A Robust Transform Estimator Based on Residual Analysis and Its Application on UAV Aerial Images

doi:10.3390/rs10020291

	A Robust Transform Estimator Based on Residual Analysis and Its Application on UAV Aerial Images
	Cai, Guorong 1,2; Su, Songzhi 3; Leng, Chengcai 4; Wu, Yundong 1,2; Lu, Feng 2,5
刊名	REMOTE SENSING
	2018-02-01
卷号	10 期号:2 页码:19
关键词	transform estimation residual order 3D reconstruction camera pose estimation
ISSN号	2072-4292
DOI	10.3390/rs10020291
通讯作者	Su, Songzhi(ssz@xmu.edu.cn)
英文摘要	Estimating the transformation between two images from the same scene is a fundamental step for image registration, image stitching and 3D reconstruction. State-of-the-art methods are mainly based on sorted residual for generating hypotheses. This scheme has acquired encouraging results in many remote sensing applications. Unfortunately, mainstream residual based methods may fail in estimating the transform between Unmanned Aerial Vehicle (UAV) low altitude remote sensing images, due to the fact that UAV images always have repetitive patterns and severe viewpoint changes, which produce lower inlier rate and higher pseudo outlier rate than other tasks. We performed extensive experiments and found the main reason is that these methods compute feature pair similarity within a fixed window, making them sensitive to the size of residual window. To solve this problem, three schemes that based on the distribution of residuals are proposed, which are called Relational Window (RW), Sliding Window (SW), Reverse Residual Order (RRO), respectively. Specially, RW employs a relaxation residual window size to evaluate the highest similarity within a relaxation model length. SW fixes the number of overlap models while varying the length of window size. RRO takes the permutation of residual values into consideration to measure similarity, not only including the number of overlap structures, but also giving penalty to reverse number within the overlap structures. Experimental results conducted on our own built UAV high resolution remote sensing images show that the proposed three strategies all outperform traditional methods in the presence of severe perspective distortion due to viewpoint change.
资助项目	National Natural Science Foundation of China[61363049] ; National Natural Science Foundation of China[61702251] ; National Natural Science Foundation of China[61572409] ; National Natural Science Foundation of China[61402386] ; National Natural Science Foundation of China[61571188] ; Key Technical Project of Fujian Province[2017H6015] ; Natural Science Foundation of Fujian Province[2016J01310] ; Natural Science Foundation of Fujian Province[2016J01309] ; Open Project Program of the Key Laboratory of Nondestructive Testing, Ministry of Education[ZD201429007]
WOS关键词	SCANNING POINT CLOUDS ; SAMPLE CONSENSUS ; MODEL ; REGISTRATION ; RECONSTRUCTION ; TRANSLATION ; REGRESSION ; AIRBORNE ; FEATURES ; SEARCH
WOS研究方向	Remote Sensing
语种	英语
出版者	MDPI
WOS记录号	WOS:000427542100135
资助机构	National Natural Science Foundation of China ; Key Technical Project of Fujian Province ; Natural Science Foundation of Fujian Province ; Open Project Program of the Key Laboratory of Nondestructive Testing, Ministry of Education
内容类型	期刊论文
源URL	[http://ir.igsnrr.ac.cn/handle/311030/57188]
专题	中国科学院地理科学与资源研究所
通讯作者	Su, Songzhi
作者单位	1.Jimei Univ, Sch Comp Engn, Xiamen 360121, Peoples R China 2.Fujian Collaborat Innovat Ctr Big Data Applicat G, Fuzhou 350003, Fujian, Peoples R China 3.Xiamen Univ, Sch Informat Sci & Technol, Xiamen 361000, Peoples R China 4.Northwest Univ, Sch Math, Xian 710127, Shaanxi, Peoples R China 5.Chinese Acad Sci, Inst Geog Sci & Nat Resources Res, State Key Lab Resources & Environm Informat Syst, Beijing 100101, Peoples R China
推荐引用方式 GB/T 7714	Cai, Guorong,Su, Songzhi,Leng, Chengcai,et al. A Robust Transform Estimator Based on Residual Analysis and Its Application on UAV Aerial Images[J]. REMOTE SENSING,2018,10(2):19.
APA	Cai, Guorong,Su, Songzhi,Leng, Chengcai,Wu, Yundong,&Lu, Feng.(2018).A Robust Transform Estimator Based on Residual Analysis and Its Application on UAV Aerial Images.REMOTE SENSING,10(2),19.
MLA	Cai, Guorong,et al."A Robust Transform Estimator Based on Residual Analysis and Its Application on UAV Aerial Images".REMOTE SENSING 10.2(2018):19.