Title :
Space efficient 3-D model indexing
Author :
Jacobs, David W.
Author_Institution :
Artificial Intelligence Lab., MIT, Cambridge, MA, USA
Abstract :
It is shown that the set of 2-D images produced by a group of 3-D point features of a rigid model can be optimally represented with two lines in two high-dimensional spaces. This result is used to match images and model groups by table lookup. The table is efficiently built and accessed through analytic methods that account for the effect of sensing error. In real images, it reduces the set of potential matches by a factor of several thousand. This representation of a model´s images is used to analyze two other approaches to recognition. It is determined when invariants exist in several domains, and it is shown that there is an infinite set of qualitatively similar nonaccidental properties
Keywords :
image processing; table lookup; 3-D model indexing; 3-D point features; sensing error; table lookup; Artificial intelligence; Contracts; Image analysis; Image recognition; Indexing; Jacobian matrices; Laboratories; Object recognition; Research initiatives; Table lookup;
Conference_Titel :
Computer Vision and Pattern Recognition, 1992. Proceedings CVPR '92., 1992 IEEE Computer Society Conference on
Conference_Location :
Champaign, IL
Print_ISBN :
0-8186-2855-3
DOI :
10.1109/CVPR.1992.223153
