Vehicle-mounted Lidar steel rail point cloud extraction method based on generalized neighborhood height difference

An extraction method and neighborhood technology, applied in image analysis, image enhancement, instruments, etc., can solve problems such as low degree of automation, inability to extract continuous rail point clouds across the board, and low extraction accuracy of rail point clouds.

Active Publication Date: 2019-08-30
SOUTHWEST JIAOTONG UNIV
View PDF13 Cites 6 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

[0009] 1. The accuracy of rail point cloud extraction is low;
[0010] 2. Unable to extract the continuous rail point cloud;
[0012] 4. The degree of automation is low and manual intervention is required

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
  • Vehicle-mounted Lidar steel rail point cloud extraction method based on generalized neighborhood height difference
  • Vehicle-mounted Lidar steel rail point cloud extraction method based on generalized neighborhood height difference
  • Vehicle-mounted Lidar steel rail point cloud extraction method based on generalized neighborhood height difference

Examples

Experimental program
Comparison scheme
Effect test

Embodiment Construction

[0044]The present invention will be described in further detail below in conjunction with the accompanying drawings and specific implementation methods.

[0045] A method for extracting rail point cloud of vehicle-mounted Lidar rail based on generalized neighborhood height difference proposed by the present invention, the flow chart is as follows figure 1 As shown, the specific steps are:

[0046] Step 1: Segment the point cloud of the ballast bed according to the scanning angle or trajectory line of the vehicle Lidar point cloud, the result is as follows figure 2 As shown (the situation including the fork is as follows image 3 shown).

[0047] Step 2: Use statistical filtering and other algorithms to remove noise points in the ballast bed point cloud caused by factors such as rail self-occlusion, and record the ballast bed point cloud after removing noise points as {P m ,m=1,2,3,...}.

[0048] Step 3: Columnar Neighborhood Search :P i Point cloud for the track bed {P ...

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 vehicle-mounted Lidar steel rail point cloud extraction method based on generalized neighborhood height difference. The vehicle-mounted Lidar steel rail point cloud extraction method specifically comprises the following steps: 1, segmenting track bed point cloud according to a scanning angle or a track line of a vehicle-mounted Lidar point cloud; 2, adopting a statisticalfiltering algorithm to remove noise points caused by shielding factors of the steel rail in the ballast bed point cloud, and obtaining the ballast bed point cloud with the noise points removed; 3, carrying out columnar neighborhood search on one point in the ballast bed point cloud; 4, calculating the generalized neighborhood height difference of the point based on the columnar neighborhood; 5, repeating the step 3-4 until the generalized neighborhood height difference calculation of all points of the ballast bed area is completed, and a histogram is made; and 6, combining track knowledge anda generalized neighborhood height difference histogram to extract a steel rail vertex cloud. The vehicle-mounted Lidar steel rail point cloud extraction method can automatically extract the whole-line continuous steel rail vertex cloud, improves the extraction precision of the steel rail point cloud, is less in dependence on additional data, and is simple to implement.

Description

technical field [0001] The invention belongs to the field of rail transit computer vision, and in particular relates to a method for extracting a point cloud of a vehicle-mounted Lidar rail based on a generalized neighborhood height difference. Background technique [0002] With the development of on-board laser scanning technology, this technology has the advantages of fast scanning speed and high accuracy of point cloud acquisition, and has a good application prospect in many fields such as asset survey, track measurement, track modeling and boundary analysis in the railway industry. Since the track is a key object in the railway system, extracting the track rail point cloud from the vehicle-mounted Lidar point cloud is the core basic problem faced by various applications in the railway field. [0003] Chinese Invention Patent Publication No. CN104236499A discloses an automatic railway measurement method based on point cloud data. The method determines the approximate are...

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 Applications(China)
IPC IPC(8): G06T19/20G06T7/10G06T5/00
CPCG06T19/20G06T7/10G06T5/002G06T2207/10012Y02T90/00
Inventor 张同刚陈丞李世超安炯阚余辉谢富贵
Owner SOUTHWEST JIAOTONG UNIV
Who we serve
  • R&D Engineer
  • R&D Manager
  • IP Professional
Why Eureka
  • Industry Leading Data Capabilities
  • Powerful AI technology
  • Patent DNA Extraction
Social media
Try Eureka
PatSnap group products

Browse by: Latest US Patents, China's latest patents, Technical Efficacy Thesaurus, Application Domain, Technology Topic.

© 2024 PatSnap. All rights reserved.Legal|Privacy policy|Modern Slavery Act Transparency Statement|Sitemap