Looking for breakthrough ideas for innovation challenges? Try Patsnap Eureka!

A method for extracting point cloud contours of plane building components based on global graph clustering

A technology for extracting building components and contours, applied in the computer field, can solve problems such as difficulty in applying small curved surfaces to extract scenes, difficulty in determining the starting and ending range of intersection lines, etc., and achieves the effect of strong adaptability and high precision

Active Publication Date: 2021-07-16
上海黑塞智能科技有限公司
View PDF8 Cites 0 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

However, for the surface-based method, it is usually difficult to determine the starting and ending range of the intersection line and it is difficult to apply to the edge extraction scene of the small surface

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 more

Image

Smart Image Click on the blue labels to locate them in the text.
Viewing Examples
Smart Image
  • A method for extracting point cloud contours of plane building components based on global graph clustering
  • A method for extracting point cloud contours of plane building components based on global graph clustering
  • A method for extracting point cloud contours of plane building components based on global graph clustering

Examples

Experimental program
Comparison scheme
Effect test

Embodiment

[0049] The implementation of the planar reconstruction method proposed by the present invention includes two main stages: detection and extraction of planar segments and geometric modeling of planar segments. Specifically, the first stage can be divided into point cloud segmentation and plane detection. For segmentation, a bottom-up point cloud segmentation method is proposed, which utilizes supervoxel structure and global graph-based optimization to achieve automatic and unsupervised segmentation of point clouds. A flatness-based extraction is performed on the segments in a subsequent step, and only planar segments and their neighborhoods are selected as candidates for planar fitting. The points of the plane can be identified by the parametric model given by the flatness calculation. The boundary points of the plane are then extracted by the Alpha shape. The resulting base line segments are extracted and merged by mean shift clustering. For the geometric modeling of the pl...

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

No PUM Login to View More

Abstract

The present invention relates to a method for extracting point cloud contours of planar building components based on global graph clustering. Point cloud data characterized by geometric features of voxels; Step 2: Construct a global graph model for point cloud data characterized by geometric features of super-voxels; Step 3: Perform clustering optimization on the global graph model and further extract planes fragments; Step 4: Extract the final surface building component point cloud contours from the planar fragments. Compared with the prior art, the present invention has the advantages of high contour extraction accuracy, wide application range and the like.

Description

technical field [0001] The invention relates to the field of computer technology, in particular to a method for extracting point cloud contours of planar building components based on global graph clustering. Background technique [0002] LiDAR technology has been widely used to obtain geospatial information in urban scenes. Typically, unstructured 3D point clouds are used to represent the acquired geospatial information, which are usually characterized by high density and large volume. However, due to the lack of topological information, using a single point to directly describe a 3D scene is an impractical solution that cannot meet the needs of describing urban scenes. In addition, large-scale scenes and massive point cloud data also make point cloud data processing face great challenges. Compared with mere points and lines, planes and their edge contours can be regarded as a better representation of 3D scenes, especially in urban scenes with many man-made architectural s...

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
no application Login to View More
Patent Type & Authority Patents(China)
IPC IPC(8): G06K9/00G06K9/46
CPCG06V20/64G06V10/44
Inventor 徐聿升叶真潘玥顾振雄
Owner 上海黑塞智能科技有限公司
Who we serve
  • R&D Engineer
  • R&D Manager
  • IP Professional
Why Patsnap Eureka
  • Industry Leading Data Capabilities
  • Powerful AI technology
  • Patent DNA Extraction
Social media
Patsnap Eureka Blog
Learn More
PatSnap group products