中国科学院机构知识库网格
Chinese Academy of Sciences Institutional Repositories Grid
A Graph Matching and Energy Minimization Based Algorithm for Lunar Surface Image Mosaic

文献类型:会议论文

作者Li, Chuan; Liu, Zhi-Yong; Yang, Xu; Qiao, Hong; Liu, Chuan-Kai; Liu, ZY
出版日期2015
会议名称1st Chinese Conference on Computer Vision (CCCV)
会议日期SEP 18-20, 2015
会议地点Xidian Univ, Sch Comp Sci & Technol, Xian, PEOPLES R CHINA
关键词Lunar image mosaic Graph matching Energy Minimization GNCCP
通讯作者Liu, ZY
英文摘要This paper concerns the problem of lunar surface image mosaic, including both image registration andimage stitching procedures. A wide viewing composite obtained by mosaic technique plays an important role in many lunar rover's operations. Considering particular characters in lunar surfaceimages, such as large geometrical deformations, significant illumination differences and repeated patterns, previous image mosaic techniques often fail to create a qualified composite. In this paper, anovel algorithm is introduced to tackle the lunar surface image mosaic problem. Specifically, in theimage registration procedure, to deal with the misregistration problem caused by large geometrical deformation and repeated patterns, structural information is introduced to solve the feature correspondence by formulating it as a graph matching problem. In the image stitching procedure, anenergy minimization method is proposed based on the graduated nonconvexity and concavity procedure (GNCCP), to handle the visible seams caused by illumination differences and ghosting problem caused by large parallax in the overlapped area. Comparative experiments on real lunar surfaceimages acquired by Yutu rover and Apollo image gallery validate the effectiveness of the proposed method.
会议录COMPUTER VISION, CCCV 2015, PT I
源URL[http://ir.ia.ac.cn/handle/173211/12863]  
专题自动化研究所_复杂系统管理与控制国家重点实验室_机器人应用与理论组
通讯作者Liu, ZY
推荐引用方式
GB/T 7714
Li, Chuan,Liu, Zhi-Yong,Yang, Xu,et al. A Graph Matching and Energy Minimization Based Algorithm for Lunar Surface Image Mosaic[C]. 见:1st Chinese Conference on Computer Vision (CCCV). Xidian Univ, Sch Comp Sci & Technol, Xian, PEOPLES R CHINA. SEP 18-20, 2015.

入库方式: OAI收割

来源:自动化研究所

浏览0
下载0
收藏0
其他版本

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。