Abstract
We define two measures on views: view likelihood and view stability. View likelihood measures the probability that a certain view of a given 3D object is observed; it may be used to identify typical, or "characteristic," views. View stability measures how little the image changes as the viewpoint is slightly perturbed; it may be used to identify "generic" views. Both definitions are shown to be identical up to the prior probability of camera orientations, and determined by the 2D metric used to compare images. We analytically derive the stability and likelihood measures for two feature-based 2D metrics, where the most stable and most likely view is shown to be the flattest view of the 3D shape. Incorporating view likelihood or stability in 3D object recognition and 3D reconstruction increases the chance of robust performance. In particular, we propose to use these measures to enhance 3D object recognition and 3D reconstruction algorithms, by adding a second step where the most likely solution is selected among all feasible solutions. These applications are demonstrated using simulated and real images.
Original language | English |
---|---|
Pages (from-to) | 97-108 |
Number of pages | 12 |
Journal | IEEE Transactions on Pattern Analysis and Machine Intelligence |
Volume | 19 |
Issue number | 2 |
DOIs | |
State | Published - 1997 |
Bibliographical note
Funding Information:This research was sponsored by ARPA through the U.S. Office of Naval Research under Grant N00014-93-1-1202, R&T Project Code 4424341-01.
Keywords
- 3d reconstruction
- Bayesian vision
- Canonical views
- Characteristic views
- Generic views
- Object recognition
- View likelihood
- View stability