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

Linear feature extracting method for three-dimensional point cloud

A technology of straight line features and extraction methods, applied in image data processing, 3D image processing, instruments, etc., can solve problems such as false positive detection, wrong straight line, false negative detection, etc., achieve reliable results and reduce complexity.

Active Publication Date: 2014-07-23
XIAMEN UNIV
View PDF2 Cites 24 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

This method has some obvious disadvantages: firstly, the method of Hough transform tends to cause a lot of false detections in areas with high-density edges; secondly, because the gradient direction of edge points is not considered, this method is easy to produce abnormal directions the straight line; finally, using a fixed threshold makes the method prone to significant false positives or false negatives
However, the method based on plane extraction has the following disadvantages: the boundary of the plane is difficult to determine; this method can only extract significant straight lines, and it is difficult to detect the intersection of two narrow planes
The narrow facet itself is also difficult to extract from the point cloud, and is easily affected by noise; for complex data, this method is easy to extract wrong straight lines at non-planar places

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
  • Linear feature extracting method for three-dimensional point cloud
  • Linear feature extracting method for three-dimensional point cloud
  • Linear feature extracting method for three-dimensional point cloud

Examples

Experimental program
Comparison scheme
Effect test

Embodiment

[0046] see figure 1 , the invention discloses a method for extracting straight line features from a three-dimensional point cloud, which comprises the following steps:

[0047] S1. Project the original point cloud into the two-dimensional space along different directions, generate multiple 2D images and retain the depth information, and use non-realistic rendering technology to convert the depth information into image gray values, so that the 2D image has clear edges.

[0048] Non-photorealistic rendering techniques such as Global Illumination Model, Screen Space Ambient Lighting (SSAO), and EDL can make 2D images have sharp edges. The global illumination model is usually used to enhance the relief and edge information of the surface. Using such a model often requires a lot of computing time and its normal vector and other information, so it is not suitable for large-scale 3D point cloud processing. SSAO and EDL only use the image depth information and run in the image coordi...

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 invention discloses a linear feature extracting method for three-dimensional point cloud. The linear feature extracting method for the three-dimensional point cloud includes the following steps: S1, projecting an original point cloud to a two-dimensional space along different directions to generate a plurality of two-dimensional images, keeping the depth information, using a non-photorealistic rendering technology to convert the depth information into an image grey value, and enabling each two-dimensional image to have clear edges; S2, extracting a two-dimensional linear support area from the two-dimensional image; S3, projecting the two-dimensional linear support area to the three-dimensional space to obtain a three-dimensional linear support area. By means of projection and back projection, the extraction for the three-dimensional linear support area is converted into the extraction for the two-dimensional linear support area, the data processing complexity is lowered, and linear features can be quickly and precisely extracted from large amount of point cloud data.

Description

technical field [0001] The invention relates to the field of three-dimensional point cloud processing, in particular to a method for extracting straight line features of a three-dimensional point cloud. Background technique [0002] The linear structure of point cloud includes curved structure and straight line structure. In view of the fact that most man-made objects have planar features and the intersection of two planes is a straight line, using a straight line to represent the point cloud structure becomes a natural and appropriate choice. For the extraction of straight line features, most of the research results focus on 2D images, including the straight line extraction of a single image and the 3D straight line reconstruction of multi-view images. However, only a few research results are oriented to line extraction from point clouds. [0003] Line detection in 2D images has been studied for decades. The traditional method is to first use the Canny edge detection ope...

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
IPC IPC(8): G06T15/00G06T7/00
Inventor 王程林阳斌程俊陈碧黎贾福凯李军
Owner XIAMEN UNIV
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