We present a method to detect characters on signboards in natural scene images. For many applications, both classifier with small computational cost and the efficient feature set,...
Abstract. We present an approach for modeling and realtime rendering of outdoor scenes, for use in virtual reality applications such as flight simulators and multi-user virtual env...
Video footage of real crowded scenes still poses severe challenges for automated surveillance. This paper evaluates clustering methods for finding independent dominant motion fi...
Abstract. Text detection in urban scenes is a hard task due to the high variability of text appearance: different text fonts, changes in the point of view, or partial occlusion are...
In this paper we present a framework for semantic scene parsing and object recognition based on dense depth maps. Five viewindependent 3D features that vary with object class are e...