Scattered point cloud triangularization method based on support vector machine
A technology of support vector machines and scattered points, which is used in image data processing, 3D modeling, instruments, etc., and can solve problems such as complex topological relationships, easy generation of singular triangular meshes or holes, and imperfect triangulation theory and algorithms.
Pending Publication Date: 2021-05-07
SHAOXING UNIVERSITY
View PDF0 Cites 3 Cited by
- Summary
- Abstract
- Description
- Claims
- Application Information
AI Technical Summary
Problems solved by technology
However, for the scattered data points in the spatial domain, the topological relationship among them is more complicated. If the same triangulation algorithm as the two-dimensional data is used, it is difficult to achieve the desired effect.
Therefore, the current triangulation theory and algorithm for spatially scattered data points are not yet perfect, and further research is needed
Especially when the measurement points are unevenly distributed, contain redundant data or are partially incomplete, the existing direct triangulation algorithms are prone to generate singular triangle meshes or holes
Method used
the structure of the environmentally friendly knitted fabric provided by the present invention; figure 2 Flow chart of the yarn wrapping machine for environmentally friendly knitted fabrics and storage devices; image 3 Is the parameter map of the yarn covering machine
View moreImage
Smart Image Click on the blue labels to locate them in the text.
Smart ImageViewing Examples
Examples
Experimental program
Comparison scheme
Effect test
Embodiment Construction
[0068] This embodiment discloses a method for triangulating a scattered point cloud based on a support vector machine. The method is as follows: figure 1 As shown, it mainly includes boundary feature extraction of Z-direction single-valued point cloud data, generation of triangular meshes in the plane domain, surface fitting based on LS-SVM, and generation of triangular meshes in the spatial domain by 3D mapping. This method first finds the minimum rectangular bounding box of the original point cloud data in the plane, and resamples the data points with the minimum point cloud density mean in the original data in this bounding box, and generates a plane triangular mesh; use the original point cloud The boundary polygon clips the triangular mesh in the quadrilateral domain of the plane to obtain the triangular mesh in the actual boundary domain; then the least squares support vector machine is used to fit the compressed original 3D point cloud, and the plane The triangular mesh...
the structure of the environmentally friendly knitted fabric provided by the present invention; figure 2 Flow chart of the yarn wrapping machine for environmentally friendly knitted fabrics and storage devices; image 3 Is the parameter map of the yarn covering machine
Login to View More PUM
Login to View More Abstract
The invention relates to a scattered point cloud triangulation method based on a support vector machine, and the method comprises the steps: firstly solving a minimum rectangular bounding box of original point cloud data in a plane, carrying out the data point resampling in the bounding box according to a minimum point cloud density mean value in the original data, and generating a planar triangular mesh; cutting the triangular mesh in a planar quadrilateral domain by using the original point cloud boundary polygon to obtain a triangular mesh in an actual boundary domain; and then fitting a compressed original three-dimensional point cloud by applying a least square support vector machine, and mapping the triangular mesh in the plane domain to the space through the fitting model to obtain the triangular mesh of the three-dimensional space. Examples verifies that regular triangular grids can be still generated when the method is used to process redundant or locally incomplete data, and singular grids or holes are not easy to generate.
Description
Technical field: [0001] The invention relates to a method for triangulating scattered point clouds based on support vector machines. Background technique: [0002] At present, in the fields of industrial product design, medical inspection, establishment of digital human body model, and three-dimensional map drawing, it is necessary to obtain the surface shape information of the physical model. Commonly used surface information acquisition devices are coordinate measuring machines, laser scanners and computerized tomography scanners (Computerized Tomography, CT). The data points obtained by these devices are in different forms, and the data obtained by the three-dimensional coordinate measuring machine and CT are distributed on plane slices parallel to each other, and there is a certain organizational regularity in the local area. However, from a global perspective, the data points obtained by these three devices are characterized by scattered distribution. In the subsequen...
Claims
the structure of the environmentally friendly knitted fabric provided by the present invention; figure 2 Flow chart of the yarn wrapping machine for environmentally friendly knitted fabrics and storage devices; image 3 Is the parameter map of the yarn covering machine
Login to View More Application Information
Patent Timeline
Login to View More Patent Type & Authority Applications(China)
IPC IPC(8): G06T17/20G06T19/20
CPCG06T17/20G06T19/20
Inventor 吴福忠赖金涛
Owner SHAOXING UNIVERSITY