Structured-Patch Optimization for Dense Correspondence | |
Qin, Xiameng1; Shen, Jianbing1; Mao, Xiaoyang2; Li, Xuelong3; Jia, Yunde1 | |
2015-03-01 | |
发表期刊 | IEEE TRANSACTIONS ON MULTIMEDIA |
卷号 | 17期号:3页码:295-306 |
摘要 | This paper presents a new method to compute the dense correspondences between two images by using the energy optimization and the structured patches. In terms of the property of the sparse feature and the principle that nearest sub-scenes and neighbors are much more similar, we design a new energy optimization to guide the dense matching process and find the reliable correspondences. The sparse features are also employed to design a new structure to describe the patches. Both transformation and deformation with the structured patches are considered and incorporated into an energy optimization framework. Thus, our algorithm can match the objects robustly in complicated scenes. Finally, a local refinement technique is proposed to solve the perturbation of the matched patches. Experimental results demonstrate that our method outperforms the state-of-the-art matching algorithms. |
文章类型 | Article |
关键词 | Dense Correspondence Features Match Optimization Structured Patch |
WOS标题词 | Science & Technology ; Technology |
DOI | 10.1109/TMM.2015.2395078 |
收录类别 | SCI ; EI |
关键词[WOS] | OPTICAL-FLOW ; EXTRACTION ; STEREO ; IMAGES ; VIDEO |
语种 | 英语 |
WOS研究方向 | Computer Science ; Telecommunications |
WOS类目 | Computer Science, Information Systems ; Computer Science, Software Engineering ; Telecommunications |
WOS记录号 | WOS:000351585700003 |
引用统计 | |
文献类型 | 期刊论文 |
条目标识符 | http://ir.opt.ac.cn/handle/181661/24113 |
专题 | 光谱成像技术研究室 |
作者单位 | 1.Beijing Inst Technol, Sch Comp Sci, Beijing Lab Intelligent Informat Technol, Beijing 100081, Peoples R China 2.Univ Yamanashi, Interdisciplinary Grad Sch Med & Engn, Kofu, Yamanashi 4008510, Japan 3.Chinese Acad Sci, Xian Inst Opt & Precis Mech, Ctr Opt Imagery Anal & Learning, State Key Lab Transient Opt & Photon, Xian 710119, Peoples R China |
推荐引用方式 GB/T 7714 | Qin, Xiameng,Shen, Jianbing,Mao, Xiaoyang,et al. Structured-Patch Optimization for Dense Correspondence[J]. IEEE TRANSACTIONS ON MULTIMEDIA,2015,17(3):295-306. |
APA | Qin, Xiameng,Shen, Jianbing,Mao, Xiaoyang,Li, Xuelong,&Jia, Yunde.(2015).Structured-Patch Optimization for Dense Correspondence.IEEE TRANSACTIONS ON MULTIMEDIA,17(3),295-306. |
MLA | Qin, Xiameng,et al."Structured-Patch Optimization for Dense Correspondence".IEEE TRANSACTIONS ON MULTIMEDIA 17.3(2015):295-306. |
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 | ||
Structured-Patch Opt(2956KB) | 期刊论文 | 出版稿 | 限制开放 | CC BY | 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