Vehicle tracking in video sequences is typically carried out by matching 2-d views (images or features) of the vehicle from one frame to the next. These views are adapted by gradu...
We propose a new technique for fusing multiple cues to robustly segment an object from its background in video sequences that suffer from abrupt changes of both illumination and po...
Francesc Moreno-Noguer, Alberto Sanfeliu, Dimitris...
We address the topic of real-time analysis and recognition of silhouettes. The method that we propose first produces object features obtained by a new type of morphological operato...