Adaptive depth constraint-based underwater binocular image feature matching
Objective In this paper, to address sparse feature points and unique epipolar constraints, an adaptive depth constraint-based underwater feature matching (ADC-UFM) scheme is proposed. MethodsBy combining a features from accelerated segment test (FAST) operator with scale invariant feature transform...
| Main Authors: | , , , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
Editorial Office of Chinese Journal of Ship Research
2021-12-01
|
| Series: | Zhongguo Jianchuan Yanjiu |
| Subjects: | |
| Online Access: | http://www.ship-research.com/cn/article/doi/10.19693/j.issn.1673-3185.02197 |
| _version_ | 1831643429424070656 |
|---|---|
| author | Jiahe TIAN Ning WANG Tingkai CHEN Chunyan LI Shuai CHEN |
| author_facet | Jiahe TIAN Ning WANG Tingkai CHEN Chunyan LI Shuai CHEN |
| author_sort | Jiahe TIAN |
| collection | DOAJ |
| description | Objective In this paper, to address sparse feature points and unique epipolar constraints, an adaptive depth constraint-based underwater feature matching (ADC-UFM) scheme is proposed. MethodsBy combining a features from accelerated segment test (FAST) operator with scale invariant feature transform (SIFT) descriptors, the matching accuracy can be dramatically improved. By introducing an underwater refractive factor, the matching constraint model (MCM) can be effectively established, thereby contributing to eliminating mismatched points. The adaptive threshold choosing (ATC) module is finely devised to preserve image feature information in changeable underwater environments to an extreme extent. ResultsComprehensive experiments show that the proposed ADC-UFM scheme can outperform typical matching schemes including SIFT, speeded-up robust features (SURF) and SIFT feature matching based on underwater curve constraint (UCC-SIFT), which not only achieves 85.2% matching accuracy but also meets the real-time requirements. ConclusionThe results of this study can provide a reliable guarantee for subsequent underwater 3D reconstruction based on the binocular vision system. |
| first_indexed | 2024-12-19T12:59:53Z |
| format | Article |
| id | doaj.art-8fc4e2d1201c447abbf83ed485d31bf7 |
| institution | Directory Open Access Journal |
| issn | 1673-3185 |
| language | English |
| last_indexed | 2024-12-19T12:59:53Z |
| publishDate | 2021-12-01 |
| publisher | Editorial Office of Chinese Journal of Ship Research |
| record_format | Article |
| series | Zhongguo Jianchuan Yanjiu |
| spelling | doaj.art-8fc4e2d1201c447abbf83ed485d31bf72022-12-21T20:20:17ZengEditorial Office of Chinese Journal of Ship ResearchZhongguo Jianchuan Yanjiu1673-31852021-12-0116612413110.19693/j.issn.1673-3185.02197ZG2197Adaptive depth constraint-based underwater binocular image feature matchingJiahe TIAN0Ning WANG1Tingkai CHEN2Chunyan LI3Shuai CHEN4College of Marine Electrical Engineering, Dalian Maritime University, Dalian 116026, ChinaCollege of Marine Engineering, Dalian Maritime University, Dalian 116026, ChinaCollege of Marine Electrical Engineering, Dalian Maritime University, Dalian 116026, ChinaCollege of Marine Electrical Engineering, Dalian Maritime University, Dalian 116026, ChinaCollege of Marine Electrical Engineering, Dalian Maritime University, Dalian 116026, ChinaObjective In this paper, to address sparse feature points and unique epipolar constraints, an adaptive depth constraint-based underwater feature matching (ADC-UFM) scheme is proposed. MethodsBy combining a features from accelerated segment test (FAST) operator with scale invariant feature transform (SIFT) descriptors, the matching accuracy can be dramatically improved. By introducing an underwater refractive factor, the matching constraint model (MCM) can be effectively established, thereby contributing to eliminating mismatched points. The adaptive threshold choosing (ATC) module is finely devised to preserve image feature information in changeable underwater environments to an extreme extent. ResultsComprehensive experiments show that the proposed ADC-UFM scheme can outperform typical matching schemes including SIFT, speeded-up robust features (SURF) and SIFT feature matching based on underwater curve constraint (UCC-SIFT), which not only achieves 85.2% matching accuracy but also meets the real-time requirements. ConclusionThe results of this study can provide a reliable guarantee for subsequent underwater 3D reconstruction based on the binocular vision system.http://www.ship-research.com/cn/article/doi/10.19693/j.issn.1673-3185.02197adaptive depth constraint (adc)underwater binocular imagesfeature matchingmismatched point elimination |
| spellingShingle | Jiahe TIAN Ning WANG Tingkai CHEN Chunyan LI Shuai CHEN Adaptive depth constraint-based underwater binocular image feature matching Zhongguo Jianchuan Yanjiu adaptive depth constraint (adc) underwater binocular images feature matching mismatched point elimination |
| title | Adaptive depth constraint-based underwater binocular image feature matching |
| title_full | Adaptive depth constraint-based underwater binocular image feature matching |
| title_fullStr | Adaptive depth constraint-based underwater binocular image feature matching |
| title_full_unstemmed | Adaptive depth constraint-based underwater binocular image feature matching |
| title_short | Adaptive depth constraint-based underwater binocular image feature matching |
| title_sort | adaptive depth constraint based underwater binocular image feature matching |
| topic | adaptive depth constraint (adc) underwater binocular images feature matching mismatched point elimination |
| url | http://www.ship-research.com/cn/article/doi/10.19693/j.issn.1673-3185.02197 |
| work_keys_str_mv | AT jiahetian adaptivedepthconstraintbasedunderwaterbinocularimagefeaturematching AT ningwang adaptivedepthconstraintbasedunderwaterbinocularimagefeaturematching AT tingkaichen adaptivedepthconstraintbasedunderwaterbinocularimagefeaturematching AT chunyanli adaptivedepthconstraintbasedunderwaterbinocularimagefeaturematching AT shuaichen adaptivedepthconstraintbasedunderwaterbinocularimagefeaturematching |