Most of behavior recognition methods proposed so far share the limitations of bottom-up analysis, and singleobject assumption; the bottom-up analysis can be confused by erroneous ...
Symbol spotting problem requires feature extraction strategies able to generalize from training samples and to localize the target object while discarding most part of the image. ...
This paper presents a bottom-up tracking algorithm for surveillance applications where speed and reliability in the case of multiple matches and occlusions are major concerns. The...
Abstract. We introduce a shape detection framework called Contour Context Selection for detecting objects in cluttered images using only one exemplar. Shape based detection is inva...
This paper describes a method for visual surveillance based on biologically motivated dynamic visual attention in video image sequences. Our system is based on the extraction and ...