Temporal Tracking With Implicit Templates
Abstract
This work is devoted to the segmentation and tracking of structures undergoing large deformations in an image sequence. The overall goal is the modelling of complex moving and deforming structures that simultaneously brings compression of the data, segmentation and tracking of the structures on temporal sequences of images. Deforming structures are approximated by implicit templates, defined as level sets of some particular implicit functions. Implicit functions offer an interesting tool for the modelling of visco-elastic structures. Structures are approximated using an energy minimization process ; the energy functional carries information about position, tangent and curvature. The implicit functions used in this work are defined by some control points, their radius of influence, and an iso-value. Once the structures are segmented, tracking is modelled using the displacements of the control points and the variation of the radii of influence. The method is first applied on echocardiographic images, providing promising results for segmentation. We also apply the method on a sequence of images displaying a vortex formation, and we show that such a vortex structure can also be segmented and tracked with implicit functions.