Better Correspondence by Registration
Accurate image correspondence is crucial for estimating multiple-view geometry. In this paper, we present a registration-based method for improving accuracy of the image correspondences. We apply the method to fundamental matrix estimation under practical situations where there are both erroneous matches (outliers) and small feature location errors. Our registration-based method can correct feature locational error to less than 0.1 pixel, remedying localization inaccuracy due to feature detectors. Moreover, we carefully examine feature similarity based on their post-alignment appearance, providing a more reasonable prior for subsequent outlier detection. Experiments show that we can improve feature localization accuracy of the MSER feature detector, which recovers the most accurate feature localization as reported in a recent study by Haja and others. As a result of applying our method, we recover the fundamental matrix with better accuracy and more efficiency.
Unable to display preview. Download preview PDF.
- 5.Chum, O., Matas, J.: Matching with PROSAC: Progressive sample consensus. In: Proceedings of Computer Vision and Pattern Recognition, pp. I: 220–226 (2005)Google Scholar
- 6.Haja, A., Jahne, B., Abraham, S.: Localization accuracy of region detectors. In: Proceedings of Computer Vision and Pattern Recognition, June 2008, pp. 1–8 (2008)Google Scholar
- 9.Georgel, P., Benhimane, S., Navab, N.: A unified approach combining photometric and geometric information for pose estimation. In: Proceedings of British Machine Vision Conference, pp. 133–142 (2008)Google Scholar
- 11.Obdrzalek, S., Matas, J.: Image retrieval using local compact DCT-based representation, pp. 490–497 (2003)Google Scholar
- 16.Luong, Q., Deriche, R., Faugeras, O., Papadopoulo, T.: On determining the fundamental matrix: Analysis of different methods and experimental results (1993)Google Scholar
- 20.Conn, A.R., Gould, N.I.M., Toint, P.L.: Trust-Region Methods. Society for Industrial and Applied Mathematics and Mathematical Programming Society (2000)Google Scholar
- 21.Riggi, F., Toews, M., Arbel, T.: Fundamental matrix estimation via TIP - transfer of invariant parameters. In: Proceedings of the International Conference on Pattern Recognition, Hong Kong, August 2006, pp. 21–24 (2006)Google Scholar