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.

[1]  Matthew A. Brown,et al.  Automatic Panoramic Image Stitching using Invariant Features , 2007, International Journal of Computer Vision.

[2]  Jiri Matas,et al.  Robust wide-baseline stereo from maximally stable extremal regions , 2004, Image Vis. Comput..

[3]  Andrew Zisserman,et al.  Automated location matching in movies , 2003, Comput. Vis. Image Underst..

[4]  Jean-Michel Morel,et al.  From Gestalt Theory to Image Analysis: A Probabilistic Approach , 2007 .

[5]  Cordelia Schmid,et al.  A Comparison of Affine Region Detectors , 2005, International Journal of Computer Vision.

[6]  Dima Damen,et al.  British Machine Vision Conference (BMVC) , 2007 .

[7]  Andrew Zisserman,et al.  Planar grouping for automatic detection of vanishing lines and points , 2000, Image Vis. Comput..

[8]  David G. Lowe,et al.  Scene modelling, recognition and tracking with invariant image features , 2004, Third IEEE and ACM International Symposium on Mixed and Augmented Reality.

[9]  Marie-Odile Berger,et al.  Determining point correspondences between two views under geometric constraint and photometric consistency , 2010 .

[10]  Matthijs C. Dorst.  Distinctive Image Features from Scale-Invariant Keypoints , 2011 .

[11]  Lionel Moisan,et al.  A Probabilistic Criterion to Detect Rigid Point Matches Between Two Images and Estimate the Fundamental Matrix , 2004, International Journal of Computer Vision.

[12]  Alvaro Collet,et al.  Making specific features less discriminative to improve point-based 3D object recognition , 2010, 2010 IEEE Computer Society Conference on Computer Vision and Pattern Recognition.

[13]  Ian D. Reid,et al.  Locally Planar Patch Features for Real-Time Structure from Motion , 2004, BMVC.

[14]  Andrea Vedaldi,et al.  Vlfeat: an open and portable library of computer vision algorithms , 2010, ACM Multimedia.

[15]  Jean-Michel Morel,et al.  From Gestalt Theory to Image Analysis , 2008 .

[16]  Jean-Michel Morel,et al.  A Theory of Shape Identification , 2008 .

[17]  Yann Gousseau,et al.  An A Contrario Decision Method for Shape Element Recognition , 2006, International Journal of Computer Vision.

[18]  Jean-Michel Morel,et al.  ASIFT: A New Framework for Fully Affine Invariant Image Comparison , 2009, SIAM J. Imaging Sci..

[19]  Cordelia Schmid,et al.  Scale & Affine Invariant Interest Point Detectors , 2004, International Journal of Computer Vision.

[20]  James J. Little,et al.  Vision-based global localization and mapping for mobile robots , 2005, IEEE Transactions on Robotics.

[21]  Vincent Lepetit,et al.  Keypoint recognition using randomized trees , 2006, IEEE Transactions on Pattern Analysis and Machine Intelligence.

[22]  Dana H. Ballard,et al.  Learning to perceive and act by trial and error , 1991, Machine Learning.

[23]  Julien Rabin,et al.  A Statistical Approach to the Matching of Local Features , 2009, SIAM J. Imaging Sci..