Anti-collision early warning method, vehicle-mounted device and storage medium

Abstract

The invention provides an anti-collision early warning method, a vehicle-mounted device and a storage medium. The anti-collision early warning method comprises the steps that image information and radar information are acquired; determining a main lane line in the vehicle driving direction according to the image information; the image information and the radar information are fused, obstacles in the main lane line are determined, and motion parameters of the vehicle and the obstacles are obtained; calculating the predicted collision time of the vehicle and the obstacle according to the motion parameters; the braking time of the vehicle is calculated, and if the predicted collision time is smaller than the braking time, early warning information is sent out. According to the invention, the accuracy of anti-collision early warning of the vehicle can be improved.

Description

Technical Field

[0001] The present application relates to the field of vehicle technology, and in particular to an anti-collision warning method, a vehicle-mounted device and a storage medium. Background Art

[0002] The collision prevention system is a vehicle driving assistance system that is used to identify obstacles around the vehicle and avoid collisions between the vehicle and the surrounding obstacles. However, the existing collision prevention system has the problem of inaccurate recognition when identifying obstacles on curves, which is prone to misjudgment, thus causing safety hazards. Summary of the invention

[0003] The embodiments of the present application disclose an anti-collision warning method, a vehicle-mounted device and a storage medium, which can solve the technical problem of inaccurate obstacle recognition when a vehicle is traveling on a curve.

[0004] The present application provides an anti-collision warning method, which includes: acquiring image information and radar information; determining a main lane line in a vehicle's driving direction according to the image information; fusing the image information and the radar information to determine obstacles within the main lane line and acquiring motion parameters of the vehicle and the obstacle; calculating an estimated collision time between the vehicle and the obstacle according to the motion parameters; calculating the braking time of the vehicle, and issuing a warning message if the estimated collision time is less than the braking time.

[0005] In some optional embodiments, the image information and the radar information are fused to obtain motion parameters of the vehicle and the obstacle, including: determining the relative distance and relative speed between the vehicle and the obstacle based on the fused image information and the radar information; and predicting the forward distance of the obstacle based on the image information and the relative speed.

[0006] In some optional embodiments, predicting the distance traveled by the obstacle based on the image information and the relative speed includes: obtaining the interval time between taking two adjacent images, and two relative speeds corresponding to the obstacles in the two adjacent images; calculating the acceleration of the obstacle based on the interval time and the two relative speeds; and calculating the distance traveled based on the interval time and the acceleration.

[0007] In some optional embodiments, calculating the impact time between the vehicle and the obstacle based on the motion parameters includes: calculating the impact time between the vehicle and the obstacle based on the relative distance, the forward distance and the relative speed.

[0008] In some optional embodiments, calculating the braking time of the vehicle includes: determining the driving speed of the vehicle based on the radar information; calculating the braking distance of the vehicle based on the driving speed of the vehicle and the acceleration of gravity; and calculating the braking time based on the braking distance and the driving speed of the vehicle.

[0009] In some optional embodiments, determining the main lane line in the direction of vehicle travel based on the image information includes: converting the image information acquired by using an image sensor into a bird's-eye view; moving a sliding window on the bird's-eye view, and fitting the pixel points in the sliding window using the least squares method to determine the main lane line.

[0010] In some optional embodiments, the fusing of the image information and the radar information includes: establishing an image coordinate system based on the bird's-eye view; determining a world coordinate system corresponding to the radar information obtained by a radar sensor, and the world coordinates of the obstacle in the world coordinate system; and converting the pixel coordinates into coordinates on the image coordinate system using an inverse perspective transformation matrix.

[0011] In some optional embodiments, the fusing of the image information and the radar information to determine obstacles within the main lane line includes: determining the obstacles within the main lane line based on the coordinates of the obstacles in the image coordinate system corresponding to the bird's-eye view and the main lane line.

[0012] The present application also provides a vehicle-mounted device, which includes a processor and a memory, and the processor is used to implement the anti-collision warning method when executing a computer program stored in the memory.

[0013] The present application also provides a computer-readable storage medium, on which a computer program is stored. When the computer program is executed by a processor, the anti-collision warning method is implemented.

[0014] In the anti-collision warning method provided by the present application, in order to improve the accuracy of identifying obstacles during vehicle driving, first, the main lane line in the vehicle driving direction is determined based on the image information, and then the acquired image information and radar information are fused to determine the obstacles in the main lane line and obtain the motion parameters of the vehicle and the obstacles, and finally, the estimated collision time between the vehicle and the obstacle is calculated based on the motion parameters, and if the estimated collision time is less than the braking time, a warning message is issued. The present application can improve the accuracy of anti-collision warning. BRIEF DESCRIPTION OF THE DRAWINGS

[0015] Figure 1 It is a schematic diagram of a vehicle-mounted device provided in an embodiment of the present application.

[0016] Figure 2 It is a flow chart of the anti-collision warning method provided in an embodiment of the present application.

[0017] Figure 3 It is a coordinate diagram of the curved lane lines and obstacles provided in an embodiment of the present application.

[0018] Figure 4 It is a coordinate diagram of the straight lane line and obstacles provided in an embodiment of the present application. DETAILED DESCRIPTION

[0019] To facilitate understanding, some illustrations of concepts related to the embodiments of the present application are given by way of example for reference.

[0020] It should be noted that in this application, "at least one" means one or more, and "more than one" means two or more than two. "And / or" describes the association relationship of associated objects, indicating that three relationships may exist. For example, A and / or B can mean: A exists alone, A and B exist at the same time, and B exists alone, where A and B can be singular or plural. The terms "first", "second", "third", "fourth", etc. (if any) in the specification, claims and drawings of this application are used to distinguish similar objects, rather than to describe a specific order or sequence.

[0021] In order to better understand the anti-collision warning method, vehicle-mounted device and storage medium provided in the embodiments of the present application, the application scenario of the anti-collision warning method of the present application is first described below.

[0022] Figure 1 is a schematic diagram of a vehicle-mounted device provided in an embodiment of the present application. The anti-collision warning method provided in an embodiment of the present application is applied to a vehicle-mounted device 1, and the vehicle-mounted device 1 includes, but is not limited to, a memory 11, at least one processor 12, an image sensor 13, and a radar sensor 14 connected to each other via a communication bus 10. The memory 11 can be used to store an anti-collision warning system 110 installed in the vehicle-mounted device 1, and the program code of each program segment in the anti-collision warning system 110 can be stored in the memory 11 of the vehicle-mounted device 1 and executed by at least one processor 12 to realize the function of anti-collision warning.

[0023] The image sensor 13 may be an onboard device of the vehicle or an external camera device of the vehicle, such as a camera, to capture multiple images or videos in front of the vehicle.

[0024] The radar sensor 14 may be a vehicle-mounted device or a radar device externally connected to the vehicle, and is used to detect obstacles near the vehicle. The obstacles may be any objects or pedestrians that hinder the vehicle from traveling.

[0025] Figure 1 What is shown is merely an example of the vehicle-mounted device 1 and does not constitute a limitation of the vehicle-mounted device 1. In actual applications, the vehicle-mounted device 1 may include more or fewer components than shown in the figure, or a combination of certain components, or different components. For example, the vehicle-mounted device 1 may also include input and output devices, network access devices, etc.

[0026] In an embodiment of the present application, the vehicle-mounted device 1 is applied to a vehicle. For example, it can be a vehicle-mounted device in a vehicle (for example, a vehicle computer), or it can be an independent vehicle-mounted device (for example, a computer, a laptop computer, a mobile phone, etc.) and can communicate and exchange data with the vehicle-mounted equipment, thereby realizing control of the vehicle.

[0027] The collision prevention system is a vehicle driving assistance system that is used to identify obstacles around the vehicle and avoid collisions between the vehicle and the surrounding obstacles. However, the existing collision prevention system has the problem of inaccurate recognition when identifying obstacles on curves, which is prone to misjudgment and causes safety hazards.

[0028] In order to solve the technical problem of inaccurate obstacle identification when the vehicle is driving, the embodiment of the present application provides an anti-collision warning method, which is applied to the vehicle-mounted device 1 and can improve the accuracy of obstacle identification during vehicle driving.

[0029] like Figure 2 FIG. 2 is a flowchart of a collision avoidance warning method provided by an embodiment of the present application. The collision avoidance warning method described in the present application is applied to a vehicle-mounted device (eg Figure 1 According to different requirements, the order of the steps in the flowchart can be changed, and some steps can be omitted.

[0030] Step S21, acquiring image information and radar information.

[0031] In one embodiment, the vehicle-mounted device may be a device installed on a vehicle, and the vehicle-mounted device may include multiple sensors, such as an image sensor and a radar sensor. The vehicle-mounted device may also be connected to multiple sensors to achieve data interaction, for example, the image sensor may be a driving recorder.

[0032] The image sensor may include a camera device for shooting, which may be a monocular camera device. The image sensor is used to obtain image information. For example, the image sensor may be used to shoot a video of the front during driving, and then each frame may be extracted from the video as the image information of the vehicle. Alternatively, the image sensor may be used to shoot a picture, and the image information may be an image around the vehicle or a foreground image in front of the vehicle's driving path. The image information includes the main lane where the vehicle is located during driving.

[0033] The radar sensor can detect the target and determine the spatial position of the target by radio. The target can be an object or pedestrian around the vehicle. When the vehicle is driving, the radar sensor is used to obtain radar information around the vehicle. The radar information can be an object or pedestrian around the vehicle.

[0034] Step S22, determining the main lane line in the vehicle's driving direction according to the image information.

[0035] In one embodiment, an image sensor may be used to obtain image information in front of a vehicle, wherein the image information may be a foreground image captured in front of the vehicle. Usually, the foreground image captured on the vehicle is a distorted image, and the foreground image needs to be distorted corrected to obtain a corrected image.

[0036] Specifically, the distortion correction of the foreground image includes establishing an image coordinate system corresponding to the foreground image, obtaining coordinates with a certain distortion corresponding to each non-zero pixel point in the foreground image, obtaining the internal parameters of the camera module that shoots the foreground image, and the internal parameters are used to determine the degree of distortion of the coordinates with a certain distortion. According to the internal parameters, the coordinates with a certain distortion are obtained to obtain the distortion-free coordinates corresponding to the foreground image.

[0037] In order to improve the smoothness of the corrected image, the weights corresponding to the coordinates with certain distortion and the coordinates without distortion are obtained respectively. The coordinates with certain distortion are smoothly corrected by weighted method to ensure the authenticity of the image.

[0038] After obtaining the corrected image, the corrected image is subjected to image grayscale, gradient threshold, color threshold and saturation threshold preprocessing, etc., and information irrelevant to the lane line in the corrected image is removed to obtain a binary image, and the binary image is subjected to perspective transformation to obtain a bird's-eye view. The bird's-eye view refers to a three-dimensional image drawn from a certain point at a high altitude using a high viewpoint method based on the perspective principle, which is more realistic than a plane image.

[0039] The binary image is obtained by removing the information irrelevant to the lane line in the corrected image. Specifically, the characteristics of lanes on the same road surface being approximately parallel are used, and the perspective effect is eliminated by using perspective transformation. Each non-zero pixel in the corrected image is used as a target point, and the coordinate point of the target point is calculated by using the coordinate transformation formula to obtain an inverse transformation matrix, and the inverse transformation matrix is ​​used to obtain a bird's-eye view. The bird's-eye view eliminates the interference of the surrounding environment of the road and the sky, and only retains the road lane information contained in the area of ​​interest in lane line detection, which can effectively reduce the amount of complex background calculations.

[0040] After the foreground image is converted into a bird's-eye view, the lane line is searched by moving a sliding window on the bird's-eye view. Since the lane line is continuous, the pixels in the lower half of the bird's-eye view can be counted in a histogram. The place where the maximum value appears can be considered as the intersection of the lane line and the bottom of the upper half of the bird's-eye view. Using the sliding window, the search starts from the intersection from bottom to top. For each sliding window, the pixels with grayscale values ​​not equal to 0 in the sliding window are counted. If the number of non-zero pixels currently counted is greater than the preset threshold, the search is considered successful. For example, a sliding window with a width of 200 pixels can be used for movement, and the distance of each movement can be 200 pixels. The center position of the next sliding window is determined by the average value of the horizontal coordinates of all non-zero pixels in the current window. If the number of non-zero pixels currently counted is less than the preset threshold, it indicates that the lane may be curved and is about to exceed the range of the current sliding window, or the current sliding window is at the interval position of the dotted lane. At this time, the average value of the horizontal coordinates corresponding to all pixels of the previous N sliding windows is selected as the window center position of the next sliding window, so as to ensure that the sliding window can move with the change of the lane. During the movement of the sliding window, the least square method is used to fit the pixel points in the sliding window to generate the main lane line, which may include a left main lane line and a right main lane line.

[0041] Step S23, fusing the image information and the radar information, determining the obstacles within the main lane line, and obtaining the motion parameters of the vehicle and the obstacles.

[0042] In order to determine whether there is an obstacle between the left main lane line and the right main lane line, the image information obtained by the image sensor and the radar information obtained by the radar sensor are fused.

[0043] Specifically, the obstacle is located by using a radar sensor. First, the world coordinate system corresponding to the radar information obtained by the radar sensor and the world coordinates (X w ,Y w ,Z w ), the relationship between the image coordinate system and the world coordinate system is determined by the external parameter matrix of the radar sensor and the image sensor, as shown below:

[0044]

[0045] In the above formula, (X c ,Y c ,Z c ) is the coordinate corresponding to the world coordinate in the image coordinate system, Represents the extrinsic parameter matrix of the radar sensor and the image sensor.

[0046] Based on the relationship between the image coordinate system and the world coordinate system, as well as the external parameter matrix of the radar sensor and the image sensor And the intrinsic parameter K of the image sensor, the world coordinates corresponding to the obstacle are converted into pixel coordinates in the image coordinate system as follows:

[0047]

[0048] In the above formula, [u,v,1] represents the transformation of the obstacle into two-dimensional pixel coordinates in image coordinates.

[0049] After the world coordinates of the obstacle are converted into pixel coordinates, the pixel coordinates are converted into coordinates in the image coordinate system using the inverse perspective transformation matrix, so that the image information and radar information can be fused.

[0050] After fusing the image information and the radar information, it is determined whether there is an obstacle in the main lane line according to the coordinates of the obstacle in the image coordinate system corresponding to the bird's-eye view and the expression corresponding to the curve fitted to the main lane line, where the expression corresponding to the curve fitted to the main lane line includes the quadratic equation fL(x) fitted to the left lane line and the quadratic equation fR(x) fitted to the right lane line.

[0051] Figure 3 It is a schematic diagram of curved lane lines and obstacle coordinates provided in an embodiment of the present application.

[0052] In one embodiment, if Figure 3 As shown in the figure, assuming that the vehicle is traveling on a curve, determine whether the position of obstacle point A and obstacle point B are within the main lane line. Substitute the coordinates of point A and point B into fL(x) and fR(x) respectively to obtain point C and point D on the left main lane line and the right main lane line. Connect point A, point B, point C and point D, then point C is located on the line connecting point A and point B and on the left main lane line, and point D is located on the line connecting point A and point B and on the right main lane line. According to the positions of point A, point B, point C and point D, determine whether the obstacle is within the main lane line.

[0053] If the obstacle is on the line between point C and point D, it means that the obstacle is within the main lane line. Figure 3 Point B in the figure, obtain the motion parameters of the obstacle and the vehicle corresponding to point B according to the radar sensor. If the obstacle is not on the line between point C and point D, such as Figure 3 Point A in the figure indicates that the obstacle is not within the main lane line and does not affect the vehicle's driving on the main lane line.

[0054] Figure 4 It is a coordinate diagram of the straight lane line and obstacles provided in an embodiment of the present application.

[0055] In one embodiment, if Figure 4 As shown in , assuming that the vehicle is traveling in a straight line, the horizontal coordinate of the obstacle point in the image coordinate system and the horizontal coordinate of the main lane line can be used to determine whether the obstacle point is within the main lane line, such as Figure 4 As shown, assuming that the horizontal coordinate X1 of the left lane line is 18, the horizontal coordinate X2 of the right lane line is 24, and the horizontal coordinate X3 of the obstacle E is 20. Since X2>X3>X1, it indicates that the obstacle E is within the main lane line. The horizontal coordinate X4 of the obstacle F is 30. Since X4>X2>X1, it indicates that the obstacle F is not within the main lane line and is located on the right side of the right lane line.

[0056] After determining that there is an obstacle in the main lane, in order to avoid the impact of the obstacle on the moving vehicle, the motion parameters of the vehicle and the obstacle are obtained.

[0057] Based on the fused image information and radar information, the relative distance and relative speed between the vehicle and the obstacle are determined, and the forward distance of the obstacle is predicted based on the image information and relative speed.

[0058] Among them, predicting the obstacle's forward distance based on image information and relative speed includes obtaining the interval time between shooting two adjacent images. When the frame rate is 30 frames per second, the interval time t=1 / 30 second. Assuming that the obstacle is moving at a constant speed, the radar sensor is used to obtain the relative speed corresponding to the first shot of the two adjacent images, which is recorded as v1, and the second shot is recorded as v2. The relative speed refers to the relative speed between the vehicle and the obstacle obtained by the radar sensor during shooting. According to the interval time and the two recorded relative speeds, the acceleration of the obstacle is calculated. For example, the acceleration a of the obstacle can be calculated by the formula v2=v1+at. After obtaining the acceleration a of the obstacle, according to the formula S=v0t+at 2 / 2, the obstacle's advance distance S can be calculated, where v0 represents the initial velocity of the obstacle during the interval. The above method of calculating the advance distance is not limited here, for example, the advance distance can be calculated using the initial velocity and final velocity during the interval.

[0059] This application determines whether there are obstacles in the main lane based on the fused image information and radar information, avoiding misjudgment of pedestrians or objects outside the main lane. After determining that there are obstacles in the main lane, the motion parameters of the vehicle and the obstacle are obtained to calculate the relevant information of the vehicle and the obstacle, thereby improving the vehicle's early warning capability and efficiency.

[0060] Step S24, calculating the estimated collision time between the vehicle and the obstacle based on the motion parameters.

[0061] In order to determine the impact of obstacles in the main lane on the moving vehicle, it is necessary to predict the collision time between the vehicle and the obstacle. The collision time refers to the predicted collision time between the vehicle and the obstacle after the obstacle is discovered during the vehicle's operation.

[0062] In one embodiment, the estimated time of impact between the vehicle and the obstacle is calculated based on the motion parameters calculated above, where the motion parameters include relative distance, forward distance and relative speed. The estimated time of impact between the vehicle and the obstacle is calculated based on the relative distance, forward distance and relative speed. For example, estimated time of impact TTC = (relative distance + forward distance) / relative speed.

[0063] Step S25, calculating the braking time of the vehicle, and issuing a warning message if the estimated collision time is less than the braking time.

[0064] After calculating the estimated time of impact TTC, the vehicle's speed is determined based on the radar information, and the braking distance of the vehicle is calculated based on the vehicle's speed and gravity acceleration. The braking time is calculated based on the braking distance and the vehicle's speed. The braking time is the time from the driver stepping on the brake until the vehicle stops, and it is also the minimum time the vehicle is expected to hit the obstacle. For example, braking time TTCmin = braking distance / relative speed, braking distance = (driving speed * driving speed) / (2 * 0.9 * g), where g is the acceleration of gravity.

[0065] Compare the expected collision time TTC with the braking time TTCmin. If the expected collision time TTC is less than the braking time TTCmin, it means that the vehicle has hit an obstacle before it has completely stopped after braking. At this time, the vehicle issues a warning message, allowing the driver to change the direction of travel or take emergency measures. If the expected collision time TTC is greater than the braking time TTCmin, it means that the obstacle is within a safe distance from the vehicle.

[0066] In the anti-collision warning method provided by the present application, in order to improve the accuracy of identifying obstacles during vehicle driving, first, the main lane line in the direction of vehicle driving is determined based on image information, and secondly, the acquired image information and radar information are fused to determine the obstacles in the main lane line and obtain the motion parameters of the vehicle and the obstacles, and finally, the estimated collision time between the vehicle and the obstacle is calculated based on the motion parameters. If the estimated collision time is less than the braking time, a warning message is issued. The present application can improve the accuracy of anti-collision warnings, and can also avoid misjudging obstacles that are not in the main lane line, frequently reminding the driver, and affecting the driving experience.

[0067] Please continue reading Figure 1In this embodiment, the memory 11 may be an internal memory of the vehicle-mounted device 1, that is, a memory built into the vehicle-mounted device 1. In other embodiments, the memory 11 may also be an external memory of the vehicle-mounted device 1, that is, a memory externally connected to the vehicle-mounted device 1.

[0068] In some embodiments, the vehicle-mounted device 1 includes a terminal that can automatically perform numerical calculations and / or information processing according to pre-set or stored instructions, and its hardware includes but is not limited to microprocessors, application-specific integrated circuits, programmable gate arrays, digital processors, and embedded devices.

[0069] It should be noted that the vehicle-mounted device 1 is only an example, and other existing or future electronic products that are suitable for the present application should also be included in the protection scope of the present application and included here by reference.

[0070] In some embodiments, the memory 11 is used to store program codes and various data. For example, the memory 11 can be used to store the program code and various data installed in the memory 11 of the vehicle-mounted device 1, and realize high-speed and automatic access to programs or data during the operation of the vehicle-mounted device 1. The memory 11 includes a read-only memory (ROM), a programmable read-only memory (PROM), an erasable programmable read-only memory (EPROM), a one-time programmable read-only memory (OTPROM), an electronically erasable rewritable read-only memory (EEPROM), a compact disc (CD-ROM) or other optical disc storage, magnetic disk storage, magnetic tape storage, or any other computer-readable storage medium that can be used to carry or store data.

[0071] In some embodiments, the at least one processor 12 may be composed of an integrated circuit, for example, a single packaged integrated circuit, or a plurality of packaged integrated circuits with the same or different functions, including one or more central processing units (CPUs), microprocessors, digital processing chips, graphics processors, and a combination of various control chips. The at least one processor 12 is the control core (Control Unit) of the vehicle-mounted device 1, and uses various interfaces and lines to connect various components of the entire vehicle-mounted device 1, and executes or executes programs or modules stored in the memory 11, and calls data stored in the memory 11 to execute various functions of the vehicle-mounted device 1 and process data, such as executing Figure 1 The function of the collision avoidance warning is shown.

[0072] In some embodiments, the anti-collision warning system 110 is run in the vehicle-mounted device 1. The anti-collision warning system 110 may include a plurality of functional modules composed of program code segments. The program code of each program segment in the anti-collision warning system 110 may be stored in the memory 11 of the vehicle-mounted device 1 and executed by at least one processor 12 to implement Figure 1 The function of the collision avoidance warning is shown.

[0073] In this embodiment, the anti-collision warning system 110 can be divided into multiple functional modules according to the functions it performs. The module referred to in this application refers to a series of computer program segments that can be executed by at least one processor and can complete fixed functions, which are stored in a memory.

[0074] Although not shown, the vehicle-mounted device 1 may also include a power source (such as a battery) for supplying power to various components. Preferably, the power source may be logically connected to the at least one processor 12 through a power management device, so that the power management device can manage charging, discharging, and power consumption. The power source may also include one or more DC or AC power sources, recharging devices, power failure test circuits, power converters or inverters, power status indicators, and other arbitrary components. The vehicle-mounted device 1 may also include a variety of sensors, Bluetooth modules, Wi-Fi modules, etc., which will not be repeated here.

[0075] It should be understood that the embodiment is for illustration only and the scope of the patent application is not limited to this structure.

[0076] The above-mentioned integrated unit implemented in the form of a software function module can be stored in a computer-readable storage medium. The above-mentioned software function module is stored in a storage medium, including a number of instructions for enabling a vehicle-mounted device (which can be a server, a personal computer, etc.) or a processor to execute a part of the method described in each embodiment of the present application.

[0077] The memory 11 stores program codes, and the at least one processor 12 can call the program codes stored in the memory 11 to execute related functions. The program codes stored in the memory 11 can be executed by the at least one processor 12, thereby realizing the functions of the various modules to achieve the purpose of anti-collision warning.

[0078] In the several embodiments provided in this application, it should be understood that the disclosed devices and methods can be implemented in other ways. For example, the device embodiments described above are only illustrative, for example, the division of the modules is only a logical function division, and there may be other division methods in actual implementation.

[0079] The modules described as separate components may or may not be physically separated, and the components shown as modules may or may not be physical units, that is, they may be located in one place or distributed on multiple network units. Some or all of the modules may be selected according to actual needs to achieve the purpose of the solution of this embodiment.

[0080] In addition, each functional module in each embodiment of the present application can be integrated into one processing unit, or each unit can exist physically separately, or two or more units can be integrated into one unit. The above integrated unit can be implemented in the form of hardware or in the form of hardware plus software functional modules.

[0081] It is obvious to those skilled in the art that the present application is not limited to the details of the above exemplary embodiments, and that the present application can be implemented in other specific forms without departing from the spirit or basic features of the present application. Therefore, from any point of view, the embodiments should be regarded as exemplary and non-restrictive, and the scope of the present application is limited by the attached claims rather than the above description, so it is intended to include all changes that fall within the meaning and scope of the equivalent elements of the claims in the present application. Any figure mark in the claims should not be regarded as limiting the claims involved. In addition, it is obvious that the word "comprising" does not exclude other units or, and the singular does not exclude the plural. Multiple units or devices stated in the device claim can also be implemented by one unit or device through software or hardware. The words first, second, etc. are used to indicate names, and do not indicate any particular order.

[0082] Finally, it should be noted that the above embodiments are only used to illustrate the technical solution of the present application and are not intended to limit it. Although the present application has been described in detail with reference to the above preferred embodiments, a person of ordinary skill in the art should understand that the technical solution of the present application may be modified or replaced by equivalents without departing from the spirit and scope of the technical solution of the present application.

Claims

1. A collision avoidance warning method, characterized in that: The method comprises: Obtain image information and radar information; Determine the main lane line in the direction of vehicle travel according to the image information; Fusing the image information and the radar information, determining obstacles within the main lane and obtaining motion parameters of the vehicle and the obstacles; Calculating an estimated collision time between the vehicle and the obstacle according to the motion parameters; The braking time of the vehicle is calculated, and if the estimated collision time is less than the braking time, a warning message is issued.

2. The anti-collision warning method according to claim 1, characterized in that: The fusing the image information and the radar information to obtain motion parameters of the vehicle and the obstacle includes: Determine the relative distance and relative speed between the vehicle and the obstacle according to the fused image information and the radar information; The distance of the obstacle is predicted based on the image information and the relative speed.

3. The anti-collision warning method according to claim 2, characterized in that: The predicting the distance of the obstacle based on the image information and the relative speed includes: Obtaining the interval time between taking two adjacent images and two relative speeds corresponding to the obstacles in the two adjacent images; Calculating the acceleration of the obstacle according to the interval time and the two relative speeds; The travel distance is calculated according to the interval time and the acceleration.

4. The anti-collision warning method according to claim 3, characterized in that: The calculating the collision time between the vehicle and the obstacle according to the motion parameter includes: The collision time between the vehicle and the obstacle is calculated according to the relative distance, the forward distance and the relative speed.

5. The anti-collision warning method according to claim 2, characterized in that: The calculating the braking time of the vehicle comprises: determining a travel speed of the vehicle according to the radar information; Calculating a braking distance of the vehicle according to the vehicle's travel speed and gravity acceleration; The braking time is calculated according to the braking distance and the driving speed of the vehicle.

6. The anti-collision warning method according to claim 1, characterized in that: Determining the main lane line in the vehicle driving direction according to the image information includes: Converting the image information obtained by using an image sensor into a bird's-eye view; The main lane line is determined by moving a sliding window on the bird's-eye view and fitting the pixel points in the sliding window using the least squares method.

7. The anti-collision warning method according to claim 6, characterized in that: The fusing of the image information and the radar information includes: Establishing an image coordinate system based on the bird's-eye view; Determine a world coordinate system corresponding to the radar information acquired by the radar sensor, and a world coordinate of the obstacle in the world coordinate system; Convert the world coordinates corresponding to the obstacle into pixel coordinates on the image information according to the external parameter matrices of the radar sensor and the image sensor and the internal parameters of the image sensor; The pixel coordinates are converted into coordinates in the image coordinate system using an inverse perspective transformation matrix.

8. The anti-collision warning method according to claim 7, characterized in that: The fusing the image information and the radar information to determine the obstacle in the main lane line includes: The obstacle within the main lane line is determined according to the coordinates of the obstacle in the image coordinate system corresponding to the bird's-eye view and the main lane line.

9. A vehicle-mounted device, characterized in that: The vehicle-mounted device includes a processor and a memory, and the processor is used to execute a computer program stored in the memory to implement the anti-collision warning method as described in any one of claims 1 to 8.

10. A computer-readable storage medium, characterized in that: The computer-readable storage medium stores at least one instruction, and when the at least one instruction is executed by the processor, the anti-collision warning method according to any one of claims 1 to 8 is implemented.

Images