A feature extraction and correspondence algorithm for laser range finder with sensor uncertainty  

作　　者：孙英杰 曹其新 李杰 

机构地区：[1]Robotics Research Institute,Shanghai Jiao Tong University,Shanghai 20030, China [2]Intelligent Maintenance Systems, University of Wisconsin, Milwaukee 53201,U.S.A,

出　　处：《Journal of Harbin Institute of Technology(New Series)》2004年第4期361-367,共7页哈尔滨工业大学学报（英文版）

基　　金：SponsoredbytheNationalNaturalScienceFoundationofChina (GrantNo .5 0 1 2 85 0 4and 5 0 390 0 6 3) .

摘　　要：This paper presents a feature extraction and correspondence algorithm which employs a novel feature transform. Unlike conventional approaches such as Hough Transform, we employ a robust but simple approach to extract the geometrical feature under real dynamic world conditions. Multi-threshold segmentation and the split-and-merge method are employed to interpret geometrical features such as edge, concave corners, convex corners, and segments in a unified framework. The features are represented by feature tree (F-Tree) so as to compactly represent the environments and some important properties of the F-Tree are discussed in this paper. To demonstrate the validity of the approach, we show the actual experiment results which are based on real Laser Range Finder data and real time analysis. The comparative study with Hough Transform shows the advantages and the high performance of the proposed algorithm.This paper presents a feature extraction and correspondence algorithm which employs a novel feature transform. Unlike conventional approaches such as Hough Transform, we employ a robust but simple approach to extract the geometrical feature under real dynamic world conditions. Multi-threshold segmentation and the split-and-merge method are employed to interpret geometrical features such as edge, concave corners, convex corners, and segments in a unified framework. The features are represented by feature tree (F-Tree) so as to compactly represent the environments and some important properties of the F-Tree are discussed in this paper. To demonstrate the validity of the approach, we show the actual experiment results which are based on real Laser Range Finder data and real time analysis. The comparative study with Hough Transform shows the advantages and the high performance of the proposed algorithm.

关 键 词：feature extraction and correspondence multi-threshold segmentation EIGENSPACE feature tree sensor uncertainty 

分 类 号：TP391.41[自动化与计算机技术—计算机应用技术]