Intersection processing method of ground line, line marking machine and computer storage medium

Abstract

The application discloses a ground line intersection processing method, a line marking machine and a computer storage medium. The line marking machine comprises a vision unit. The ground line intersection processing method comprises the following steps: acquiring a current detection image by the vision unit, and identifying a ground line region from the detection image; judging whether the line marking machine is currently in a ground line intersection scene according to geometric features of the ground line region and position information of the line marking machine; when it is determined that the line marking machine is in the ground line intersection scene, performing branch separation processing on the ground line region according to the geometric features and attitude information of the line marking machine, and obtaining a main direction ground line region; performing lateral deviation fitting on the main direction ground line region and a preset target ground line region, and performing deviation correction control on the line marking machine. The application can ensure the accuracy and stability of lateral deviation calculation in the ground line intersection scene.

Description

Technical Field

[0001] This application relates to the field of line marking technology, specifically to a method for processing the intersection of ground lines, a line marking machine, and a computer storage medium. Background Technology

[0002] Currently, when marking lines on the ground, it is necessary to detect and adjust deviations during the operation of the marking equipment to ensure the relative accuracy between the sprayed position and the target ground line. In existing solutions, manual calibration is typically performed using auxiliary equipment such as lasers to ensure that the marking equipment's direction of travel is consistent with the target ground line. With the increasing demand for automated construction, a vision-based correction scheme can also be adopted. This involves using cameras to capture ground images and employing methods such as image segmentation, boundary extraction, centerline fitting, or geometric calculations to obtain the deviation between the marking equipment and the target ground line, and then using this information for correction control.

[0003] However, in actual operations, ground lines often present complex scenarios such as right-angle corners and path intersections. Visual correction schemes are easily interfered with in such scenarios, which in turn affects the accuracy and stability of the lateral deviation calculation between the visual correction scheme and the target ground line. Summary of the Invention

[0004] In view of this, this application provides a method for processing intersections of ground lines, a marking machine, and a computer storage medium to ensure the accuracy and stability of lateral deviation calculation in ground line intersection scenarios. The technical solution of this application is as follows: The first aspect of this application provides a ground line intersection processing method applied to a line marking machine. The line marking machine includes a vision unit. The ground line intersection processing method includes: acquiring a current detection image through the vision unit and identifying a ground line region from the detection image; determining whether the line marking machine is currently in a ground line intersection scene based on the geometric features of the ground line region and the position information of the line marking machine; when it is determined to be in a ground line intersection scene, performing branch separation processing on the ground line region based on the geometric features and the posture information of the line marking machine to obtain a main direction ground line region; performing lateral deviation fitting between the main direction ground line region and a preset target ground line region, and performing correction control of the line marking machine.

[0005] In one embodiment of this application, the geometric features include connected intersection structures, L-shaped bend structures, T-shaped branch structures, multi-line proximity structures, boundary abrupt change structures, and / or concave corner point structures.

[0006] In one embodiment of this application, determining whether the line marking machine is currently in a ground line intersection scene based on the geometric features of the ground line area and the position information of the line marking machine includes: obtaining the distance between the line marking machine and the ground line intersection scene based on the position information and the target ground line area; when the distance is determined to be less than a preset value, extracting the connected intersection structure, the L-shaped turning structure, the T-shaped branch structure, the multi-line approaching structure, the boundary abrupt change structure, and / or the concave corner point structure from the ground line area; and determining that the line marking machine is in the ground line intersection scene when the connected intersection structure, the L-shaped turning structure, the T-shaped branch structure, the multi-line approaching structure, the boundary abrupt change structure, and / or the concave corner point structure are extracted.

[0007] In one embodiment of this application, the step of performing branch separation processing on the ground line region based on the geometric features and the attitude information of the marking machine to obtain the main direction ground line region includes: determining the main direction of the marking machine based on the attitude information; determining the branch regions of the ground line region based on the connecting intersection structure, the L-shaped turning structure, the T-shaped branch structure, the multi-line approach structure, the boundary abrupt change structure and / or the concave corner point structure; segmenting the ground line region based on the main direction and the branch regions, removing the branch regions, and retaining the main direction ground line region in the main direction.

[0008] In one embodiment of this application, identifying the ground line region from the detected image includes: processing the detected image using a preset image segmentation algorithm based on ground line features to obtain multiple valid window images; when the number of valid window images is greater than or equal to a preset value, extracting the ground line region from the multiple valid window images; when the number of valid window images is less than the preset value, discarding the detected image of the current frame and obtaining the detected image of the next frame to re-process the intersection points.

[0009] In one embodiment of this application, the method further includes: after obtaining the ground line region, extracting the boundary to be detected and the centerline from the ground line region; when it is determined that the angle between the boundary to be detected and the preset target boundary is greater than a preset angle, and / or the centerline cannot be extracted, discarding the detection image of the current frame, and obtaining the detection image of the next frame to re-process the intersection point.

[0010] In one embodiment of this application, the method further includes: after obtaining the main direction ground line region, extracting the centerline from the main direction ground line region; and correcting the boundary of the main direction ground line region according to the centerline and the preset ground line width.

[0011] In one embodiment of this application, it further includes: when it is determined that the scene is not at the intersection of ground lines, performing lateral deviation fitting based on the ground line area and the preset target ground line area, and the deviation correction control of the marking machine.

[0012] A second aspect of this application provides a line marking machine, including a vision unit and a controller, wherein the vision unit is connected to the controller, and the controller is used to execute the ground line intersection processing method.

[0013] A third aspect of this application provides a computer storage medium storing a computer program, which, when executed by a processor, causes the processor to perform the ground line intersection processing method.

[0014] It is understood that in the ground line intersection processing method of this application embodiment, when it is determined that the marking machine is in the ground line intersection scene through the geometric features of the ground line area and the position information of the marking machine, the ground line area identified in the detection image is subjected to branch separation processing. The ground line area in the main direction is retained and the preset target ground line area is fitted with lateral deviation, and the marking machine is corrected. This can avoid the influence of the ground line area in the branch direction on the lateral deviation calculation, thereby improving the accuracy and stability of the lateral deviation calculation. Attached Figure Description

[0015] Figure 1 This is a flowchart illustrating a ground line intersection processing method provided in an embodiment of this application.

[0016] Figure 2 This is a flowchart illustrating a method for determining the intersection of ground lines according to an embodiment of this application.

[0017] Figure 3 This is a flowchart illustrating a method for obtaining a main direction ground line area according to an embodiment of this application.

[0018] Figure 4 This is a schematic flowchart of a ground line area identification method provided in an embodiment of this application.

[0019] Figure 5 This is a flowchart illustrating the second method for handling the intersection of ground lines provided in this application embodiment.

[0020] Figure 6 This is a flowchart illustrating the third method for handling the intersection of ground lines provided in this application embodiment.

[0021] Figure 7 This is a flowchart illustrating the fourth method for handling the intersection of ground lines provided in this application embodiment.

[0022] Figure 8This is a schematic block diagram of a marking machine provided in an embodiment of this application. Detailed Implementation

[0023] It should be noted that in the embodiments of this application, "at least one" means one or more, and "more than one" means two or more. "And / or" describes the relationship between related objects, indicating that three relationships can exist. For example, A and / or B can represent: A existing alone, A and B existing simultaneously, or B existing alone, where A and B can be singular or plural. The terms "first," "second," "third," "fourth," etc. (if present) in the specification, claims, and drawings of this application are used to distinguish similar objects, not to describe a specific order or sequence.

[0024] It should also be noted that the methods disclosed in the embodiments of this application or the methods shown in the flowcharts include one or more steps for implementing the method. Without departing from the scope of the claims, the execution order of multiple steps can be interchanged, and some steps can also be deleted.

[0025] Currently, when marking lines on the ground, it is necessary to detect and adjust deviations during the operation of the marking equipment to ensure the relative accuracy between the sprayed position and the target ground line. In existing solutions, manual calibration is typically performed using auxiliary equipment such as lasers to ensure that the marking equipment's direction of travel is consistent with the target ground line. With the increasing demand for automated construction, a vision-based correction scheme can also be adopted. This involves using cameras to capture ground images and employing methods such as image segmentation, boundary extraction, centerline fitting, or geometric calculations to obtain the deviation between the marking equipment and the target ground line, and then using this information for correction control.

[0026] However, in actual operations, ground lines often present complex scenarios such as right-angle corners and path intersections. Visual correction schemes are easily interfered with in such scenarios, which in turn affects the accuracy and stability of the lateral deviation calculation between the visual correction scheme and the target ground line.

[0027] This application provides a method for processing intersections of ground lines, a marking machine, and a computer storage medium to ensure the accuracy and stability of lateral deviation calculation in ground line intersection scenarios.

[0028] Please refer to Figure 1 , Figure 1 This is a flowchart illustrating a ground line intersection processing method provided in an embodiment of this application. The ground line intersection processing method is applied to a marking machine, which includes a vision unit. The ground line intersection processing method specifically includes the following steps: Step S11: Obtain the current detection image through the vision unit and identify the ground line region from the detection image.

[0029] In this embodiment, the vision unit of the line marking machine is used to acquire a detection image of the target area. The detection image may include old ground line areas. By detecting the boundary position and width of these ground line areas, the line marking machine can accurately cover them during the repainting process. The target area includes the area in front of the line marking machine; that is, the vision unit may include a camera to acquire a detection image of the area in front of the line marking machine.

[0030] The line marking machine may also include a controller connected to the aforementioned vision unit. The controller receives the detection images from the vision unit to identify the ground line area and its boundary position and width.

[0031] In some embodiments, an image segmentation algorithm can be used to identify ground line regions in the detection image. For example, the controller of the line marking machine can pre-store the aforementioned image segmentation algorithm and the features of the ground line regions. After receiving the detection image transmitted by the vision unit, the controller segments the detection image according to the image segmentation algorithm, and then selects a valid window image from many segmented images based on the features of the ground line regions, thereby obtaining an image containing only the ground line regions, and thus completing the identification of the ground line regions.

[0032] Step S12: Based on the geometric features of the ground line area and the position information of the marking machine, determine whether the marking machine is currently in the ground line intersection scene.

[0033] In this embodiment, after identifying and extracting the ground line region in the detection image, the controller further identifies the geometric features of the ground line region. These geometric features include the connected intersection structure, L-shaped bend structure, T-shaped branch structure, multi-line proximity structure, boundary abrupt structure, and / or concave corner structure of the ground line region. The geometric features also include the boundary, centerline, and curvature of the ground line region. The controller can first identify the centerline of the ground line region and further identify whether there are multiple centerlines, whether the centerlines exhibit bends or branches, etc., to identify the aforementioned connected intersection structure, L-shaped bend structure, T-shaped branch structure, multi-line proximity structure, boundary abrupt structure, and / or concave corner structure.

[0034] After identifying the geometric features of the ground line area, the controller determines whether the marking machine is currently in a ground line intersection scenario based on these features and the machine's position. A ground line intersection scenario refers to a pre-defined distance in front of the marking machine, including connected intersection areas, L-shaped bend areas, T-shaped branch areas, areas with multiple lines approaching each other, abrupt boundary changes, or concave corner areas, etc., without specific limitations. In a ground line intersection scenario, the ground line area includes the main direction ground line area and at least one branch line area. The main direction ground line area is the portion of the ground line area aligned with the marking machine's current working direction. The branch line area is a branch of the ground line area that is not aligned with the marking machine's current working direction.

[0035] The position information of the line marking machine can be obtained through the positioning unit. That is, the line marking machine also includes a positioning unit. The controller is connected to the positioning unit and obtains the position information of the line marking machine in real time through the positioning unit.

[0036] Step S13: When the scene is determined to be at the intersection of ground lines, perform branch separation processing on the ground line area based on geometric features and the attitude information of the marking machine to obtain the main direction ground line area.

[0037] In this embodiment, the line marking machine may further include an inertial detection unit, which is used to acquire the attitude information of the line marking machine, including acceleration and heading angle. The controller acquires the heading angle of the line marking machine through the inertial detection unit, thereby determining the main direction of the line marking machine. Further, based on the main direction of the line marking machine and the geometric features of the ground line area, the controller determines the main direction ground line area and at least one branch line area within the ground line area.

[0038] In this process, after the controller determines the main direction ground line area and at least one branch line area in the ground line area, it separates and removes at least one branch line area, retaining the main direction ground line area, thereby avoiding the influence of the branch line area on subsequent deviation calculations.

[0039] Step S14: Perform lateral deviation fitting based on the main direction ground line area and the preset target ground line area, and control the deviation correction of the marking machine.

[0040] In this embodiment, the target ground line area includes at least the centerline, boundary, start and end point positions, curvature change information of the centerline, and curvature change information of the boundary, constituting the entire specification of the marking machine in this marking operation. This allows the controller to perform marking operations based on the target ground line area and the real-time identified ground line area. Specifically, after obtaining the target ground line area, the controller controls the marking machine to perform the marking operation. During the marking operation, the controller also controls the vision unit, positioning unit, inertial detection unit, and nozzle unit to work collaboratively, detecting the actual ground line area ahead in real time and comparing and correcting it with the target ground line area to ensure that the actual marking accurately covers the target marking area.

[0041] It is understood that in the ground line intersection processing method of this application embodiment, when it is determined that the marking machine is in the ground line intersection scene through the geometric features of the ground line area and the position information of the marking machine, the ground line area identified in the detection image is subjected to branch separation processing. The ground line area in the main direction is retained and the preset target ground line area is fitted with lateral deviation, and the marking machine is corrected. This can avoid the influence of the ground line area in the branch direction on the lateral deviation calculation, thereby improving the accuracy and stability of the lateral deviation calculation.

[0042] Please refer to Figure 2 , Figure 2 A flowchart illustrating a method for determining ground line intersections in an embodiment of this application is shown, specifically including the following steps: Step S21: Based on the location information and the target ground line area, obtain the distance between the intersection point of the line marking machine and the ground line.

[0043] In this embodiment of the application, after the controller obtains the position information of the line marking machine in real time through the positioning unit during the operation, it can use the position information to match the target ground line area, identify the current position of the line marking machine in the target ground line area, and then obtain the distance between the ground line intersection scene in the main direction. The ground line intersection scene can be a ground line connecting and intersecting area, L-shaped turning area, T-shaped branch area, multi-line approaching area, boundary change area, or concave corner point area that the line marking machine is about to reach in the main direction, etc., which is not limited here.

[0044] Step S22: When the distance is less than the preset value, extract the connected intersection structure, L-shaped turning structure, T-shaped branch structure, multi-line approach structure, boundary abrupt change structure and / or concave corner point structure from the ground line area.

[0045] In this embodiment of the application, when the controller determines that the distance between the line marking machine and the intersection of the ground line is less than a preset value, it means that the line marking machine is very close to the intersection of the ground line. Then, it can extract the connected intersection structure, L-shaped turning structure, T-shaped branch structure, multi-line approach structure, boundary abrupt change structure and / or concave corner point structure from the current ground line area.

[0046] Step S23: When a connected intersection structure, L-shaped bend structure, T-shaped branch structure, multi-line approach structure, boundary abrupt change structure and / or concave corner point structure is extracted, determine that it is in a ground line intersection scene.

[0047] It is understandable that when the controller successfully extracts connected intersection structures, L-shaped turning structures, T-shaped branch structures, multi-line approach structures, boundary abrupt change structures, and / or concave corner point structures from the ground line area, it indicates that the marking machine is in a ground line intersection scenario.

[0048] In this embodiment, the controller only performs geometric feature recognition and extraction of the ground line area and makes a judgment on the ground line intersection scene after determining the scene where the line marking machine is close to the intersection of the ground lines by using location information. This can reduce the amount of computation of the controller and thus reduce the power consumption of the line marking machine.

[0049] Please refer to Figure 3 , Figure 3 A flowchart illustrating a method for obtaining a main direction ground line region, provided in this application embodiment, specifically includes the following steps: Step S31: Determine the main direction of the marking machine based on the attitude information.

[0050] In this embodiment of the application, the above-mentioned attitude information includes the acceleration and heading angle of the line marking machine, and the controller can determine the main direction of the current operation of the line marking machine based on the heading angle of the line marking machine.

[0051] Step S32: Determine the branch areas of the ground line region based on the interconnected intersection structure, L-shaped turning structure, T-shaped branching structure, multi-line proximity structure, boundary abrupt change structure and / or concave corner point structure.

[0052] Step S33: Divide the ground line area according to the main direction and the branch road area, remove the branch road area, and retain the main direction ground line area in the main direction.

[0053] In this embodiment, the controller can determine the branch area and the main direction ground line area in the ground line area based on the main direction and geometric features, and perform segmentation processing on the ground line area to remove the branch area and retain the main direction ground line area in the main direction, thereby avoiding the branch area from affecting the subsequent lateral deviation calculation.

[0054] Please refer to Figure 4 , Figure 4 A flowchart illustrating a ground line region identification method provided in this application embodiment specifically includes the following steps: Step S41: Process the detected image using a preset image segmentation algorithm based on the ground line features to obtain multiple effective window images.

[0055] In this embodiment, the aforementioned ground line features include the ground line's color, reflectivity, and texture, etc. The ground line's color can be white or yellow, etc., and is not limited here. The controller processes the detection image using an image segmentation algorithm based on the preset ground line features, dividing the detection image into multiple window images, and retaining multiple valid window images that match the ground line features.

[0056] Step S42: When the number of valid window images is greater than or equal to a preset value, extract the ground line region from multiple valid window images.

[0057] Step S43: When the number of valid window images is less than a preset value, discard the detection image of the current frame and obtain the detection image of the next frame to re-process the intersection point.

[0058] In this embodiment, when the controller determines that the number of valid window images of the current detection image is greater than or equal to a preset value, it can determine that the detection image includes a ground line region and extract the ground line region from the valid window images. When the number of valid window images is less than the preset value, it indicates that the detected image is not a ground line region, but may be other noise with ground line characteristics. Discarding the current frame's detection image as noise can avoid affecting subsequent lateral deviation calculations and ensure the continuity of the line marking machine's correction control.

[0059] Please refer to Figure 5 , Figure 5 A flowchart illustrating the second ground line intersection processing method provided in this application embodiment specifically includes the following steps: Step S51: Obtain the current detection image through the vision unit and identify the ground line region from the detection image.

[0060] In this embodiment of the application, step S51 is the same as step S11, and will not be repeated here.

[0061] Step S52: After obtaining the ground line region, extract the boundary and centerline to be detected from the ground line region.

[0062] Step S53: If the angle between the boundary to be detected and the preset target boundary is greater than the preset angle, and / or the centerline cannot be extracted, discard the detection image of the current frame, obtain the detection image of the next frame, re-process the intersection point, and return to step S51.

[0063] It is understandable that when the controller determines that the angle between the boundary to be detected and the preset target boundary is greater than the preset angle, and / or the centerline cannot be extracted, that is, what is extracted from the detection image is not the ground line area, but other noise with ground line characteristics, the detection image of the current frame that is noise is discarded, which can avoid affecting the subsequent lateral deviation calculation and ensure the continuity of the line marking machine's correction control.

[0064] Step S54: Based on the geometric features of the ground line area and the position information of the marking machine, determine whether the marking machine is currently in the ground line intersection scene.

[0065] Step S55: When the scene is determined to be at the intersection of ground lines, perform branch separation processing on the ground line area based on geometric features and the attitude information of the marking machine to obtain the main direction ground line area.

[0066] Step S56: Perform lateral deviation fitting based on the main direction ground line area and the preset target ground line area, and control the deviation correction of the marking machine.

[0067] In this embodiment of the application, steps S54 to S56 are the same as steps S12 to S14, and will not be repeated here.

[0068] Please refer to Figure 6 , Figure 6 A flowchart illustrating the third ground line intersection processing method provided in this application embodiment specifically includes the following steps: Step S61: Obtain the current detection image through the vision unit and identify the ground line region from the detection image.

[0069] Step S62: Based on the geometric features of the ground line area and the position information of the marking machine, determine whether the marking machine is currently in the ground line intersection scene.

[0070] Step S63: When the scene is determined to be at the intersection of ground lines, perform branch separation processing on the ground line area based on geometric features and the attitude information of the marking machine to obtain the main direction ground line area.

[0071] In this embodiment of the application, steps S61 to S63 are the same as steps S11 to S13, and will not be repeated here.

[0072] Step S64: After obtaining the main direction ground line area, extract the centerline from the main direction ground line area.

[0073] Step S65: Correct the boundary of the main direction ground line area according to the centerline and the preset ground line width.

[0074] In this embodiment, after obtaining the main direction ground line region, the controller can further identify the current width of the main direction ground line region, calculate the deviation between the current width and the preset ground line width, and determine whether the deviation is less than the preset deviation value. If the deviation is greater than or equal to the preset deviation value, it is considered an abnormal detection, and the extracted main direction ground line region can be determined to be noise. Discarding the detection image of the current frame containing noise avoids affecting subsequent lateral deviation calculations and ensures the continuity of the line marking machine's correction control. For example, if the preset ground line width is A, the controller determines that the width of the main direction ground line region is 0.35. A and 1.65 When the distance is between A and B, the area along the ground line in the main direction is considered valid; otherwise, it is considered invalid noise.

[0075] Furthermore, the controller determines that the deviation is less than a preset deviation value, or the width is within 0.35. A and 1.65 When the distance is between A, the main direction ground line area is determined to be valid, and the boundary position of the main direction ground line area is corrected to leftV = centerV - A / 2, rightV = centerV + A / 2, where leftV is the left boundary, rightV is the right boundary, and centerV is the centerline position.

[0076] Step S66: Perform lateral deviation fitting based on the main direction ground line area and the preset target ground line area, and control the deviation correction of the marking machine.

[0077] Please refer to Figure 7 , Figure 7 A flowchart illustrating the fourth ground line intersection processing method provided in this application embodiment specifically includes the following steps: Step S71: Obtain the current detection image through the vision unit and identify the ground line region from the detection image.

[0078] Step S72: Based on the geometric features of the ground line area and the position information of the marking machine, determine whether the marking machine is currently in the ground line intersection scene.

[0079] Step S73: When the scene is determined to be at the intersection of ground lines, perform branch separation processing on the ground line area based on geometric features and the attitude information of the marking machine to obtain the main direction ground line area.

[0080] Step S74: Perform lateral deviation fitting based on the main direction ground line area and the preset target ground line area, and control the deviation correction of the marking machine.

[0081] In this embodiment of the application, steps S71 to S64 are the same as steps S11 to S14, and will not be described again here.

[0082] Step S75: When it is determined that the scene is not at the intersection of the ground line, the lateral deviation is fitted according to the ground line area and the preset target ground line area, and the deviation correction control of the marking machine is performed.

[0083] Please refer to Figure 8 , Figure 8 This is a schematic block diagram of a line marking machine provided in an embodiment of this application. The line marking machine 800 includes a vision unit 810 and a controller 820. The vision unit 810 is connected to the controller 820, and the controller 820 is used to execute the intersection processing method of ground lines in any of the above embodiments.

[0084] It is understood that the beneficial effects of the above-mentioned line marking machine can be compared with the beneficial effects of the ground line intersection processing method in the foregoing embodiments, and will not be repeated here.

[0085] This application embodiment also provides a computer storage medium storing a computer program that, when executed by a processor, causes the processor to perform the above-described ground line intersection processing method.

[0086] In the above embodiments, implementation can be achieved entirely or partially through software, hardware, firmware, or any combination thereof. When implemented using software, it can be implemented entirely or partially as a computer program product. The computer program product includes one or more computer instructions. When the computer program instructions are loaded and executed on a computer, all or part of the processes or functions described in the embodiments of this application are generated. The computer can be a general-purpose computer, a special-purpose computer, a computer network, or other programmable device. The computer instructions can be stored in a computer storage medium or transmitted through the computer storage medium. The computer instructions can be transmitted from one website, computer, server, or data center to another website, computer, server, or data center via wired (e.g., coaxial cable, fiber optic, Digital Subscriber Line (DSL)) or wireless (e.g., infrared, wireless, microwave, etc.) means. The computer storage medium can be any available medium that a computer can access or a data storage device such as a server or data center that integrates one or more available media. The available media may be magnetic media (e.g., floppy disks, hard disks, magnetic tapes), optical media (e.g., Digital Versatile Discs (DVDs)), or semiconductor media (e.g., solid-state disks (SSDs)).

[0087] Those skilled in the art will understand that all or part of the processes in the methods of the above embodiments can be implemented by a computer program instructing related hardware. This program can be stored in a computer-readable storage medium, and when executed, it can include the processes of the embodiments of the methods described above. The aforementioned storage medium includes various media capable of storing program code, such as ROM, RAM, magnetic disks, or optical disks. Unless otherwise specified, the technical features of this embodiment and its implementation can be combined arbitrarily.

[0088] The embodiments described above are merely preferred embodiments of this application and are not intended to limit the scope of this application. Any modifications and improvements made by those skilled in the art to the technical solutions of this application without departing from the spirit of this application should fall within the protection scope defined by the claims of this application.

Claims

1. A method for processing the intersection of ground lines, characterized in that, Applied to a line marking machine, the line marking machine includes a vision unit, and the method for processing the intersection of the ground lines includes: The visual unit acquires the current detection image and identifies ground line regions from the detection image; Based on the geometric features of the ground line area and the position information of the marking machine, it is determined whether the marking machine is currently in a ground line intersection scenario; When it is determined that the scene is at the intersection of ground lines, the ground line area is subjected to branch separation processing based on the geometric features and the attitude information of the marking machine to obtain the main direction ground line area; The lateral deviation is fitted based on the main direction ground line area and the preset target ground line area, and the deviation correction control of the marking machine is performed.

2. The method for processing the intersection of ground lines as described in claim 1, characterized in that, The geometric features include connected intersection structures, L-shaped bend structures, T-shaped branch structures, multi-line proximity structures, boundary abrupt change structures, and / or concave corner point structures.

3. The method for processing the intersection of ground lines as described in claim 2, characterized in that, The step of determining whether the line marking machine is currently in a ground line intersection scenario based on the geometric features of the ground line area and the position information of the line marking machine includes: Based on the location information and the target ground line area, the distance between the intersection point of the marking machine and the ground line is obtained; When the distance is determined to be less than a preset value, the connected intersection structure, the L-shaped turning structure, the T-shaped branch structure, the multi-line approach structure, the boundary abrupt change structure, and / or the concave corner point structure are extracted from the ground line area; When the connected intersection structure, the L-shaped turning structure, the T-shaped branch structure, the multi-line approach structure, the boundary abrupt change structure, and / or the concave corner point structure are extracted, it is determined that the scene is the intersection of the ground lines.

4. The method for handling the intersection of ground lines as described in claim 2, characterized in that, The step of performing branch separation processing on the ground line region based on the geometric features and the attitude information of the marking machine to obtain the main direction ground line region includes: The main direction of the marking machine is determined based on the attitude information; The branch areas of the ground line region are determined based on the connected intersection structure, the L-shaped turning structure, the T-shaped branching structure, the multi-line approach structure, the boundary abrupt change structure, and / or the concave corner point structure. The ground line area is segmented according to the main direction and the branch area, the branch area is removed, and the ground line area in the main direction is retained.

5. The method for processing the intersection of ground lines as described in claim 1, characterized in that, The step of identifying ground line regions from the detected image includes: Based on the ground line features, the detected image is processed by a preset image segmentation algorithm to obtain multiple effective window images; When the number of valid window images is greater than or equal to a preset value, the ground line region is extracted from the multiple valid window images; When the number of valid window images is determined to be less than the preset value, the detected image of the current frame is discarded, and the detected image of the next frame is obtained to re-process the intersection point.

6. The method for processing the intersection of ground lines as described in claim 1, characterized in that, Also includes: After obtaining the ground line region, the boundary and centerline to be detected are extracted from the ground line region; If the angle between the boundary to be detected and the preset target boundary is greater than a preset angle, and / or the centerline cannot be extracted, the detection image of the current frame is discarded, and the detection image of the next frame is obtained to re-process the intersection point.

7. The method for processing the intersection of ground lines as described in claim 1, characterized in that, Also includes: After obtaining the main direction ground line region, the centerline is extracted from the main direction ground line region; Based on the centerline and the preset ground line width, the boundary of the main direction ground line area is corrected.

8. The method for processing the intersection of ground lines as described in claim 1, characterized in that, Also includes: When it is determined that the scene is not at the intersection of the ground lines, the lateral deviation is fitted based on the ground line area and the preset target ground line area, and the line marking machine is controlled to correct the deviation.

9. A marking machine, characterized in that, It includes a vision unit and a controller, the vision unit being connected to the controller, the controller being used to perform the ground line intersection processing method as described in any one of claims 1 to 8.

10. A computer storage medium, characterized in that, The computer storage medium stores a computer program, which, when executed by a processor, causes the processor to perform the ground line intersection processing method as described in any one of claims 1 to 8.

Images