Lecture notes in computer science
Author:
Keywords:
PSI_VISICS
Abstract:
© 1994, Springer Verlag. All rights reserved. Within an invariance framework, the recognition of plane objects under general viewpoints and perspective projection calls for the extraction of two-dimensional projective invariants. If the possible poses of the object are constrained with respect to the camera, however, simpler groups than the projective transformations become relevant, and consequently, simpler invariants exist. Several such special types of pose constraints are discussed – all amount to the object plane remaining parallel to its original orientation – and the corresponding groups are outlined. For each group a number of invariants are derived to illustrate the gain in simplicity.