Many approaches to object recognition are founded on probability theory, and can be broadly characterized as either generative or discriminative according to whether or not the dis...
A novel statistical approch for detection and tracking of objects is presented here, which uses both edge and color information in a particle filter. The approach does not need an...
Supporting continuous mining queries on data streams requires algorithms that (i) are fast, (ii) make light demands on memory resources, and (iii) are easily to adapt to concept dr...
We present a novel approach to automatically find spatial configurations of local features occurring frequently on instances of a given object class, and rarely on the background....
Till Quack, Vittorio Ferrari, Bastian Leibe, Luc J...
A novel scheme for the detection of object boundaries is presented. The technique is based on active contours evolving in time according to intrinsic geometric measures of the imag...