Knowledge Commons of Institute of Automation,CAS
High accuracy correspondence field estimation via MST based patch matching | |
Zhang, Feihu; Xu, Shibiao; Zhang, Xiaopeng | |
发表期刊 | MULTIMEDIA TOOLS AND APPLICATIONS |
ISSN | 1380-7501 |
2020-01-28 | |
页码 | 19 |
通讯作者 | Xu, Shibiao(shibiao.xu@ia.ac.cn) ; Zhang, Xiaopeng(xiaopeng.zhang@ia.ac.cn) |
摘要 | This paper presents an effective framework for correspondence field estimation. The core idea is to construct pixel-level and superpixel-level patch matching to achieve high accuracy estimation as well as fast speed computation. To this end, a hybrid edge-preserving supported weighting approach is first developed, which contributes to better performance on the pixel level, especially on those in the regions of fine structures. Then, a local Minimum Spanning Tree (MST) is constructed to describe regions and develop the adaptive smooth penalty weights, so that the over-patching in large textureless regions can be effectively avoided. In addition, the MST is further extended to handle occlusions in way of edge preserving strategy. Finally, all the above treatments are collected into an optimization model where the objective function is developed in terms of Markov Random Filed (MRF). In computation, a fast yet efficient iterative optimization strategy is developed. Our approach achieves favorable place on optical flow benchmark, which locates at the top two and top four for endpoint error and angular error evaluations among more than 130 approaches listed in the webpage. |
关键词 | Optical flow Minimum spanning tree PatchMatch |
DOI | 10.1007/s11042-020-08633-y |
关键词[WOS] | ADAPTIVE SUPPORT ; OPTICAL-FLOW ; STEREO |
收录类别 | SCI |
语种 | 英语 |
资助项目 | National Key R&D Program of China[2018YFB2100602] ; National Natural Science Foundation of China[61620106003] ; National Natural Science Foundation of China[61971418] ; National Natural Science Foundation of China[61771026] ; National Natural Science Foundation of China[61671451] ; National Natural Science Foundation of China[61571046] ; National Key R&D Program of China[2018YFB2100602] ; National Natural Science Foundation of China[61620106003] ; National Natural Science Foundation of China[61971418] ; National Natural Science Foundation of China[61771026] ; National Natural Science Foundation of China[61671451] ; National Natural Science Foundation of China[61571046] |
项目资助者 | National Key R&D Program of China ; National Natural Science Foundation of China |
WOS研究方向 | Computer Science ; Engineering |
WOS类目 | Computer Science, Information Systems ; Computer Science, Software Engineering ; Computer Science, Theory & Methods ; Engineering, Electrical & Electronic |
WOS记录号 | WOS:000515728500005 |
出版者 | SPRINGER |
七大方向——子方向分类 | 三维视觉 |
引用统计 | |
文献类型 | 期刊论文 |
条目标识符 | http://ir.ia.ac.cn/handle/173211/38321 |
专题 | 多模态人工智能系统全国重点实验室_三维可视计算 |
通讯作者 | Xu, Shibiao; Zhang, Xiaopeng |
作者单位 | Chinese Acad Sci, Natl Lab Pattern Recognit, Inst Automat, Beijing 100190, Peoples R China |
第一作者单位 | 模式识别国家重点实验室 |
通讯作者单位 | 模式识别国家重点实验室 |
推荐引用方式 GB/T 7714 | Zhang, Feihu,Xu, Shibiao,Zhang, Xiaopeng. High accuracy correspondence field estimation via MST based patch matching[J]. MULTIMEDIA TOOLS AND APPLICATIONS,2020:19. |
APA | Zhang, Feihu,Xu, Shibiao,&Zhang, Xiaopeng.(2020).High accuracy correspondence field estimation via MST based patch matching.MULTIMEDIA TOOLS AND APPLICATIONS,19. |
MLA | Zhang, Feihu,et al."High accuracy correspondence field estimation via MST based patch matching".MULTIMEDIA TOOLS AND APPLICATIONS (2020):19. |
条目包含的文件 | 条目无相关文件。 |
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