In the Saddle: Chasing fast and repeatable features

A novel similarity-covariant feature detector that extracts points whose neighborhoods, when treated as a 3D intensity surface, have a saddle-like intensity profile. The saddle condition is verified efficiently by intensity comparisons on two concentric rings that must have exactly two dark-to-bright and two bright-to-dark transitions satisfying certain geometric constraints. Experiments show that the Saddle features are general, evenly spread and appearing in high density in a range of images. The Saddle detector is among the fastest proposed. In comparison with detector with similar speed, the Saddle features show superior matching performance on number of challenging datasets.

[1]  Noah Snavely,et al.  Image matching using local symmetry features , 2012, 2012 IEEE Conference on Computer Vision and Pattern Recognition.

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

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

[4]  C. Lawrence Zitnick,et al.  Edge foci interest points , 2011, 2011 International Conference on Computer Vision.

[5]  Pierre Vandergheynst,et al.  FREAK: Fast Retina Keypoint , 2012, 2012 IEEE Conference on Computer Vision and Pattern Recognition.

[6]  Cordelia Schmid,et al.  An Affine Invariant Interest Point Detector , 2002, ECCV.

[7]  Jan-Michael Frahm,et al.  From structure-from-motion point clouds to fast location recognition , 2009, 2009 IEEE Conference on Computer Vision and Pattern Recognition.

[8]  Jiri Matas,et al.  WxBS: Wide Baseline Stereo Generalizations , 2015, BMVC.

[9]  Vincent Lepetit,et al.  Fully automated and stable registration for augmented reality applications , 2003, The Second IEEE and ACM International Symposium on Mixed and Augmented Reality, 2003. Proceedings..

[10]  Richard Szeliski,et al.  Building Rome in a day , 2009, 2009 IEEE 12th International Conference on Computer Vision.

[11]  Stepán Obdrzálek,et al.  Sub-linear Indexing for Large Scale Object Recognition , 2005, BMVC.

[12]  Mark Hedley,et al.  Fast corner detection , 1998, Image Vis. Comput..

[13]  Paul L. Rosin.  Measuring Corner Properties , 1999, Comput. Vis. Image Underst..

[14]  Jan-Michael Frahm,et al.  Fast robust reconstruction of large-scale environments , 2010, 2010 44th Annual Conference on Information Sciences and Systems (CISS).

[15]  Vincent Lepetit,et al.  Feature Harvesting for Tracking-by-Detection , 2006, ECCV.

[16]  David G. Lowe,et al.  Object recognition from local scale-invariant features , 1999, Proceedings of the Seventh IEEE International Conference on Computer Vision.

[17]  Stephen M. Smith,et al.  SUSAN—A New Approach to Low Level Image Processing , 1997, International Journal of Computer Vision.

[18]  Tony Lindeberg,et al.  Discrete Scale-Space Theory and the Scale-Space Primal Sketch , 1991 .

[19]  Cordelia Schmid,et al.  A performance evaluation of local descriptors , 2005, IEEE Transactions on Pattern Analysis and Machine Intelligence.

[20]  Christopher G. Harris,et al.  A Combined Corner and Edge Detector , 1988, Alvey Vision Conference.

[21]  Vincent Lepetit,et al.  BRIEF: Binary Robust Independent Elementary Features , 2010, ECCV.

[22]  Christopher Hunt,et al.  Notes on the OpenSURF Library , 2009 .

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

[24]  Michael Isard,et al.  Object retrieval with large vocabularies and fast spatial matching , 2007, 2007 IEEE Conference on Computer Vision and Pattern Recognition.

[25]  James J. Little,et al.  Mobile Robot Localization and Mapping with Uncertainty using Scale-Invariant Visual Landmarks , 2002, Int. J. Robotics Res..

[26]  Jiri Matas,et al.  MODS: Fast and robust method for two-view matching , 2015, Comput. Vis. Image Underst..

[27]  Gary R. Bradski,et al.  ORB: An efficient alternative to SIFT or SURF , 2011, 2011 International Conference on Computer Vision.

[28]  Paul Beaudet,et al.  Rotationally invariant image operators , 1978 .

[29]  Vincent Lepetit,et al.  TILDE: A Temporally Invariant Learned DEtector , 2014, 2015 IEEE Conference on Computer Vision and Pattern Recognition (CVPR).

[30]  Charles V. Stewart,et al.  Keypoint Descriptors for Matching Across Multiple Image Modalities and Non-linear Intensity Variations , 2007, 2007 IEEE Conference on Computer Vision and Pattern Recognition.

[31]  Andrew Zisserman,et al.  Three things everyone should know to improve object retrieval , 2012, 2012 IEEE Conference on Computer Vision and Pattern Recognition.

[32]  Cordelia Schmid,et al.  Local Grayvalue Invariants for Image Retrieval , 1997, IEEE Trans. Pattern Anal. Mach. Intell..

[33]  Yao Li,et al.  Characterness: An Indicator of Text in the Wild , 2013, IEEE Transactions on Image Processing.

[34]  Jiri Matas,et al.  On Combining Multiple Segmentations in Scene Text Recognition , 2013, 2013 12th International Conference on Document Analysis and Recognition.

[35]  Roland Siegwart,et al.  BRISK: Binary Robust invariant scalable keypoints , 2011, 2011 International Conference on Computer Vision.

[36]  Luc Van Gool,et al.  Speeded-Up Robust Features (SURF) , 2008, Comput. Vis. Image Underst..

[37]  Tom Drummond,et al.  Machine Learning for High-Speed Corner Detection , 2006, ECCV.