Research on Multi-sensor Image Matching Algorithm Based on Improved Line Segments Feature

Research on Multi-sensor Image Matching Algorithm Based on Improved Line Segments Feature

In this paper, an improved multi-sensor image matching algorithm based on line segments feature is proposed. Firstly, the line segments in the image are extracted and optimized. And the virtual feature points are constructed by the line segments. Then a set of affine transformation matrices of two i...

Full description

Bibliographic Details
Main Authors: Yuan Hui, Hao Ying-Guang, Liu Jun-Min
Format: Article
Language:English
Published: EDP Sciences 2017-01-01
Series:ITM Web of Conferences
Online Access:https://doi.org/10.1051/itmconf/20171105001
id doaj-c5c0f57842504dc1ad5428425062459a
record_format Article
spelling doaj-c5c0f57842504dc1ad5428425062459a2021-02-02T03:21:20ZengEDP SciencesITM Web of Conferences2271-20972017-01-01110500110.1051/itmconf/20171105001itmconf_ist2017_05001Research on Multi-sensor Image Matching Algorithm Based on Improved Line Segments FeatureYuan Hui0Hao Ying-Guang1Liu Jun-Min2Dalian University of Technology School of Information and Communication EngineeringDalian University of Technology School of Information and Communication EngineeringDalian University of Technology School of Information and Communication EngineeringIn this paper, an improved multi-sensor image matching algorithm based on line segments feature is proposed. Firstly, the line segments in the image are extracted and optimized. And the virtual feature points are constructed by the line segments. Then a set of affine transformation matrices of two images is obtained by different combinations of virtual feature points. And then the matching function is constructed, by which the relationship of affine transform between the two images are preliminarily determined. And the matching point set is obtained. Finally, false matching points are eliminated based on RANSAC algorithm and the final transformation matrix to accomplish accurate matching is achieved. The experimental results show that the matching accuracy of this proposed algorithm can reach up to 80%. At the same time, the speed of the algorithm is significantly improved.https://doi.org/10.1051/itmconf/20171105001
collection DOAJ
language English
format Article
sources DOAJ
author Yuan Hui
Hao Ying-Guang
Liu Jun-Min
spellingShingle Yuan Hui
Hao Ying-Guang
Liu Jun-Min
Research on Multi-sensor Image Matching Algorithm Based on Improved Line Segments Feature
ITM Web of Conferences
author_facet Yuan Hui
Hao Ying-Guang
Liu Jun-Min
author_sort Yuan Hui
title Research on Multi-sensor Image Matching Algorithm Based on Improved Line Segments Feature
title_short Research on Multi-sensor Image Matching Algorithm Based on Improved Line Segments Feature
title_full Research on Multi-sensor Image Matching Algorithm Based on Improved Line Segments Feature
title_fullStr Research on Multi-sensor Image Matching Algorithm Based on Improved Line Segments Feature
title_full_unstemmed Research on Multi-sensor Image Matching Algorithm Based on Improved Line Segments Feature
title_sort research on multi-sensor image matching algorithm based on improved line segments feature
publisher EDP Sciences
series ITM Web of Conferences
issn 2271-2097
publishDate 2017-01-01
description In this paper, an improved multi-sensor image matching algorithm based on line segments feature is proposed. Firstly, the line segments in the image are extracted and optimized. And the virtual feature points are constructed by the line segments. Then a set of affine transformation matrices of two images is obtained by different combinations of virtual feature points. And then the matching function is constructed, by which the relationship of affine transform between the two images are preliminarily determined. And the matching point set is obtained. Finally, false matching points are eliminated based on RANSAC algorithm and the final transformation matrix to accomplish accurate matching is achieved. The experimental results show that the matching accuracy of this proposed algorithm can reach up to 80%. At the same time, the speed of the algorithm is significantly improved.
url https://doi.org/10.1051/itmconf/20171105001
work_keys_str_mv AT yuanhui researchonmultisensorimagematchingalgorithmbasedonimprovedlinesegmentsfeature
AT haoyingguang researchonmultisensorimagematchingalgorithmbasedonimprovedlinesegmentsfeature
AT liujunmin researchonmultisensorimagematchingalgorithmbasedonimprovedlinesegmentsfeature
_version_ 1724308058095484928

Similar Items