Lane line detection method and laser radar

By integrating solar noise detection into LiDAR systems to enhance echo intensity differentiation, the method addresses the challenge of accurately distinguishing lane lines from the ground, improving detection accuracy and range in adverse conditions.

CN119179058APending Publication Date: 2024-12-24ROBERT BOSCH GMBH
View PDF 0 Cites 0 Cited by

Patent Information

Application Number
CN202310744724.6
Authority / Receiving Office
CN · China
Patent Type
Applications(China)
Current Assignee / Owner
Filing Date
2023-06-21
Publication Date
2024-12-24

AI Technical Summary

Technical Problem

Current lane line detection methods in ADAS systems face challenges in accurately distinguishing lane lines from the ground due to the lack of color information in LiDAR sensors and issues with camera-based solutions, particularly in low light or direct light conditions, and existing LiDAR methods struggle to distinguish lane lines and ground based on echo intensity under certain angles and distances.

Method used

Incorporating the detection of solar noise into LiDAR systems to differentiate between lane lines and ground by utilizing the uniform intensity of sunlight reflection, adding a solar noise attribute to three-dimensional point clouds to enhance echo intensity differentiation.

Benefits of technology

Enables accurate lane line detection without reducing detection distance, improving accuracy and range, especially in adverse conditions, and overcoming limitations of camera-based and traditional LiDAR methods.

✦ Generated by Eureka AI based on patent content.

Smart Images

  • Figure CN119179058A_ABST
    Figure CN119179058A_ABST
Patent Text Reader

Abstract

The invention relates to a lane line detection method and a laser radar. The method comprises the following steps: emitting infrared laser; reflected waves of the infrared laser are received, and the reflected waves of the infrared laser comprise ground reflected waves reflected back from the ground and lane line reflected waves reflected back from the lane line; forming a three-dimensional point cloud based on the ground reflected wave and the lane line reflected wave; the receiving unit is used for receiving solar noise which is formed by reflected waves generated when sunlight irradiates the ground and lane lines; detecting the echo intensity of the solar noise; extracting a three-dimensional point cloud formed by lane line reflected waves from the three-dimensional point cloud based on the echo intensity of the sun noise; and lane line detection is realized based on the three-dimensional point cloud formed by the extracted lane line reflection waves. According to the invention, the lane line and the ground can be effectively distinguished so as to realize accurate detection of the lane line.
Need to check novelty before this filing date? Find Prior Art

Description

Technical Field

[0001] The present invention relates to the field of intelligent driving technology, and in particular to a lane line detection method and a laser radar. Background Art

[0002] At present, driver assistance and autonomous driving systems (ADAS) have become an indispensable system in vehicles, which can partially release the capabilities of human drivers and improve safety and traffic efficiency. In ADAS systems, perception sensors are required to detect road lane lines to avoid penalties and safety risks, etc.

[0003] LiDAR is an active optical sensor that actively emits near-infrared laser pulses and detects the laser echoes reflected from the target, and then generates a 3D point cloud model of the surrounding environment. In recent years, LiDAR sensors have developed rapidly for their 3D point cloud capabilities. However, due to its lack of color information, LiDAR sensors have not yet made effective contributions in lane line detection. Summary of the invention

[0004] Based on the above problems in the prior art, the present invention aims to provide a lane line detection method based on laser radar and a laser radar that can accurately realize lane line detection.

[0005] A lane line detection method according to one aspect of the present invention comprises the following steps:

[0006] Emit infrared laser;

[0007] Receiving reflected waves of infrared laser, wherein the reflected waves of infrared laser include ground reflected waves reflected from the ground and lane line reflected waves reflected from the lane line;

[0008] Forming a three-dimensional point cloud based on the ground reflection wave and the lane line reflection wave;

[0009] Receiving solar noise, wherein the solar noise is formed by reflection waves generated by sunlight irradiating the ground and lane lines;

[0010] detecting the echo intensity of the solar noise;

[0011] Extracting a three-dimensional point cloud formed by the lane line reflection wave from the three-dimensional point cloud based on the echo intensity of the solar noise; and

[0012] Lane line detection is achieved based on the three-dimensional point cloud formed by the extracted lane line reflection wave.

[0013] A laser radar according to one aspect of the present invention comprises:

[0014] A transmitting unit, used for transmitting infrared laser;

[0015] A scanning unit, used for reflecting the infrared laser to the ground and lane lines;

[0016] A first receiving unit, configured to receive a reflected wave of an infrared laser, wherein the reflected wave of the infrared laser includes a ground reflected wave reflected from the ground and a lane line reflected wave reflected from the lane line;

[0017] A second receiving unit is used to receive solar noise, wherein the solar noise is formed by the reflection waves of sunlight irradiating the ground and the lane line; and

[0018] A signal processing unit is used to form a three-dimensional point cloud based on the ground reflection wave and the lane line reflection wave. On the other hand, it is further used to detect the echo intensity of the solar noise and extract the three-dimensional point cloud formed by the lane line reflection wave from the three-dimensional point cloud based on the echo intensity of the solar noise, and realize lane line detection based on the three-dimensional point cloud formed by the extracted lane line reflection wave.

[0019] The lane line detection method and laser radar according to the present invention can effectively distinguish the lane line from the ground without losing the detection distance, and can improve the accuracy of lane line detection. BRIEF DESCRIPTION OF THE DRAWINGS

[0020] The above and other objects and advantages of the present application will become more fully apparent from the following detailed description in conjunction with the accompanying drawings, in which the same or similar elements are represented by the same reference numerals.

[0021] Figure 1 This is a schematic diagram showing the detection of sunlight by a lidar.

[0022] Figure 2 It is a structural block diagram of a laser radar according to one embodiment of the present invention.

[0023] Figure 3 It is a schematic diagram of a specific process of a lane line detection method according to an embodiment of the present invention.

[0024] Figure 4 It is a pulse timing diagram of the lane line detection method of this embodiment. DETAILED DESCRIPTION

[0025] The following describes some of the various embodiments of the present invention, which are intended to provide a basic understanding of the present invention, but are not intended to identify the key or decisive elements of the present invention or to limit the scope of protection.

[0026] For the purpose of brevity and illustration, the principles of the present invention are described herein mainly with reference to its exemplary embodiments. However, those skilled in the art will readily recognize that the same principles are equally applicable to all types of lane line detection methods and laser radars, and these same principles can be implemented therein, and any such changes do not depart from the true spirit and scope of the present patent application.

[0027] Moreover, in the following description, reference is made to the accompanying drawings, which illustrate specific exemplary embodiments. Electrical, mechanical, logical and structural changes may be made to these embodiments without departing from the spirit and scope of the present invention. In addition, although the features of the present invention are disclosed in conjunction with only one of several implementations / embodiments, this feature may be combined with one or more other features of other implementations / embodiments as may be desirable and / or advantageous for any given or identifiable function. Therefore, the following description should not be regarded as limiting, and the scope of the present invention is defined by the appended claims and their equivalents.

[0028] Terms such as “having” and “including” indicate that in addition to the units (modules) and steps directly and explicitly stated in the specification and claims, the technical solution of the present invention does not exclude the situation where it has other units (modules) and steps that are not directly or explicitly stated.

[0029] First, the inventor of the present invention conducted an in-depth study on the lane line detection technology in the prior art and obtained the following findings and inventive concepts:

[0030] Current ADAS lane detection methods rely mainly on cameras to detect lanes by distinguishing the color difference between lanes and road surfaces. However, solutions that use only cameras have the following weaknesses: cameras fail in certain special situations, making lane detection unusable (e.g., in low light conditions and direct light conditions); common faults can cause systemic safety failures of the camera and disable lane detection without redundancy and cross-checking with other sensors (such common faults include mirror paint on the front car and side walls, similar colors between the ground and the lane, or human manipulation).

[0031] Compared to cameras, LiDAR cannot provide color information but detects by the intensity of the received echo. Here, the echo intensity satisfies the following formula:

[0032]

[0033] According to the above formula, the echo intensity is proportional to the target reflectivity R. Theoretically, due to the different reflectivities of the lane line and the ground (the lane line is white and has a high reflectivity, and the ground is gray and has a low reflectivity), the echo intensity will also be different. Therefore, the ground and the lane line can be distinguished by the echo intensity of the lidar. However, since the impact of the laser incident angle θ on the lane line and the ground is uncontrollable, and the target distance d to the lane line and the ground is also uncontrollable, the lane line detection based on echo intensity will still have the following problems:

[0034] In some areas, it is difficult to distinguish lane lines and the ground by echo intensity. For example, the reflected wave of the lane line in the distance will also be filtered out as the reflected wave of the ground. As an example, the echo intensity of the reflected wave of the lane line in the distance (whose reflectivity R is high and the target distance d is large) and the reflected wave of the nearby ground (whose reflectivity R is low and the target distance d is small) may become similar according to the above formula. In this way, the reflected wave of the lane line in the distance will be filtered out as the reflected wave of the nearby ground.

[0035] Next, the basic principle of the inventive concept of the present invention is explained.

[0036] Figure 1 This is a schematic diagram showing the detection of sunlight by a lidar.

[0037] The inventors have discovered that since sunlight contains infrared components, laser radar can detect infrared light, so the laser radar can detect sunlight reflected from the ground without modification.

[0038] exist Figure 1 The figure shows the reflected waves generated by the sunlight shining on the ground and the lane line respectively detected by the laser radar. Specifically, S1 represents the sunlight shining on the ground, S1' represents the reflected waves generated by the sunlight shining on the ground received by the laser radar, S2 represents the sunlight shining on the lane line, and S2' represents the reflected waves generated by the sunlight shining on the lane line received by the laser radar. Figure 1 As shown, the laser radar installed on the vehicle can receive the reflection wave S1' generated by the sunlight irradiating the ground and the reflection wave S2' generated by the sunlight irradiating the lane line.

[0039] The inventors further discovered that the distance from the sun to the earth is much greater than the diameter of the earth, so it can be considered that the intensity of sunlight received on the earth's surface is basically the same. Therefore, the intensity of sunlight reflection received by the laser radar is related to the reflection path distance of the target ground from the laser radar, but has nothing to do with the transmission path distance. The laser radar is closer to the target ground, so the difference in laser intensity received by the far ground and the near ground is obvious. Therefore, the intensity of laser reflection received by the laser radar is related to both the transmission and reflection path distances of the target ground from the laser radar. In this way, on the surface of the earth, the reflected sunlight is more uniform than the infrared laser emitted by the reflecting laser radar, which results in a uniform difference in the intensity of the reflected wave (i.e., the echo intensity) generated by the sunlight irradiating the ground and the lane line.

[0040] Here, the so-called "uniform difference" means that the intensity of the reflected wave from the sunlight hitting the lane line is always significantly greater than the intensity of the reflected wave from the sunlight hitting the ground. This is because the lane line is white and has a high reflectivity, while the ground is gray and has a low reflectivity. The reflected wave from the sunlight with high intensity is definitely from the lane line, and the reflected wave from the sunlight with low intensity is definitely from the ground. Therefore, based on such a uniform difference, the reflected wave from the lane line and the reflected wave from the ground can be easily distinguished using sunlight.

[0041] Based on the above principles and discoveries, the technical concept of the present invention is to add the function of receiving and detecting the reflected waves of sunlight (hereinafter referred to as "solar noise") to the existing laser radar. In this way, the reflected waves of sunlight can be used to effectively distinguish between the reflected waves from the ground and the reflected waves from the lane line, thereby accurately detecting the lane line.

[0042] Specifically, in the existing three-dimensional point cloud, the three-dimensional point cloud information of the point generally includes two attribute information: coordinate information and laser echo intensity. In the present invention, based on the above technical concept, in order to more effectively distinguish lane lines and the ground, on the basis of the two existing attribute information, a solar noise attribute is further added to each three-dimensional point. The solar noise attribute is used to express the echo intensity of the reflected light of the detected sunlight. The echo intensity of the reflected light of the sunlight can be used to determine whether it is the ground or the lane line.

[0043] Figure 2 It is a structural block diagram of a laser radar according to one embodiment of the present invention.

[0044] like Figure 2 As shown, a laser radar 100 according to an embodiment of the present invention comprises:

[0045] The transmitting unit 110 is used to transmit infrared laser;

[0046] A scanning unit 120, for reflecting infrared laser light onto the ground and lane lines and performing three-dimensional modeling by rotating its mirror in horizontal and vertical directions to scan a field of view (FoV);

[0047] A first receiving unit 130, configured to receive a reflected wave of an infrared laser, wherein the reflected wave of the infrared laser includes a ground reflected wave reflected from the ground and a lane line reflected wave reflected from the lane line;

[0048] A second receiving unit 140 is configured to receive solar noise, wherein the solar noise is formed by reflection waves of sunlight irradiating the ground and the lane line; and

[0049] The signal processing unit 150 is used to form a three-dimensional point cloud according to three-dimensional modeling based on the ground reflection wave and the lane line reflection wave. On the other hand, it is further used to detect the echo intensity of the solar noise and extract the three-dimensional point cloud formed by the lane line reflection wave from the three-dimensional point cloud based on the echo intensity of the solar noise, and realize lane line detection based on the three-dimensional point cloud formed by the lane line reflection wave.

[0050] Here, the first receiving unit 130 and the second receiving unit 140 may be constructed separately or integrated into one receiving unit, which is not limited in the present invention.

[0051] The signal processing unit 150 includes:

[0052] A three-dimensional point cloud forming submodule 151 is used to form a three-dimensional point cloud according to three-dimensional modeling based on the ground reflection wave and the lane line reflection wave;

[0053] A solar noise detection submodule 152, configured to detect the echo intensity of the solar noise;

[0054] An extraction submodule 153, configured to extract a three-dimensional point cloud formed by a lane line reflection wave from the three-dimensional point cloud based on the echo intensity of the solar noise; and

[0055] The lane line detection submodule 154 is used to implement lane line detection based on the three-dimensional point cloud formed by the extracted lane line reflection wave.

[0056] The extraction submodule 153 adds the echo intensity of the solar noise as attribute information to each point of the three-dimensional point cloud, and extracts the three-dimensional point cloud formed by the lane line reflection wave based on the attribute information. Specifically, the extraction submodule 153 extracts the three-dimensional point cloud with relatively high echo intensity of the solar noise as the three-dimensional point cloud formed by the lane line reflection wave, and filters the three-dimensional point cloud with relatively low echo intensity of the solar noise as the three-dimensional point cloud formed by the ground reflection wave.

[0057] Next, a lane line detection method according to an embodiment of the present invention is described.

[0058] Figure 3 It is a schematic diagram of a specific process of a lane line detection method according to an embodiment of the present invention.

[0059] like Figure 3 As shown, the lane line detection method in this example specifically includes the following steps:

[0060] S1: The scanning unit rotates to a specific azimuth and elevation direction;

[0061] S2: The transmitting unit emits infrared laser;

[0062] S3: The first receiving unit receives the reflected wave of the infrared laser;

[0063] S4: The first receiving unit determines whether the power of the reflected wave of the received infrared laser is greater than a preset point generation threshold (i.e., a threshold capable of generating a three-dimensional point cloud). If so, continue to S5; otherwise, return to S1;

[0064] S5: The second receiving unit receives solar noise (i.e., the reflected wave of sunlight shining on the ground and the lane line);

[0065] S6: The signal processing unit detects the time difference Δt between the emission of the infrared laser and the reception of the reflected wave of the infrared laser to calculate the target distance;

[0066] S7: The signal processing unit detects the echo intensity of the reflected wave of the infrared laser received by the receiving unit;

[0067] S8: The signal processing unit detects the echo intensity of the solar noise received by the second receiving unit; and

[0068] S9: The signal processing unit generates a three-dimensional point cloud based on the reflected wave of the infrared laser that is greater than a preset point generation threshold. On the other hand, the signal processing unit extracts the three-dimensional point cloud formed by the lane line reflection wave based on the detected echo intensity of the solar noise, and realizes lane line detection based on the extracted three-dimensional point cloud formed by the lane line reflection wave and the target distance.

[0069] Among them, S5, S8 and S9 are steps added compared to the prior art in order to effectively distinguish the lane lines from the ground.

[0070] In S8, the three-dimensional point cloud formed by the lane line reflection wave is extracted based on the echo intensity of the detected solar noise by the following methods:

[0071] The three-dimensional point cloud with relatively high echo intensity of solar noise is extracted as the three-dimensional point cloud formed by the lane line reflection wave, and the three-dimensional point cloud with relatively low echo intensity of solar noise is filtered as the three-dimensional point cloud formed by the ground reflection wave. Lane line detection is realized based on the extracted three-dimensional point cloud formed by the lane line reflection wave and the target distance.

[0072] For example, as an example, in the prior art, the attribute information of the three-dimensional point cloud only includes two pieces of information: x, y, z coordinates and the echo intensity of the received laser reflection wave. In the present invention, in order to distinguish between the lane line and the ground, a noise attribute is further added to the attribute information of each three-dimensional point, that is, the echo intensity of the solar noise. The echo intensity of the solar noise can express the size of the detected solar noise signal. According to the inventive concept described above, the reflected wave of sunlight with high intensity is definitely the reflected wave from the lane line and the reflected wave with low intensity is definitely the reflected wave from the ground. Therefore, the echo intensity of the solar noise can be used to distinguish the lane line reflection wave from the ground reflection wave.

[0073] Next, the pulse timing of the lane line detection method of this embodiment is described.

[0074] Figure 4 It is a pulse timing diagram of the lane line detection method of this embodiment.

[0075] exist Figure 4 In the figure, the horizontal axis (t) represents time, and the vertical axis represents power (or echo intensity). P_TX represents the transmission power of the infrared laser, P-RX represents the received power of the reflected wave of the infrared laser, P represents the echo intensity of the infrared laser pulse, PT represents the point generation threshold, PN represents the echo intensity of the solar noise, and Δt represents the time difference between the transmission and reception of the infrared laser pulse.

[0076] In the first emission time window A, an infrared laser is emitted, a reflected infrared laser pulse is received in the first receiving time window B, and immediately after the first receiving time window B ends, the reflected wave of sunlight is received in the second receiving time window C. That is, in the present invention, a new time window is opened after receiving the laser pulse, i.e., the second receiving time window C is used to receive the reflected light of sunlight (i.e., solar noise).

[0077] Moreover, as for the time size of this second receiving time window C, the inventors have learned through research that although there is no optimal time setting, it will be limited by the laser radar frame rate. For example, the laser point cloud will be refreshed 10 times per second (that is, 10Hz frame rate). Therefore, the detection time only needs to be completed within one emission and return cycle, that is, the sum of the first emission time window A, the first receiving time window B and the second receiving time window C is set to be less than one emission and reception cycle, wherein the emission and reception cycle refers to the time length from the emission of the infrared laser to the reception of the reflected wave of the infrared laser. In addition, the inventors have also found that the longer the time window is set, the better the detection effect will be. This is because the shorter the time, the more susceptible it is to the influence of other environmental noise.

[0078] As described above, according to the lane line detection method and laser radar of the present invention, a new signal acquisition stage (receiving solar noise) and a new signal processing stage (detecting the echo intensity of solar noise) are added to the existing laser radar. In this way, since the solar noise is uniform and the reflection characteristics of the lane line and the ground are different (i.e., the reflectivity is different), the lane line reflection wave can be easily extracted from the reflection waves of the ground and the lane line by means of the noise energy level of the sunlight.

[0079] Furthermore, since the noise level of sunlight is independent of the distance between the road and the LiDAR, lane lines can be extracted from the ground without reducing the maximum lane detection range. The inventors have found through measured data that there are three situations in the LiDAR lane line detection in the prior art:

[0080] (1) Without ground filtering, the maximum lane detection range is 175 meters;

[0081] (2) When ground filtering is partially applied, the maximum lane detection range is 117 meters;

[0082] (3) When ground filtering is fully applied, the maximum lane detection range is 64 meters.

[0083] Here, the so-called application of ground filtering in the prior art refers to filtering the ground reflection waves in the laser radar point cloud echo intensity view using the intensity histogram.

[0084] Compared with the laser radar in the prior art, by adopting the present invention to achieve ground filtering by receiving and detecting solar noise, the maximum lane line detection range can still be guaranteed to be 162 meters, which is 2.5 times higher than the 64 meters in the case (3) of the prior art.

[0085] Furthermore, the lane line detection method and laser radar of the present invention can more accurately detect lane lines by taking advantage of the present invention in the following situations:

[0086] (1) Under abnormal camera conditions (e.g., dark light conditions, direct light conditions);

[0087] (2) In the case of common failures of the camera components (e.g., mirror surfaces and human camera manipulation);

[0088] (3) Solve the problems caused by lane detection based on lidar echo intensity, such as incorrectly distinguishing lane lines and the ground within a certain range under a specific laser incident angle and accidentally filtering out distant lane lines during ground filtering.

[0089] The above are only specific implementations of the present application, but the protection scope of the present application is not limited thereto. Those skilled in the art can think of other feasible changes or substitutions based on the technical scope disclosed in the present application, and such changes or substitutions are all included in the protection scope of the present application. In the absence of conflict, the implementation modes of the present application and the features in the implementation modes can also be combined with each other. The protection scope of the present application shall be subject to the description of the claims.

Claims

1. A lane line detection method, characterized in that: The following steps are involved: Emit infrared laser; Receiving reflected waves of infrared laser, wherein the reflected waves of infrared laser include ground reflected waves reflected from the ground and lane line reflected waves reflected from the lane line; Forming a three-dimensional point cloud based on the ground reflection wave and the lane line reflection wave; Receiving solar noise, wherein the solar noise is formed by reflection waves generated by sunlight irradiating the ground and lane lines; detecting the echo intensity of the solar noise; Extracting a three-dimensional point cloud formed by lane line reflection waves from the three-dimensional point cloud based on the echo intensity of the solar noise; and Lane line detection is achieved based on the three-dimensional point cloud formed by the extracted lane line reflection wave.

2. The lane line detection method according to claim 1, characterized in that: The extracting of the three-dimensional point cloud formed by the lane line reflection wave from the three-dimensional point cloud based on the echo intensity of the solar noise comprises: For each point of the three-dimensional point cloud, adding the echo intensity of the solar noise as attribute information; and A three-dimensional point cloud formed by the lane line reflection wave is extracted based on the attribute information.

3. The lane line detection method according to claim 2, characterized in that: The extracting of the three-dimensional point cloud formed by the lane line reflection wave based on the attribute information comprises: The three-dimensional point cloud with relatively high echo intensity of the solar noise is extracted as the three-dimensional point cloud formed by the lane line reflection wave, and the three-dimensional point cloud with relatively low echo intensity of the solar noise is filtered as the three-dimensional point cloud formed by the ground reflection wave.

4. The lane line detection method according to claim 1, characterized in that: The time window for receiving the reflected wave of the infrared laser is set as the first receiving time window, The time window for receiving solar noise is set as a second receiving time window, The second receiving time window is located after the first receiving time window.

5. The lane line detection method according to claim 4, characterized in that: The time window for emitting infrared laser light is set as the first emission time window, The sum of the first transmitting time window, the first receiving time window and the second receiving time window is set to be less than one transmitting and receiving cycle, wherein the transmitting and receiving cycle refers to the length of time from transmitting the infrared laser to receiving the reflected wave of the infrared laser.

6. A laser radar, characterized in that: include: A transmitting unit, used for transmitting infrared laser; A scanning unit, used for reflecting the infrared laser to the ground and lane lines; A first receiving unit, configured to receive a reflected wave of an infrared laser, wherein the reflected wave of the infrared laser includes a ground reflected wave reflected from the ground and a lane line reflected wave reflected from the lane line; A second receiving unit is used to receive solar noise, wherein the solar noise is formed by reflection waves generated by sunlight irradiating the ground and the lane line; and A signal processing unit is used to form a three-dimensional point cloud based on the ground reflection wave and the lane line reflection wave. On the other hand, it is further used to detect the echo intensity of the solar noise and extract the three-dimensional point cloud formed by the lane line reflection wave from the three-dimensional point cloud based on the echo intensity of the solar noise, and realize lane line detection based on the three-dimensional point cloud formed by the extracted lane line reflection wave.

7. The laser radar according to claim 6, characterized in that The signal processing unit comprises: A three-dimensional point cloud forming submodule, used to form a three-dimensional point cloud based on the ground reflection wave and the lane line reflection wave; A solar noise detection submodule, used to detect the echo intensity of the solar noise; an extraction submodule, configured to extract a three-dimensional point cloud formed by a lane line reflection wave from the three-dimensional point cloud based on the echo intensity of the solar noise; and The lane line detection submodule is used to detect the lane line based on the three-dimensional point cloud formed by the extracted lane line reflection wave.

8. The laser radar according to claim 7, characterized in that: The extraction submodule adds the echo intensity of the solar noise as attribute information to each point of the three-dimensional point cloud, and extracts the three-dimensional point cloud formed by the lane line reflection wave based on the attribute information.

9. The laser radar according to claim 8, characterized in that The extraction submodule extracts the three-dimensional point cloud with relatively high echo intensity of the solar noise as the three-dimensional point cloud formed by the lane line reflection wave, and filters the three-dimensional point cloud with relatively low echo intensity of the solar noise as the three-dimensional point cloud formed by the ground reflection wave.

10. The laser radar according to claim 6, characterized in that: The time window in which the first receiving unit receives the reflected wave of the infrared laser is set as a first receiving time window, The time window for the second receiving unit to receive solar noise is set as a second receiving time window, The second receiving time window is located after the first receiving time window.

11. The laser radar according to claim 10, characterized in that: The time window in which the emitting unit emits infrared laser light is set as a first emitting time window, The sum of the first transmitting time window, the first receiving time window and the second receiving time window is set to be less than one transmitting and receiving cycle, wherein the transmitting and receiving cycle refers to the length of time from transmitting the infrared laser to receiving the reflected wave of the infrared laser.

12. A computer readable medium having a computer program stored thereon, characterized in that: When the computer program is executed by a processor, the lane line detection method according to any one of claims 1 to 5 is implemented.

13. A computer device comprising a storage module, a processor, and a computer program stored in the storage module and executable on the processor, characterized in that: When the processor executes the computer program, the lane line detection method according to any one of claims 1 to 5 is implemented.