GMS: Grid-based motion statistics for fast, ultra-robust feature correspondence

Feature matching aims at generating correspondences across images, which is widely used in many computer vision tasks. Although considerable progress has been made on feature descriptors and fast matching for initial correspondence hypotheses, selecting good ones from them is still challenging and c...

Full description

Saved in:
Bibliographic Details
Main Authors: BIAN, Jia-Wang, LIN, Wen-yan, LIU, Yun, ZHANG, Le, YEUNG, Sai-Kit, CHENG, Ming-Ming, REID, Ian
Format: text
Language:English
Published: Institutional Knowledge at Singapore Management University 2019
Subjects:
GMS
Online Access:https://ink.library.smu.edu.sg/sis_research/5877
https://ink.library.smu.edu.sg/context/sis_research/article/6892/viewcontent/Bian2020_Article_GMSGrid_BasedMotionStatisticsF__1_.pdf
Tags: Add Tag
No Tags, Be the first to tag this record!
Institution: Singapore Management University
Language: English
id sg-smu-ink.sis_research-6892
record_format dspace
spelling sg-smu-ink.sis_research-68922021-03-29T05:54:02Z GMS: Grid-based motion statistics for fast, ultra-robust feature correspondence BIAN, Jia-Wang LIN, Wen-yan LIU, Yun ZHANG, Le YEUNG, Sai-Kit CHENG, Ming-Ming REID, Ian Feature matching aims at generating correspondences across images, which is widely used in many computer vision tasks. Although considerable progress has been made on feature descriptors and fast matching for initial correspondence hypotheses, selecting good ones from them is still challenging and critical to the overall performance. More importantly, existing methods often take a long computational time, limiting their use in real-time applications. This paper attempts to separate true correspondences from false ones at high speed. We term the proposed method (GMS) grid-based motion Statistics, which incorporates the smoothness constraint into a statistic framework for separation and uses a grid-based implementation for fast calculation. GMS is robust to various challenging image changes, involving in viewpoint, scale, and rotation. It is also fast, e.g., take only 1 or 2 ms in a single CPU thread, even when 50K correspondences are processed. This has important implications for real-time applications. What’s more, we show that incorporating GMS into the classic feature matching and epipolar geometry estimation pipeline can significantly boost the overall performance. Finally, we integrate GMS into the well-known ORB-SLAM system for monocular initialization, resulting in a significant improvement. 2019-12-01T08:00:00Z text application/pdf https://ink.library.smu.edu.sg/sis_research/5877 https://ink.library.smu.edu.sg/context/sis_research/article/6892/viewcontent/Bian2020_Article_GMSGrid_BasedMotionStatisticsF__1_.pdf http://creativecommons.org/licenses/by-nc-nd/4.0/ Research Collection School Of Computing and Information Systems eng Institutional Knowledge at Singapore Management University Feature matching Epipolar geometry Visual SLAM Structure-from-motion GMS Databases and Information Systems
institution Singapore Management University
building SMU Libraries
continent Asia
country Singapore
Singapore
content_provider SMU Libraries
collection InK@SMU
language English
topic Feature matching
Epipolar geometry
Visual SLAM
Structure-from-motion
GMS
Databases and Information Systems
spellingShingle Feature matching
Epipolar geometry
Visual SLAM
Structure-from-motion
GMS
Databases and Information Systems
BIAN, Jia-Wang
LIN, Wen-yan
LIU, Yun
ZHANG, Le
YEUNG, Sai-Kit
CHENG, Ming-Ming
REID, Ian
GMS: Grid-based motion statistics for fast, ultra-robust feature correspondence
description Feature matching aims at generating correspondences across images, which is widely used in many computer vision tasks. Although considerable progress has been made on feature descriptors and fast matching for initial correspondence hypotheses, selecting good ones from them is still challenging and critical to the overall performance. More importantly, existing methods often take a long computational time, limiting their use in real-time applications. This paper attempts to separate true correspondences from false ones at high speed. We term the proposed method (GMS) grid-based motion Statistics, which incorporates the smoothness constraint into a statistic framework for separation and uses a grid-based implementation for fast calculation. GMS is robust to various challenging image changes, involving in viewpoint, scale, and rotation. It is also fast, e.g., take only 1 or 2 ms in a single CPU thread, even when 50K correspondences are processed. This has important implications for real-time applications. What’s more, we show that incorporating GMS into the classic feature matching and epipolar geometry estimation pipeline can significantly boost the overall performance. Finally, we integrate GMS into the well-known ORB-SLAM system for monocular initialization, resulting in a significant improvement.
format text
author BIAN, Jia-Wang
LIN, Wen-yan
LIU, Yun
ZHANG, Le
YEUNG, Sai-Kit
CHENG, Ming-Ming
REID, Ian
author_facet BIAN, Jia-Wang
LIN, Wen-yan
LIU, Yun
ZHANG, Le
YEUNG, Sai-Kit
CHENG, Ming-Ming
REID, Ian
author_sort BIAN, Jia-Wang
title GMS: Grid-based motion statistics for fast, ultra-robust feature correspondence
title_short GMS: Grid-based motion statistics for fast, ultra-robust feature correspondence
title_full GMS: Grid-based motion statistics for fast, ultra-robust feature correspondence
title_fullStr GMS: Grid-based motion statistics for fast, ultra-robust feature correspondence
title_full_unstemmed GMS: Grid-based motion statistics for fast, ultra-robust feature correspondence
title_sort gms: grid-based motion statistics for fast, ultra-robust feature correspondence
publisher Institutional Knowledge at Singapore Management University
publishDate 2019
url https://ink.library.smu.edu.sg/sis_research/5877
https://ink.library.smu.edu.sg/context/sis_research/article/6892/viewcontent/Bian2020_Article_GMSGrid_BasedMotionStatisticsF__1_.pdf
_version_ 1770575642961641472