RES-Q: Robust Outlier Detection Algorithm for Fundamental Matrix Estimation

doi:10.1109/ACCESS.2018.2867915

	RES-Q: Robust Outlier Detection Algorithm for Fundamental Matrix Estimation
	Bharati, Sushil Pratap 2; Cen, Feng 3; Sharda, Ajay 1; Wang, Guanghui 2,4
刊名	IEEE ACCESS
	2018
卷号	6 页码:48664-48674
关键词	Fundamental Matrix Stereo Vision Robust Statistics Outliers Detection
ISSN号	2169-3536
DOI	10.1109/ACCESS.2018.2867915
文献子类	Article
英文摘要	Detection of outliers present in noisy images for an accurate fundamental matrix estimation is an important research topic in the field of 3-D computer vision. Although a lot of research is conducted in this domain, not much study has been done in utilizing the robust statistics for successful outlier detection algorithms. This paper proposes to utilize a reprojection residual error-based technique for outlier detection. Given a noisy stereo image pair obtained from a pair of stereo cameras and a set of initial point correspondences between them, reprojection residual error and 3-sigma principle together with robust statistic-based Qn estimator (RES-Q) is proposed to efficiently detect the outliers and estimate the fundamental matrix with superior accuracy. The proposed RES-Q algorithm demonstrates greater precision and lower reprojection residual error than the state-of-the-art techniques. Moreover, in contrast to the assumption of Gaussian noise or symmetric noise model adopted by most previous approaches, the RES-Q is found to be robust for both symmetric and asymmetric random noise assumptions. The proposed algorithm is experimentally tested on both synthetic and real image data sets, and the experiments show that RES-Q is more effective and efficient than the classical outlier detection algorithms.
WOS关键词	INTELLIGENT VEHICLES ; EPIPOLAR GEOMETRY ; SAMPLE CONSENSUS ; FACTORIZATION ; REGISTRATION ; RECOGNITION ; REMOVAL ; VISION ; MOTION
WOS研究方向	Computer Science ; Engineering ; Telecommunications
语种	英语
出版者	IEEE-INST ELECTRICAL ELECTRONICS ENGINEERS INC
WOS记录号	WOS:000445484000001
资助机构	Kansas NASA EPSCoR Program(KNEP-PDG-10-2017-KU) ; United States Department of Agriculture (USDA)(USDA 2017-67007-26153) ; General Research Fund of the University of Kansas(2228901) ; National Natural Science Foundation of China(61573351)
内容类型	期刊论文
源URL	[http://ir.ia.ac.cn/handle/173211/27908]
专题	中国科学院自动化研究所
通讯作者	Wang, Guanghui
作者单位	1.Kansas State Univ, Biol & Agr Engn, Manhattan, KS 66506 USA 2.Univ Kansas, Dept Elect Engn & Comp Sci, Lawrence, KS 66045 USA 3.Tongji Univ, Coll Elect & Informat Engn, Dept Control Sci & Engn, Shanghai 200092, Peoples R China 4.Chinese Acad Sci, Inst Automat, Beijing 100190, Peoples R China
推荐引用方式 GB/T 7714	Bharati, Sushil Pratap,Cen, Feng,Sharda, Ajay,et al. RES-Q: Robust Outlier Detection Algorithm for Fundamental Matrix Estimation[J]. IEEE ACCESS,2018,6:48664-48674.
APA	Bharati, Sushil Pratap,Cen, Feng,Sharda, Ajay,&Wang, Guanghui.(2018).RES-Q: Robust Outlier Detection Algorithm for Fundamental Matrix Estimation.IEEE ACCESS,6,48664-48674.
MLA	Bharati, Sushil Pratap,et al."RES-Q: Robust Outlier Detection Algorithm for Fundamental Matrix Estimation".IEEE ACCESS 6(2018):48664-48674.