Noise-resistant matching algorithm integrating regional information for low-light stereo vision | |
Feng, Huahui1,2; Zhang, Geng1; Hu, Bingliang1; Zhang, Xin1; Li, Siyuan1,2,3 | |
作者部门 | 光谱成像技术研究室 |
2019-01 | |
发表期刊 | JOURNAL OF ELECTRONIC IMAGING |
ISSN | 1017-9909;1560-229X |
卷号 | 28期号:1 |
产权排序 | 1 |
摘要 | Low-light stereo vision is a challenging problem because images captured in dark environment usually suffer from strong random noises. Some widely adopted algorithms, such as semiglobal matching, mainly depend on pixel-level information. The accuracy of local feature matching and disparity propagation decreases when pixels become noisy. Focusing on this problem, we proposed a matching algorithm that utilizes regional information to enhance the robustness to local noisy pixels. This algorithm is based on the framework of ADCensus feature and semiglobal matching. It extends the original algorithm in two ways. First, image segmentation information is added to solve the problem of incomplete path and improve the accuracy of cost calculation. Second, the matching cost volume is calculated with AD-SoftCensus measure that minimizes the impact of noise by changing the pattern of the census descriptor from binary to trinary. The robustness of the proposed algorithm is validated on Middlebury datasets, synthetic data, and real world data captured by a low-light camera in darkness. The results show that the proposed algorithm has better performance and higher matching rate among top-ranked algorithms on low signal-to-noise ratio data and high accuracy on the Middlebury benchmark datasets. (C) 2019 SPIE and IS&T |
关键词 | stereo matching low-light random noise regional information |
DOI | 10.1117/1.JEI.28.1.013050 |
收录类别 | SCI ; EI |
语种 | 英语 |
WOS记录号 | WOS:000460119700050 |
出版者 | IS&T & SPIE |
EI入藏号 | 20191106619862 |
引用统计 | |
文献类型 | 期刊论文 |
条目标识符 | http://ir.opt.ac.cn/handle/181661/31325 |
专题 | 光谱成像技术研究室 |
通讯作者 | Li, Siyuan |
作者单位 | 1.Chinese Acad Sci, Xian Inst Opt & Precis Mech, Key Lab Spectral Imaging Technol CAS, Xian, Shaanxi, Peoples R China 2.Univ Chinese Acad Sci, Beijing, Peoples R China 3.Xi An Jiao Tong Univ, Xian, Shaanxi, Peoples R China |
推荐引用方式 GB/T 7714 | Feng, Huahui,Zhang, Geng,Hu, Bingliang,et al. Noise-resistant matching algorithm integrating regional information for low-light stereo vision[J]. JOURNAL OF ELECTRONIC IMAGING,2019,28(1). |
APA | Feng, Huahui,Zhang, Geng,Hu, Bingliang,Zhang, Xin,&Li, Siyuan.(2019).Noise-resistant matching algorithm integrating regional information for low-light stereo vision.JOURNAL OF ELECTRONIC IMAGING,28(1). |
MLA | Feng, Huahui,et al."Noise-resistant matching algorithm integrating regional information for low-light stereo vision".JOURNAL OF ELECTRONIC IMAGING 28.1(2019). |
条目包含的文件 | ||||||
文件名称/大小 | 文献类型 | 版本类型 | 开放类型 | 使用许可 | ||
Noise-resistant matc(4560KB) | 期刊论文 | 出版稿 | 限制开放 | CC BY-NC-SA | 请求全文 |
除非特别说明,本系统中所有内容都受版权保护,并保留所有权利。
修改评论