Title :
A new mothed for epipolar line rectification
Author :
Xu, Xiaoyan ; Liu, Ran ; Yi, Lin
Author_Institution :
Coll. of Comput. Sci., Chongqing Univ., Chongqing, China
Abstract :
An improved algorithm of epipolar line rectification for stereo pairs, which combines Seitz Method with Francesco Method, is proposed. Firstly, the fundamental matrix is calculated using the improved eight-point algorithm (or other improved methods such as weighted normalization algorithm) and then as an input for Seitz Method to get the projective transformation matrices. Finally, these matrices are used to initialize the Francesco method for optimization, avoiding in this way local minima as well as the dependence on the precision of the fundamental matrix. Experimental results show that the presented method works more accurately with low image distortion in contrast to Francesco Method and Mallon Method.
Keywords :
computational geometry; matrix algebra; stereo image processing; Francesco Method; Mallon Method; Seitz Method; epipolar line rectification; fundamental matrix; image distortion; improved eight-point algorithm; projective transformation matrices; stereo pairs; Cancer; Computer science; Educational institutions; Geometry; Hospitals; Optimization methods; Pixel; Radio access networks; Sufficient conditions; Testing; epipolar geometry; epipolar line rectification; image rectification; projective rectification; stereo pairs;
Conference_Titel :
Intelligent Computing and Intelligent Systems, 2009. ICIS 2009. IEEE International Conference on
Conference_Location :
Shanghai
Print_ISBN :
978-1-4244-4754-1
Electronic_ISBN :
978-1-4244-4738-1
DOI :
10.1109/ICICISYS.2009.5357665