Skip to main page content
Access keys NCBI Homepage MyNCBI Homepage Main Content Main Navigation
, 29 (8), 1470-5

Tracking Deforming Objects Using Particle Filtering for Geometric Active Contours

Affiliations

Tracking Deforming Objects Using Particle Filtering for Geometric Active Contours

Yogesh Rathi et al. IEEE Trans Pattern Anal Mach Intell.

Abstract

Tracking deforming objects involves estimating the global motion of the object and its local deformations as a function of time. Tracking algorithms using Kalman filters or particle filters have been proposed for finite dimensional representations of shape, but these are dependent on the chosen parametrization and cannot handle changes in curve topology. Geometric active contours provide a framework which is parametrization independent and allow for changes in topology. In the present work, we formulate a particle filtering algorithm in the geometric active contour framework that can be used for tracking moving and deforming objects. To the best of our knowledge, this is the first attempt to implement an approximate particle filtering algorithm for tracking on a (theoretically) infinite dimensional state space.

Figures

Fig. 1
Fig. 1
Likelihood probability distribution (a) with (b) without using importance density q(·) for frame 2 of car sequence (200 particles).
Fig. 2
Fig. 2
Tracking the van sequence.
Fig. 3
Fig. 3
(a) Tracking results using Chan-Vese [32]. (b) Tracking using the proposed method.
Fig. 4
Fig. 4
Couple sequence: Demonstrates multiple object tracking.
Fig. 5
Fig. 5
Plane sequence: Tracking with 30 particles. Images have been cropped for better visualization.
Fig. 6
Fig. 6
Plane sequence: Tracking with condensation filter using 1,200 particles. Images have been cropped for better visualization.

Similar articles

See all similar articles

Cited by 8 PubMed Central articles

See all "Cited by" articles

Publication types

Feedback