Lane line optimization method and device, electronic equipment and storage medium

Abstract

The application relates to the technical field of intelligent vehicles, in particular to a lane line optimization method and device, an electronic device and a storage medium, the method comprising the following steps: acquiring lane lines of at least one lane and a plurality of vehicle targets; according to the lane line type of the at least one lane and the distance from each vehicle target to each lane line, suppressing or completing the lane lines of the at least one lane; after suppressing or completing the lane lines of the at least one lane, performing equi-proportion compression on the lane in which the current vehicle is located based on a preset lane standard width, obtaining new left and right lane line distances, and performing distance transformation on the new left and right lane line distances, and then optimizing all the lane lines according to the distance-transformed new left and right lane line distances. According to the lane line optimization method, the lane line optimization algorithm and the mutual suppression algorithm of the vehicle target and the lane line are designed, so that the lane line jitter problem can be processed and the misidentification of the vehicle target or the lane line can be corrected.

Description

Technical Field

[0001] This application relates to the field of intelligent vehicle technology, and in particular to a method, apparatus, electronic device and storage medium for optimizing lane lines. Background Technology

[0002] With economic development, transportation systems have gradually become the lifeline and hub of travel activities, and people's ever-increasing living standards place higher demands on the efficiency and convenience of travel. In recent years, the development of intelligent vehicles has received increasing attention and importance, and the importance of communication between people and cars has become increasingly prominent. Therefore, the reconstruction of real-world scenarios is particularly important. Target reconstruction is the core of scenario reconstruction. By reconstructing real-world scenarios, the driving status of the vehicle and its surrounding environment can be effectively reflected, which is crucial for the driver's driving decisions.

[0003] In related technologies, scene reconstruction is mainly implemented on the instrument panel or vehicle infotainment system. Since advanced vehicle-to-everything (V2X) and road-to-everything (Road-to-Everything) collaboration technologies have not yet been widely implemented, current perception of surrounding information still relies on sensors around the vehicle. While sensors around the vehicle require high data accuracy for autonomous driving control and decision-making, accuracy is less critical for scene reconstruction. The more important aspects are displaying relative relationships, stability, and smoothness.

[0004] However, given that current sensors need to transmit accurate location information, it is debatable whether human-computer interaction needs to display such precise relative positional relationships. For example, when a vehicle is driving in the middle of a lane, the distance between the vehicle and the left or right lane line will inevitably fluctuate slightly. Displaying this actual detection distance would reduce the effectiveness of the display. Summary of the Invention

[0005] This application provides a method, apparatus, electronic device, and storage medium for optimizing lane lines, in order to solve problems such as lane line jitter and misidentification of lane lines or vehicle targets.

[0006] The first aspect of this application provides a lane line optimization method, comprising the following steps: acquiring lane lines of at least one lane and multiple vehicle targets; suppressing or supplementing the lane lines of the at least one lane according to the lane line type of the at least one lane and the distance from each vehicle target to each lane line; and after suppressing or supplementing the lane lines of the at least one lane, proportionally compressing the lane where the current vehicle is located based on a preset standard lane width to obtain new left and right lane line distances, and after performing distance transformation on the new left and right lane line distances, optimizing all lane lines according to the new left and right lane line distances after distance transformation.

[0007] Based on the above technical means, by suppressing or supplementing the lane lines and the distance from the vehicle target to each lane line of the acquired multiple lanes, and performing distance transformation, the optimization of all lane lines can be achieved.

[0008] Further, in one embodiment of this application, the distance transformation of the new left and right lane line distances includes: transforming the new left and right lane line distances based on a preset trapezoidal transformation algorithm, wherein the preset trapezoidal transformation algorithm is as follows: when the new left and right lane line distances are (0, width / 2-α), the distance transformation of the new left and right lane line distances = Distance*width / (width-2α); when the new left and right lane line distances are (width / 2-α, width / 2+α), the distance transformation of the new left and right lane line distances = width / 2; when the new left and right lane line distances are (width / 2+α, width), the distance transformation of the new left and right lane line distances = (Distance-width / 2-α)*width / (1-2α)+width / 2; where Distance is the distance, width is the standard width of the lane, and α is the standard value.

[0009] Based on the above technical means and the lane line distance transformation method, the problem of lane line vibration is effectively solved.

[0010] Furthermore, in one embodiment of this application, after obtaining the lane lines of the at least one lane and multiple vehicle targets, the method further includes: removing vehicle targets from the multiple vehicle targets that do not meet preset conditions.

[0011] By using the aforementioned technical methods, multiple vehicle targets that do not meet the preset conditions of the lane lines are eliminated, effectively reducing the interference from vehicle targets.

[0012] Furthermore, in one embodiment of this application, the preset condition is that the plurality of vehicle targets are located between the leftmost lane line and the rightmost lane line of the at least one lane.

[0013] Based on the aforementioned technical means, vehicle misidentification can be achieved by using the lane lines where the vehicle target is located.

[0014] Furthermore, in one embodiment of this application, the above-mentioned lane line optimization method further includes: obtaining all optimized lane line types; and filtering out lane lines that do not meet preset filtering conditions from all lane line types.

[0015] By using the aforementioned technical methods, multiple lane lines that do not meet the lane line type requirements are filtered out, effectively mitigating the situation of lane line type jumps.

[0016] A second aspect of this application provides a lane line optimization device, comprising: an acquisition module for acquiring lane lines of at least one lane and multiple vehicle targets; a correction module for suppressing or supplementing lane lines of the at least one lane according to the lane line type of the at least one lane and the distance from each vehicle target to each lane line; and an optimization module for, after suppressing or supplementing lane lines of the at least one lane, proportionally compressing the lane where the current vehicle is located based on a preset standard lane width to obtain new left and right lane line distances, and after performing distance transformation on the new left and right lane line distances, optimizing all lane lines according to the new left and right lane line distances after distance transformation.

[0017] Further, in one embodiment of this application, the optimization module includes: a distance transformation unit, used to transform the new left and right lane line distances based on a preset trapezoidal transformation algorithm, wherein the preset trapezoidal transformation algorithm is as follows: when the new left and right lane line distance is (0, width / 2-α), the new left and right lane line distance after distance transformation = Distance*width / (width-2α); when the distance is (width / 2-α, width / 2+α), the new left and right lane line distance after distance transformation = width / 2; when the new left and right lane line distance is (width / 2+α, width), the new left and right lane line distance after distance transformation = (Distance-width / 2-α)*width / (1-2α)+width / 2; where Distance is the distance, width is the standard width of the lane, and α is the standard width.

[0018] Furthermore, in one embodiment of this application, after acquiring the lane lines of the at least one lane and multiple vehicle targets, the acquisition module further includes: a rejection unit, used to reject vehicle targets among the multiple vehicle targets that do not meet preset conditions.

[0019] Furthermore, in one embodiment of this application, the preset condition is that the plurality of vehicle targets are located between the leftmost lane line and the rightmost lane line of the at least one lane.

[0020] Furthermore, in one embodiment of this application, the lane line optimization device described above further includes: an acquisition unit for acquiring all optimized lane line types; and a filtering unit for filtering out lane lines among all lane line types that do not meet preset filtering conditions.

[0021] A third aspect of this application provides an electronic device, including: 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 lane line optimization method as described in the above embodiments.

[0022] A fourth aspect of this application provides a computer-readable storage medium having a computer program stored thereon, which is executed by a processor to implement the lane line optimization method as described in the above embodiments.

[0023] This application embodiment acquires lane lines of at least one lane and multiple vehicle targets, and suppresses or completes lane lines of at least one lane according to the lane line type of at least one lane and the distance from each vehicle target to each lane line. Then, based on a preset standard lane width, the lane where the current vehicle is located is compressed proportionally to obtain new left and right lane line distances, and performs distance transformation. Thus, all lane lines are optimized based on the new left and right lane line distances after distance transformation. This solves the problem of lane line jitter and misidentification of lane lines or vehicle targets.

[0024] Additional aspects and advantages of this application will be set forth in part in the description which follows, and in part will be obvious from the description, or may be learned by practice of this application. Attached Figure Description

[0025] The above and / or additional aspects and advantages of this application will become apparent and readily understood from the following description of the embodiments taken in conjunction with the accompanying drawings, wherein:

[0026] Figure 1 This is a flowchart of a lane line optimization method according to an embodiment of this application;

[0027] Figure 2 This is a schematic diagram illustrating the implementation steps of an embodiment of this application.

[0028] Figure 3 This is a block diagram of a lane line optimization device according to an embodiment of this application;

[0029] Figure 4 This is a schematic diagram of the structure of an electronic device according to an embodiment of this application.

[0030] Explanation of reference numerals in the attached drawings: 10 - Lane line optimization device; 100 - Acquisition module; 200 - Correction module; 300 - Optimization module. Detailed Implementation

[0031] The embodiments of this application are described in detail below. Examples of the embodiments are shown in the accompanying drawings, wherein the same or similar reference numerals denote the same or similar elements or elements having the same or similar functions throughout. The embodiments described below with reference to the accompanying drawings are exemplary and intended to explain this application, and should not be construed as limiting this application.

[0032] The following describes a lane line optimization method, apparatus, electronic device, and storage medium according to embodiments of this application with reference to the accompanying drawings. Addressing the issues of lane line jitter and misidentification of lane lines or vehicle targets mentioned in the background art, this application provides a lane line optimization method. In this method, lane lines of at least one lane and multiple vehicle targets are acquired. Based on the lane line type of the at least one lane and the distance from each vehicle target to each lane line, the lane lines of the at least one lane are suppressed or supplemented. Then, based on a preset standard lane width, the lane where the current vehicle is located is proportionally compressed to obtain new left and right lane line distances. Distance transformation is then performed, thereby optimizing all lane lines based on the new left and right lane line distances after the distance transformation. Through the lane line optimization algorithm and the mutual suppression algorithm between targets and lane lines, lane line jitter can be processed and misidentification of vehicle targets or lane lines can be corrected.

[0033] Specifically, Figure 1 This is a flowchart illustrating a lane line optimization method according to an embodiment of this application.

[0034] like Figure 1 As shown, the method for optimizing lane markings includes the following steps:

[0035] In step S101, lane lines for at least one lane and multiple vehicle targets are acquired.

[0036] Specifically, in this embodiment of the application, the sensor data around the vehicle can be obtained through the ADAS (Advanced Driver Assistance System) controller, such as lane line information of at least one lane, multiple vehicle target information, etc.

[0037] Furthermore, in one embodiment of this application, after obtaining the lane lines of at least one lane and multiple vehicle targets, the method further includes: removing vehicle targets from the multiple vehicle targets that do not meet preset conditions.

[0038] The preset condition is that multiple vehicle targets are located between the leftmost lane line and the rightmost lane line of at least one lane.

[0039] Specifically, such as Figure 2As shown, in this embodiment of the application, after obtaining lane line information of at least one lane and multiple vehicle target information, it is also necessary to calculate the distance of multiple vehicle targets from each lane line, so as to eliminate redundant vehicle targets that do not meet the preset conditions.

[0040] For example, if the embodiment of this application uses three lanes, targets outside the three lanes need to be removed. In this case, the distances of multiple vehicle targets from each lane line are calculated, and vehicle targets that do not meet the preset conditions are identified based on the distances and removed, thereby preventing interference from extra vehicle targets to the test.

[0041] In step S102, the lane lines of at least one lane are suppressed or supplemented according to the lane line type of at least one lane and the distance from each vehicle target to each lane line.

[0042] Specifically, such as Figure 2 As shown, due to certain hardware defects in the identification of vehicle targets in related technologies, when eliminating vehicle targets that do not meet the preset conditions, it is easy to eliminate targets that are far away, such as guardrails or roadside curbs. For example, if a vehicle is traveling on a highway, eliminating vehicles outside the guardrail will suppress that vehicle.

[0043] Therefore, embodiments of this application require suppressing or supplementing the lane lines of at least one lane based on the lane line type of at least one lane and the distance from each vehicle target to each lane line.

[0044] Specifically, in this embodiment, the distances of multiple vehicle targets to each lane line calculated above are used to correct the display information of guardrails or curbs. If a lane line is a guardrail or curb, and a vehicle target is close to that lane line, then that type of guardrail or curb can be suppressed.

[0045] Furthermore, if a lane line is not a guardrail or curb, and neither the left nor right lane lines of the vehicle target are identified, but there are other vehicle targets outside its left and / or right lines, then the left and / or right lane lines can be filled in by the vehicle targets to correct the misidentification of the lane lines.

[0046] In step S103, after suppressing or completing the lane lines of at least one lane, the lane where the current vehicle is located is compressed proportionally based on the preset standard lane width to obtain new left and right lane line distances. After the new left and right lane line distances are transformed, all lane lines are optimized based on the new left and right lane line distances after the distance transformation.

[0047] The preset standard lane width can be the standard lane width specified in this field.

[0048] Specifically, such as Figure 2 As shown, in this embodiment of the application, after suppressing or supplementing the lane line with one less lane, firstly, the standard width of the lane is determined as width; secondly, the distance between the left and right lane lines is compressed proportionally according to the sum of width to obtain new distances Distance_L and Distance_R between the left and right lane lines; finally, the new distances between the left and right lane lines are transformed, and all lane lines are optimized according to the new distances between the left and right lane lines after the distance transformation.

[0049] Further, in one embodiment of this application, the distance transformation of the new left and right lane line distances includes: transforming the new left and right lane line distances based on a preset trapezoidal transformation algorithm, wherein the preset trapezoidal transformation algorithm is as follows: when the new left and right lane line distances are (0, width / 2-α), the transformed new left and right lane line distances = Distance*width / (width-2α); when the new left and right lane line distances are (width / 2-α, width / 2+α), the transformed new left and right lane line distances = width / 2; when the new left and right lane line distances are (width / 2+α, width), the transformed new left and right lane line distances = (Distance-width / 2-α)*width / (1-2α)+width / 2;

[0050] Where Distance is the distance, width is the standard width of the lane, and α is the standard setting, which is to set the inflection point in combination with the width, and the slopes of the two lines to the left and right of the inflection point are different.

[0051] Specifically, this embodiment uses a trapezoidal transformation algorithm to transform the distances of the new left and right lane lines. For example, when the new left and right lane line distance is (width / 2-α, width / 2+α), the output distance after transformation is width / 2; when the new left and right lane line distance is (0, width / 2-α), the output distance after transformation is Distance*width / (width-2α); when the new left and right lane line distance is (width / 2+α, width), the output distance after transformation is (Distance-width / 2-α)*width / (1-2α)+width / 2. It should be noted that after calculating the distances of the left and right lane lines, this embodiment can directly add width to the left or right line of the lane to obtain the left or right lane line, thereby solving the lane line jitter problem.

[0052] Optionally, the above transformation algorithm is merely exemplary, and the embodiments of this application may also use a multi-gradient algorithm or other transformation algorithms, which are not specifically limited here. After calculating the distance between the left and right lane lines, the left-left line or right-right line can be directly widened by adding width to the left or right line.

[0053] Furthermore, in one embodiment of this application, the above-mentioned lane line optimization method further includes: obtaining all optimized lane line types; and filtering out lane lines that do not meet the preset filtering conditions from all lane line types.

[0054] The preset filtering conditions can be used to identify occasional misidentifications of vehicle targets or lane lines during driving.

[0055] Specifically, in this embodiment of the application, after optimizing all lane lines based on the new left and right lane line distances after distance transformation, the types of all optimized lane lines are obtained, and all optimized lane line types are filtered and output. Lane lines that occasionally cause misidentification are filtered out from all lane line types to reduce the abrupt changes in lane line types.

[0056] According to the lane line optimization method proposed in this application, the lane lines of at least one lane and multiple vehicle targets are obtained. Based on the lane line type of at least one lane and the distance from each vehicle target to each lane line, the lane lines of at least one lane are suppressed or supplemented. Then, based on a preset standard lane width, the lane where the current vehicle is located is compressed proportionally to obtain a new distance between the left and right lane lines. The distance is then transformed, and all lane lines are optimized based on the new distance between the left and right lane lines after the distance transformation. Through the lane line optimization algorithm and the mutual suppression algorithm between targets and lane lines, lane line jitter can be handled and misidentification of vehicle targets or lane lines can be corrected.

[0057] Next, the lane line optimization device proposed according to the embodiments of this application is described with reference to the accompanying drawings.

[0058] Figure 3 This is a block diagram of a lane line optimization device according to an embodiment of this application.

[0059] like Figure 3 As shown, the lane line optimization device 10 includes: an acquisition module 100, a correction module 200, and an optimization module 300.

[0060] The acquisition module 100 is used to acquire lane lines for at least one lane and multiple vehicle targets.

[0061] Correction module 200 is used to suppress or complete the lane lines of at least one lane based on the lane line type of at least one lane and the distance from each vehicle target to each lane line; and

[0062] The optimization module 300 is used to suppress or complete the lane lines of at least one lane, and then proportionally compress the lane where the current vehicle is located based on the preset standard lane width to obtain a new left and right lane line distance. After performing distance transformation on the new left and right lane line distance, it optimizes all lane lines based on the new left and right lane line distance after the distance transformation.

[0063] Furthermore, in one embodiment of this application, the optimization module 300 includes:

[0064] The distance transformation unit is used to transform the distances between the new left and right lane lines based on a preset trapezoidal transformation algorithm. The preset trapezoidal transformation algorithm is as follows:

[0065] When the new distance between the left and right lane lines is (0, width / 2-α), the new distance between the left and right lane lines after the distance transformation = Distance*width / (width-2α);

[0066] When the distance is (width / 2-α, width / 2+α), the new distance between the left and right lane lines after the distance transformation is width / 2;

[0067] When the new distance between the left and right lane lines is (width / 2+α, width), the new distance between the left and right lane lines after the distance transformation is (Distance-width / 2-α)*width / (1-2α)+width / 2;

[0068] Where Distance is the distance, width is the standard width of the lane, and α is the standard value.

[0069] Furthermore, in one embodiment of this application, after acquiring the lane lines of at least one lane and multiple vehicle targets, the acquisition module 100 further includes:

[0070] The elimination unit is used to eliminate vehicle targets that do not meet the preset conditions from among multiple vehicle targets.

[0071] Furthermore, in one embodiment of this application, the preset condition is that multiple vehicle targets are located between the leftmost lane line and the rightmost lane line of at least one lane.

[0072] Furthermore, in one embodiment of this application, the lane line optimization device 10 described above further includes:

[0073] The acquisition unit is used to acquire the types of all optimized lane markings;

[0074] The filtering unit is used to filter out lane lines that do not meet the preset filtering conditions from all lane line types.

[0075] According to the lane line optimization device proposed in the embodiments of this application, the device acquires the lane lines of at least one lane and multiple vehicle targets, and suppresses or completes the lane lines of at least one lane based on the lane line type of at least one lane and the distance from each vehicle target to each lane line. Then, based on a preset standard lane width, the lane where the current vehicle is located is compressed proportionally to obtain a new distance between the left and right lane lines, and performs a distance transformation. The device optimizes all lane lines based on the new distance between the left and right lane lines after the distance transformation. Through the lane line optimization algorithm and the mutual suppression algorithm between targets and lane lines, the device can handle lane line jitter and correct misidentification of vehicle targets or lane lines.

[0076] Figure 4 A schematic diagram of the structure of an electronic device provided in an embodiment of this application. The electronic device may include:

[0077] The memory 401, the processor 402, and the computer program stored on the memory 401 and capable of running on the processor 402.

[0078] When the processor 402 executes the program, it implements the lane line optimization method provided in the above embodiments.

[0079] Furthermore, electronic devices also include:

[0080] Communication interface 403 is used for communication between memory 401 and processor 402.

[0081] The memory 401 is used to store computer programs that can run on the processor 402.

[0082] The memory 401 may include high-speed RAM (Random Access Memory) memory, and may also include non-volatile memory, such as at least one disk storage.

[0083] If the memory 401, processor 402, and communication interface 403 are implemented independently, then the communication interface 403, memory 401, and processor 402 can be interconnected via a bus to complete communication between them. The bus can be an ISA (Industry Standard Architecture) bus, a PCI (Peripheral Component Interconnect) bus, or an EISA (Extended Industry Standard Architecture) bus, etc. The bus can be divided into address bus, data bus, control bus, etc. For ease of representation, Figure 4 The bus is represented by a single thick line, but this does not mean that there is only one bus or one type of bus.

[0084] Optionally, in a specific implementation, if the memory 401, processor 402, and communication interface 403 are integrated on a single chip, then the memory 401, processor 402, and communication interface 403 can communicate with each other through an internal interface.

[0085] Processor 402 may be a CPU (Central Processing Unit), an ASIC (Application Specific Integrated Circuit), or one or more integrated circuits configured to implement embodiments of this application.

[0086] This application also provides a computer-readable storage medium storing a computer program that, when executed by a processor, implements the lane line optimization method described above.

[0087] In the description of this specification, the references to terms such as "one embodiment," "some embodiments," "example," "specific example," or "some examples," etc., indicate that a specific feature, structure, material, or characteristic described in connection with that embodiment or example is included in at least one embodiment or example of this application. In this specification, the illustrative expressions of the above terms do not necessarily refer to the same embodiment or example. Furthermore, the specific features, structures, materials, or characteristics described may be combined in any suitable manner in one or more embodiments or examples. Moreover, without contradiction, those skilled in the art can combine and integrate the different embodiments or examples described in this specification, as well as the features of different embodiments or examples.

[0088] Furthermore, the terms "first" and "second" are used for descriptive purposes only and should not be construed as indicating or implying relative importance or implicitly specifying the number of technical features indicated. Thus, a feature defined as "first" or "second" may explicitly or implicitly include at least one of that feature. In the description of this application, "N" means at least two, such as two, three, etc., unless otherwise explicitly specified.

[0089] Any process or method described in the flowchart or otherwise herein can be understood as representing a module, segment, or portion of code comprising one or more N executable instructions for implementing custom logic functions or processes, and the scope of the preferred embodiments of this application includes additional implementations in which functions may be performed not in the order shown or discussed, including substantially simultaneously or in reverse order depending on the functions involved, as should be understood by those skilled in the art to which embodiments of this application pertain.

[0090] It should be understood that the various parts of this application can be implemented using hardware, software, firmware, or a combination thereof. In the above embodiments, the N steps or methods can be implemented using software or firmware stored in memory and executed by a suitable instruction execution system. For example, if implemented in hardware, as in another embodiment, it can be implemented using any one or a combination of the following techniques known in the art: discrete logic circuits having logic gates for implementing logical functions on data signals, application-specific integrated circuits (ASICs) having suitable combinational logic gates, programmable gate arrays (FPGAs), field-programmable gate arrays (FPGAs), etc.

[0091] Those skilled in the art will understand that all or part of the steps of the methods described in the above embodiments can be implemented by a program instructing related hardware, and the program can be stored in a computer-readable storage medium. When executed, the program includes one or a combination of the steps of the method embodiments.

[0092] Although embodiments of this application have been shown and described above, it is understood that the above embodiments are exemplary and should not be construed as limiting this application. Those skilled in the art can make changes, modifications, substitutions and variations to the above embodiments within the scope of this application.

Claims

1. A method for optimizing lane markings, characterized in that, Includes the following steps: Obtain lane lines for at least one lane and multiple vehicle targets; Based on the lane line type of the at least one lane and the distance from each vehicle target to each lane line, suppress or complete the lane lines of the at least one lane; as well as After suppressing or completing the lane lines of at least one lane, the lane where the current vehicle is located is compressed proportionally based on a preset standard lane width to obtain a new left and right lane line distance. After performing distance transformation on the new left and right lane line distance, all lane lines are optimized based on the new left and right lane line distance after distance transformation. The process of transforming the distances between the new left and right lane lines includes: Based on a preset trapezoidal transformation algorithm, the distances between the new left and right lane lines are transformed, wherein the preset trapezoidal transformation algorithm is as follows: When the new left and right lane line distance is (0, width / 2-α), the new left and right lane line distance after distance transformation = Distance*width / (width-2α). When the new left and right lane line distances are (width / 2-α, width / 2+α), the new left and right lane line distances after the distance transformation = width / 2; When the new distance between the left and right lane lines is (width / 2+α, width), the distance between the new left and right lane lines after the distance transformation = (Distance-width / 2-α)*width / (1-2α)+width / 2; Where Distance is the distance, width is the standard width of the lane, and α is the standard value.

2. The method according to claim 1, characterized in that, After acquiring the lane lines of the at least one lane and multiple vehicle targets, the method further includes: Vehicle targets that do not meet the preset conditions are removed from the plurality of vehicle targets.

3. The method according to claim 2, characterized in that, The preset condition is that the multiple vehicle targets are located between the leftmost lane line and the rightmost lane line of the at least one lane.

4. The method according to claim 1, characterized in that, Also includes: Get all the optimized lane line types; Filter out lane lines that do not meet the preset filtering conditions from all the lane line types.

5. A lane marking optimization device, characterized in that, include: The acquisition module is used to acquire lane lines for at least one lane and multiple vehicle targets; The correction module is used to suppress or complete the lane lines of the at least one lane based on the lane line type of the at least one lane and the distance from each vehicle target to each lane line; as well as The optimization module is used to suppress or complete the lane lines of at least one lane, and then proportionally compress the lane where the current vehicle is located based on a preset standard lane width to obtain a new left and right lane line distance. After performing a distance transformation on the new left and right lane line distance, all lane lines are optimized based on the new left and right lane line distance after the distance transformation. The optimization module includes: The distance transformation unit is used to transform the distance between the new left and right lane lines based on a preset trapezoidal transformation algorithm, wherein the preset trapezoidal transformation algorithm is: When the new left and right lane line distance is (0, width / 2-α), the new left and right lane line distance after distance transformation = Distance*width / (width-2α). When the distance is (width / 2-α, width / 2+α), the new left and right lane line distances after the distance transformation = width / 2; When the new distance between the left and right lane lines is (width / 2+α, width), the distance between the new left and right lane lines after the distance transformation = (Distance-width / 2-α)*width / (1-2α)+width / 2; Where Distance is the distance, width is the standard width of the lane, and α is the standard value.

6. The apparatus according to claim 5, characterized in that, After acquiring the lane lines of the at least one lane and multiple vehicle targets, the acquisition module further includes: The elimination unit is used to eliminate vehicle targets that do not meet the preset conditions from the plurality of vehicle targets.

7. An electronic device, characterized in that, include: A memory, a processor, and a computer program stored in the memory and executable on the processor, the processor executing the program to implement the lane line optimization method as described in any one of claims 1-4.

8. A computer-readable storage medium having a computer program stored thereon, characterized in that, The program is executed by the processor to implement the lane line optimization method as described in any one of claims 1-4.

Images