Tracking points on deformable objects using curvature information
The objective of this paper is to present a significant improvement to the approach of Duncan et al. [1, 8] to analyze the deformations of curves in sequences of 2D images. This approach is based on the paradigm that high curvature points usually possess an anatomical meaning, and are therefore good landmarks to guide the matching process, especially in the absence of a reliable physical or deformable geometric model of the observed structures.
As Duncan's team, we therefore propose a method based on the minimization of an energy which tends to preserve the matching of high curvature points, while ensuring a smooth field of displacement vectors everywhere.
The innovation of our work stems from the explicit description of the mapping between the curves to be matched, which ensures that the resulting displacement vectors actually map points belonging to the two curves, which was not the case in Duncan's approach.
We have actually implemented the method in 2-D and we present the results of the tracking of a heart structure in a sequence of ultrasound images.
KeywordsComputer Vision Displacement Vector Displacement Field IEEE Computer Society Search Area
- 1.A. Amini, R. Owen, L. Staib, P. Anandan, and J. Duncan, non-rigid motion models for tracking the left ventricular wall. Lecture notes in computer science: Information processing in medical images. 1991. Springer-Verlag.Google Scholar
- 2.Nicholas Ayache, Isaac Cohen, and Isabelle Herlin. Medical image tracking. In Active Vision, Andrew Blake and Alan Yuille, chapter 20. MIT Press, 1992. In press.Google Scholar
- 3.Fred L. Bookstein. Principal warps: Thin-plate splines and the decomposition of deformations. IEEE Transactions on Pattern Analysis and Machine Intelligence, PAMI-11(6):567–585, June 1989.Google Scholar
- 4.Isaac Cohen, Nicholas Ayache, and Patrick Sulger. Tracking points on deformable objects using curvature information. Technical Report 1595, INRIA, March 1992.Google Scholar
- 5.Isaac Cohen, Laurent D. Cohen, and Nicholas Ayache. Using deformable surfaces to segment 3-D images and infer differential structures. Computer Vision, Graphics, and Image Processing: Image Understanding, 1992. In press.Google Scholar
- 6.Laurent D. Cohen and Isaac Cohen. A finite element method applied to new active contour models and 3-D reconstruction from cross sections. In Proc. Third International Conference on Computer Vision, pages 587–591. IEEE Computer Society Conference, December 1990. Osaka, Japan.Google Scholar
- 7.Court B. Cutting. Applications of computer graphics to the evaluation and treatment of major craniofacial malformation. In Jayaram K. Udupa and Gabor T. Herman, editors, 3-D Imaging in Medicine. CRC Press, 1989.Google Scholar
- 8.J.S. Duncan, R.L. Owen, L.H. Staib, and P. Anandan. Measurement of non-rigid motion using contour shape descriptors. In Proc. Computer Vision and Pattern Recognition, pages 318–324. IEEE Computer Society Conference, June 1991. Lahaina, Maui, Hawaii.Google Scholar
- 9.A. Guéziec and N. Ayache. Smoothing and matching of 3D-space curves. In Proceedings of the Second European Conference on Computer Vision 1992, Santa Margherita Ligure, Italy, May 1992.Google Scholar
- 10.I.L. Herlin and N. Ayache. Features extraction and analysis methods for sequences of ultrasound images. In Proceedings of the Second European Conference on Computer Vision 1992, Santa Margherita Ligure, Italy, May 1992.Google Scholar
- 11.Ellen Catherine Hildreth. The Measurement of Visual Motion. The MIT Press, Cambridge, Massachusetts, 1984.Google Scholar
- 12.Bradley Horowitz and Alex Pentland. Recovery of non-rigid motion and structures. In Proc. Computer Vision and Pattern Recognition, pages 325–330. IEEE Computer Society Conference, June 1991. Lahaina, Maui, Hawaii.Google Scholar
- 13.L.D. Landau and E.M. Lifshitz. Theory of elasticity. Pergamon Press, Oxford, 1986.Google Scholar
- 14.Dimitri Metaxas and Demetri Terzopoulos. Constrained deformable superquadrics and nonrigid motion tracking. In Proc. Computer Vision and Pattern Recognition, pages 337–343. IEEE Computer Society Conference, June 1991. Lahaina, Maui, Hawaii.Google Scholar
- 15.Sanjoy K. Mishra, Dmitry B. Goldgof, and Thomas S. Huang. Motion analysis and epicardial deformation estimation from angiography data. In Proc. Computer Vision and Pattern Recognition, pages 331–336. IEEE Computer Society Conference, June 1991. Lahaina, Maui, Hawaii.Google Scholar
- 16.O. Monga, N. Ayache, and P. Sander. From voxel to curvature. In Proc. Computer Vision and Pattern Recognition, pages 644–649. IEEE Computer Society Conference, June 1991. Lahaina, Maui, Hawaii.Google Scholar