1 April 1992 Three-dimensional model alignment without computing pose
Author Affiliations +
Abstract
Most current object recognition systems are based on a 3D model which is used to describe the image projection of an object over all viewpoints. We introduce a new technique which can predict the geometry of an object under projective transformation. The object geometry is represented by a set of corresponding features taken from two views. The projected geometry can be constructed in any third view, using a viewpoint invariant derived from the correspondences.
© (1992) COPYRIGHT Society of Photo-Optical Instrumentation Engineers (SPIE). Downloading of the abstract is permitted for personal use only.
Joseph L. Mundy, Joseph L. Mundy, Paul Max Payton, Paul Max Payton, Michael H. Brill, Michael H. Brill, Eamon B. Barrett, Eamon B. Barrett, Richard P. Welty, Richard P. Welty, } "Three-dimensional model alignment without computing pose", Proc. SPIE 1623, The 20th AIPR Workshop: Computer Vision Applications: Meeting the Challenges, (1 April 1992); doi: 10.1117/12.58060; https://doi.org/10.1117/12.58060
PROCEEDINGS
13 PAGES


SHARE
Back to Top