Detecting Keypoints with Stable Position, Orientation, and Scale under Illumination Changes

Local feature approaches to vision geometry and object recognition are based on selecting and matching sparse sets of visually salient image points, known as 'keypoints' or 'points of interest'. Their performance depends critically on the accuracy and reliability with which corresponding keypoints can be found in subsequent images. Among the many existing keypoint selection criteria, the popular Forstner-Harris approach explicitly targets geometric stability, defining keypoints to be points that have locally maximal self-matching precision under translational least squares template matching. However, many applications require stability in orientation and scale as well as in position. Detecting translational key- points and verifying orientation/scale behaviour post hoc is suboptimal, and can be misleading when different motion variables interact. We give a more principled formulation, based on extending the Forstner-Harris approach to general motion models and robust template matching. We also incorporate a simple local appear- ance model to ensure good resistance to the most common illumination variations. We illustrate the resulting methods and quantify their performance on test images.

[1]  Marsha Jo Hannah,et al.  Computer matching of areas in stereo images. , 1974 .

[2]  Hans P. Morevec.  Towards automatic visual obstacle avoidance , 1977, IJCAI 1977.

[3]  Hans P. Moravec.  Towards Automatic Visual Obstacle Avoidance , 1977, IJCAI.

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

[5]  Takeo Kanade,et al.  An Iterative Image Registration Technique with an Application to Stereo Vision , 1981, IJCAI.

[6]  Armin Gruen,et al.  Adaptive Least Squares Correlation With Geometrical Constraints , 1986, Other Conferences.

[7]  J. Alison Noble,et al.  Finding Corners , 1988, Alvey Vision Conference.

[8]  Robyn A. Owens,et al.  Feature detection from local energy , 1987, Pattern Recognit. Lett..

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

[10]  Rachid Deriche,et al.  Recovering and characterizing image features using an efficient model based approach , 1993, Proceedings of IEEE Conference on Computer Vision and Pattern Recognition.

[11]  Wolfgang Förstner,et al.  A Framework for Low Level Feature Extraction , 1994, ECCV.

[12]  Carlo Tomasi,et al.  Good features to track , 1994, 1994 Proceedings of IEEE Conference on Computer Vision and Pattern Recognition.

[13]  Jan-Olof Eklundh,et al.  Computer Vision — ECCV '94 , 1994, Lecture Notes in Computer Science.

[14]  Peter Kovesi,et al.  Image Features from Phase Congruency , 1995 .

[15]  Daniel Reisfeld,et al.  The constrained phase congruency feature detector: simultaneous localization, classification and scale determination , 1996, Pattern Recognit. Lett..

[16]  K. Atkinson.  Close Range Photogrammetry and Machine Vision , 1996 .

[17]  Robyn A. Owens,et al.  2D feature detection via local energy , 1997, Image Vis. Comput..

[18]  Robert Laganière,et al.  Morphological corner detection , 1998, Sixth International Conference on Computer Vision (IEEE Cat. No.98CH36271).

[19]  Han Wang,et al.  Gray Level Corner Detection , 1998, MVA.

[20]  Gregory D. Hager,et al.  Efficient Region Tracking With Parametric Models of Geometry and Illumination , 1998, IEEE Trans. Pattern Anal. Mach. Intell..

[21]  Andrew Zisserman,et al.  Feature Based Methods for Structure and Motion Estimation , 1999, Workshop on Vision Algorithms.

[22]  O. Faugeras,et al.  The Geometry of Multiple Images , 1999 .

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

[24]  Cordelia Schmid,et al.  Indexing Based on Scale Invariant Interest Points , 2001, ICCV.

[25]  David G. Lowe,et al.  Local feature view clustering for 3D object recognition , 2001, Proceedings of the 2001 IEEE Computer Society Conference on Computer Vision and Pattern Recognition. CVPR 2001.

[26]  Andrew Zisserman,et al.  Viewpoint invariant texture matching and wide baseline stereo , 2001, Proceedings Eighth IEEE International Conference on Computer Vision. ICCV 2001.

[27]  Mads Nielsen,et al.  Computer Vision — ECCV 2002 , 2002, Lecture Notes in Computer Science.

[28]  Richard Szeliski,et al.  Vision Algorithms: Theory and Practice , 2002, Lecture Notes in Computer Science.

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

[30]  Matthew Toews,et al.  Entropy-of-likelihood feature selection for image correspondence , 2003, Proceedings Ninth IEEE International Conference on Computer Vision.

[31]  Cordelia Schmid,et al.  Evaluation of Interest Point Detectors , 2000, International Journal of Computer Vision.

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

[33]  Karl Rohr,et al.  Recognizing corners by fitting parametric models , 1992, International Journal of Computer Vision.

[34]  Hiroshi Murase,et al.  Parametric Feature Detection , 1996, International Journal of Computer Vision.

[35]  Rachid Deriche,et al.  A computational approach for corner and vertex detection , 1993, International Journal of Computer Vision.

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

[37]  Karl Rohr,et al.  Localization properties of direct corner detectors , 1994, Journal of Mathematical Imaging and Vision.