This paper introduces an edge-based object recognition method that is robust with respect to clutter, occlusion and object deformations. The method combines the use of local featu...
We propose an approach to identify and segment objects from scenes that a person (or robot) encounters in Activities of Daily Living (ADL). Images collected in those cluttered sce...
Abstract. We present a system for detecting shadows in dynamic outdoor scenes. The technique is based on fusing background subtraction operations performed on both color and dispar...
Claus B. Madsen, Thomas B. Moeslund, Amit Pal, Sha...
Abstract. We present some recent progress in designing and implementing two interactive image-based 3D modeling systems. The first system constructs 3D models from a collection of ...
Heung-Yeung Shum, Richard Szeliski, Simon Baker, M...
In this paper we present a novel algorithm for video scene segmentation. We model a scene as a semantically consistent chunk of audio-visual data. Central to the segmentation fram...