An improved image rectification algorithm based on particle swarm optimization

Authors:
Hongwei Gao;Ben Niu;Bin Li;Yang Yu
Affiliations:
School of Information Science & Engineering, Shenyang Ligong University Shenyang, China;Hefei Institute of Intelligent Machines, Chinese Academy of Sciences Hefei, China and College of Management, ShenzhenUniversity Shenzhen, China;School of Information Science & Engineering, Shenyang Ligong University Shenyang, China;School of Information Science & Engineering, Shenyang Ligong University Shenyang, China
Venue:
ICIC'10 Proceedings of the 6th international conference on Advanced intelligent computing theories and applications: intelligent computing
Year:
2010

Citing 5
Cited 0

Three-dimensional computer vision: a geometric viewpoint

Three-dimensional computer vision: a geometric viewpoint
Determining the Epipolar Geometry and its Uncertainty: A Review

International Journal of Computer Vision
Theory and Practice of Projective Rectification

International Journal of Computer Vision
Cylindrical rectification to minimize epipolar distortion

CVPR '97 Proceedings of the 1997 Conference on Computer Vision and Pattern Recognition (CVPR '97)
Symbiotic multi-swarm PSO for portfolio optimization

ICIC'09 Proceedings of the Intelligent computing 5th international conference on Emerging intelligent computing technology and applications

Quantified Score

Hi-index	0.00

Visualization

Abstract

Image rectification is a method to apply projective transformation to image pair which can ensure the epipolar lines in one horizontal line. There is only horizontal disparity in two images and the matching speed can be improved in this situation. A simple rectification method is described in this paper. It takes the element in the fundamental matrix and epipole as initial value and uses PSO to calculate eight optimal points according with rectification rule by RANSAC robust estimation method. Then, the practical and optimal projective transformation matrixes are confirmed. Epipolar line rectification experiments based on synthetical image and real image show the validity of the algorithm.