A novel torchlight data association strategy for surface registration
This paper presents a novel method for rigid surface registration using torchlight structure as data association, and the new method improves the correctness of point matching. When two sets of point clouds are merged, assume a set of torchlight beams parallely pass through them, and each light ray...
Saved in:
Main Authors: | , |
---|---|
Other Authors: | |
Format: | Conference or Workshop Item |
Language: | English |
Published: |
2013
|
Subjects: | |
Online Access: | https://hdl.handle.net/10356/101799 http://hdl.handle.net/10220/16370 |
Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
Institution: | Nanyang Technological University |
Language: | English |
id |
sg-ntu-dr.10356-101799 |
---|---|
record_format |
dspace |
spelling |
sg-ntu-dr.10356-1017992020-03-07T13:24:50Z A novel torchlight data association strategy for surface registration Ying, Ying Wang, Han School of Electrical and Electronic Engineering IEEE/RSJ International Conference on Intelligent Robots and Systems (2012 : Vilamoura, Portugal) DRNTU::Engineering::Electrical and electronic engineering This paper presents a novel method for rigid surface registration using torchlight structure as data association, and the new method improves the correctness of point matching. When two sets of point clouds are merged, assume a set of torchlight beams parallely pass through them, and each light ray passes the overlapped data twice, one on each set. The Euclidean distance on such pair is taken as measurement of the separation. When the two sets are optimally aligned, the registration error is minimized. Hence, surface registration problem is reduced to a six degree of freedom searching procedure. Preprocessing, optimization, and acceleration modules are introduced to normalize raw data, explore registration space, and reduce execution time. Unlike the Iterative Closest Point (ICP) algorithm, the proposed approach does not require pre-alignment information. Secondly, the performance of ICP is poor when the overlapped area between two sets is not sufficiently large. The proposed approach does not suffer from these problems. Based on various experiments, the proposed approach shows the superior performance over ICP. 2013-10-10T04:23:54Z 2019-12-06T20:44:41Z 2013-10-10T04:23:54Z 2019-12-06T20:44:41Z 2012 2012 Conference Paper Wang, H., & Ying, Y. (2012). A novel torchlight data association strategy for surface registration. 2012 IEEE/RSJ International Conference on Intelligent Robots and Systems (IROS), pp.1708-1713. https://hdl.handle.net/10356/101799 http://hdl.handle.net/10220/16370 10.1109/IROS.2012.6385485 en |
institution |
Nanyang Technological University |
building |
NTU Library |
country |
Singapore |
collection |
DR-NTU |
language |
English |
topic |
DRNTU::Engineering::Electrical and electronic engineering |
spellingShingle |
DRNTU::Engineering::Electrical and electronic engineering Ying, Ying Wang, Han A novel torchlight data association strategy for surface registration |
description |
This paper presents a novel method for rigid surface registration using torchlight structure as data association, and the new method improves the correctness of point matching. When two sets of point clouds are merged, assume a set of torchlight beams parallely pass through them, and each light ray passes the overlapped data twice, one on each set. The Euclidean distance on such pair is taken as measurement of the separation. When the two sets are optimally aligned, the registration error is minimized. Hence, surface registration problem is reduced to a six degree of freedom searching procedure. Preprocessing, optimization, and acceleration modules are introduced to normalize raw data, explore registration space, and reduce execution time. Unlike the Iterative Closest Point (ICP) algorithm, the proposed approach does not require pre-alignment information. Secondly, the performance of ICP is poor when the overlapped area between two sets is not sufficiently large. The proposed approach does not suffer from these problems. Based on various experiments, the proposed approach shows the superior performance over ICP. |
author2 |
School of Electrical and Electronic Engineering |
author_facet |
School of Electrical and Electronic Engineering Ying, Ying Wang, Han |
format |
Conference or Workshop Item |
author |
Ying, Ying Wang, Han |
author_sort |
Ying, Ying |
title |
A novel torchlight data association strategy for surface registration |
title_short |
A novel torchlight data association strategy for surface registration |
title_full |
A novel torchlight data association strategy for surface registration |
title_fullStr |
A novel torchlight data association strategy for surface registration |
title_full_unstemmed |
A novel torchlight data association strategy for surface registration |
title_sort |
novel torchlight data association strategy for surface registration |
publishDate |
2013 |
url |
https://hdl.handle.net/10356/101799 http://hdl.handle.net/10220/16370 |
_version_ |
1681048402768429056 |