Abstract: In this talk we present a method for grouping relevant object contours in edge maps by taking advantage of contour-skeleton duality. Regularizing contours and skeletons simultaneously allows us to combine both low level perceptual constraints as well as higher level model constraints in a very effective way. The models are represented as a set of skeleton paths. Skeletons are treated as trajectories of an imaginary virtual robot in a discrete space of “symmetric points” obtained from pairs of edge segments. Boundaries are then defined as the maps obtained by grouping the associated pairs of edge segments along the trajectories. Casting the grouping problem in this manner makes it similar to the problem of Simultaneous Localization and Mapping (SLAM). Hence we adapt the state-of-the-art probabilistic framework namely Rao-Blackwellized particle filtering that has been successfully applied to SLAM to maximize the joint posterior over skeletons and contours. The experimental results demonstrate the robustness of our approach.
This is a joint work with Nageh Adluru, a graduate student at Temple University.