Title :
The space requirements of indexing under perspective projections
Author :
Jacobs, David W.
Author_Institution :
NEC Res. Inst., Princeton, NJ, USA
fDate :
3/1/1996 12:00:00 AM
Abstract :
Object recognition systems can be made more efficient through the use of table lookup to match features. The cost of this indexing process depends on the space required to represent groups of model features in such a lookup table. We determine the space required to perform indexing of arbitrary sets of 3D model points for lookup from a single 2D image formed under perspective projection. We show that in this case, one must use a 3D surface to represent model groups, and we provide an analytic description of such a surface. This is in contrast to the cases of scaled-orthographic or affine projection, in which only a 2D surface is required to represent a group of model features. This demonstrates a fundamental way in which the recognition of objects under perspective projection is more complex than is recognition under other projection models
Keywords :
computational complexity; feature extraction; image matching; indexing; object recognition; stereo image processing; table lookup; 2D images; 3D model points; feature matching; geometric hashing; indexing process; invariants; object recognition; perspective projections; space complexity; table lookup; Extraterrestrial measurements; Indexing; Information analysis; Jacobian matrices; Machine intelligence; National electric code; Object recognition; Size measurement; Table lookup;
Journal_Title :
Pattern Analysis and Machine Intelligence, IEEE Transactions on