Automatic extraction technology of street lamp poles based on vehicle laser scanning point clouds

A vehicle-mounted laser scanning and automatic extraction technology, applied in the field of intelligent transportation system and smart city construction, can solve the problem of insufficient degree of algorithm automation, and achieve the effect of good robustness and low time complexity

Active Publication Date: 2016-10-12
XIAMEN UNIV
View PDF6 Cites 35 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

However, this algorithm requires manual judgment whether to perform segmentation, and the degree of automation of the algorithm is not high enough.

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
  • Automatic extraction technology of street lamp poles based on vehicle laser scanning point clouds
  • Automatic extraction technology of street lamp poles based on vehicle laser scanning point clouds
  • Automatic extraction technology of street lamp poles based on vehicle laser scanning point clouds

Examples

Experimental program
Comparison scheme
Effect test

Embodiment

[0037] The implementation steps of the automatic extraction technology based on the mobile vehicle laser scanning point cloud street light pole proposed by the present invention are as follows:

[0038] S1. Preprocessing for filtering ground points and dividing non-ground points into supervoxel sets

[0039] S11. According to the driving trajectory data collected by the vehicle-mounted laser scanning system, the original point cloud is divided into segments along the direction of the road;

[0040] S12. For each segment of point cloud data, use a method based on RANSAC (Random Sampling Consensus Algorithm) to filter ground points. The average height of the inner cluster point set obtained by the first plane fitting is taken as the average height of the ground points. Next, in each iteration of plane fitting, calculate the distance between the unclassified points in the fitted inner group point set and the fitting plane. If the distance is less than the preset threshold, the unc...

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 an automatic extraction technology of street lamp poles based on vehicle laser scanning point clouds. The technology comprises the following steps: carrying out pre-processing including filtering ground points and dividing non-ground points into super-voxel sets; positioning all pole-shaped objects in the scene which might be street lamp poles; carrying out position-oriented segmentation and obtaining the pole-shaped objects; using extracted pole features and global features to describe the pole-shaped objects obtained through segmentation; training random forests and classifier SVMs with manually-labeled training samples, and using the trained random forests and classifier SVMs to classify the pole-shaped objects segmented through the step S3 to identify the street lamp poles. The algorithm of the invention has good robustness under complex environment such as incomplete or obscured street light, and the time complexity of the algorithm is very low, and thus the algorithm can be quickly applied to point clouds of large-scale scenes.

Description

technical field [0001] The invention relates to an intelligent traffic system and the construction of a smart city, in particular to an automatic street lamp extraction technology based on a vehicle-mounted laser scanning point cloud. Background technique [0002] There are currently three types of light pole extraction methods for point clouds, namely algorithms based on shape features, algorithms based on prior knowledge, and algorithms based on shape template matching. In the paper "Detection and classification of pole-like objects from mobile laser scanning data of urban environments" published by Yokoyama et al. in the International Journal of CAD / CAM, first filter the ground points of the input point cloud, and then use the K nearest neighbor algorithm to point cloud For segmentation, the Laplacian operator is used to smooth the segmented point cloud to remove the influence of noise, and finally the principal component analysis is used to classify the point cloud to ex...

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): G06K9/62G06T7/00
CPCG06F18/214G06F18/2411
Inventor 李军吴凡温程璐陈一平贾宏王程
Owner XIAMEN 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