Issue No. 10 - October (1991 vol. 13)
DOI Bookmark: http://doi.ieeecomputersociety.org/10.1109/34.99233
<p>Invariant descriptors are shape descriptors that are unaffected by object pose, by perspective projection, or 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 3D 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 3D objects with plane faces are described. All these ideas are demonstrated using images of real scenes. The stability of a range of invariant descriptors to measurement error is treated in detail.</p>
invariant descriptors; pose-invariant recognition; perspective projection invariance; 3D object recognition; 3D model-based vision; curved plane objects; computerised pattern recognition; computerised picture processing
J. Mundy, A. Zisserman, C. Coelho, A. Heller, C. Rothwell and D. Forsyth, "Invariant Descriptors for 3D Object Recognition and Pose," in IEEE Transactions on Pattern Analysis & Machine Intelligence, vol. 13, no. , pp. 971-991, 1991.