Title :
A robust method for estimating the fundamental matrix
Author :
Junqing, Shen ; Mingxing, Hu ; Baozong, Yuan
Author_Institution :
Instn. of Inf. Sci., Northern Jiaotong Univ., Beijing, China
Abstract :
We present a novel method for estimating the fundamental matrix, a key problem arising in stereovision. The method aims to minimize a cost function that is derived from maximum likelihood considerations. The minimizer turns out. to be significantly more robust than that of the linear method of eight points.
Keywords :
computer vision; geometry; matrix algebra; maximum likelihood estimation; minimisation; stereo image processing; computer vision; cost function minimization; epipolar geometry; fundamental matrix estimation; maximum likelihood considerations; stereovision; Cameras; Computational geometry; Computer vision; Cost function; Equations; Information geometry; Information science; Layout; Maximum likelihood estimation; Robustness;
Conference_Titel :
Signal Processing, 2002 6th International Conference on
Print_ISBN :
0-7803-7488-6
DOI :
10.1109/ICOSP.2002.1181200
