We derive a probabilistic framework for robust, realtime, visual tracking of multiple previously unseen objects from a moving camera. This framework models the discrete depth orde...
Inspired by psychophysical studies of the human cognitive abilities we propose a novel aspect and a method for performance evaluation of contour based shape recognition algorithms ...
Vision algorithms utilizing camera networks with a common field of view are becoming increasingly feasible and important. Calibration of such camera networks is a challenging and ...
We introduce a new class of distinguished regions based on detecting the most salient convex local arrangements of contours in the image. The regions are used in a similar way to ...
Due to distortion, noise, segmentation errors, overlap, and occlusion of objects in digital images, it is usually impossible to extract complete object contours or to segment the ...