Graph-based parallel large scale structure from motion

doi:10.1016/j.patcog.2020.107537

CORC > 自动化研究所 > 中国科学院自动化研究所 > 模式识别国家重点实验室 > 机器人视觉团队

	Graph-based parallel large scale structure from motion
	Chen, Yu 2; Shen, Shuhan 1,3; Chen, Yisong 2; Wang, Guoping 2
刊名	PATTERN RECOGNITION
	2020-11-01
卷号	107 页码:11
关键词	Clustering Structure from motion Minimum spanning tree
ISSN号	0031-3203
DOI	10.1016/j.patcog.2020.107537
通讯作者	Shen, Shuhan(shshen@nlpr.ia.ac.cn)
英文摘要	While Structure from Motion achieves great success in 3D reconstruction, it still meets challenges on large scale scenes. Incremental SfM approaches are robust to outliers, but are limited by low efficiency and easy suffer from drift problem. Though Global SfM methods are more efficient than incremental approaches, they are sensitive to outliers, and would also meet memory limitation and time bottleneck. In this work, large scale SfM is deemed as a graph problem, where graph are respectively constructed in image clustering step and local reconstructions merging step. By leveraging the graph structure, we are able to handle large scale dataset in divide-and-conquer manner. Firstly, images are modelled as graph nodes, with edges are retrieved from geometric information after feature matching. Then images are divided into independent clusters by a image clustering algorithm, and followed by a subgraph expansion step, the connection and completeness of scenes are enhanced by walking along a maximum spanning tree, which is utilized to construct overlapping images between clusters. Secondly, Image clusters are distributed into servers to execute SfM in parallel mode. Thirdly, after local reconstructions complete, we construct a minimum spanning tree to find accurate similarity transformations. Then the minimum spanning tree is transformed into a Minimum Height Tree to find a proper anchor node, and is further utilized to prevent error accumulation. We evaluate our approach on various kinds of datasets and our approach shows superiority over the state-of-the-art in accuracy and efficiency. Our algorithm is open-sourced in https://github.com/AIBluefisher/GraphSfM. (C) 2020 Elsevier Ltd. All rights reserved.
资助项目	National Key Technology Research and Development Program of China[2017YFB1002705] ; National Key Technology Research and Development Program of China[2017YFB0203002] ; National Key Technology Research and Development Program of China[2017YFB1002601] ; National Natural Science Foundation of China(NSFC)[61632003] ; National Natural Science Foundation of China(NSFC)[61661146002] ; National Natural Science Foundation of China(NSFC)[61872398] ; Equipment Development Project[315050501]
WOS关键词	MODEL ; OPTIMIZATION ; ACCURATE ; CUTS
WOS研究方向	Computer Science ; Engineering
语种	英语
出版者	ELSEVIER SCI LTD
WOS记录号	WOS:000552866000067
资助机构	National Key Technology Research and Development Program of China ; National Natural Science Foundation of China(NSFC) ; Equipment Development Project
内容类型	期刊论文
源URL	[http://ir.ia.ac.cn/handle/173211/40286]
专题	自动化研究所_模式识别国家重点实验室_机器人视觉团队
通讯作者	Shen, Shuhan
作者单位	1.Univ Chinese Acad Sci, Sch Artificial Intelligence, Beijing 100049, Peoples R China 2.Peking Univ, Sch Elect Engn & Comp Sci, Dept Comp Sci & Technol, Graph & Interact Lab, Beijing, Peoples R China 3.Chinese Acad Sci, Inst Automat, Natl Lab Pattern Recognit, Beijing 100190, Peoples R China
推荐引用方式 GB/T 7714	Chen, Yu,Shen, Shuhan,Chen, Yisong,et al. Graph-based parallel large scale structure from motion[J]. PATTERN RECOGNITION,2020,107:11.
APA	Chen, Yu,Shen, Shuhan,Chen, Yisong,&Wang, Guoping.(2020).Graph-based parallel large scale structure from motion.PATTERN RECOGNITION,107,11.
MLA	Chen, Yu,et al."Graph-based parallel large scale structure from motion".PATTERN RECOGNITION 107(2020):11.