A Novel Error Criterion of Fundamental Matrix Based on Principal Component Analysis

被引:0
作者
Bian, Yuxia [1 ]
Fang, Shuhong [1 ]
Zhou, Ye [2 ]
Wu, Xiaojuan [1 ]
Zhen, Yan [3 ]
Chu, Yongbin [1 ]
机构
[1] Chengdu Univ Informat Technol, Coll Resources & Environm, Chengdu 610000, Peoples R China
[2] Sichuan Zhihui Geog Informat Technol Co Ltd, Chengdu 610000, Peoples R China
[3] Southwest Petr Univ, Coll Earth Sci & Technol, Chengdu 610000, Peoples R China
基金
中国国家自然科学基金;
关键词
fundamental matrix; error; covariance; matrix differential theory; principal component analysis; Manhattan norm; epipolar geometric distance; EPIPOLAR GEOMETRY; UNCERTAINTY;
D O I
10.3390/rs14215341
中图分类号
X [环境科学、安全科学];
学科分类号
08 ; 0830 ;
摘要
Estimating the fundamental matrix (FM) using the known corresponding points is a key step for three-dimensional (3D) scene reconstruction, and its uncertainty directly affects camera calibration and point-cloud calculation. The symmetric epipolar distance is the most popular error criterion for estimating FM error, but it depends on the accuracy, number, and distribution of known corresponding points and is biased. This study mainly focuses on the error quantitative criterion of FM itself. First, the calculated FM process is reviewed with the known corresponding points. Matrix differential theory is then used to derive the covariance equation of FMs in detail. Subsequently, the principal component analysis method is followed to construct the scalar function as a novel error criterion to measure FM error. Finally, three experiments with different types of stereo images are performed to verify the rationality of the proposed method. Experiments found that the scalar function had approximately 90% correlation degree with the Manhattan norm, and greater than 80% with the epipolar geometric distance. Consequently, the proposed method is also appropriate for estimating FM error, in which the error ellipse or normal distribution curve is the reasonable error boundary of FM. When the error criterion value of this method falls into a normal distribution curve or an error ellipse, its corresponding FM is considered to have less error and be credible. Otherwise, it may be necessary to recalculate an FM to reconstruct 3D models.
引用
收藏
页数:18
相关论文
共 36 条
[21]  
Shi C.Y., 2000, GUID EXPR UNC MEAS, P9
[22]  
Sur F., 2008, 19 BRIT MACH VIS C B, V2008, P10
[23]  
Tian Zhuo, 2014, Applied Mechanics and Materials, V687-691, P3984, DOI 10.4028/www.scientific.net/AMM.687-691.3984
[24]   The development and comparison of robust methods for estimating the Fundamental Matrix [J].
Torr, PHS ;
Murray, DW .
INTERNATIONAL JOURNAL OF COMPUTER VISION, 1997, 24 (03) :271-300
[25]   MLESAC: A new robust estimator with application to estimating image geometry [J].
Torr, PHS ;
Zisserman, A .
COMPUTER VISION AND IMAGE UNDERSTANDING, 2000, 78 (01) :138-156
[26]   Bayesian model estimation and selection for epipolar geometry and generic manifold fitting [J].
Torr, PHS .
INTERNATIONAL JOURNAL OF COMPUTER VISION, 2002, 50 (01) :35-61
[27]   Two-View Geometry Estimation Using RANSAC With Locality Preserving Constraint [J].
Wang, Gang ;
Sun, Xiaoliang ;
Shang, Yang ;
Wang, Zi ;
Shi, Zhongchen ;
Yu, Qifeng .
IEEE ACCESS, 2020, 8 :7267-7279
[28]   A Global Fundamental Matrix Estimation Method of Planar Motion Based on Inlier Updating [J].
Wei, Liang ;
Huo, Ju .
SENSORS, 2022, 22 (12)
[29]   FSASAC: Random Sample Consensus Based on Data Filter and Simulated Annealing [J].
Wei Ruoyan ;
Wang Junfeng .
IEEE ACCESS, 2021, 9 :164935-164948
[30]  
Yan K., 2018, OPT PRECIS ENG, V26, P1, DOI [10.3788/OPE.20182602.0461, DOI 10.3788/OPE.20182602.0461]