论文信息 - Homography matrix genetic consensus estimation algorithm

Homography matrix genetic consensus estimation algorithm

Homography matrix plays an important role in image stitching, camera calibration and other areas of computer vision. This paper presents a novel robust algorithm HM-GCE to estimate homography matrix with principles of genetic algorithm. Related experiments prove its superiority on the robustness, precision and time-consuming compared to the RANSAC algorithm.

Zhi Xue | Jun Zhou | Da Yao

[1] Olivier D. Faugeras,et al. The fundamental matrix: Theory, algorithms, and stability analysis , 2004, International Journal of Computer Vision.

[2] Heiko Hirschmüller,et al. Evaluation of Cost Functions for Stereo Matching , 2007, 2007 IEEE Conference on Computer Vision and Pattern Recognition.

[3] Charles V. Stewart,et al. MINPRAN: A New Robust Estimator for Computer Vision , 1995, IEEE Trans. Pattern Anal. Mach. Intell..

[4] Robert C. Bolles,et al. Random sample consensus: a paradigm for model fitting with applications to image analysis and automated cartography , 1981, CACM.

[5] Richard I. Hartley,et al. In Defense of the Eight-Point Algorithm , 1997, IEEE Trans. Pattern Anal. Mach. Intell..

[6] David E. Goldberg,et al. Genetic Algorithms in Search Optimization and Machine Learning , 1988 .

[7] Bernhard P. Wrobel,et al. Multiple View Geometry in Computer Vision , 2001 .

[8] Annick M. Leroy,et al. Robust Regression and Outlier Detection. , 1989 .

[9] Andrew Zisserman,et al. MLESAC: A New Robust Estimator with Application to Estimating Image Geometry , 2000, Comput. Vis. Image Underst..

[10] G LoweDavid,et al. Distinctive Image Features from Scale-Invariant Keypoints , 2004 .