VF-SIFT: Very Fast SIFT Feature Matching
Feature-based image matching is one of the most fundamental issues in computer vision tasks. As the number of features increases, the matching process rapidly becomes a bottleneck. This paper presents a novel method to speed up SIFT feature matching. The main idea is to extend SIFT feature by a few pairwise independent angles, which are invariant to rotation, scale and illumination changes. During feature extraction, SIFT features are classified based on their introduced angles into different clusters and stored in multidimensional table. Thus, in feature matching, only SIFT features that belong to clusters, where correct matches may be expected are compared. The performance of the proposed methods was tested on two groups of images, real-world stereo images and standard dataset images, through comparison with the performances of two state of the arte algorithms for ANN searching, hierarchical k-means and randomized kd-trees. The presented experimental results show that the performance of the proposed method extremely outperforms the two other considered algorithms. The experimental results show that the feature matching can be accelerated about 1250 times with respect to exhaustive search without losing a noticeable amount of correct matches.
KeywordsVery Fast SIFT VF-SIFT Fast features matching Fast image matching
Unable to display preview. Download preview PDF.
- 2.Ke, Y., Sukthankar, R.: PCA-sift: A more distinctive representation for local image descriptors. In: Int. Conf. on Computer Vision and Pattern Recognition, pp. 506–513 (2004)Google Scholar
- 3.Mikolajczyk, K., Schmid, C.: A performance evaluation of local descriptors. IEEE Transactions on pattern analysis and machine intelligence 27(10) (2005)Google Scholar
- 5.Sinha, S.N., Frahm, J.-M., Pollefeys, M., Genc, Y.: GPU-based video feature tracking and matching. Technical report, Department of Computer Science, UNC Chapel Hill (2006)Google Scholar
- 6.Heymann, S., Miller, K., Smolic, A., Froehlich, B., Wiegand, T.: SIFT implementation and optimization for general-purpose gpu. In: WSCG 2007 (January 2007)Google Scholar
- 7.Chariot, A., Keriven, R.: GPU-boosted online image matching. In: 19th Int. Conf. on Pattern Recognition, Tampa, Florida, USA (2008)Google Scholar
- 8.Se, S., Ng, H., Jasiobedzki, P., Moyung, T.: Vision based modeling and localization for planetary exploration rovers. In: Proceedings of International Astronautical Congress (2004)Google Scholar
- 9.Firedman, J.H., Bentley, J.L., Finkel, R.A.: An algorithm for finding best matches in logarithmic expected time. ACM Transactions Mathematical Software, 209–226 (1977)Google Scholar
- 10.Muja, M., Lowe, D.G.: Fast Approximate Nearest Neighbors with Automatic Algorithm Configuration. In: Int. Conf. on Computer Vision Theory and Applications (2009)Google Scholar
- 11.Alhwarin, F., Ristic Durant, D., Gräser, A.: Speeded up image matching using split and extended SIFT features. In: Conf. on Computer Vision Theory and Applications (2010)Google Scholar
- 12.Simon, M.K., Shihabi, M.M., Moon, T.: Optimum Detection of Tones Transmitted by a Spacecrft, TDA PR 42-123, pp.69–98 (1995)Google Scholar
- 13.Image database: http://lear.inrialpes.fr/people/Mikolajczyk/Database/index.html