How to Overcome Perceptual Aliasing in ASIFT?
SIFT is one of the most popular algorithms to extract points of interest from images. It is a scale+rotation invariant method. As a consequence, if one compares points of interest between two images subject to a large viewpoint change, then only a few, if any, common points will be retrieved. This may lead subsequent algorithms to failure, especially when considering structure and motion or object recognition problems. Reaching at least affine invariance is crucial for reliable point correspondences. Successful approaches have been recently proposed by several authors to strengthen scale+rotation invariance into affine invariance, using viewpoint simulation (e.g. the ASIFT algorithm). However, almost all resulting algorithms fail in presence of repeated patterns, which are common in man-made environments, because of the so-called perceptual aliasing. Focusing on ASIFT, we show how to overcome the perceptual aliasing problem. To the best of our knowledge, the resulting algorithm performs better than any existing generic point matching procedure.
KeywordsSimulated Image Repeated Pattern Sift Feature Epipolar Line Epipolar Geometry
Unable to display preview. Download preview PDF.
- 3.Gordon, I., Lowe, D.: Scene modelling, recognition and tracking with invariant image features. In: Proc. International Symposium on Mixed and Augmented Reality (ISMAR), pp. 110–119 (2004)Google Scholar
- 11.Molton, N.D., Davison, A.J., Reid, I.D.: Locally planar patch features for real-time structure from motion. In: Proc. British Machine Vision Conference, BMVC (2004)Google Scholar
- 12.Whitehead, S., Ballard, D.: Learning to perceive and act by trial and error. Machine Learning 7, 45–83 (1991)Google Scholar
- 15.Noury, N., Sur, F., Berger, M.O.: Determining point correspondences between two views under geometric constraint and photometric consistency. Research Report 7246, INRIA (2010)Google Scholar
- 20.Hsiao, E., Collet, A., Hebert, M.: Making specific features less discriminative to improve point-based 3D object recognition. In: Proc. Conference on Computer Vision and Pattern Recognition, CVPR (2010)Google Scholar
- 21.Morel, J.M., Yu, G.: ASIFT. In: IPOL Workshop (2009), http://www.ipol.im/pub/algo/my_affine_sift (Consulted 6.30.2010)
- 22.Vedaldi, A., Fulkerson, B.: VLFeat: An open and portable library of computer vision algorithms (2008), http://www.vlfeat.org/ (Consulted 6.30.2010)