Probabilistic Curve Evolution Using Particle Filters
Yongsheng Pan, J.D. Birdwell, Seddik M. Djouadi · 2006
A probabilistic active contour model is formulated, in which curve evolution is viewed as state estimation for a nonlinear dynamical system. The method is implemented using particle filters in a Bayesian framework. Level set methods are utilized and enable the proposed model to handle topological changes. Experimental results show that the proposed method works well for complicated images, but is, as expected, computationally intense.