Lane line optimal fusion method and device, vehicle and storage medium

Abstract

The invention particularly relates to a lane line optimal fusion method and device, a vehicle and a storage medium, and the method comprises the steps: carrying out the detection of a lane line of a road in front of the vehicle based on a current frame image, obtaining a first lane line length, and obtaining a curve fitting equation and a fitting error of the lane line, if the first lane line length does not reach the set target lane line length, estimating a second lane line length which is not detected in the lane line of the road in front of the vehicle based on a curve fitting equation to obtain a first curve segment corresponding to the second lane line length and an estimation error, and then measuring the length of a second lane line according to the geometric information of the lane line to obtain a second curve segment and a measurement error corresponding to the length of the second lane line, and further obtaining an optimal fusion lane line of the vehicle according to the first curve segment, the second curve segment and the error values. Therefore, the problems that lane line detection is incomplete, and the change rule of a front lane line cannot be predicted in advance due to obstacle shielding and the like are solved.

Description

Technical Field

[0001] The present application relates to the field of vehicle technology, and in particular to an optimal fusion method, device, vehicle and storage medium for lane lines. Background Art

[0002] The lane keeping system plays a vital role in the driving process of self-driving cars. It needs to continuously perceive the lane line to determine the curvature of the road ahead and the deviation of the vehicle within the lane line, so as to control the steering angle to keep the self-driving car in the center of the lane line.

[0003] In related technologies, the perception of lane lines mainly relies on the image information provided by the forward-looking camera, and uses machine learning or deep learning algorithms to identify the lane lines on the image and convert pixel coordinates into spatial coordinates, thereby calculating the curvature of the lane lines and the offset distance of the autonomous driving vehicle relative to the center line of the lane.

[0004] However, in the above lane line perception method, there may be lane line obstruction due to the vehicle in front or other obstacles, resulting in detection failure, and there is a lack of super-field prediction ability for lane line changes in front, as well as lane line recognition accuracy, which urgently needs to be solved. Summary of the invention

[0005] The present application provides an optimal lane line fusion method, device, vehicle and storage medium to solve the problems of incomplete lane line detection due to lane line obstruction, poor light conditions, etc. and the inability to predict the changing pattern of the lane line ahead in advance by relying on visual perception.

[0006] The first aspect of the present application provides an optimal lane line fusion method, comprising the following steps:

[0007] Determine the target lane line length of the road ahead of the vehicle;

[0008] Acquire a current frame image of the road ahead of the vehicle, detect the lane line of the road ahead of the vehicle based on the current frame image using a preset detection algorithm, obtain a first lane line length of the road ahead of the vehicle, and obtain a curve fitting equation of the lane line and a fitting error corresponding to the curve fitting equation based on the first lane line length;

[0009] determining whether the length of the first lane line reaches the target lane line length; if the length of the first lane line does not reach the target lane line length, estimating the length of a second lane line that is not detected in the lane line of the road ahead of the vehicle based on the curve fitting equation, and obtaining a first curve segment corresponding to the second lane line length and an estimation error corresponding to the first curve segment;

[0010] Acquire lane line geometry information of the road ahead of the vehicle, measure the length of a second lane line that is not detected in the lane line of the road ahead of the vehicle according to the lane line geometry information, obtain a second curve segment corresponding to the second lane line length and a measurement error corresponding to the second curve segment, and obtain an optimal fused lane line for the vehicle based on the fitting error, the first curve segment, the estimation error, the second curve segment and the measurement error.

[0011] According to one embodiment of the present application, determining the target lane line length of the road ahead of the vehicle includes:

[0012] Obtaining the current speed of the vehicle;

[0013] A corresponding target coefficient is matched based on the current vehicle speed, and a target lane line length of the road ahead of the vehicle is determined according to the product of the current vehicle speed and the target coefficient.

[0014] According to an embodiment of the present application, measuring the length of a second lane line that is not detected in the lane line of the road ahead of the vehicle according to the lane line geometry information to obtain a second curve segment corresponding to the second lane line length includes:

[0015] Acquiring road curvature information of the road ahead of the vehicle;

[0016] The length of the second lane line is measured using the road curvature information to obtain a second curve segment corresponding to the length of the second lane line.

[0017] According to one embodiment of the present application, obtaining the optimal fused lane line of the vehicle based on the fitting error, the first curve segment, the estimation error, the second curve segment and the measurement error includes:

[0018] Calculate a lane line gain coefficient of the road ahead of the vehicle based on the fitting error, the estimation error and the measurement error;

[0019] The lane line gain coefficients are weighted by using a preset weighting method to obtain a first gain coefficient corresponding to the first curve segment and a second gain coefficient corresponding to the second curve segment;

[0020] The optimal fused lane line of the vehicle is obtained by summing the product of the first curve segment and the first gain coefficient and the product of the second curve segment and the second gain coefficient.

[0021] According to one embodiment of the present application, after obtaining the optimal fused lane line of the vehicle based on the fitting error, the first curve segment, the estimation error, the second curve segment and the measurement error, the method further includes:

[0022] Calculating the fusion error of the optimal fusion lane line;

[0023] Determining whether the fusion error is greater than or equal to a preset error threshold;

[0024] If the fusion error is less than the preset error threshold, the preset display interface is controlled to display the optimal fusion lane line; otherwise, the preset display interface is controlled not to display the optimal fusion lane line.

[0025] According to the optimal fusion method of lane lines in the embodiment of the present application, the lane lines of the road ahead of the vehicle are detected based on the current frame image to obtain the length of the first lane line, and then the curve fitting equation and fitting error of the lane line are obtained. If the length of the first lane line does not reach the set target lane line length, the length of the second lane line that is not detected in the lane line of the road ahead of the vehicle is estimated based on the curve fitting equation to obtain the first curve segment and the estimation error corresponding to the length of the second lane line, and then the length of the second lane line is measured according to the geometric information of the lane line to obtain the second curve segment and the measurement error corresponding to the length of the second lane line, and then the optimal fusion lane line of the vehicle is obtained according to the first curve segment, the second curve segment and the above-mentioned error values. Thus, the problems of incomplete lane line detection caused by obstacles and the inability to predict the change law of the lane line ahead in advance are solved. By sensing the current frame image, the lane line curve equation is fitted, and the lane line extension line is detected for estimation. At the same time, the estimation results are fused and calculated in combination with the geometric information of the navigation map to obtain the optimal estimation of the lane line, thereby improving the accuracy and robustness of lane line detection.

[0026] A second aspect of the present application provides an optimal fusion device for lane lines, including:

[0027] A determination module, used to determine a target lane line length of a road ahead of the vehicle;

[0028] a first acquisition module, configured to acquire a current frame image of the road ahead of the vehicle, detect the lane line of the road ahead of the vehicle based on the current frame image using a preset detection algorithm, obtain a first lane line length of the road ahead of the vehicle, and obtain a curve fitting equation of the lane line and a fitting error corresponding to the curve fitting equation based on the first lane line length;

[0029] a judgment module, configured to judge whether the length of the first lane line reaches the target lane line length; if the length of the first lane line does not reach the target lane line length, estimating the length of a second lane line that is not detected in the lane line of the road ahead of the vehicle based on the curve fitting equation, and obtaining a first curve segment corresponding to the second lane line length and an estimation error corresponding to the first curve segment;

[0030] A second acquisition module is used to obtain lane line geometry information of the road ahead of the vehicle, measure the length of a second lane line that is not detected in the lane line of the road ahead of the vehicle according to the lane line geometry information, obtain a second curve segment corresponding to the second lane line length and a measurement error corresponding to the second curve segment, and obtain an optimal fused lane line of the vehicle based on the fitting error, the first curve segment, the estimation error, the second curve segment and the measurement error.

[0031] According to an embodiment of the present application, the determining module is specifically used to:

[0032] Obtaining the current speed of the vehicle;

[0033] A corresponding target coefficient is matched based on the current vehicle speed, and a target lane line length of the road ahead of the vehicle is determined according to the product of the current vehicle speed and the target coefficient.

[0034] According to an embodiment of the present application, the second acquisition module is specifically used to:

[0035] Acquiring road curvature information of the road ahead of the vehicle;

[0036] The length of the second lane line is measured using the road curvature information to obtain a second curve segment corresponding to the length of the second lane line.

[0037] According to an embodiment of the present application, the second acquisition module is specifically used to:

[0038] Calculate a lane line gain coefficient of the road ahead of the vehicle based on the fitting error, the estimation error and the measurement error;

[0039] The lane line gain coefficients are weighted by using a preset weighting method to obtain a first gain coefficient corresponding to the first curve segment and a second gain coefficient corresponding to the second curve segment;

[0040] The optimal fused lane line of the vehicle is obtained by summing the product of the first curve segment and the first gain coefficient and the product of the second curve segment and the second gain coefficient.

[0041] According to an embodiment of the present application, after obtaining the optimal fused lane line of the vehicle based on the fitting error, the first curve segment, the estimation error, the second curve segment and the measurement error, the second acquisition module is further used to:

[0042] Calculating the fusion error of the optimal fusion lane line;

[0043] Determining whether the fusion error is greater than or equal to a preset error threshold;

[0044] If the fusion error is less than the preset error threshold, the preset display interface is controlled to display the optimal fusion lane line; otherwise, the preset display interface is controlled not to display the optimal fusion lane line.

[0045] According to the optimal fusion device of the lane line of the embodiment of the present application, the lane line of the road ahead of the vehicle is detected based on the current frame image to obtain the length of the first lane line, and then the curve fitting equation and fitting error of the lane line are obtained. If the length of the first lane line does not reach the set target lane line length, the length of the second lane line that is not detected in the lane line of the road ahead of the vehicle is estimated based on the curve fitting equation to obtain the first curve segment and the estimation error corresponding to the length of the second lane line, and then the length of the second lane line is measured according to the geometric information of the lane line to obtain the second curve segment and the measurement error corresponding to the length of the second lane line, and then the optimal fusion lane line of the vehicle is obtained according to the first curve segment, the second curve segment and the above-mentioned error values. Thus, the problems of incomplete lane line detection caused by obstacles and the inability to predict the change law of the lane line ahead in advance are solved. By sensing the current frame image, the lane line curve equation is fitted, and the lane line extension line is detected for estimation. At the same time, the estimation results are fused and calculated in combination with the geometric information of the navigation map to obtain the optimal estimation of the lane line, thereby improving the accuracy and robustness of lane line detection.

[0046] A third aspect of the present application provides a vehicle, comprising: a memory, a processor, and a computer program stored in the memory and executable on the processor, wherein the processor executes the program to implement the optimal lane line fusion method as described in the above embodiment.

[0047] A fourth aspect of the present application provides a computer-readable storage medium, wherein the computer-readable storage medium stores computer instructions, and the computer instructions are used to enable the computer to execute the optimal lane line fusion method as described in the above embodiment.

[0048] The fifth aspect of the present application provides a computer program product, including a computer program, which is executed to implement the optimal lane line fusion method described in the above embodiment.

[0049] Additional aspects and advantages of the present application will be given in part in the description below, and in part will become apparent from the description below, or will be learned through the practice of the present application. BRIEF DESCRIPTION OF THE DRAWINGS

[0050] The above and / or additional aspects and advantages of the present application will become apparent and easily understood from the following description of the embodiments in conjunction with the accompanying drawings, in which:

[0051] Figure 1 A flowchart of an optimal lane line fusion method provided according to an embodiment of the present application;

[0052] Figure 2 A schematic diagram of the optimal estimation of lane lines and their errors according to one embodiment of the present application;

[0053] Figure 3 is a block diagram of an optimal fusion device for lane lines according to an embodiment of the present application;

[0054] Figure 4 It is a schematic diagram of the structure of a vehicle according to an embodiment of the present application. DETAILED DESCRIPTION

[0055] The embodiments of the present application are described in detail below, and examples of the embodiments are shown in the accompanying drawings, wherein the same or similar reference numerals throughout represent the same or similar elements or elements having the same or similar functions. The embodiments described below with reference to the accompanying drawings are exemplary and are intended to be used to explain the present application, and should not be construed as limiting the present application.

[0056] The following describes the optimal fusion method, device, vehicle and storage medium of the lane line of the embodiment of the present application with reference to the accompanying drawings. In view of the problem mentioned in the above background technology that the lane line detection is incomplete due to reasons such as lane line occlusion and poor light conditions, and the change law of the lane line ahead cannot be predicted in advance by relying on visual perception, the present application provides an optimal fusion method for lane lines, in which the lane line of the road ahead of the vehicle is detected based on the current frame image to obtain the length of the first lane line, and then the curve fitting equation and fitting error of the lane line are obtained. If the length of the first lane line does not reach the set target lane line length, the length of the second lane line that is not detected in the lane line of the road ahead of the vehicle is estimated based on the curve fitting equation to obtain the first curve segment and estimation error corresponding to the length of the second lane line, and then the length of the second lane line is measured according to the geometric information of the lane line to obtain the second curve segment and measurement error corresponding to the length of the second lane line, and then the optimal fusion lane line of the vehicle is obtained according to the first curve segment, the second curve segment and the above error values. As a result, the problems of incomplete lane line detection due to obstacle obstruction and the inability to predict the changing pattern of the lane line ahead in advance are solved. By perceiving the current frame image, the lane line curve equation is fitted, and the lane line extension line is detected for estimation. At the same time, the estimation results are fused and calculated in combination with the geometric information of the navigation map to obtain the optimal estimate of the lane line, thereby improving the accuracy and robustness of lane line detection.

[0057] Specifically, Figure 1 A flowchart of an optimal lane line fusion method provided in an embodiment of the present application.

[0058] like Figure 1 As shown, the optimal fusion method of the lane line includes the following steps:

[0059] In step S101 , a target lane line length of the road ahead of the vehicle is determined.

[0060] According to one embodiment of the present application, determining a target lane line length of the road ahead of a vehicle includes: obtaining the current driving speed of the vehicle; matching a corresponding target coefficient based on the current driving speed, and determining the target lane line length of the road ahead of the vehicle based on the product of the current driving speed and the target coefficient.

[0061] Specifically, during daily driving, when a user wants to detect the road ahead of the vehicle, the detection accuracy may decrease due to various reasons such as line of sight obstruction, poor lighting conditions, and single-frame detection limitations. For example, the vehicle ahead or other obstacles block the lane lines, and the image quality obtained by the camera decreases at night or in severe weather conditions, affecting the recognition accuracy of the lane lines. Lane line detection is performed based on a single-frame image, and there is a lack of super-field prediction capabilities for changes in the lane lines ahead. Therefore, to solve the above-mentioned problems, an embodiment of the present application is based on a lane line fusion perception algorithm, which combines visual images and lane line geometry information provided by a navigation map to improve the accuracy and robustness of lane line detection, and solves the problem of inaccurate results of the vision-based lane line perception algorithm caused by lane lines being blocked by vehicles, poor lighting conditions, etc.

[0062] Specifically, first, the current speed of the vehicle is obtained; second, the corresponding target coefficient is matched based on the current speed v obtained. The target lane line length S of the road ahead of the vehicle to be detected can be determined according to the product of the current driving speed and the target coefficient, that is, the expression can be expressed as

[0063] It should be noted that the detection method adopted in the embodiment of the present application sets a target lane line of a certain length that needs to be detected, and the value range of the target lane line length is (0≤S≤200m).

[0064] In step S102, a current frame image of the road in front of the vehicle is obtained, and the lane line of the road in front of the vehicle is detected based on the current frame image using a preset detection algorithm to obtain a first lane line length of the road in front of the vehicle, and based on the first lane line length, a curve fitting equation of the lane line and a fitting error corresponding to the curve fitting equation are obtained.

[0065] Among them, the preset detection algorithm can be selected by technical personnel in this field according to the requirements of the detection method, and is not specifically limited here.

[0066] Specifically, Figure 2As shown, after determining the target lane line length to be detected, the embodiment of the present application further obtains the current frame image of the road in front of the vehicle, and uses a preset detection algorithm, such as segmentation or classification, to detect the lane line of the road in front of the vehicle based on the current frame image, and detects the first lane line length of the road in front of the vehicle, that is, the lane line length of the road in front of the vehicle that can be detected according to the current frame image using the preset detection algorithm, and obtains the curve fitting equation of the lane line and the fitting error corresponding to the curve fitting equation based on the first lane line length, wherein the curve fitting equation can be based on polynomial fitting, or based on other curve fitting methods. In the embodiment of the present application, the curve fitting equation is assumed to be The fitting error is The fitting error is obtained through statistical data after multiple measurements on sample data using a preset detection algorithm.

[0067] In step S103, it is determined whether the length of the first lane line reaches the target lane line length. If the length of the first lane line does not reach the target lane line length, the length of the second lane line that is not detected in the lane line of the road ahead of the vehicle is estimated based on the curve fitting equation to obtain the first curve segment corresponding to the second lane line length and the estimation error corresponding to the first curve segment.

[0068] Specifically, Figure 2 As shown in FIG. 1 , during the detection process, due to reasons such as line of sight obstruction and illumination, the accuracy of lane line length detection will be affected. Therefore, it is also necessary to determine the length of the first lane line detected, that is, to determine whether the length of the first lane line reaches the set target lane line length. If the length of the first lane line does not reach the target lane line length, the undetected portion of the lane line of the road ahead of the vehicle, that is, the length of the second lane line is estimated using a curve fitting equation, and the first curve segment corresponding to the second lane line length and the estimation error corresponding to the first curve segment are estimated, where the estimated first curve segment can be expressed as x′ k ={s t+1 ,s t+2 ,s t+3 , ..., s t+n}, the corresponding estimation error is recorded as The estimated error is calculated from t and n, which are statistical parameters obtained from multiple measurements. Among them, A and B are coefficients, and the estimated error is obtained through statistical data after multiple measurements on sample data using a preset detection algorithm.

[0069] In step S104, the lane line geometry information of the road ahead of the vehicle is obtained, and the length of the second lane line that is not detected in the lane line of the road ahead of the vehicle is measured according to the lane line geometry information to obtain the second curve segment corresponding to the second lane line length and the measurement error corresponding to the second curve segment, and the optimal fused lane line of the vehicle is obtained based on the fitting error, the first curve segment, the estimation error, the second curve segment and the measurement error.

[0070] According to one embodiment of the present application, the length of a second lane line that is not detected in the lane line of the road ahead of the vehicle is measured based on lane line geometry information to obtain a second curve segment corresponding to the second lane line length, including: obtaining road curvature information of the road ahead of the vehicle; and measuring the length of the second lane line using the road curvature information to obtain a second curve segment corresponding to the second lane line length.

[0071] According to one embodiment of the present application, the optimal fused lane line of the vehicle is obtained based on the fitting error, the first curve segment, the estimation error, the second curve segment and the measurement error, including: calculating the lane line gain coefficient of the road ahead of the vehicle based on the fitting error, the estimation error and the measurement error; weighting the lane line gain coefficient using a preset weight allocation method to obtain a first gain coefficient corresponding to the first curve segment and a second gain coefficient corresponding to the second curve segment; and obtaining the optimal fused lane line of the vehicle by adding the product of the first curve segment and the first gain coefficient and the product of the second curve segment and the second gain coefficient.

[0072] Among them, the preset weight allocation method can be set by technical personnel in this field according to actual detection requirements and is not specifically limited here.

[0073] Specifically, Figure 2 As shown, in order to improve the detection accuracy of lane lines, the embodiment of the present application combines lane line geometry information with visual images for joint detection. First, the lane line geometry information of the road ahead of the vehicle provided by the navigation map information is obtained; secondly, the length of the second lane line that is not detected in the lane line of the road ahead of the vehicle is measured and supplemented according to the lane line geometry information, that is, according to the curvature information of the road ahead displayed on the navigation map, the length of the undetected second lane line is measured using the road curvature information to obtain the second curve segment corresponding to the length of the second lane line and the measurement error corresponding to the second curve segment, wherein the second curve segment is recorded as The error is recorded as The measurement error is obtained from the statistical data during the navigation map mapping process; secondly, the lane line gain coefficient of the road ahead of the vehicle is calculated based on the fitting error, estimation error and measurement error. The lane line gain coefficient is weighted by using a preset weight distribution method to obtain a first gain coefficient (e.g. K k) and the second gain coefficient corresponding to the second curve segment (e.g. 1-K k ), the optimal fusion lane line of the vehicle is obtained by summing the product of the first curve segment and the first gain coefficient and the product of the second curve segment and the second gain coefficient, that is, the optimal estimation of the vehicle lane line, which can be expressed as in, and Error

[0074] According to one embodiment of the present application, after obtaining the optimal fusion lane line of the vehicle based on the fitting error, the first curve segment, the estimation error, the second curve segment and the measurement error, it also includes: calculating the fusion error of the optimal fusion lane line; judging whether the fusion error is greater than or equal to a preset error threshold; if the fusion error is less than the preset error threshold, controlling the preset display interface to display the optimal fusion lane line, otherwise, controlling the preset display interface not to display the optimal fusion lane line.

[0075] Among them, the preset error threshold can be set by technical personnel in this field according to actual detection requirements and is not specifically limited here.

[0076] Specifically, after obtaining the optimal fusion lane line of the vehicle, the embodiment of the present application needs to further calculate the fusion error of the optimal fusion lane line. And determine whether the fusion error is greater than or equal to the preset error threshold. If the fusion error is less than the preset error threshold, it means that the calculated fusion-perceived lane line, that is, the optimal fusion lane line does not exist or has a small error. At this time, the preset display interface, such as the human-computer interaction interface, is controlled to display the optimal fusion lane line; if the fusion error is greater than or equal to the preset error threshold, it means that the calculated fusion-perceived lane line has a large error. At this time, the preset display interface is controlled not to display the optimal fusion lane line, and a more cautious strategy is adopted in the lane centering control algorithm, such as reducing the vehicle speed, reducing the distance to the lane centerline preview point, etc.

[0077] Therefore, based on the above specific discussion, the embodiment of the present application combines the lane line geometry information provided by the visual image and the navigation map, uses the lane line fusion perception algorithm to set the target lane line length that needs to be detected, and then uses the current frame image to detect the lane line and fit the curve, and then estimates the undetected part of the lane line and supplements it with the navigation map information. Finally, the visual detection results and the navigation map information are fused through the gain coefficient to obtain the optimal estimate of the lane line, and it is displayed when the fusion error is less than the preset error threshold, thereby effectively improving the safety and reliability of the autonomous driving vehicle.

[0078] According to the optimal fusion method of lane lines in the embodiment of the present application, the lane lines of the road ahead of the vehicle are detected based on the current frame image to obtain the length of the first lane line, and then the curve fitting equation and fitting error of the lane line are obtained. If the length of the first lane line does not reach the set target lane line length, the length of the second lane line that is not detected in the lane line of the road ahead of the vehicle is estimated based on the curve fitting equation to obtain the first curve segment and the estimation error corresponding to the length of the second lane line, and then the length of the second lane line is measured according to the geometric information of the lane line to obtain the second curve segment and the measurement error corresponding to the length of the second lane line, and then the optimal fusion lane line of the vehicle is obtained according to the first curve segment, the second curve segment and the above-mentioned error values. Thus, the problems of incomplete lane line detection caused by obstacles and the inability to predict the change law of the lane line ahead in advance are solved. By sensing the current frame image, the lane line curve equation is fitted, and the lane line extension line is detected for estimation. At the same time, the estimation results are fused and calculated in combination with the geometric information of the navigation map to obtain the optimal estimation of the lane line, thereby improving the accuracy and robustness of lane line detection.

[0079] Next, the optimal fusion device for lane lines proposed in accordance with an embodiment of the present application will be described with reference to the accompanying drawings.

[0080] Figure 3 It is a block diagram of an optimal fusion device for lane lines in an embodiment of the present application.

[0081] like Figure 3 As shown, the optimal fusion device 10 for lane lines includes: a determination module 100, a first acquisition module 200, a judgment module 300 and a second acquisition module 400.

[0082] Wherein, the determination module 100 is used to determine the target lane line length of the road ahead of the vehicle;

[0083] The first acquisition module 200 is used to acquire a current frame image of the road in front of the vehicle, detect the lane line of the road in front of the vehicle based on the current frame image using a preset detection algorithm, obtain the length of the first lane line of the road in front of the vehicle, and obtain a curve fitting equation of the lane line and a fitting error corresponding to the curve fitting equation based on the first lane line length;

[0084] A judgment module 300 is used to judge whether the length of the first lane line reaches the target lane line length. If the length of the first lane line does not reach the target lane line length, the length of the second lane line that is not detected in the lane line of the road ahead of the vehicle is estimated based on the curve fitting equation to obtain a first curve segment corresponding to the second lane line length and an estimation error corresponding to the first curve segment;

[0085] The second acquisition module 400 is used to obtain lane line geometry information of the road ahead of the vehicle, measure the length of a second lane line that is not detected in the lane line of the road ahead of the vehicle according to the lane line geometry information, obtain a second curve segment corresponding to the second lane line length and a measurement error corresponding to the second curve segment, and obtain the optimal fused lane line of the vehicle based on the fitting error, the first curve segment, the estimation error, the second curve segment and the measurement error.

[0086] According to an embodiment of the present application, the determination module 100 is specifically configured to:

[0087] Get the current speed of the vehicle;

[0088] The corresponding target coefficient is matched based on the current driving speed, and the target lane line length of the road ahead of the vehicle is determined according to the product of the current driving speed and the target coefficient.

[0089] According to an embodiment of the present application, the second acquisition module 400 is specifically configured to:

[0090] Obtaining road curvature information of the road ahead of the vehicle;

[0091] The length of the second lane line is measured using the road curvature information to obtain a second curve segment corresponding to the length of the second lane line.

[0092] According to an embodiment of the present application, the second acquisition module 400 is specifically configured to:

[0093] Calculate a lane line gain coefficient of the road ahead of the vehicle based on the fitting error, the estimation error, and the measurement error;

[0094] The lane line gain coefficients are weighted by using a preset weight distribution method to obtain a first gain coefficient corresponding to the first curve segment and a second gain coefficient corresponding to the second curve segment;

[0095] The optimal fused lane line of the vehicle is obtained by summing the product of the first curve segment and the first gain coefficient and the product of the second curve segment and the second gain coefficient.

[0096] According to one embodiment of the present application, after obtaining the optimal fused lane line of the vehicle based on the fitting error, the first curve segment, the estimation error, the second curve segment and the measurement error, the second acquisition module 400 is further used to:

[0097] Calculate the fusion error of the optimal fusion lane line;

[0098] Determine whether the fusion error is greater than or equal to a preset error threshold;

[0099] If the fusion error is less than the preset error threshold, the preset display interface is controlled to display the optimal fusion lane line; otherwise, the preset display interface is controlled not to display the optimal fusion lane line.

[0100] According to the optimal fusion device of the lane line of the embodiment of the present application, the lane line of the road ahead of the vehicle is detected based on the current frame image to obtain the length of the first lane line, and then the curve fitting equation and fitting error of the lane line are obtained. If the length of the first lane line does not reach the set target lane line length, the length of the second lane line that is not detected in the lane line of the road ahead of the vehicle is estimated based on the curve fitting equation to obtain the first curve segment and the estimation error corresponding to the length of the second lane line, and then the length of the second lane line is measured according to the geometric information of the lane line to obtain the second curve segment and the measurement error corresponding to the length of the second lane line, and then the optimal fusion lane line of the vehicle is obtained according to the first curve segment, the second curve segment and the above-mentioned error values. Thus, the problems of incomplete lane line detection caused by obstacles and the inability to predict the change law of the lane line ahead in advance are solved. By sensing the current frame image, the lane line curve equation is fitted, and the lane line extension line is detected for estimation. At the same time, the estimation results are fused and calculated in combination with the geometric information of the navigation map to obtain the optimal estimation of the lane line, thereby improving the accuracy and robustness of lane line detection.

[0101] Figure 4 A schematic diagram of the structure of a vehicle provided in an embodiment of the present application. The vehicle may include:

[0102] Memory 401 , processor 402 , and a computer program stored in the memory 401 and executable on the processor 402 .

[0103] When the processor 402 executes the program, the optimal lane line fusion method provided in the above embodiment is implemented.

[0104] Furthermore, the vehicle also includes:

[0105] The communication interface 403 is used for communication between the memory 401 and the processor 402 .

[0106] The memory 401 is used to store computer programs that can be executed on the processor 402 .

[0107] The memory 401 may include a high-speed RAM memory, and may also include a non-volatile memory (non-volatile memory), such as at least one disk memory.

[0108] If the memory 401, the processor 402 and the communication interface 403 are implemented independently, the communication interface 403, the memory 401 and the processor 402 can be connected to each other through a bus and communicate with each other. The bus can be an Industry Standard Architecture (ISA) bus, a Peripheral Component Interconnect (PCI) bus or an Extended Industry Standard Architecture (EISA) bus. The bus can be divided into an address bus, a data bus, a control bus, etc. For ease of representation, Figure 4 Only one thick line is used in the diagram, but this does not mean that there is only one bus or only one type of bus.

[0109] Optionally, in a specific implementation, if the memory 401, the processor 402 and the communication interface 403 are integrated on a chip, the memory 401, the processor 402 and the communication interface 403 can communicate with each other through an internal interface.

[0110] The processor 402 may be a central processing unit (CPU), or an application specific integrated circuit (ASIC), or one or more integrated circuits configured to implement the embodiments of the present application.

[0111] This embodiment also provides a computer-readable storage medium on which a computer program is stored. When the program is executed by a processor, the optimal lane line fusion method as described above is implemented.

[0112] This embodiment also provides a computer program product, including a computer program, which is executed to implement the optimal lane line fusion method of the above embodiment.

[0113] In the description of this specification, the description with reference to the terms "one embodiment", "some embodiments", "example", "specific example", or "some examples" etc. means that the specific features, structures, materials or characteristics described in conjunction with the embodiment or example are included in at least one embodiment or example of the present application. In this specification, the schematic representations of the above terms do not necessarily refer to the same embodiment or example. Moreover, the specific features, structures, materials or characteristics described may be combined in any one or N embodiments or examples in a suitable manner. In addition, those skilled in the art may combine and combine the different embodiments or examples described in this specification and the features of the different embodiments or examples, without contradiction.

[0114] In addition, the terms "first" and "second" are used for descriptive purposes only and should not be understood as indicating or implying relative importance or implicitly indicating the number of technical features indicated. Therefore, a feature defined as "first" or "second" may explicitly or implicitly include at least one of the features. In the description of this application, "N" means at least two, such as two, three, etc., unless otherwise clearly and specifically defined.

[0115] Any process or method description in a flowchart or otherwise described herein may be understood to represent a module, fragment or portion of code comprising one or more executable instructions for implementing the steps of a custom logical function or process, and the scope of the preferred embodiments of the present application includes alternative implementations in which functions may not be performed in the order shown or discussed, including performing functions in a substantially simultaneous manner or in reverse order depending on the functions involved, which should be understood by technicians in the technical field to which the embodiments of the present application belong.

[0116] The logic and / or steps represented in the flowchart or otherwise described herein, for example, can be considered as an ordered list of executable instructions for implementing logical functions, and can be embodied in any computer-readable medium for use by an instruction execution system, device or apparatus (such as a computer-based system, a system including a processor, or other system that can fetch instructions from an instruction execution system, device or apparatus and execute instructions), or in combination with these instruction execution systems, devices or apparatuses. For the purpose of this specification, "computer-readable medium" can be any device that can contain, store, communicate, propagate or transmit a program for use by an instruction execution system, device or apparatus, or in combination with these instruction execution systems, devices or apparatuses. More specific examples of computer-readable media (a non-exhaustive list) include the following: an electrical connection with one or N wirings (electronic devices), a portable computer disk box (magnetic device), a random access memory (RAM), a read-only memory (ROM), an erasable and programmable read-only memory (EPROM or flash memory), a fiber optic device, and a portable compact disk read-only memory (CDROM). In addition, the computer-readable medium may even be paper or other suitable medium on which the program is printed, since the program may be obtained electronically, for example, by optically scanning the paper or other medium and then editing, interpreting or otherwise processing in a suitable manner if necessary, and then stored in a computer memory.

[0117] It should be understood that the various parts of the present application can be implemented by hardware, software, firmware or a combination thereof. In the above-mentioned embodiment, the N steps or methods can be implemented by software or firmware stored in a memory and executed by a suitable instruction execution system. For example, if implemented by hardware, as in another embodiment, it can be implemented by any one of the following technologies known in the art or their combination: a discrete logic circuit having a logic gate circuit for implementing a logic function for a data signal, a dedicated integrated circuit having a suitable combination of logic gate circuits, a programmable gate array (PGA), a field programmable gate array (FPGA), etc.

[0118] A person skilled in the art may understand that all or part of the steps in the above-mentioned embodiment method may be completed by instructing related hardware through a program, and the program may be stored in a computer-readable storage medium, which, when executed, includes one or a combination of the steps of the method embodiment.

[0119] In addition, each functional unit in each embodiment of the present application may be integrated into a processing module, or each unit may exist physically separately, or two or more units may be integrated into one module. The above-mentioned integrated module may be implemented in the form of hardware or in the form of a software functional module. If the integrated module is implemented in the form of a software functional module and sold or used as an independent product, it may also be stored in a computer-readable storage medium.

[0120] The storage medium mentioned above may be a read-only memory, a magnetic disk or an optical disk, etc. Although the embodiments of the present application have been shown and described above, it can be understood that the above embodiments are exemplary and cannot be understood as limiting the present application. A person of ordinary skill in the art may change, modify, replace and modify the above embodiments within the scope of the present application.

Claims

1. An optimal lane line fusion method, characterized in that: The following steps are involved: Determine the target lane line length of the road ahead of the vehicle; Acquire a current frame image of the road ahead of the vehicle, detect the lane line of the road ahead of the vehicle based on the current frame image using a preset detection algorithm, obtain a first lane line length of the road ahead of the vehicle, and obtain a curve fitting equation of the lane line and a fitting error corresponding to the curve fitting equation based on the first lane line length; determining whether the length of the first lane line reaches the target lane line length; if the length of the first lane line does not reach the target lane line length, estimating the length of a second lane line that is not detected in the lane line of the road ahead of the vehicle based on the curve fitting equation, and obtaining a first curve segment corresponding to the second lane line length and an estimation error corresponding to the first curve segment; Acquire lane line geometry information of the road ahead of the vehicle, measure the length of a second lane line that is not detected in the lane line of the road ahead of the vehicle according to the lane line geometry information, obtain a second curve segment corresponding to the second lane line length and a measurement error corresponding to the second curve segment, and obtain an optimal fused lane line for the vehicle based on the fitting error, the first curve segment, the estimation error, the second curve segment and the measurement error.

2. The method according to claim 1, characterized in that Determining a target lane line length of the road ahead of the vehicle includes: Obtaining the current speed of the vehicle; A corresponding target coefficient is matched based on the current vehicle speed, and a target lane line length of the road ahead of the vehicle is determined according to the product of the current vehicle speed and the target coefficient.

3. The method according to claim 1, characterized in that The measuring, according to the lane line geometry information, the length of a second lane line that is not detected in the lane line of the road ahead of the vehicle to obtain a second curve segment corresponding to the second lane line length includes: Acquiring road curvature information of the road ahead of the vehicle; The length of the second lane line is measured using the road curvature information to obtain a second curve segment corresponding to the length of the second lane line.

4. The method according to claim 1, characterized in that: The obtaining of an optimal fused lane line for the vehicle based on the fitting error, the first curve segment, the estimation error, the second curve segment and the measurement error comprises: Calculate a lane line gain coefficient of the road ahead of the vehicle based on the fitting error, the estimation error and the measurement error; The lane line gain coefficients are weighted by using a preset weighting method to obtain a first gain coefficient corresponding to the first curve segment and a second gain coefficient corresponding to the second curve segment; The optimal fused lane line of the vehicle is obtained by summing the product of the first curve segment and the first gain coefficient and the product of the second curve segment and the second gain coefficient.

5. The method according to claim 4, characterized in that After obtaining the optimal fused lane line of the vehicle based on the fitting error, the first curve segment, the estimation error, the second curve segment and the measurement error, the method further includes: Calculating the fusion error of the optimal fusion lane line; Determining whether the fusion error is greater than or equal to a preset error threshold; If the fusion error is less than the preset error threshold, the preset display interface is controlled to display the optimal fusion lane line; otherwise, the preset display interface is controlled not to display the optimal fusion lane line.

6. An optimal fusion device for lane lines, characterized in that: include: A determination module, used to determine a target lane line length of a road ahead of the vehicle; a first acquisition module, configured to acquire a current frame image of the road ahead of the vehicle, detect the lane line of the road ahead of the vehicle based on the current frame image using a preset detection algorithm, obtain a first lane line length of the road ahead of the vehicle, and obtain a curve fitting equation of the lane line and a fitting error corresponding to the curve fitting equation based on the first lane line length; a judgment module, configured to judge whether the length of the first lane line reaches the target lane line length; if the length of the first lane line does not reach the target lane line length, estimating the length of a second lane line that is not detected in the lane line of the road ahead of the vehicle based on the curve fitting equation, and obtaining a first curve segment corresponding to the second lane line length and an estimation error corresponding to the first curve segment; A second acquisition module is used to obtain lane line geometry information of the road ahead of the vehicle, measure the length of a second lane line that is not detected in the lane line of the road ahead of the vehicle according to the lane line geometry information, obtain a second curve segment corresponding to the second lane line length and a measurement error corresponding to the second curve segment, and obtain an optimal fused lane line of the vehicle based on the fitting error, the first curve segment, the estimation error, the second curve segment and the measurement error.

7. The device according to claim 6, characterized in that The determination module is specifically used for: Obtaining the current speed of the vehicle; A corresponding target coefficient is matched based on the current vehicle speed, and a target lane line length of the road ahead of the vehicle is determined according to the product of the current vehicle speed and the target coefficient.

8. The device according to claim 6, characterized in that The second acquisition module is specifically used for: Acquiring road curvature information of the road ahead of the vehicle; The length of the second lane line is measured using the road curvature information to obtain a second curve segment corresponding to the length of the second lane line.

9. A vehicle, characterized in that: include: A memory, a processor, and a computer program stored in the memory and executable on the processor, wherein the processor executes the program to implement the optimal lane line fusion method as described in any one of claims 1 to 5.

10. A computer-readable storage medium having a computer program stored thereon, characterized in that: The program is executed by a processor to implement the optimal lane line fusion method as described in any one of claims 1-5.

Images