Matching with GUISAC-Guided Sample Consensus
Summary :
The traditional RANSAC samples uniformly in the dataset which is not efficient in the task with rich prior information. This letter proposes GUISAC (Guided Sample Consensus), which samples with the guidance of various prior information. In image matching, GUISAC extracts seed points sets evenly on images based on various prior factors at first, then it incorporates seed points sets into the sampling subset with a growth function, and a new termination criterion is used to decide whether the current best hypothesis is good enough. Finally, experimental results show that the new method GUISAC has a great advantage in time-consuming than other similar RANSAC methods, and without loss of accuracy.
- Publication
- IEICE TRANSACTIONS on Information Vol.E104-D No.2 pp.346-349
- Publication Date
- 2021/02/01
- Publicized
- 2020/11/16
- Online ISSN
- 1745-1361
- DOI
- 10.1587/transinf.2020EDL8110
- Type of Manuscript
- LETTER
- Category
- Image Recognition, Computer Vision
Authors
Hengyong XIANG
Institute of Microelectronics of the Chinese Academy of Sciences (IMECAS),University of Chinese Academy of Sciences (UCAS)
Li ZHOU
Institute of Microelectronics of the Chinese Academy of Sciences (IMECAS)
Xiaohui BA
Institute of Microelectronics of the Chinese Academy of Sciences (IMECAS),University of Chinese Academy of Sciences (UCAS)
Jie CHEN
Institute of Microelectronics of the Chinese Academy of Sciences (IMECAS)
Keyword
Latest Issue
Copyrights notice of machine-translated contents
The copyright of the original papers published on this site belongs to IEICE. Unauthorized use of the original or translated papers is prohibited. See IEICE Provisions on Copyright for details.
Cite this
Copy
Hengyong XIANG, Li ZHOU, Xiaohui BA, Jie CHEN, "Matching with GUISAC-Guided Sample Consensus" in IEICE TRANSACTIONS on Information,
vol. E104-D, no. 2, pp. 346-349, February 2021, doi: 10.1587/transinf.2020EDL8110.
Abstract: The traditional RANSAC samples uniformly in the dataset which is not efficient in the task with rich prior information. This letter proposes GUISAC (Guided Sample Consensus), which samples with the guidance of various prior information. In image matching, GUISAC extracts seed points sets evenly on images based on various prior factors at first, then it incorporates seed points sets into the sampling subset with a growth function, and a new termination criterion is used to decide whether the current best hypothesis is good enough. Finally, experimental results show that the new method GUISAC has a great advantage in time-consuming than other similar RANSAC methods, and without loss of accuracy.
URL: https://global.ieice.org/en_transactions/information/10.1587/transinf.2020EDL8110/_p
Copy
@ARTICLE{e104-d_2_346,
author={Hengyong XIANG, Li ZHOU, Xiaohui BA, Jie CHEN, },
journal={IEICE TRANSACTIONS on Information},
title={Matching with GUISAC-Guided Sample Consensus},
year={2021},
volume={E104-D},
number={2},
pages={346-349},
abstract={The traditional RANSAC samples uniformly in the dataset which is not efficient in the task with rich prior information. This letter proposes GUISAC (Guided Sample Consensus), which samples with the guidance of various prior information. In image matching, GUISAC extracts seed points sets evenly on images based on various prior factors at first, then it incorporates seed points sets into the sampling subset with a growth function, and a new termination criterion is used to decide whether the current best hypothesis is good enough. Finally, experimental results show that the new method GUISAC has a great advantage in time-consuming than other similar RANSAC methods, and without loss of accuracy.},
keywords={},
doi={10.1587/transinf.2020EDL8110},
ISSN={1745-1361},
month={February},}
Copy
TY - JOUR
TI - Matching with GUISAC-Guided Sample Consensus
T2 - IEICE TRANSACTIONS on Information
SP - 346
EP - 349
AU - Hengyong XIANG
AU - Li ZHOU
AU - Xiaohui BA
AU - Jie CHEN
PY - 2021
DO - 10.1587/transinf.2020EDL8110
JO - IEICE TRANSACTIONS on Information
SN - 1745-1361
VL - E104-D
IS - 2
JA - IEICE TRANSACTIONS on Information
Y1 - February 2021
AB - The traditional RANSAC samples uniformly in the dataset which is not efficient in the task with rich prior information. This letter proposes GUISAC (Guided Sample Consensus), which samples with the guidance of various prior information. In image matching, GUISAC extracts seed points sets evenly on images based on various prior factors at first, then it incorporates seed points sets into the sampling subset with a growth function, and a new termination criterion is used to decide whether the current best hypothesis is good enough. Finally, experimental results show that the new method GUISAC has a great advantage in time-consuming than other similar RANSAC methods, and without loss of accuracy.
ER -
English
