current vehicle driving image sequence and use the SURF algorithm to detect feature points and determine candidate feature points;

[0084] Tracking module 711: used to track the position of the candidate feature points using optical flow based on feature matching, calculate the motion vector of each candidate feature point, and estimate the camera motion path;

[0085] Output module 712: used to smooth the camera motion path based on the Kalman filter algorithm and output driving images arranged in time series;

[0086] Judgment module 720: is used to determine whether the activation warning condition is met for each movable object in each driving image; if the activation warning condition is met, it is identified as an obstacle, and the obstacles are numbered in ascending order from the current vehicle to the farthest; the activation warning condition is a warning distance describing the obstacle in front of the vehicle that may cause obstruction to the vehicle's movement;

[0087] Preferably, the judgment module 720 includes a first classification unit 721, a first judgment unit 722, a second judgment unit 723, a second classification unit 724, and a third judgment unit 725, wherein:

[0088] First classification unit 721: used to perform identification and classification based on the driving image to obtain a set of vehicles traveling in the same direction and a set of vehicles traveling in opposite directions;

[0089] First judgment unit 722: is used to determine whether each first element in the same direction driving set is in the same lane as the current vehicle; if the first element is in the same lane as the current vehicle, it is the first object to be monitored.

[0090] The second judgment unit 723 is used to determine whether each second element in the set of opposite driving directions is in an adjacent lane or the same lane as the current vehicle. If the second element is in an adjacent lane or the same lane as the current vehicle, it is the first monitoring object.

[0091] Second classification unit 724: used to classify based on the first object to be monitored and preset classification conditions to obtain a second set of objects to be monitored, wherein the preset classification conditions are the average driving speed classification threshold.

[0092] The third judgment unit 725 is used to make judgments based on each second object to be monitored in the second set of objects to be monitored and the corresponding preset warning distance. The preset warning distance refers to the maximum safe distance for an obstacle to enter the anti-collision monitoring field. If the second object to be monitored is within the corresponding preset warning distance, it is determined to be an obstacle.

[0093] Preferably, the third judgment unit 725 includes an input unit 7251, an acquisition subunit 7252, and a first calculation unit 7253, wherein:

[0094] Input unit 7251: is used to determine a first feature parameter based on each of the second objects to be monitored, wherein the first feature parameter is the average moving speed and average deceleration corresponding to each of the obstacles;

[0095] Acquisition subunit 7252: used to acquire a second feature parameter and a third feature parameter, wherein the second feature parameter is the current vehicle speed, deceleration, driver braking response characteristic coefficient, and preset safe travel time; and the third feature parameter is the influence coefficient of the current road on the vehicle braking distance.

[0096] First calculation unit 7253: used to calculate based on the first feature parameter, the second feature parameter and the third feature parameter to obtain the preset warning distance.

[0097] The second acquisition module 730 is used to acquire travel data and braking data based on the obstacle corresponding to the smallest number, wherein the travel data is the driving speed and acceleration of the current vehicle and the obstacle; and the braking data includes the distance between the current vehicle and the obstacle, braking reaction time, and braking coordination time.

[0098] Warning module 740: used to determine the collision warning level based on the travel data and the braking data, and to perform vehicle collision avoidance control according to the collision warning level.

[0099] Preferably, the aforementioned early warning module 740 includes a second calculation unit 741, a third calculation unit 742, a fourth calculation unit 743, and a fourth judgment unit 744, wherein:

[0100] Second calculation unit 741: used to calculate the relative distance based on the travel data and the braking data;

[0101] The third calculation unit 742 is used to determine whether the relative distance is within a preset pursuit distance, where the preset pursuit distance is a preset maximum safe distance between adjacent vehicles and obstacles; if the relative distance is within the preset pursuit distance, the relative speed and relative acceleration of the current vehicle and the obstacle are calculated based on the travel data.

[0102] Fourth calculation unit 743: used to calculate, based on the relative velocity, the relative acceleration and the distance, the collision time and the collision time threshold;

[0103] The fourth judgment unit 744 is used to determine whether the collision time is less than the collision time threshold. If the collision time is less than the collision time threshold, a warning signal is issued.

[0104] It should be noted that the specific methods by which each module performs operations in the system described in the above embodiments have been described in detail in the embodiments related to the method, and will not be elaborated here.

[0105] Example 3:

[0106] Corresponding to the above method embodiments, this embodiment also provides an automotive collision avoidance control device. The automotive collision avoidance control device described below can be referred to in correspondence with the automotive collision avoidance control method described above.

[0107] Figure 3 This is a block diagram illustrating an automotive collision avoidance control device 800 according to an exemplary embodiment. Figure 3 As shown, the vehicle collision avoidance control device 800 may include: a processor 801 and a memory 802. The vehicle collision avoidance control device 800 may also include one or more of a multimedia component 803, an I / O interface 804, and a communication component 805.

[0108] The processor 801 controls the overall operation of the vehicle collision avoidance control device 800 to complete all or part of the steps in the aforementioned vehicle collision avoidance control method. The memory 802 stores various types of data to support the operation of the vehicle collision avoidance control device 800. This data may include, for example, instructions for any application or method operating on the vehicle collision avoidance control device 800, and application-related data. The memory 802 can be implemented using any type of volatile or non-volatile storage device or a combination thereof, such as Static Random Access Memory (SRAM), Electrically Erasable Programmable Read-Only Memory (EEPROM), Erasable Programmable Read-Only Memory (EPROM), Programmable Read-Only Memory (PROM), Read-Only Memory (ROM), magnetic storage, flash memory, magnetic disk, or optical disk. The multimedia component 803 may include a screen and audio components. The screen may be, for example, a touchscreen, and the audio component is used to output and / or input audio signals. For example, the audio component may include a microphone for receiving external audio signals. The received audio signals may be further stored in memory 802 or transmitted via communication component 805. The audio component also includes at least one speaker for outputting audio signals. I / O interface 804 provides an interface between processor 801 and other interface modules, such as a keyboard, mouse, buttons, etc. These buttons may be virtual or physical buttons. Communication component 805 is used for wired or wireless communication between the vehicle collision avoidance control device 800 and other devices. Wireless communication may include Wi-Fi, Bluetooth, Near Field Communication (NFC), 2G, 3G, or 4G, or a combination of these. Therefore, the corresponding communication component 805 may include a Wi-Fi module, a Bluetooth module, or an NFC module.

[0109] In an exemplary embodiment, the vehicle collision avoidance control device 800 may be implemented by one or more application-specific integrated circuits (ASICs), digital signal processors (DSPs), digital signal processing devices (DSPDs), programmable logic devices (PLDs), field-programmable gate arrays (FPGAs), controllers, microcontrollers, microprocessors, or other electronic components to perform the vehicle collision avoidance control method described above.

[0110] Example 4:

[0111] Corresponding to the above method embodiments, this embodiment also provides a storage medium. The storage medium described below can be referred to in conjunction with the vehicle collision avoidance control method described above.

[0112] A storage medium storing a computer program, which, when executed by a processor, implements the steps of the vehicle collision avoidance control method described in the above method embodiments.

[0113] The storage medium can be any storage medium capable of storing program code, such as a USB flash drive, external hard drive, read-only memory (ROM), random access memory (RAM), magnetic disk, or optical disk.

[0114] The above description is merely a preferred embodiment of the present invention and is not intended to limit the invention. Various modifications and variations can be made to the present invention by those skilled in the art. Any modifications, equivalent substitutions, improvements, etc., made within the spirit and principles of the present invention should be included within the scope of protection of the present invention.

[0115] The above description is merely a specific embodiment of the present invention, but the scope of protection of the present invention is not limited thereto. Any variations or substitutions that can be easily conceived by those skilled in the art within the technical scope disclosed in the present invention should be included within the scope of protection of the present invention. Therefore, the scope of protection of the present invention should be determined by the scope of the claims.

Claims

1. A method for preventing collisions in automobiles, characterized in that, include: The current vehicle driving image sequence is acquired, and the SURF algorithm is used to detect feature points and determine candidate feature points. The optical flow method based on feature matching tracks the positions of the candidate feature points, calculates the motion vector of each candidate feature point, and estimates the camera motion path. The camera motion path is smoothed using the Kalman filter algorithm, and driving images are output based on time series arrangement. Based on each movable object in each driving image, it is determined whether the activation warning condition is met; if the activation warning condition is met, it is identified as an obstacle, and the obstacles are numbered in ascending order from the nearest to the farthest from the current vehicle; the activation warning condition is a warning distance describing the obstacle in front of the vehicle that may cause obstruction to the vehicle's movement. Based on the obstacle corresponding to the smallest number, travel data and braking data are obtained. The travel data is the driving speed and acceleration of the current vehicle and the obstacle. The braking data includes the distance between the current vehicle and the obstacle, braking reaction time, and braking coordination time. The collision warning level is determined based on the travel data and the braking data, and vehicle collision avoidance control is performed according to the collision warning level.

2. The vehicle collision avoidance control method according to claim 1, characterized in that, Determining whether the conditions for triggering a warning are met for each movable object in each of the driving images includes: Based on the driving images, identification and classification are performed to obtain sets of vehicles traveling in the same direction and sets of vehicles traveling in opposite directions. Based on each first element in the same direction driving set, it is determined whether it is in the same lane as the current vehicle. If the first element is in the same lane as the current vehicle, it is the first object to be monitored. Based on each second element in the set of opposite driving directions, it is determined whether it is in the adjacent lane or the same lane as the current vehicle. If the second element is in the adjacent lane or the same lane as the current vehicle, it is the first monitoring object. Based on the first monitored object and the preset classification conditions, a second set of monitored objects is obtained. The preset classification conditions are the average driving speed classification threshold. The judgment is made based on each second object to be monitored in the second set of objects to be monitored and the corresponding preset warning distance. The preset warning distance refers to the maximum safe distance for an obstacle to enter the collision avoidance monitoring field. If the second object to be monitored is within the corresponding preset warning distance, it is determined to be an obstacle.

3. The vehicle collision avoidance control method according to claim 2, characterized in that, The method for calculating the preset warning distance includes: A first characteristic parameter is determined for each of the second monitored objects, wherein the first characteristic parameter is the average moving speed and average deceleration corresponding to each type of obstacle; The second feature parameter and the third feature parameter are obtained. The second feature parameter is the current vehicle speed, deceleration, driver braking response characteristic coefficient, and preset safe travel time. The third feature parameter is the influence coefficient of the current road on the vehicle braking distance. The preset warning distance is calculated based on the first feature parameter, the second feature parameter, and the third feature parameter.

4. The vehicle collision avoidance control method according to claim 3, characterized in that, The formula for calculating the preset warning distance is: Where: L is the preset warning distance; V h and V q These represent the current vehicle speed and the obstacle speed, respectively; a h and a q λ represents the deceleration of the current vehicle and the obstacle, respectively; λ is the driver's braking response characteristic coefficient; T is the preset safe travel time; θ is the influence coefficient of the current road on the vehicle's braking distance; μ is the estimated friction coefficient corresponding to different road surface conditions, where μ min The friction coefficient of the abnormal road surface, μ n f(μ) represents the friction coefficient under normal road surface conditions, where normal road surface conditions refer to a road surface at room temperature, dry, and free of impurities; min f(μ) represents the adhesion coefficient of the abnormal road surface. n () represents the adhesion coefficient of a normal road surface.

5. The vehicle collision avoidance control method according to claim 1, characterized in that, Determining the collision warning level based on the travel data and the braking data includes: The relative distance is calculated based on the travel data and the braking data. Based on the relative distance, it is determined whether the vehicle is within a preset catch-up distance, which is a preset maximum safe distance between adjacent vehicles and obstacles. If the relative distance is within the preset catch-up distance, the relative speed and relative acceleration of the current vehicle and the obstacle are calculated based on the travel data. Based on the relative velocity, the relative acceleration, and the distance, the collision time and the collision time threshold are calculated. Determine whether the collision time is less than the collision time threshold. If the collision time is less than the collision time threshold, issue a warning signal.

6. The vehicle collision avoidance control method according to claim 5, characterized in that, The formula for calculating the relative distance is: Where: D is the relative distance between the current vehicle and the obstacle; V h and V q These represent the current vehicle speed and the obstacle speed, respectively; a h and a q These represent the decelerations of the current vehicle and the obstacle, respectively; T a and T b These are braking reaction time and braking coordination time, respectively.

7. The vehicle collision avoidance control method according to claim 5, characterized in that, The formula for calculating the collision time and collision time threshold is as follows: Wherein: T r and T m These represent the collision time and the collision time threshold, respectively; V is the relative velocity; T... a denoted as braking reaction time; 'a' as relative acceleration; and 'H' as the distance between the current vehicle and the obstacle.

8. A vehicle collision avoidance control system, characterized in that, Includes modules for performing the vehicle collision avoidance control method according to any one of claims 1 to 7, said modules comprising: The first acquisition module is used to acquire the current vehicle driving image sequence and use the SURF algorithm to detect feature points and determine candidate feature points. Tracking module: used to track the positions of the candidate feature points using optical flow based on feature matching, calculate the motion vector of each candidate feature point, and estimate the camera motion path; Output module: used to smooth the camera motion path based on the Kalman filter algorithm and output driving images arranged in time series; Judgment module: used to determine whether the activation warning condition is met for each movable object in each driving image; if the activation warning condition is met, it is identified as an obstacle, and the obstacles are numbered in ascending order from the current vehicle to the farthest; the activation warning condition is a warning distance describing the obstacle in front of the vehicle that may cause obstruction to the vehicle's movement; The second acquisition module is used to acquire travel data and braking data based on the obstacle corresponding to the smallest number. The travel data is the driving speed and acceleration of the current vehicle and the obstacle. The braking data includes the distance between the current vehicle and the obstacle, braking reaction time, and braking coordination time. Warning module: used to determine the collision warning level based on the travel data and the braking data, and to perform vehicle collision avoidance control according to the collision warning level.

9. A vehicle collision avoidance control device, characterized in that, include: Memory, used to store computer programs; A processor for executing the computer program to implement the steps of the method for avoiding collisions with a vehicle as described in any one of claims 1 to 7.

10. A storage medium, characterized in that: The storage medium stores a computer program that, when executed by a processor, implements the steps of the vehicle collision avoidance control method as described in any one of claims 1 to 7.

Images