CN115439605A - Crawler surface measurement detection and identification method, application, equipment and computer program product - Google Patents

Abstract

The invention relates to the technical field of rubber track design, in particular to a track surface measurement, detection and identification method, application, equipment and computer program product. The invention uses reverse engineering technology to perform operations such as noise reduction, registration, completion, surface generation, and format conversion on the point cloud, so as to realize the conversion from the track surface point cloud to a three-dimensional digital model. The invention can quickly acquire the three-dimensional data model of the track surface, and improve the efficiency of track inspection and measurement; at the same time, the model can be used for three-dimensional finite element simulation analysis of the track to facilitate subsequent product optimization.

Description

Method, application, device and computer program for track surface measurement, detection and identification product

technical field

The invention relates to the technical field of rubber track design, in particular to a track surface measurement detection and identification method, application, equipment and computer program product.

Background technique

In the past 30 years, 3D scanning measurement and reverse engineering technology have developed rapidly in China. The 3D scanners on the market are becoming more and more diversified. According to different usage conditions, they can be roughly divided into four categories: airborne, vehicle-mounted, fixed-station, and hand-held. The accuracy, speed, and stability of the scanner have been greatly improved; compared with the rapid development of 3D scanning measurement, the intelligent, refined, and functional processing of 3D point clouds still needs to be improved.

The point cloud data of 3D scanning is complicated, the point cloud distribution is uneven, and the point cloud shape is incomplete, which makes it impossible to intelligently process point clouds in large quantities; different measurement systems, different environments, and different measurement methods will affect the accuracy of point cloud acquisition ; In the process of generating the surface, the deformation of the point cloud causes the obtained surface to be too smooth, which greatly reduces the accuracy of the final digital model.

The track is time-consuming in the daily inspection and measurement process. If the 3D scanning technology is used for daily inspection of the track, the following problems exist:

1) The occlusion between the iron teeth of the track makes it impossible to obtain a complete point cloud image of the track at one time;

2) Point cloud noise reduction is not intelligent enough, the noise reduction is too small to completely remove the noise, and the point cloud contour features are not obvious if the noise reduction is excessive;

3) There are errors in point cloud stitching;

4) The surface generation of the point cloud will over-smooth the surface, resulting in a mismatch between the generated track surface and the physical details.

Contents of the invention

In order to solve the above-mentioned technical problems, the object of the present invention is to provide a method for measuring, detecting and identifying crawler tracks based on point cloud-to-image conversion. The method uses reverse engineering technology to perform noise reduction, registration, completion, and surface recognition on point clouds. Generation, format conversion and other operations to realize the conversion of track surface point cloud to 3D digital model.

In order to achieve the above object, the present invention adopts the following technical solutions:

A method for measuring, detecting and identifying crawler surfaces based on point cloud-to-image, the method comprising the following steps:

S1 obtains the point cloud information of the track:

Use a handheld laser 3D scanner to scan the same track twice to obtain two sets of point cloud data in different directions of the probability belt;

S2 filters the point cloud, removes interference points, and extracts feature points:

Import two sets of point clouds into the editor at the same time, perform discrete point deletion, filter noise reduction, and normal vector estimation processing on them, delete the noise points of the point cloud, extract useful feature points, and reduce its resolution while retaining the point cloud outline. Rate;

S3 point cloud for registration processing:

Among the two sets of point clouds, one set is fixed as the bull’s-eye point cloud; the other set is used as the floating point cloud, which is continuously matched with the bull’s-eye point cloud through non-stop rotation and movement until they overlap completely; According to the characteristic points, the floating point cloud estimates the position of the bullseye point cloud according to these characteristic points, and the same characteristic points are merged, that is, the two sets of point clouds are merged;

S4 generates surface patches:

After the two sets of point clouds are registered, use the principle of three points to form a plane, connect the point clouds into a piece in the form of triangular patches, and complete the merging of the two sets of point clouds;

S5 repairs and complements the surface:

The sheet composed of two sets of point clouds is composed of countless triangular planes, which are smoothed and smoothed to reduce the "nails" on the surface of the surface and make the entire surface look smoother;

S6 parametric surface:

After cloud repair and completion, create contour lines based on nodes, use contour lines to form surface grids, create NURBS surface patches, and complete the conversion from point cloud to surface after fitting and merging surfaces, realizing the reverse engineering of crawler point cloud to surface.

Preferably, the step S3 further includes performing simple processing on the obtained point cloud, and deleting the free point cloud and the environment point cloud which are not connected with the subject point cloud.

Preferably, the step S3 utilizes the global registration module in the compiler to adjust all point clouds according to the local registration, so that all point clouds are precisely coincident, and the final fine point cloud registration is completed.

Preferably, the editor in step S5 calculates the vacant local features according to the global features of the point cloud, and completes them in the form of triangular patches.

Further, the present invention also discloses the application of the method in the establishment of three-dimensional digital model of crawler belt.

Further, the invention also discloses the application of the method in the three-dimensional finite element simulation analysis of the crawler.

Further, the present invention also discloses a computer device, including a memory, a processor, and a computer program stored on the memory, and the processor executes the computer program to implement the method.

Further, the present invention also discloses a computer-readable storage medium, on which a computer program or instruction is stored, and the computer program or instruction implements the method when executed by a processor.

Further, the present invention also discloses a computer program product, including a computer program or instruction, and when the computer program or instruction is executed by a processor, the method is realized.

Due to the adoption of the above-mentioned technical scheme, the present invention uses reverse engineering technology to perform operations such as noise reduction, registration, completion, surface generation, and format conversion on the point cloud to realize the conversion of the track surface point cloud to a three-dimensional digital model. The invention can quickly acquire the three-dimensional data model of the track surface, and improve the efficiency of track inspection and measurement; at the same time, the model can be used for three-dimensional finite element simulation analysis of the track to facilitate subsequent product optimization.

Description of drawings

Fig. 1 is a flow chart of converting a crawler point cloud to a 3D data model according to the present invention.

Fig. 2 is a schematic diagram of transformation from point cloud to 3D data model in the present invention.

Fig. 3 is the point cloud diagram of the track scanning of the present invention.

Fig. 4 is a point cloud map of the track registration of the present invention.

Fig. 5 is a comparison diagram of point cloud restoration and completion in the present invention.

Fig. 6 is the three-dimensional data model of the crawler belt of the present invention.

detailed description

In order to show the purpose and technical solution of the present invention more clearly, the present invention will be further described in detail below in conjunction with the accompanying drawings. The described embodiments are only some, not all, embodiments of the present invention. Based on the embodiments of the present invention, all other embodiments obtained in the field without creative work fall within the protection scope of the present invention.

As shown in Figure 1 and Figure 2, a method for measuring, detecting and identifying track surface based on point cloud to image, the method includes the following steps:

S1 obtains the point cloud information of the track:

Use a handheld laser 3D scanner to scan the same track twice to obtain two sets of point cloud data in different directions of the probability belt, as shown in Figure 3. Perform simple processing on the obtained point cloud, delete the free point cloud and environment point cloud that are not connected with the main body point cloud.

S2 filters the point cloud, removes interference points, and extracts feature points:

Import two sets of point clouds into the editor at the same time, perform discrete point deletion, filter noise reduction, normal vector estimation, etc., delete the noise points of the point cloud, extract useful feature points, and reduce the noise while retaining the outline of the point cloud. resolution.

S3 point cloud for registration processing:

Among the two sets of point clouds, one set is fixed as the bull's-eye point cloud; the other set is used as the floating point cloud, which is continuously matched with the bull's-eye point cloud through continuous rotation and movement until they are completely coincident. Points with the same characteristics are selected in the two sets of point clouds, and the floating point cloud estimates the position of the bullseye point cloud based on these feature points, and the same feature points are merged to merge the two sets of point clouds.

Since the same feature points of the two sets of point clouds are limited, under normal circumstances, the registration of feature points to feature points can only achieve local registration. The global registration module in the compiler is used to adjust all point clouds according to the local registration, so that all point clouds are accurately coincident, and the final point cloud fine registration is completed, as shown in Figure 4.

S4 generates surface patches:

After the two sets of point clouds are registered, using the principle that three points form a plane, the point clouds are connected into a piece in the form of triangular patches, and the merging of the two sets of point clouds is completed.

S5 repairs and complements the surface:

Since the sheet composed of two sets of point clouds is composed of countless triangular planes, it needs to be smoothed, polished, etc. to reduce the "nails" on the surface of the surface and make the entire surface look smoother.

The track is an irregular object. When the laser scanner scans its shape, it will think that the features of the track itself are mutually occluded and cannot obtain all the features of the track 100%. In the later stage of point cloud processing, it is necessary to complete the features missed by the scanner. The editor will calculate the vacant local features according to the global features of the point cloud, and complete them in the form of triangular patches, as shown in Figure 5.

S6 parametric surface:

Points and points constitute lines, and lines intersect to form a grid. Using the nodes in the grid, the transformation from point cloud to surface can be realized.

After the point cloud is repaired and completed, the contour line is created according to the nodes, the contour line is used to form a surface grid, and the NURBS surface patch is created. After fitting and merging the surfaces, the conversion from the point cloud to the surface is completed, and the reverse engineering of the crawler point cloud to the surface is realized. As shown in Figure 6.

The above is the description of the embodiments of the present invention, through the above description of the disclosed embodiments, those skilled in the art can realize or use the present invention. Various modifications to these examples will be apparent to those skilled in the art. The general principles defined herein may be implemented in other embodiments without departing from the spirit or scope of the invention. Therefore, the present invention will not be limited to these embodiments shown herein, but will conform to the widest scope consistent with the principles and novel points disclosed herein.

Claims (9)

1. A crawler track surface measurement detection and recognition method based on point cloud transfer image, the method comprises the following steps: S1 obtains the point cloud information of the track: Use a handheld laser 3D scanner to scan the same track twice to obtain two sets of point cloud data in different directions of the probability belt; S2 filters the point cloud, removes interference points, and extracts feature points: Import two sets of point clouds into the editor at the same time, perform discrete point deletion, filter noise reduction, and normal vector estimation processing on them, delete the noise points of the point cloud, extract useful feature points, and reduce its resolution while retaining the outline of the point cloud Rate; S3 point cloud for registration processing: Among the two sets of point clouds, one set is fixed as the bull’s-eye point cloud; the other set is used as the floating point cloud, which is continuously matched with the bull’s-eye point cloud through non-stop rotation and movement until they overlap completely; According to the characteristic points, the floating point cloud estimates the position of the bullseye point cloud according to these characteristic points, and the same characteristic points are merged, that is, the two sets of point clouds are merged; S4 generates surface patches: After the two sets of point clouds are registered, use the principle of three points to form a plane, connect the point clouds into a piece in the form of triangular patches, and complete the merging of the two sets of point clouds; S5 repairs and complements the surface: The sheet composed of two sets of point clouds is composed of countless triangular planes, which are smoothed and smoothed to reduce the "nails" on the surface of the surface and make the entire surface look smoother; S6 parametric surface: After cloud repair and completion, create contour lines based on nodes, use contour lines to form surface grids, create NURBS surface patches, and complete the conversion from point cloud to surface after fitting and merging surfaces, realizing the reverse engineering of crawler point cloud to surface. 2. A kind of track surface measurement detection and recognition method based on point cloud to image according to claim 1, characterized in that, step S3 also includes performing simple processing on the obtained point cloud, deleting and disconnecting the subject point cloud free point cloud and environment point cloud. 3. a kind of track surface measurement detection and recognition method based on point cloud to image according to claim 1, is characterized in that, step S3 utilizes the global registration module in the compiler, adjusts all point clouds according to local registration, Accurately coincide all point clouds to complete the final point cloud fine registration. 4. a kind of crawler surface measurement detection and recognition method based on point cloud to image according to claim 1, it is characterized in that, step S5 utilizes editor to be able to calculate after the local feature of vacancy according to the global feature of point cloud , completed in the form of triangular faces. 5. The application of the method described in any one of claims 1-4 in the establishment of a crawler track three-dimensional digital model. 6. Application of the method according to any one of claims 1-4 in the three-dimensional finite element simulation analysis of crawler tracks. 7. A computer device, comprising a memory, a processor and a computer program stored on the memory, wherein the processor executes the computer program to implement the method according to any one of claims 1-4. 8. A computer-readable storage medium, on which a computer program or instruction is stored, wherein, when the computer program or instruction is executed by a processor, the method according to any one of claims 1-4 is implemented. 9. A computer program product, comprising computer programs or instructions, characterized in that, when the computer program or instructions are executed by a processor, the method according to any one of claims 1-4 is implemented.

Images