Proceedings chapter

A probabilistic approach to 3-D inference of geons from a 2-D view

Published inApplications of Artificial Intelligence X: Machine Vision and Robotics, Editors Kevin W. Bowyer, p. 579-588
Presented at Orlando (FLA, USA)
  • SPIE Proceedings; 1708
Publication date1992

A new, probabilistic approach for inferring 3-D volumetric primitives from a single 2-D view is presented. This recognition relies on the assumption that every object can be decomposed into component parts that belong to a finite set or alphabet of volumetric primitives (geons). For each possible primitive from the permissible set, a conditional probability function is computed. This law specifies the probability of obtaining the primitive given an observable 2- D measure or feature. The distribution functions are determined by simulation, on the basis of a representative number of random projections of the primitives. The measures themselves are chosen in such a way that they can easily be extracted from real images and their discriminative power for the volumetric primitive inference is high. Examples illustrate the proposed approach.

Citation (ISO format)
JACOT-DESCOMBES, Alain, PUN, Thierry. A probabilistic approach to 3-D inference of geons from a 2-D view. In: Applications of Artificial Intelligence X: Machine Vision and Robotics. Orlando (FLA, USA). [s.l.] : [s.n.], 1992. p. 579–588. (SPIE Proceedings)
  • PID : unige:47772

Technical informations

Creation03/06/2015 5:12:13 PM
First validation03/06/2015 5:12:13 PM
Update time03/14/2023 10:59:07 PM
Status update03/14/2023 10:59:07 PM
Last indexation08/29/2023 3:11:04 PM
All rights reserved by Archive ouverte UNIGE and the University of GenevaunigeBlack