INVARIANT DESCRIPTORS FOR 3-D OBJECT RECOGNITION AND POSE

Invariant descriptors are shape descriptors that are unaffected by object pose, by perspective projection, and by the intrinsic parameters of the camera. These descriptors can be constructed using the methods of invariant theory, which are briefly surveyed. A range of applications of invariant descriptors in three-dimensional model-based vision is demonstrated. First, a model-based vision system that recognizes curved plane objects, irrespective of their pose, is demonstrated. Curves are not reduced to polyhedral approximations but are handled as objects in their own right. Models are generated directly from image data. Once objects have been recognized, their pose can be computed. Invariant descriptors for three-dimensional objects with plane faces are described. All these ideas are demonstrated on images of real scenes. The stability of a range of invariant descriptors to measurement error is treated in detail.