Image Rectification Algorithm Based on Immune Monoclonal Strategy
Year: 2010
Journal of Information and Computing Science, Vol. 5 (2010), Iss. 2 : pp. 109–116
Abstract
To rapidly and accurately search the corresponding points along scan-lines, rectification of stereo image pairs are performed so that all the epipolar lines are parallel to the horizontal scan-lines and the vertical difference between the corresponding epipolar lines is zero. According to the layered rectification algorithm presented by charles loop, we can divide the process of rectification into three steps including projective transformation, affine transformation and shearing transformation. The key to proposed algorithm is the computation of projective matrix, the algorithm uses the affine epipolar geometry constraint to compute projective matrix and determines the optimal value of unknown parameters in projective matrix by immune monoclonal strategy. In the process of solving the matrix, the algorithm does not require the relative matrix be positive definite. The experiments show that the proposed algorithm is an effective image rectification algorithm and it has the obvious advantage in mean vertical difference, distortion and speed of rectification.
Journal Article Details
Publisher Name: Global Science Press
Language: English
DOI: https://doi.org/2024-JICS-22718
Journal of Information and Computing Science, Vol. 5 (2010), Iss. 2 : pp. 109–116
Published online: 2010-01
AMS Subject Headings:
Copyright: COPYRIGHT: © Global Science Press
Pages: 8