Abstract
This paper presents an original approach to the detection of corners (multiple points) in images which overcomes some of the problems often encountered when these detected corners are used for matching purposes. The method is based on the mathematical morphology algorithm for contour extraction: the watershed. It has two main advantages: first, corner detection relies only on the gradient image (first order derivatives), and second, it can give automatically a topological and geometrical description of corner (number and direction of the edges which stem from the corner). As the second order derivatives of the image are not used, the corners are better localised with our approach than with the classical approaches. The richer description of the corners helps us to use them in matching processes. Two examples of application are given: corner tracking, and position refinement using a model of corner.
This is a preview of subscription content, log in via an institution to check access.
Preview
Unable to display preview. Download preview PDF.
References
P.R. Beaudet. Rotationnaly invariant image operators. In IJCPR, pages 579–583, Kyoto, Japan, 1978.
S. Beucher. Watershed, hierarchical segmentation and waterfall algorithm. In Jean Serra and Pierre Soile, editors, Mathematical Morphology and Its Applications to Image Processing, pages 69–76. Kluwer Academic Publishers, 1994.
S. Beucher and Ch. Lantuéjoul. Use of watersheds in contour detection. In Proc. International Workshop on Image Processing, Real-Time Edge and Motion Detection/Estimation, Rennes, September 1979.
J.F. Canny. A computational approach to edge detection. PAMI, 1986.
D.E. Catlin. Estimation, Control and the Discrete Kalman Filter. Springer Verlag, 1989.
Ingemar J. Cox. A Review of Statistical Data Association Techniques for Motion Correspondence. IJGV, 10(1):53–66, Feb 1993.
R. Deriche and T. Blaszka. Recovering and Characterizing Image Features Using An Efficient Model Based Approach. In CCVPR, June 1993.
R Deriche and O. Faugeras. 2-D curve matching using high curvature points: Application to stereovision. In ICPR, pages 240–242, 1990.
Rachid Deriche. Using Canny's Criteria to Derive an Optimal Edge Detector Recursively Implemented. In IJCV, volume 2, pages 15–20, April 1987.
Rachid Deriche and Olivier Faugeras. Tracking Line Segments. Image and Vision Computing, 8(4):261–270, November 1990.
Rachid Deriche and Gérard Giraudon. A Computational Approach for Corner and Vertex Detection. IJCV, 10(2):101–124, 1993.
L. Dreschler and H. H. Nagel. On the selection of critical points and local curvature exterma of region boundaries for interframe matching. In ICPR, pages 542–544, 1982.
C. Harris and M. Stephens. A combined corner and edge detector. In Proceedings of the 4th Alvey Vision Conference, pages 189–192, August 1988.
L. Kitchen and A. Rosenfeld. Gray-level corner detection. Pattern Recognition Letters, 1:95–102, December 1982.
G. Medioni and Y. Yasumoto. Corner Detection and Curve Representation Using Cubic B-Splines. CVGIP, pages 39:267–278, 1987.
Farzin Mokhtarian and Alan K. Mackworth. Scale-based description and recogntion of planar curves and 2D shapes. PAMI, 8(1):34–43, 1986.
L. Najman. Morphologie Mathématique: de la Segmentation d'Images à l'Analyse Multivoque. Thèse de doctorat, Université Paris-Dauphine, Paris, France, Avril 1994.
L. Najman and M. Schmitt. Dynamics of contours and hierarchical segmentation. PAMI, 1994. submitted.
L. Najman and M. Schmitt. Watershed of a continuous function. Signal Processing, 38(1):99–112, July 1994. Special issue on Mathematical Morphology.
Laurent Najman and Régis Vaillant. Topological and geometrical corners by watershed. Technical Report ASRF-95-1, Thomson-CSF, L.C.R., January 1995.
I.D. Reid and D.W. Murray. Tracking foveated corner clusters using affine structure. In ICCV, pages 76–83, Berlin, German, May 1993.
Karl Rohr. Localization Properties of Direct Corner Detectors. Journal of Mathematical Imaging and Vision, 4:139–150, 1994.
Olli Silvén and Tapio Repo. Experiments with Monocular Visual Tracking and Environment Modeling. In ICCV, pages 84–92, Berlin, German, May 1993.
Cho-Kuak Teh and Roland T. Chin. On the Detection of Dominant Points on Digital Curves. PAMI, 11(8):859–872, August 1989.
L. Vincent and P. Soille. Watersheds in digital spaces: an efficient algorithm based on immersion simulations. PAMI, Vol. 13(No. 6):583–598, 1991.
H. Wang and J.M. Brady. Corner detection for 3D vision using array of processors. In Proceedings BARNAIMAGE-91, Barcelon, Spain, 1991.
Author information
Authors and Affiliations
Editor information
Rights and permissions
Copyright information
© 1995 Springer-Verlag Berlin Heidelberg
About this paper
Cite this paper
Najman, L., Vaillant, R. (1995). Topological and geometrical corners by watershed. In: Hlaváč, V., Šára, R. (eds) Computer Analysis of Images and Patterns. CAIP 1995. Lecture Notes in Computer Science, vol 970. Springer, Berlin, Heidelberg. https://doi.org/10.1007/3-540-60268-2_305
Download citation
DOI: https://doi.org/10.1007/3-540-60268-2_305
Published:
Publisher Name: Springer, Berlin, Heidelberg
Print ISBN: 978-3-540-60268-2
Online ISBN: 978-3-540-44781-8
eBook Packages: Springer Book Archive