The Community for Technology Leaders
Green Image
<p><b>Abstract</b>—Recognition of 3D objects using computer vision is complicated by the fact that geometric features vary with view orientation. An important factor in designing recognition algorithms in such situations is understanding the variation of certain critical features such as angles. In this paper we derive the two dimensional joint density function of two angles in a scene given an isotropic view orientation and an orthographic projection. The analytic expression for the densities are useful in determining statistical decision rules to recognize surfaces and objects. Experiments to evaluate the usefulness of the proposed methods are reported.</p>
Object recognition, feature variation, computer vision, image understanding, scene analysis, model based recognition, 3D recognition, statistical decisions.
Raashid Malik, Taegkeun Whangbo, "Angle Densities and Recognition of 3D Objects", IEEE Transactions on Pattern Analysis & Machine Intelligence, vol. 19, no. , pp. 52-57, January 1997, doi:10.1109/34.566810
89 ms
(Ver 3.1 (10032016))