Last update: 9 of April, 2007

BACK

Tracking and Describing Deformable
Objects Using Active Contour Models

Frederic Fol Leymarie

Master of Engineering thesis

Technical Report CIM-90-9
McGill Research Center for Intelligent Machines

February 1990, McGill University, Montreal, QC, Canada

Abstract

In this thesis we consider a number of issues in developing techniques and algorithms to automate the visual tracking of deformable objects in the plane. We have applied these techniques in cell locomotion and tracking studies. We examine two classes of computer vision problems. First, we consider the segmentation of a noisy intensity image and the tracking of a nonrigid object. Second, we consider the shape analysis of an amorphous object. In evaluating these problems, we explore a new technique based on an active contour model commonly called a "snake." The snake permits us to simultaneously solve, in constrained cases, both the segmentation and tracking problems. We present a detailed analysis of the snake model, emphasizing its limitations and shortcomings, and propose various improvements to the original description of the model. Then, we study the two complementary types of shape descriptors: boundary- and region-based. We propose to combine these within the context of the grassfire transform. Two new algorithms are described. First, we present a contour segmentation technique using mathematical morphology on the curvature function, we call curvature morphology. Accurate localization for different scales of curvature features is achieved, leading to a Morphological Curvature Scale-space or MCS. Second, the snake model is used to simulate the grassfire transform using the previously extracted contour features. This permits us to produce a multiscale skeleton representation of shape which is based on the Euclidean distance metric. New significance criteria for our shape descriptors, such as the ``region-support'' of curvature extrema and the ``ridge-support'' of skeleton branches are also proposed. Finally, numerous implementation details are discussed; for example, the description of an efficient sequential Euclidean distance transform.

 

Keywords: Cell tracking, chemotaxis and chemokinesis, neutrophils, pseudopods, image segmentation, Burt's hierarchical discrete correlation, Gaussian and Laplacian pyramids, scale-spaces, active contour models or snake, Euler-Lagrange equations, computational molecules, stiffness matrix, viscosity, pentadiagonal matrices, potential surfaces, chain-code, curvature, mathematical morphology for functions, grassfire transform, distance surface, skeletons, Blum's 2D medial axis, graphs for shape, dynamic skeletons.

 

List of Publications linked to this work:

  1. F. Leymarie and M. D. Levine, Tracking Deformable Objects in the Plane Using an Active Contour Model, IEEE-PAMI, Vol.15(6), pp. 617-634, June 1993.
  2. F. Leymarie and M. D. Levine, Simulating the Grassfire Transform Using an Active Contour Model, IEEE-PAMI, Vol.14(1), pp. 56-75, Jan. 1992.
  3. F. Leymarie and M. D. Levine, Fast Raster Scan Distance Propagation on the Discrete Rectangular Lattice, CVGIP-IU, Vol.55(1), pp. 84-94, Jan. 1992. Academic Press.
  4. F. Leymarie, Tracking and Describing Deformable Objects Using Active Contour Models, Technical Report TR-CIM-90-9, Computer Vision and Robotics Laboratory, McGill University, Montreal, Quebec, Canada, M.Eng. thesis. February 1990.
  5. F. Leymarie and M. D. Levine, Skeletons from Snakes, in "Progress in Image Analysis and Processing", (V. Cantoni et al., ed.), pp. 186-193, Singapore: World Scientific, 1990. Proc. of the 5th International Conference on Image Analysis and Processing, (Positano, Italiy), Sept. 1989.
  6. F. Leymarie and M. D. Levine, New method for shape description based on an active contour model. Proceedings of SPIE conference on "Visual Communications and Image Processing", vol. 1199-1, (Philadelphia, Penn., U.S.A.), pp. 390-401, Nov. 1989.
  7. F. Leymarie and M. D. Levine, Curvature Morphology, Proceedings of Vision Interface '89, (London, OT, Canada), pp. 102-109, June 1989.
  8. F. Leymarie and M. D. Levine. Snakes and Skeletons. Technical Report TR-CIM-89-1, Computer Vision and Robotics Laboratory, McGill University, Montreal, Quebec, Canada, Jan. 1989.
  9. F. Leymarie and M. D. Levine. Curvature morphology. Technical Report TR-CIM-88-26, Computer Vision and Robotics Laboratory, McGill University, Montreal, Quebec, Canada, Dec. 1988.

 

BACK

© Frederic Fol Leymarie : ffl(at)gold(dot)ac(dot)uk --- 2002-07