Vehicle control method, device and equipment and computer readable storage medium

Abstract

The invention relates to a vehicle control method, device and equipment and a computer readable storage medium. The lane line and the pedal line are obtained by detecting the all-around image collected by the all-around image collection device, the image collection distance is short, the influence of the environment and the clear degree of the lane line is low, the deviation distance of the vehicle is further calculated according to the distance between the lane line and the pedal line in the all-around image, and the vehicle deviation accuracy is improved. According to the method, lane line misrecognition caused by poor image acquisition effect is effectively avoided, the influence of factors such as severe weather or light pollution is reduced, the precision of vehicle control in the lane keeping process is improved, and the effectiveness and safety of functions in the driving process are ensured.

Description

Technical Field

[0001] This disclosure relates to the field of intelligent driving technology, and in particular to a vehicle control method, apparatus, device, and computer-readable storage medium. Background Technology

[0002] Lane keeping assist is one of the important functions of autonomous driving. Activating lane keeping assist can help the driver keep the vehicle in the middle of the lane and prevent the vehicle from deviating unintentionally due to driver inattention or fatigue.

[0003] Existing lane keeping assist systems primarily use a front-facing camera to capture images of the road surface ahead of the vehicle, identify lane lines in the image, and then control the vehicle to maintain its lane position.

[0004] However, when the front-facing vision camera cannot capture a clear image of the lane lines, such as when there is dirt or rain on the windshield, the lane lines are not obvious, there is strong light ahead, or the weather is very bad, the lane line information identified will be incorrect or deviated, which will have a significant impact on the lane assist function and will not be able to guarantee the accuracy of vehicle control. Summary of the Invention

[0005] To address the aforementioned technical problems, this disclosure provides a vehicle control method, apparatus, device, and computer-readable storage medium to ensure the accuracy of vehicle control.

[0006] In a first aspect, embodiments of this disclosure provide a vehicle control method, including:

[0007] During vehicle operation, surround view images of the vehicle's surroundings are captured using onboard surround view image acquisition equipment.

[0008] Image analysis is performed on the surround view image to obtain the lane lines and foot lines in the surround view image;

[0009] The vehicle's deviation distance relative to the lane centerline is calculated based on the distance between the lane line and the foot line.

[0010] The target steering wheel control amount required to correct the deviation distance is calculated based on the deviation distance, vehicle speed, and current steering wheel angle.

[0011] The vehicle is controlled according to the target steering wheel control amount.

[0012] In some embodiments, performing image analysis on the surround view image to obtain lane lines and footpath lines in the surround view image includes:

[0013] The toroidal image is corrected based on the intrinsic and extrinsic parameter matrices and distortion matrix of the image acquisition device to obtain the corrected toroidal image.

[0014] The corrected surround view image is input into the threshold segmentation detection model for detection to obtain the lane line marking image output by the threshold segmentation detection model;

[0015] The foot track detection line extracted from the panoramic image is extended to obtain the foot track.

[0016] In some embodiments, extending the detection line to obtain the pedal line includes:

[0017] For each side of the detection line, extend the detection line to both ends to the center position of the front wheel and the center position of the rear wheel on the same side, respectively, to obtain the pedal line.

[0018] In some embodiments, calculating the vehicle's deviation distance relative to the lane centerline based on the distance between the lane line and the footboard line includes:

[0019] Obtain the pixel distance between the foot track line and the lane line on the same side in the surround view image;

[0020] The actual distance between the foot track and the lane line on the same side is obtained by multiplying the intrinsic and extrinsic parameters of the image acquisition device with the pixel distance.

[0021] The deviation distance is calculated based on the difference in the actual distances corresponding to the footboard lines on both sides.

[0022] In some embodiments, obtaining the pixel distance between the foot track line and the lane line on the same side in the surround view image includes:

[0023] When the lane line is not parallel to the pedal line, for each pedal line, the distance from the starting point of the pedal line to the starting point of the lane line on the same side, the distance from the midpoint of the pedal line to the midpoint of the lane line, and the distance from the ending point of the pedal line to the ending point of the lane line on the same side are obtained respectively.

[0024] Calculate the average of the starting point distance, the midpoint distance, and the ending point distance to obtain the pixel distance between the foot track on one side and the lane line on the same side.

[0025] In some embodiments, calculating the target steering control amount required to correct the deviation distance based on the deviation distance, vehicle speed, and current steering wheel angle includes:

[0026] The target correction deviation angle is obtained by dividing the deviation distance by the product of the preset correction time and the vehicle speed;

[0027] The target steering wheel angle is obtained by looking up the table according to the preset calibration table and the target correction deviation angle. The preset calibration table includes the mapping relationship between the steering wheel angle and the vehicle deviation angle.

[0028] The target steering wheel control amount is obtained by calculating the difference between the target steering wheel angle and the current steering wheel angle.

[0029] Secondly, embodiments of this disclosure provide a vehicle control device, comprising:

[0030] The acquisition module is used to acquire surround view images of the vehicle's surroundings using an onboard surround view image acquisition device while the vehicle is in motion.

[0031] The acquisition module is used to perform image analysis on the surround view image to acquire lane lines and foot lines in the surround view image;

[0032] The first calculation module is used to calculate the vehicle's deviation distance relative to the lane centerline based on the distance between the lane line and the foot line;

[0033] The second calculation module is used to calculate the target steering wheel control amount required to correct the deviation distance based on the deviation distance, vehicle speed and current steering wheel angle.

[0034] The control module is used to control the vehicle according to the target steering wheel control amount.

[0035] Thirdly, embodiments of this disclosure provide an electronic device, including:

[0036] Memory;

[0037] Processor; and

[0038] Computer programs;

[0039] The computer program is stored in the memory and configured to be executed by the processor to implement the method as described in the first aspect.

[0040] Fourthly, embodiments of this disclosure provide a computer-readable storage medium having a computer program stored thereon, the computer program being executed by a processor to implement the method described in the first aspect.

[0041] Fifthly, embodiments of this disclosure provide a vehicle including the device, electronic device, or computer-readable storage medium described above.

[0042] The vehicle control method, apparatus, device, and computer-readable storage medium provided in this disclosure detect lane lines and foot lines in the surround view image acquired by the surround view image acquisition device. The image acquisition distance is relatively short, and it is less affected by environmental factors and the clarity of the lane lines. Furthermore, the vehicle's deviation distance is calculated based on the distance between the lane lines and foot lines in the surround view image. This effectively avoids lane line misidentification caused by poor image acquisition, reduces the impact of factors such as severe weather or light pollution, improves the accuracy of vehicle control during lane keeping, and ensures the effectiveness and safety of the function during driving. Attached Figure Description

[0043] The accompanying drawings, which are incorporated in and form a part of this specification, illustrate embodiments consistent with this disclosure and, together with the description, serve to explain the principles of this disclosure.

[0044] To more clearly illustrate the technical solutions in the embodiments of this disclosure or the prior art, the accompanying drawings used in the description of the embodiments or the prior art will be briefly introduced below. Obviously, for those skilled in the art, other drawings can be obtained based on these drawings without creative effort.

[0045] Figure 1 A flowchart of a vehicle control method provided in an embodiment of this disclosure;

[0046] Figure 2 A schematic diagram illustrating an application scenario provided by an embodiment of this disclosure;

[0047] Figure 3 This is a diagram illustrating the architecture of a vehicle control method according to another embodiment of this disclosure.

[0048] Figure 4 This is a schematic diagram of the structure of the vehicle control device provided in the embodiments of this disclosure;

[0049] Figure 5 This is a schematic diagram of the structure of an electronic device provided in an embodiment of this disclosure. Detailed Implementation

[0050] To better understand the above-mentioned objectives, features, and advantages of this disclosure, the solutions disclosed herein will be further described below. It should be noted that, unless otherwise specified, the embodiments and features described herein can be combined with each other.

[0051] Numerous specific details are set forth in the following description in order to provide a full understanding of this disclosure, but this disclosure may also be implemented in other ways different from those described herein; obviously, the embodiments in the specification are only some, and not all, of the embodiments of this disclosure.

[0052] This disclosure provides a vehicle control method, which will be described below with reference to specific embodiments.

[0053] Figure 1 This is a flowchart illustrating a vehicle control method provided in an embodiment of this disclosure. This method can be applied to... Figure 2 The application scenario shown includes controlling a vehicle 21 and a server 22. The vehicle 21 is equipped with in-vehicle devices, which may specifically be a car infotainment system, smartphone, PDA, tablet computer, laptop computer, all-in-one machine, intelligent driving device, etc. It is understood that the vehicle control method provided in this embodiment can also be applied to other scenarios.

[0054] The following combination Figure 2 The application scenarios shown are for Figure 1 The vehicle control method shown is described below, and the specific steps of this method are as follows:

[0055] S101. During vehicle operation, surround view images of the vehicle's surroundings are collected using an on-board surround view image acquisition device.

[0056] Among them, the vehicle-mounted surround view image acquisition device can be multiple vehicle-mounted surround view cameras.

[0057] A surround-view image can be a 360° view of the vehicle's surroundings. Specifically, a surround-view image can be obtained by stitching together images captured separately by multiple onboard surround-view cameras.

[0058] S102. Perform image analysis on the surround view image to obtain the lane lines and foot lines in the surround view image.

[0059] Image analysis includes processing and detecting the panoramic image.

[0060] Specifically, after preprocessing the surround view image such as distortion correction and image cropping, the processed image is detected to obtain the lane lines on both sides of the vehicle and the foot lines on the vehicle body itself.

[0061] The footwell lines are located at the lower edge of the car doors, with one footwell line on each of the left and right sides of the vehicle. When the vehicle is traveling straight, the footwell lines are usually parallel to the lane lines.

[0062] In some embodiments, a trained threshold segmentation detection model can be used to detect the surround view image. Specifically, taking lane line recognition as an example, the threshold segmentation detection model is trained using sample images with labeled lane line information. Unlabeled sample images are used as input to the threshold segmentation detection model, and labeled sample images are used as output to train the model. This allows the threshold segmentation detection model to learn the ability to label lane lines in the image, resulting in a trained threshold segmentation detection model. Furthermore, in practice, the surround view image is input into the trained threshold segmentation detection model to obtain the lane line marking images on both sides of the vehicle, as output by the threshold segmentation detection model, thereby acquiring the lane lines in the surround view image.

[0063] In some embodiments, the actual pedal lines of the vehicle body can be mapped onto the surround view image based on the vehicle's design data and the calibration parameters of the surround view image acquisition device, thereby obtaining the pedal lines in the surround view image. Optionally, the pedal line detection results of the surround view image are verified against the mapping results of the actual pedal lines of the vehicle body to finally obtain the pedal lines in the surround view image.

[0064] S103. Calculate the vehicle's deviation distance relative to the lane centerline based on the distance between the lane line and the foot line.

[0065] Specifically, the vehicle's deviation distance relative to the center line is calculated based on the difference between the distances between the footwell lines on both sides of the vehicle and the lane lines on the same side.

[0066] Specifically, the pixel distance between the lane lines and foot lines in the surround view image can be obtained, and the actual distance between the lane lines and foot lines can be calculated based on the calibration parameters of the surround view image acquisition device and the pixel distance.

[0067] Optionally, if the distance between the left foot pedal line and the left lane line is the first distance, and the distance between the right foot pedal line and the right lane line is the second distance, then the deviation distance of the vehicle relative to the center line of the lane is half the difference between the first distance and the second distance.

[0068] S104. Calculate the target steering wheel control amount required to correct the deviation distance based on the deviation distance, vehicle speed, and current steering wheel angle.

[0069] There is a fixed correspondence between the steering wheel angle and the front wheel offset angle. Therefore, vehicle speed and the current steering wheel angle jointly affect the vehicle's lateral deviation speed. The deviation distance is used as the target for correction, and the steering wheel control amount required to correct this deviation distance is calculated by combining the vehicle speed and the current steering wheel angle (current front wheel offset angle).

[0070] Specifically, the target correction deviation angle is obtained by dividing the deviation distance by the product of the preset correction time and the vehicle speed; the target steering wheel angle is obtained by looking up the table according to the preset calibration table and the target correction deviation angle, wherein the preset calibration table includes the mapping relationship between the steering wheel angle and the front wheel deviation angle; the target steering wheel control amount is obtained by calculating the difference between the target steering wheel angle and the current steering wheel angle.

[0071] The preset correction time is the time required to correct the vehicle from its current state to a normal lane-keeping state, typically set to 1 second or 1.5 seconds.

[0072] That is, the following relationship exists between the deviation distance x, the front wheel deviation angle θ, the vehicle speed V, and the preset correction time T:

[0073] x=θ*V*T

[0074] In some embodiments, a vehicle kinematics model can be established based on the above calculation process. By inputting the deviation distance, vehicle speed and current steering wheel angle into the vehicle kinematics model, the target steering wheel control quantity can be obtained.

[0075] S105. Control the vehicle according to the target steering wheel control amount.

[0076] Once the target steering wheel control value is calculated, the vehicle can be controlled based on this value to return it to the center line of the lane.

[0077] At the same time, new surround view images are collected again through the surround view image acquisition device, and the above steps are repeated. This cyclical control method keeps the vehicle in a relatively central position in the lane.

[0078] This embodiment of the disclosure acquires a surround-view image of the vehicle's surroundings using an onboard surround-view image acquisition device during vehicle operation; performs image analysis on the surround-view image to obtain lane lines and foot lines; calculates the vehicle's deviation distance relative to the lane centerline based on the distance between the lane lines and foot lines; calculates the target steering wheel control amount required to correct the deviation distance based on the deviation distance, vehicle speed, and current steering wheel angle; and controls the vehicle based on the target steering wheel control amount. By detecting and acquiring lane lines and foot lines from the surround-view image acquired by the surround-view image acquisition device, the image acquisition distance is relatively short, and the impact of environmental influences and lane line clarity is low. Furthermore, the vehicle's deviation distance is calculated based on the distance between the lane lines and foot lines in the surround-view image, effectively avoiding lane line misidentification caused by poor image acquisition quality, reducing the impact of factors such as severe weather or light pollution, improving the accuracy of vehicle control during lane keeping, and ensuring the effectiveness and safety of the function during driving.

[0079] In addition, the vehicle control method provided in this disclosure can also be combined with existing forward-facing lane keeping functions to improve environmental interference resistance and lane recognition accuracy.

[0080] In some embodiments, the step of performing image analysis on the surround view image to obtain lane lines and pedal lines in the surround view image includes: correcting the surround view image based on the intrinsic and extrinsic parameter matrices and distortion matrix of the image acquisition device to obtain a corrected surround view image; inputting the corrected surround view image into a threshold segmentation detection model for detection to obtain a lane line marking image output by the threshold segmentation detection model; and extending the pedal line detection line extracted from the surround view image to obtain the pedal line. Specifically, extending the detection line to obtain the pedal line includes: for each side of the detection line, extending the detection line to both ends to the center positions of the front wheel and the rear wheel on the same side, respectively, to obtain the pedal line.

[0081] The surround view image acquisition equipment mounted on the vehicle is calibrated and measured in advance to obtain the intrinsic and extrinsic parameter matrix and distortion matrix of the surround view image acquisition equipment. The intrinsic and extrinsic parameter matrix and distortion matrix together determine the calibration relationship between the pixel point and the actual spatial point.

[0082] Specifically, the calibration board is placed at different spatial positions within the image acquisition range of the panoramic image acquisition device. Multiple calibration board images are acquired using the Zhang Zhengyou calibration measurement method. The sequence of multiple calibration board images is then input into a general camera calibration model to calibrate the intrinsic and extrinsic parameters of the image acquisition device, thereby calculating the intrinsic and extrinsic parameter matrix and distortion matrix of the image acquisition device.

[0083] Based on the calibrated intrinsic and extrinsic parameter matrices and distortion matrix, distortion correction is performed on the acquired surround view image to ensure that the corrected image accurately reflects the real environment. Then, image detection is performed on the corrected surround view image to extract lane lines and pedal lines, extending these detection lines to the center positions of the front and rear wheels. In other words, the detection lines correspond to the actual pedals on the vehicle, and the pedal lines in the surround view image are extensions from the center positions of the front and rear wheels.

[0084] Based on the above embodiments, the step of calculating the vehicle's deviation distance relative to the lane centerline based on the distance between the lane line and the footboard line includes: obtaining the pixel distance between the footboard line and the lane line on the same side in the surround view image; calculating the product of the intrinsic and extrinsic parameters of the image acquisition device and the pixel distance to obtain the actual distance between the footboard line and the lane line on the same side; and calculating the deviation distance based on the difference between the actual distances corresponding to the footboard lines on both sides.

[0085] The step of obtaining the pixel distance between the pedal line and the lane line on the same side in the surround view image includes: when the lane line and the pedal line are not parallel, for each pedal line, obtaining the distance from the starting point of the pedal line to the starting point of the lane line on the same side, the distance from the midpoint of the pedal line to the midpoint of the lane line, and the distance from the ending point of the pedal line to the ending point of the lane line on the same side; calculating the average value of the starting point distance, the midpoint distance, and the ending point distance to obtain the pixel distance between the pedal line on one side and the lane line on the same side.

[0086] Optionally, the angle between the lane line and the pedal line in the image can be calculated to determine whether the lane line and the pedal line are parallel. When the lane line and the pedal line are parallel, it means that the vehicle's direction of travel is parallel to the lane direction. At this time, the distance between each point on one side of the pedal line and the same lane line is equal, and the distance between the pedal line on one side and the lane line on the same side can be directly obtained.

[0087] When the lane line and the pedal line are not parallel, it means that the distance between each point on the pedal line on one side and the lane line on the same side is not equal in the direction of vehicle travel and the direction of lane. In this case, it is not possible to directly obtain the distance between the pedal line on one side and the lane line on the same side. Therefore, it is necessary to take several points on the pedal line to calculate the distance between the pedal line on one side and the lane line on the same side.

[0088] Taking the left pedal line as an example, as described above, the left pedal line is between the center of the left front wheel and the center of the left rear wheel. The center of the left front wheel can be used as the start or end point of the left pedal line, and correspondingly, the center of the left rear wheel can be used as the end or start point of the left pedal line. This embodiment does not limit this; the example using the center of the left front wheel as the start point and the center of the left rear wheel as the midpoint is explained below. The distance from the center of the left front wheel to the left lane line is obtained as the start distance, the distance from the midpoint of the left pedal line to the left lane line is obtained as the midpoint distance, and the distance from the center of the left rear wheel to the left lane line is obtained as the end distance. The average of the start distance, midpoint distance, and end distance is further calculated as the pixel distance between the left lane line and the left pedal line. Similarly, the distance between the right lane line and the right pedal line is calculated in the same way. It should be noted that the calculations here are all pixel distances. The actual distance between the left lane line and the left foot pedal line, and the actual distance between the right lane line and the right foot pedal line can be obtained by multiplying the pixel distance with the intrinsic and extrinsic parameters of the image acquisition device. The vehicle's deviation distance is calculated by the difference between the actual distances between the left lane line and the left foot pedal line and the actual distances between the right lane line and the right foot pedal line.

[0089] This disclosure provides a method for calculating deviation distance. When the vehicle's direction of travel is not parallel to the lane, the distance between the vehicle and the lane lines on both sides is determined by calculating the average distance of the starting point, midpoint, and ending point of the foot track from the lane lines on the same side, effectively improving the accuracy of vehicle assisted keeping process.

[0090] Figure 3 This is a diagram illustrating the architecture of a vehicle control method according to another embodiment of this disclosure. Figure 3 As shown, the vehicle control method includes two parts: image calibration measurement and recognition, and spatial calculation and control. The image calibration measurement and recognition part can be divided into two parts: image calibration measurement and image recognition.

[0091] In the image calibration measurement, the vehicle's surround-view cameras (including at least the left and right cameras) are used to acquire images of the calibration board, obtaining a calibration board image sample set. This allows for the calibration of the surround-view cameras' intrinsic and extrinsic parameters, and the calculation of the intrinsic and extrinsic parameter matrices and distortion matrix. In the image recognition section, based on the calibrated matrices, distortion correction is applied to the surround-view images acquired by the cameras, resulting in corrected images. The corrected images are then cropped and input into a threshold segmentation detection model for lane line detection, obtaining lane line marking images on both sides of the vehicle. Simultaneously, the vehicle's footwell markings are detected, and the detection lines for these footwell markings are extracted and extended.

[0092] In the spatial calculation and control section, vehicle position calculation and correction are performed sequentially. Based on the image recognition results (lane lines and foot pedal lines in the surround view image), the distances between the lane lines and foot pedal lines on the left and right sides of the vehicle are calculated to obtain the vehicle's deviation distance. The specific calculation process is described in the above embodiment and will not be repeated here. After obtaining the vehicle deviation distance, the target steering wheel control value can be obtained based on the calculation relationship between the deviation distance, steering wheel angle, front wheel deviation angle, vehicle speed, and preset correction time. The vehicle is then controlled according to the target steering wheel control value. Furthermore, a new surround view image is acquired again through the surround view image acquisition device, and the above steps are repeated. This cyclical control method keeps the vehicle in a relatively central position within the lane.

[0093] This embodiment of the invention detects and obtains lane lines and foot lines from the surround view image acquired by the surround view image acquisition device. The image acquisition distance is relatively short, and it is less affected by environmental factors and the clarity of the lane lines. Furthermore, the vehicle's deviation distance is calculated based on the distance between the lane lines and foot lines in the surround view image. This effectively avoids lane line misidentification caused by poor image acquisition, reduces the impact of factors such as severe weather or light pollution, improves the accuracy of vehicle control during lane keeping, and ensures the effectiveness and safety of the function during driving.

[0094] In addition, the vehicle control method provided in this disclosure can also be combined with existing forward-facing lane keeping functions to improve environmental interference resistance and lane recognition accuracy.

[0095] Figure 4This is a schematic diagram of the structure of a vehicle control device provided in an embodiment of this disclosure. The vehicle control device can be an in-vehicle device as described in the above embodiments, or it can be a component or assembly within the in-vehicle device. The vehicle control device provided in this disclosure can execute the processing flow provided in the vehicle control method embodiments, such as... Figure 4 As shown, the vehicle control device 40 includes: a data acquisition module 41, an acquisition module 42, a first calculation module 43, a second calculation module 44, and a control module 45. The data acquisition module 41 is used to acquire surround-view images of the vehicle's surroundings using an onboard surround-view image acquisition device during vehicle operation. The acquisition module 42 is used to perform image analysis on the surround-view images to acquire lane lines and foot lines within the images. The first calculation module 43 is used to calculate the vehicle's deviation distance relative to the lane centerline based on the distance between the lane lines and foot lines. The second calculation module 44 is used to calculate the target steering wheel control amount required to correct the deviation distance based on the deviation distance, vehicle speed, and current steering wheel angle. The control module 45 is used to control the vehicle based on the target steering wheel control amount.

[0096] Optionally, the acquisition module 42 includes a correction unit 421, a detection module 422, and an extension unit 423; the correction unit 421 is used to correct the surround view image according to the intrinsic and extrinsic parameter matrix and distortion matrix of the image acquisition device to obtain a corrected surround view image; the detection module 422 is used to input the corrected surround view image into a threshold segmentation detection model for detection to obtain a lane marking image output by the threshold segmentation detection model; the extension unit 423 is used to extend the detection line extracted from the surround view image to obtain the pedal line.

[0097] Optionally, the extension unit 423 is used to extend the detection line on each side to the center positions of the front wheel and the rear wheel on the same side, respectively, to obtain the pedal line.

[0098] Optionally, the first calculation module 43 includes a first acquisition unit 431, a first calculation unit 432, and a second calculation unit 433; the first acquisition unit 431 is used to acquire the pixel distance between the foot track line and the lane line on the same side in the surround view image; the first calculation unit 432 is used to calculate the product of the intrinsic and extrinsic parameters of the image acquisition device and the pixel distance to obtain the actual distance between the foot track line and the lane line on the same side; the second calculation unit 433 is used to calculate the deviation distance based on the difference between the actual distances corresponding to the foot track lines on both sides.

[0099] Optionally, the first acquisition unit 431 is used to acquire, for each side of the pedal line, the distance from the starting point of the pedal line to the starting point of the same-side lane line, the distance from the midpoint of the pedal line to the midpoint of the lane line, and the distance from the ending point of the pedal line to the ending point of the same-side lane line when the lane line is not parallel to the pedal line; calculate the average value of the starting point distance, the midpoint distance and the ending point distance to obtain the pixel distance between the pedal line on one side and the lane line on the same side.

[0100] Optionally, the second calculation module 44 is specifically used to divide the deviation distance by the product of the preset correction time and the vehicle speed to obtain the target correction deviation angle; to look up the target steering wheel angle according to the preset calibration table and the target correction deviation angle, wherein the preset calibration table includes the mapping relationship between the steering wheel angle and the vehicle deviation angle; and to calculate the difference between the target steering wheel angle and the current steering wheel angle to obtain the target steering wheel control amount.

[0101] Figure 4 The vehicle control device shown in the embodiment can be used to execute the technical solution of the above method embodiment. Its implementation principle and technical effect are similar, and will not be repeated here.

[0102] Furthermore, this disclosure also provides a vehicle that includes the vehicle control device described in the above embodiments.

[0103] Figure 5 This is a schematic diagram of the structure of an electronic device provided in an embodiment of this disclosure. The electronic device can be a vehicle-mounted device as described in the above embodiments. The electronic device provided in this disclosure can execute the processing flow provided in the vehicle control method embodiments, such as… Figure 5 As shown, the electronic device 50 includes: a memory 51, a processor 52, a computer program, and a communication interface 53; wherein the computer program is stored in the memory 51 and configured to be executed by the processor 52 as described above in the vehicle control method.

[0104] In addition, this disclosure also provides a computer-readable storage medium having a computer program stored thereon, the computer program being executed by a processor to implement the vehicle control method described in the above embodiments.

[0105] Furthermore, this disclosure also provides a computer program product, which includes a computer program or instructions that, when executed by a processor, implement the vehicle control method described above.

[0106] Computer program code for performing the operations of this disclosure can be written in one or more programming languages ​​or a combination thereof, including but not limited to object-oriented programming languages ​​such as Java, Smalltalk, and C++, as well as conventional procedural programming languages ​​such as the "C" language or similar programming languages. The program code can be executed entirely on the user's computer, partially on the user's computer, as a standalone software package, partially on the user's computer and partially on a remote computer, or entirely on a remote computer or server. In cases involving remote computers, the remote computer can be connected to the user's computer via any type of network—including a local area network (LAN) or a wide area network (WAN)—or can be connected to an external computer (e.g., via the Internet using an Internet service provider).

[0107] The flowcharts and block diagrams in the accompanying drawings illustrate the architecture, functionality, and operation of possible implementations of systems, methods, and computer program products according to various embodiments of this disclosure. In this regard, each block in a flowchart or block diagram may represent a module, segment, or portion of code containing one or more executable instructions for implementing a specified logical function. It should also be noted that in some alternative implementations, the functions indicated in the blocks may occur in a different order than those indicated in the drawings. For example, two consecutively indicated blocks may actually be executed substantially in parallel, and they may sometimes be executed in reverse order, depending on the functions involved. It should also be noted that each block in the block diagrams and / or flowcharts, and combinations of blocks in the block diagrams and / or flowcharts, can be implemented using a dedicated hardware-based system that performs the specified function or operation, or using a combination of dedicated hardware and computer instructions.

[0108] It should be noted that, in this document, relational terms such as "first" and "second" are used merely to distinguish one entity or operation from another, and do not necessarily require or imply any such actual relationship or order between these entities or operations. Furthermore, the terms "comprising," "including," or any other variations thereof are intended to cover non-exclusive inclusion, such that a process, method, article, or apparatus that comprises a list of elements includes not only those elements but also other elements not expressly listed, or elements inherent to such a process, method, article, or apparatus. Without further limitations, an element defined by the phrase "comprising one..." does not exclude the presence of other identical elements in the process, method, article, or apparatus that includes said element.

[0109] The above description is merely a specific embodiment of this disclosure, enabling those skilled in the art to understand or implement it. 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 this disclosure. Therefore, this disclosure is not to be limited to the embodiments described herein, but is to be accorded the widest scope consistent with the principles and novel features disclosed herein.

Claims

1. A vehicle control method, characterized in that, The method includes: During vehicle operation, surround view images of the vehicle's surroundings are captured using onboard surround view image acquisition equipment. Image analysis is performed on the surround view image to obtain the lane lines and foot lines in the surround view image; The vehicle's deviation distance relative to the lane centerline is calculated based on the distance between the lane line and the foot line. The target steering wheel control amount required to correct the deviation distance is calculated based on the deviation distance, vehicle speed, and current steering wheel angle. The vehicle is controlled according to the target steering wheel control amount.

2. The method according to claim 1, characterized in that, The step of performing image analysis on the surround view image to obtain lane lines and footpath lines in the surround view image includes: The toroidal image is corrected based on the intrinsic and extrinsic parameter matrices and distortion matrix of the image acquisition device to obtain the corrected toroidal image. The corrected surround view image is input into the threshold segmentation detection model for detection to obtain the lane line marking image output by the threshold segmentation detection model; The foot track detection line extracted from the panoramic image is extended to obtain the foot track.

3. The method according to claim 2, characterized in that, The process of extending the detection line to obtain the foot pedal line includes: For each side of the detection line, extend the detection line to both ends to the center position of the front wheel and the center position of the rear wheel on the same side, respectively, to obtain the pedal line.

4. The method according to claim 1, characterized in that, The calculation of the vehicle's deviation distance relative to the lane centerline based on the distance between the lane line and the footboard line includes: Obtain the pixel distance between the foot track line and the lane line on the same side in the surround view image; The actual distance between the foot track and the lane line on the same side is obtained by multiplying the intrinsic and extrinsic parameters of the image acquisition device with the pixel distance. The deviation distance is calculated based on the difference in the actual distances corresponding to the footboard lines on both sides.

5. The method according to claim 3, characterized in that, The step of obtaining the pixel distance between the foot track line and the lane line on the same side in the surround view image includes: When the lane line is not parallel to the pedal line, for each pedal line, the distance from the starting point of the pedal line to the starting point of the lane line on the same side, the distance from the midpoint of the pedal line to the midpoint of the lane line, and the distance from the ending point of the pedal line to the ending point of the lane line on the same side are obtained respectively. Calculate the average of the starting point distance, the midpoint distance, and the ending point distance to obtain the pixel distance between the foot track on one side and the lane line on the same side.

6. The method according to claim 1, characterized in that, The step of calculating the target steering control amount required to correct the deviation distance based on the deviation distance, vehicle speed, and current steering wheel angle includes: The target correction deviation angle is obtained by dividing the deviation distance by the product of the preset correction time and the vehicle speed; The target steering wheel angle is obtained by looking up the table according to the preset calibration table and the target correction deviation angle. The preset calibration table includes the mapping relationship between the steering wheel angle and the vehicle deviation angle. The target steering wheel control amount is obtained by calculating the difference between the target steering wheel angle and the current steering wheel angle.

7. A vehicle control device, characterized in that, The device includes: The acquisition module is used to acquire surround view images of the vehicle's surroundings using an onboard surround view image acquisition device while the vehicle is in motion. The acquisition module is used to perform image analysis on the surround view image to acquire lane lines and foot lines in the surround view image; The first calculation module is used to calculate the vehicle's deviation distance relative to the lane centerline based on the distance between the lane line and the foot line; The second calculation module is used to calculate the target steering wheel control amount required to correct the deviation distance based on the deviation distance, vehicle speed and current steering wheel angle. The control module is used to control the vehicle according to the target steering wheel control amount.

8. An electronic device, characterized in that, include: Memory; processor; as well as computer programs; The computer program is stored in the memory and configured to be executed by the processor to implement the method as described in any one of claims 1-6.

9. A computer-readable storage medium having a computer program stored thereon, characterized in that, When the computer program is executed by a processor, it implements the method as described in any one of claims 1-6.

10. A vehicle comprising: The vehicle control device as described in claim 7; Or the electronic device as described in claim 8; Alternatively, the computer-readable storage medium as described in claim 9.

Images