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...
In video surveillance, automatic methods for scene understanding and activity modeling can exploit the high redundancy of object trajectories observed over a long period of time. ...
Building on recent progress in modeling filter response statistics of natural images we integrate a statistical model into a variational framework for image segmentation. Incorpo...
We present a method for the recovery of partially occluded 3D geometric primitives from range images which might also include non-primitive objects. The method uses a technique for...
Classifying natural scenes into semantic categories has always been a challenging task. So far, many works in this field are primarily intended for single label classification, wh...