Continuous groove trajectory tracking method and system based on line structure light point cloud

The method uses line structured light point clouds to accurately and efficiently track continuous grooves by calculating height and mutation features, addressing detection inefficiencies and accuracy issues in existing technologies.

CN119068022AActive Publication Date: 2024-12-03HUAZHONG UNIV OF SCI & TECH +1
View PDF 4 Cites 0 Cited by

Patent Information

Application Number
CN202411211525.X
Authority / Receiving Office
CN · China
Patent Type
Applications(China)
Current Assignee / Owner
Filing Date
2024-08-30
Publication Date
2024-12-03
Estimated Expiration
2044-08-30

AI Technical Summary

Technical Problem

Existing methods for tracking continuous groove trajectories in industrial settings face issues such as low detection efficiency, poor generalization, and insufficient accuracy due to image resolution limitations, occlusion, and computational complexity, especially in complex deformations and multi-view template matching.

Method used

A method using line structured light point clouds to scan and calculate features like height changes and mutations, identify groove feature points, and recursively form continuous trajectories by searching along laser lines, ensuring accurate and efficient trajectory generation.

Benefits of technology

The method achieves high-accuracy, real-time detection of continuous grooves with adaptable deformation handling, eliminating the need for standard models and enhancing automated production capabilities.

✦ Generated by Eureka AI based on patent content.

Smart Images

  • Figure CN119068022A_ABST
    Figure CN119068022A_ABST
Patent Text Reader

Abstract

The invention belongs to the field of machine vision detection, and particularly discloses a continuous groove trajectory tracking method and system based on line structure light point cloud. The method comprises the steps that S100, a line laser scanner is used for scanning in the direction of a groove, and point cloud data formed by splicing all laser line point clouds are obtained; step S200, calculating features on each laser line, wherein the features comprise a feature reflecting height change and a feature of height mutation generated by a horizontal line; s300, groove feature points on the laser lines are judged according to the preset height fall range and the sudden change degree; and step S400, searching from the starting point, recursively forming continuous track points from the starting point along the laser rays according to the continuity of the track of the groove and the feature points, and obtaining the track of the continuous groove. The method can realize trajectory tracking with the same precision level as the sensor, has the advantages of high precision and real-time detection, and is suitable for trajectory generation of various continuous grooves.
Need to check novelty before this filing date? Find Prior Art

Description

Technical Field

[0001] The present invention belongs to the field of machine vision, and more specifically, relates to a method and system for tracking the trajectory of a continuous groove based on a line structured light point cloud. Background Art

[0002] In industrial production and automated manufacturing, detecting and processing the trajectory of grooves (such as grooves formed at weld joints, grooves at product assembly joints, etc.) is an important task. Image-based processing methods have problems such as insufficient image resolution and poor accuracy, occlusion at complex trajectory photography positions, and poor robustness of multi-view template matching to deformation, which limits the extraction of groove trajectories and affects accuracy and reliability. Methods based on point cloud volume, center of gravity, PCA principal components, and geometric shapes of circumscribed sphere rectangles are difficult to accurately find the unique features that distinguish grooves from others. Methods based on feature descriptors such as PFH (point feature histogram), FPFH (fast point feature histogram), and SHOT (rotation-invariant feature) have the problem of large computational complexity and poor real-time performance. Methods based on registration have the problem of poor adaptability to deformation, the need for standard models, and no generalization ability for similar features.

[0003] Therefore, it is urgent to propose a new method for the trajectory generation problem of continuous concave grooves, which can uniformly solve the problem of continuous groove trajectory extraction while taking into account efficiency and accuracy. Summary of the invention

[0004] In response to the above defects or improvement needs of the prior art, the present invention provides a method and system for tracking the trajectory of a continuous groove based on a line structured light point cloud, the purpose of which is to solve the problems of low detection efficiency, lack of generalization, insufficient accuracy and inability to meet the needs of automated production in the prior art of continuous trajectory generation of concave grooves through teaching.

[0005] To achieve the above object, according to one aspect of the present invention, a method for tracking a continuous groove trajectory based on a line structured light point cloud is provided, comprising the following steps:

[0006] Step S100, using a line laser scanner to scan along the direction of the groove to obtain point cloud data composed of point clouds of various laser lines;

[0007] Step S200, calculating the features of each laser line, including features reflecting the magnitude of height changes and features reflecting height mutations of horizontal lines;

[0008] Step S300, determining the groove feature points on the laser line according to a preset height difference range and mutation degree;

[0009] Step S400, searching from the starting point, according to the continuity of the groove track, recursively forming continuous track points from the starting point along the laser line according to the feature points, and obtaining the track of the continuous groove.

[0010] Further, step S200 includes:

[0011] Step S210, calculating the height difference information of a laser line and calculating the peak point and peak value of the height difference information;

[0012] Step S220, calculating the variance ratio information of a laser line and calculating the peak point and peak value of the variance ratio information.

[0013] Further, in step S210, the depth data on a laser line is first represented as a discrete sequence; for each point P on the laser line i , calculate point P i The depth average of the left and right windows, and then find the absolute value of the difference between the depth averages of the left and right windows ΔH i ,Right now:

[0014] ΔH i =|mean(P i-n ,…,P i-1 )-mean(P i+1 ,…,P i+n )|

[0015] Among them, n represents the size of the window, mean() represents the average depth, P i-n Represents the point of the left window, P i+n Indicates the point in the right window; the peak point corresponds to the maximum value in the height difference information, and the peak value is the difference value corresponding to the peak point; by calculating the peak value of the height difference information sequence and its corresponding peak point index, the size of the height difference on the laser line is determined to reflect the contour of the groove;

[0016] In step S220, the sum of the variances of the left and right windows is calculated and compared with the variance of the bilateral window, that is:

[0017]

[0018] Among them, sum() means summation, and Var() means variance.

[0019] Further, step S300 includes:

[0020] Step S310, traverse the height drop peak index, if its drop range is greater than or equal to the preset height drop lower limit and less than or equal to the preset height drop upper limit, and there is a variance ratio peak index and the height drop peak index The absolute difference is less than or equal to the preset variance and the maximum peak difference distance of the height, then the height drop peak index is considered to be a groove point;

[0021] Step S320 , the variance search lower limit is decreased in sequence from the initial feature variance ratio according to the variance ratio decreasing amount until the groove point set is not empty and the feature variance ratio is greater than or equal to the lower limit of the feature variance ratio.

[0022] Further, step S310 includes:

[0023] The initial feature variance ratio and the variance ratio decrement are set. The initial feature variance ratio is set based on the pre-judgment of the groove imaging quality to ensure that normal grooves can be accurately identified under the condition of the initial feature variance ratio.

[0024] When the search feature variance ratio is greater than or equal to 1, if the groove point index was not found in the last search of the data on the laser line, the search feature variance ratio is subtracted by the decrement amount;

[0025] The search is performed according to the updated search feature variance ratio. If the groove point index cannot be found even with the smallest feature variance ratio, it is determined that there is no groove point on this laser line.

[0026] Further, step S400 includes:

[0027] Step S410, searching for a groove point on the next laser line within a search range according to an initial point on the initial line;

[0028] Step S420, accurately locate the groove point, update the trajectory point to search the next laser line until the termination line; specifically, the index of a point on the laser line is known, and the search range of the next laser line includes the index of the previous point ± the search range parameter; whenever a groove is located on a new laser line, the trajectory point is rotated toward the higher side of the groove so that it falls into the minimum point formed by the groove, and at the same time, the index of this trajectory point is updated to the index of the previous point.

[0029] Further, step S420 includes:

[0030] Step S421, take the left and right window points of the currently determined groove point, the x index of the current point is 0, convert the depth sequence information into the point cloud information of the actual interval, and express it in the xz coordinate system:

[0031] x=idx*x_resolution

[0032] z=height

[0033] Among them, idx represents the index corresponding to the point on the current laser line, x_resolution represents the resolution of the point on the current laser line, and height represents the z coordinate value of the point on the current laser line;

[0034] Step S422, rotating the sequence corresponding to xz by 45° around the origin toward the higher side of the groove, so as to ensure that the groove point becomes a local minimum point;

[0035] Step S423, finding the index k corresponding to the local minimum value in the sequence corresponding to xz;

[0036] Step S424, update the current track point index to:

[0037] idx′=idx-window+k

[0038] Among them, idx' represents the updated index of the point on the current laser line, and window represents the window size for precise positioning;

[0039] Step S425, update the previous point index to idx′.

[0040] Furthermore, the method further includes step S500 of offsetting the continuous trajectory points by a certain distance along a fixed direction or by a certain distance along the normal direction of the continuous trajectory points.

[0041] Further, step S500 includes:

[0042] Calculate the curvature ρ and normal C of the current trajectory;

[0043]

[0044] Where m represents the number of points in the neighborhood of the current point, i = 1 to m, Pi represents the i-th point in the neighborhood of the current point, P 0 represents the current point, x', y', z' represent the second-order derivatives of the xyz coordinates of the current point, x', y', z' represent the first-order derivatives of the xyz coordinates of the current point, and T represents transpose;

[0045] The trajectory point is deviated by a fixed distance along the lower side of the groove in the normal direction to obtain a new two-dimensional coordinate; on the depth map, the depth corresponding to the new two-dimensional coordinate is interpolated, and the new coordinate is used as the offset trajectory point.

[0046] According to another aspect of the present invention, a trajectory tracking system for continuous grooves based on line structured light point clouds is provided, comprising a memory, a processor and a computer program stored in the memory, wherein the processor executes the computer program to implement the steps of the trajectory tracking method for continuous grooves based on line structured light point clouds as described in any of the preceding items.

[0047] In general, the above technical solutions conceived by the present invention can achieve the following beneficial effects compared with the prior art:

[0048] (1) The method of the present invention calculates the features reflecting the size of the height change and the features of the height mutation produced by the horizontal line to identify the position of the mutation point, thereby ensuring the accurate analysis of the depth information of each laser line, thereby identifying the key feature points of the groove; then, searching from the starting point, according to the continuity of the groove trajectory, according to the feature points along the laser line from the starting point to form a continuous trajectory point, it can be scanned and tracked at the same time, so that a complete trajectory line can be traced.

[0049] (2) The present invention ensures that the trajectory is continuously generated from the starting laser line to the ending laser line, and the density of the trajectory points is determined by the search interval. The search interval multiplied by the x-axis laser point resolution is equal to the density of the trajectory points. Therefore, the density of the trajectory points can be adjusted by adjusting the search interval, thereby achieving trajectory tracking at the same level as the sensor accuracy. It has the advantages of high accuracy and real-time detection, and is suitable for trajectory generation of various types of continuous grooves. BRIEF DESCRIPTION OF THE DRAWINGS

[0050] Figure 1 It is a schematic diagram of the three-dimensional structure of the groove and the algorithm provided by the preferred embodiment of the present invention;

[0051] Figure 2 is a schematic diagram of a discrete data sequence formed by depth information on a laser line provided by a preferred embodiment of the present invention;

[0052] Figure 3 The preferred embodiment of the present invention provides Figure 2 Schematic diagram of height difference information and height difference peak value corresponding to discrete data;

[0053] Figure 4 The preferred embodiment of the present invention provides Figure 2 Schematic diagram of variance ratio information and variance ratio peak corresponding to discrete data;

[0054] Figure 5 is a schematic diagram of groove points on multiple laser lines provided by a preferred embodiment of the present invention;

[0055] Figure 6 is a flow chart of the core algorithm provided by the preferred embodiment of the present invention;

[0056] Figure 7 It is a schematic diagram of the precise positioning groove points provided by the preferred embodiment of the present invention;

[0057] Figure 8 is a flow chart of a complete process provided by a preferred embodiment of the present invention;

[0058] Fig. 9 It is a diagram showing the effect of trajectory deviation provided by a preferred embodiment of the present invention. DETAILED DESCRIPTION

[0059] In order to make the purpose, technical solutions and advantages of the present invention more clearly understood, the present invention is further described in detail below in conjunction with the accompanying drawings and embodiments. It should be understood that the specific embodiments described herein are only used to explain the present invention and are not intended to limit the present invention. In addition, the technical features involved in the various embodiments of the present invention described below can be combined with each other as long as they do not conflict with each other.

[0060] The vigorous development of machine vision technology has greatly improved productivity, and the auxiliary execution unit has achieved more intelligent operation. However, there are many problems with the existing groove extraction strategies: the image processing-based methods have poor accuracy due to insufficient image resolution, there are occlusion problems when taking photos of complex trajectories, and the multi-view template matching is not robust to deformation, which limits the accuracy and reliability of groove trajectory extraction. Methods based on point cloud geometry, such as volume, center of gravity, PCA principal components, circumscribed sphere rectangles, etc., are difficult to accurately find the unique features of the groove; methods based on feature descriptors, such as PFH, FPFH, SHOT, have large computational complexity and poor real-time performance; and methods based on registration have poor adaptability to deformation, require standard models, and lack generalization capabilities for similar features.

[0061] In view of the defects of the existing technology, such as Figures 1 to 9 As shown, the present invention provides a continuous groove trajectory tracking method based on line structured light point cloud, aiming to solve the problems of low detection efficiency, poor generalization and insufficient precision when generating continuous groove trajectory through teaching. The method has the advantages of strong ability to handle deformation problems, fast speed, high precision, no need for standard model assistance, etc., and meets the needs of automated production.

[0062] Step S100, using a line laser scanner to scan along the direction of the groove to obtain point cloud data composed of point clouds of various laser lines.

[0063] Specifically, in this embodiment, this process first requires that the scanner be aligned with the starting position of the groove, and the scanning parameters, including the intensity of the laser, scanning speed, resolution, etc., be set. During the scanning process, the line laser scanner moves along the direction of the concave groove, and the laser line scans each cross-section of the groove in turn. When the laser line contacts the groove wall, reflection occurs, and the reflected light is received by the sensor installed on the scanner. By processing the received reflected light signal, the point cloud data corresponding to each laser line can be obtained. The point cloud data is a collection of a series of three-dimensional coordinate points, and each point records its specific position in space. In order to obtain the point cloud data of the complete groove, the point cloud data obtained by scanning each laser line needs to be spliced. For example Figure 5 This stitching process relies on a precise positioning system to ensure that the position and direction of each laser line is accurately recorded and aligned.

[0064] Step S200, calculating the features on each laser line, including features reflecting the magnitude of height changes and features reflecting sudden height changes of horizontal lines.

[0065] In order to extract the features of each laser line, each point is first processed as follows Figure 2 Specifically, the height difference information is obtained by calculating the difference between the average values ​​of the left and right window data of each point, as shown in Figure 3 As shown in , this difference reflects the height change of the point. In addition, the sum of the variances of the left window and the right window of each point is calculated, and the ratio is compared with the variance of the bilateral window. This ratio is used to identify the height mutation points, such as Figure 4 As shown. Then, the peak value of the height drop information and the corresponding peak index are analyzed to determine the position of the point in the height change. Similarly, the peak value of the variance ratio and the corresponding peak index are calculated to identify the location of the mutation point. This process ensures accurate analysis of the depth information of each laser line, thereby identifying the key feature points of the groove.

[0066] In a preferred embodiment, step S200 includes:

[0067] Step S210, calculating the height difference information of a laser line and calculating the peak point and peak value of the height difference information;

[0068] Step S220, calculating the variance ratio information of a laser line and calculating the peak point and peak value of the variance ratio information.

[0069] Specifically, the depth data on a laser line is first represented as a discrete sequence. For each point P on the laser line i , we calculate the average depth of the left and right windows, and then find the absolute value of the difference between the two ΔH i ,Right now:

[0070] ΔH i =|mean(P i-n ,…,P i-1 )-mean(P i+1 ,…,P i+n )|

[0071] Among them, n represents the size of the window, mean() represents the average depth, P i-n Represents the point of the left window, P i+n Indicates the point in the right window. The peak point corresponds to the maximum value in the height drop information, and the peak value is the drop value corresponding to the peak point. By calculating the peak value of the height drop information sequence and its corresponding peak point index, we can determine the size of the height drop on the laser line, which reflects the contour of the groove.

[0072] Similarly, for the calculation of variance ratio, we can use the variance ratio of the depth data in the window to measure the high mutation situation. Specifically, we calculate the sum of the variances of the left and right windows and compare it with the variance of the bilateral window, that is:

[0073]

[0074] Where n represents the size of the feature extraction window, sum() represents summation, and Var() represents variance.

[0075] Step S300, determining the groove feature points on the laser line according to a preset height difference range and mutation degree.

[0076] In the process of generating trajectory points, we first set the height difference range of the groove, that is, the minimum height difference and the maximum height difference, and the variance ratio range of the groove, including the upper and lower limits of the variance ratio. At the same time, we also preset the maximum peak offset distance of the variance and height, which takes into account the possible error between the actual groove height difference and the variance ratio peak index.

[0077] For the depth information sequence of each laser line, first identify the peak of the height difference information to ensure that it falls within the preset height difference range. If the conditions are met, the index corresponding to the peak is marked as a possible groove point. Next, we check each possible trajectory point index to determine whether it is a real groove point index. This step involves a comparison with the variance ratio peak index. If there is an absolute difference between the variance ratio peak index and the peak index of the height difference information that is less than the preset variance and height maximum peak offset distance, the possible groove point index is marked as a groove point index.

[0078] In a preferred embodiment, step S300 includes:

[0079] Step S310, traverse the height drop peak index, if its drop range is greater than or equal to the preset height drop lower limit and less than or equal to the preset height drop upper limit, and there is a variance ratio peak index and the height drop peak index The absolute difference is less than or equal to the preset variance and the maximum peak difference distance of the height, then the height drop peak index is considered to be a groove point;

[0080] Step S320, the variance search lower limit is to be decreased in sequence from the initial feature variance ratio according to the decreasing amount of the variance ratio, until the groove point set is not empty and the feature variance ratio is greater than or equal to the feature variance ratio lower limit.

[0081] Further preferably, step S310 includes:

[0082] The initial feature variance ratio and the variance ratio decrement are set. The initial variance ratio is set based on the pre-judgment of the groove imaging quality to ensure that normal grooves can be accurately identified under the condition of the initial feature variance ratio.

[0083] When the search feature variance ratio is greater than or equal to 1, if the groove point index was not found in the last search of the laser line data, the search feature variance ratio is subtracted by the decrement amount;

[0084] The search is performed according to the updated search feature variance ratio. If the groove point index cannot be found even with the smallest feature variance ratio, it is determined that there is no groove point on this laser line.

[0085] Step S400, searching from the starting point, based on the continuity of the groove track, recursively forming continuous track points from the starting point along the laser line based on the feature points.

[0086] This process ensures that the trajectory is continuously generated from the starting laser line to the ending laser line. The density of the trajectory points is determined by the search interval. The search interval multiplied by the x-axis laser point resolution equals the density of the trajectory points. The density of the trajectory points can be adjusted by adjusting the search interval.

[0087] In a preferred embodiment, step S400 includes:

[0088] Step S410, searching for a groove point on the next laser line within a search range according to an initial point on the initial line;

[0089] Step S420, accurately locate the groove point, update the trajectory point and search for the next laser line until the termination line.

[0090] Specifically, given a point index on a laser line, the search range of the next laser line includes the previous point index ± the search range parameter. This parameter takes into account the continuity of the groove. Continuous groove lines ensure that the difference in the groove point index values ​​between laser lines is less than or equal to the search range between lines. Whenever a groove is located on a new laser line, it is necessary to rotate toward the higher side of the groove so that the track point falls into the minimum point formed by the groove, and the index of this track point will be updated to the previous point index.

[0091] In a preferred embodiment, step S420 includes:

[0092] Step S421, take the left and right window points of the currently determined groove point, the x index of the current point is 0, convert the depth sequence information into the point cloud information of the actual interval, and express it in the xz coordinate system:

[0093] x=idx*x_resolution

[0094] z=height

[0095] Among them, idx represents the index corresponding to the point on the current laser line, x_resolution represents the resolution of the point on the current laser line, and height represents the z coordinate value of the point on the current laser line;

[0096] Step S422, rotating the sequence corresponding to xz by 45° around the origin toward the higher side of the groove, so as to ensure that the groove point becomes a local minimum point;

[0097] Step S423, finding the index k corresponding to the local minimum value in the sequence corresponding to xz;

[0098] Step S424, update the current track point index to:

[0099] idx′=idx-window+k

[0100] Among them, idx' represents the updated index of the point on the current laser line, and window represents the window size for precise positioning;

[0101] Step S425, update the previous point index to idx′, such as Figure 7 As shown, the precise positioning effect is demonstrated in detail.

[0102] These steps can ensure that a continuous trajectory is generated on the laser line. The precise positioning method ensures the accuracy of trajectory generation. The limitation of the search range ensures the continuity of the trajectory. The setting of the search interval ensures that the density of the trajectory is controllable.

[0103] Step S500, according to actual needs, offsets the trajectory by a certain distance along a fixed direction or a certain distance along the normal direction of the trajectory, including:

[0104] Calculate the curvature ρ and normal C of the current trajectory;

[0105]

[0106]

[0107] Where m represents the number of points in the neighborhood of the current point, i = 1 to m, Pi represents the i-th point in the neighborhood of the current point, P 0 represents the current point, x', y', z' represent the second-order derivatives of the xyz coordinates of the current point, x', y', z' represent the first-order derivatives of the xyz coordinates of the current point, and T represents transpose;

[0108] The trajectory point is deviated by a fixed distance along the lower side of the groove in the normal direction to obtain a new two-dimensional coordinate; on the depth map, the depth corresponding to the new two-dimensional coordinate is interpolated, and the new coordinate is used as the offset trajectory point.

[0109] It will be easily understood by those skilled in the art that the above description is only a preferred embodiment of the present invention and is not intended to limit the present invention. Any modifications, equivalent substitutions and improvements made within the spirit and principles of the present invention should be included in the protection scope of the present invention.

Claims

1. A continuous groove trajectory tracking method based on line structured light point cloud, characterized in that: The steps include: Step S100, using a line laser scanner to scan along the direction of the groove to obtain point cloud data composed of point clouds of various laser lines; Step S200, calculating the features of each laser line, including features reflecting the magnitude of height changes and features reflecting height mutations of horizontal lines; Step S300, determining the groove feature points on the laser line according to a preset height difference range and mutation degree; Step S400, searching from the starting point, according to the continuity of the groove track, recursively forming continuous track points from the starting point along the laser line according to the feature points, and obtaining the track of the continuous groove.

2. The method for tracing a continuous groove based on a line structured light point cloud according to claim 1, characterized in that: Step S200 includes: Step S210, calculating the height difference information of a laser line and calculating the peak point and peak value of the height difference information; Step S220, calculating the variance ratio information of a laser line and calculating the peak point and peak value of the variance ratio information.

3. The method for tracing a continuous groove based on a line structured light point cloud according to claim 2, characterized in that: In step S210, the depth data on a laser line is first represented as a discrete sequence; for each point P on the laser line i , calculate point P i The depth average of the left and right windows, and then find the absolute value of the difference between the depth averages of the left and right windows ΔH i ,Right now: ΔH i =|mean(P i-n ,…,P i-1 )-mean(P i+1 ,…,P i+n )| Among them, n represents the size of the window, mean() represents the depth average, P i-n Represents the point of the left window, P i+n Indicates the point in the right window; the peak point corresponds to the maximum value in the height difference information, and the peak value is the difference value corresponding to the peak point; by calculating the peak value of the height difference information sequence and its corresponding peak point index, the size of the height difference on the laser line is determined to reflect the contour of the groove; In step S220, the sum of the variances of the left and right windows is calculated and compared with the variance of the bilateral window, namely: Among them, sum() means summation, and Var() means variance.

4. The method for tracing a continuous groove trajectory based on a line structured light point cloud according to claim 3, characterized in that: Step S300 includes: Step S310, traverse the height drop peak index, if its drop range is greater than or equal to the preset height drop lower limit and less than or equal to the preset height drop upper limit, and there is a variance ratio peak index and the height drop peak index The absolute difference is less than or equal to the preset variance and the maximum peak difference distance of the height, then the height drop peak index is considered to be a groove point; Step S320 , the variance search lower limit is decreased in sequence from the initial feature variance ratio according to the variance ratio decreasing amount until the groove point set is not empty and the feature variance ratio is greater than or equal to the lower limit of the feature variance ratio.

5. The method for tracing a continuous groove based on a line structured light point cloud according to claim 4, characterized in that: Step S310 includes: The initial feature variance ratio and the variance ratio decrement are set. The initial feature variance ratio is set based on the pre-judgment of the groove imaging quality to ensure that normal grooves can be accurately identified under the condition of the initial feature variance ratio. When the search feature variance ratio is greater than or equal to 1, if the groove point index was not found in the last search of the data on the laser line, the search feature variance ratio is subtracted by the decrement amount; The search is performed according to the updated search feature variance ratio. If the groove point index cannot be found even with the smallest feature variance ratio, it is determined that there is no groove point on this laser line.

6. The method for tracing a continuous groove based on a line structured light point cloud according to claim 1, characterized in that: Step S400 includes: Step S410, searching for a groove point on the next laser line within a search range according to an initial point on the initial line; Step S420, accurately locate the groove point, update the trajectory point to search the next laser line until the termination line; specifically, the index of a point on the laser line is known, and the search range of the next laser line includes the index of the previous point ± the search range parameter; whenever a groove is located on a new laser line, the trajectory point is rotated toward the higher side of the groove so that it falls into the minimum point formed by the groove, and at the same time, the index of this trajectory point is updated to the index of the previous point.

7. The method for tracking a continuous groove trajectory based on a line structured light point cloud according to claim 6, characterized in that: Step S420 includes: Step S421, take the left and right window points of the currently determined groove point, the x index of the current point is 0, convert the depth sequence information into the point cloud information of the actual interval, and express it in the xz coordinate system: x=idx*x_resoution z=height Among them, idx represents the index corresponding to the point on the current laser line, x_resolution represents the resolution of the point on the current laser line, and height represents the z coordinate value of the point on the current laser line; Step S422, rotating the sequence corresponding to xz by 45° around the origin toward the higher side of the groove, so as to ensure that the groove point becomes a local minimum point; Step S423, finding the index k corresponding to the local minimum value in the sequence corresponding to xz; Step S424, update the current track point index to: idx′=idx-window+k Among them, idx' represents the updated index of the point on the current laser line, and window represents the window size for precise positioning; Step S425, update the previous point index to idx′.

8. The method for tracing a continuous groove based on a line structured light point cloud according to claim 1, characterized in that: The method further includes step S500 of offsetting the continuous trajectory points by a certain distance along a fixed direction or by a certain distance along a normal direction of the continuous trajectory points.

9. The method for tracing a continuous groove based on line structured light point cloud according to claim 8, characterized in that: Step S500 includes: Calculate the curvature ρ and normal C of the current trajectory; Where m represents the number of points in the neighborhood of the current point, i = 1 to m, Pi represents the i-th point in the neighborhood of the current point, P0 represents the current point, x', y', z' represent the second-order derivatives of the xyz coordinates of the current point, x', y', z' represent the first-order derivatives of the xyz coordinates of the current point, and T represents transpose; The trajectory point is deviated by a fixed distance along the lower side of the groove in the normal direction to obtain a new two-dimensional coordinate; on the depth map, the depth corresponding to the new two-dimensional coordinate is interpolated, and the new coordinate is used as the offset trajectory point.

10. A continuous groove trajectory tracking system based on line structured light point cloud, comprising a memory, a processor and a computer program stored in the memory, characterized in that: The processor executes the computer program to implement the steps of the method for tracking the trajectory of a continuous groove based on a line structured light point cloud as described in any one of claims 1 to 9.

Citation Information

Patent Citations

  • Method and system for automatic generating shoe sole photopolymer coating track based on linear structure optical sensor

    CN101161151A

  • Method for detecting error of additive manufacturing cladding layer and correcting track based on point cloud information

    CN115546125A

  • Welding seam positioning robot and welding seam positioning method

    CN116175036A

  • Weld joint identification and trajectory planning method for corrugated oil tank of oil-immersed transformer

    CN118438092A