We present a real-time method for detecting deformable surfaces, with no need whatsoever for a priori pose knowledge. Our method starts from a set of wide baseline point matches b...
We present a real-time method for detecting deformable surfaces, with no need whatsoever for a priori pose knowledge. Our method starts from a set of wide baseline point matches be...
A common design of an object recognition system has
two steps, a detection step followed by a foreground withinclass
classification step. For example, consider face detection
by...
Abstract. We describe a system for autonomous learning of visual object representations and their grasp affordances on a robot-vision system. It segments objects by grasping and mo...
Dirk Kraft, Renaud Detry, Nicolas Pugeault, Emre B...
The detection and tracking of three-dimensional human body models has progressed rapidly but successful approaches typically rely on accurate foreground silhouettes obtained using...