Share Email Print
cover

Proceedings Paper

Aspect networks: using multiple views to learn and recognize 3-D objects
Author(s): Michael Seibert; Allen M. Waxman
Format Member Price Non-Member Price
PDF $14.40 $18.00

Paper Abstract

This paper addresses the problem of generating models of 3D objects automatically from exploratory view-sequences of the objects. Neural network techniques are described which cluster the frames of video-sequences into view-categories, called aspects, representing the 2D characteristic views. Feedforward processes insure that each aspect is invariant to the apparent position, size, orientation, and foreshortening of an object in the scene. The aspects are processed in conjunction with their associated aspect-transitions by the Aspect Network to learn and refine the 3D object representations on-the-fly. Recognition is indicated by the object-hypothesis which has accumulated the maximum evidence. The object-hypothesis must be'consistent with the current view, as well as the recent history of view transitions stored in the Aspect Network. The “winning” object refines its representation until either the attention of the camera is redirected or another hypothesis accumulates greater evidence.

Paper Details

Date Published: 1 April 1991
PDF: 10 pages
Proc. SPIE 1383, Sensor Fusion III: 3D Perception and Recognition, (1 April 1991); doi: 10.1117/12.25240
Show Author Affiliations
Michael Seibert, Lincoln Lab./MIT (United States)
Allen M. Waxman, Lincoln Lab./MIT (United States)


Published in SPIE Proceedings Vol. 1383:
Sensor Fusion III: 3D Perception and Recognition
Paul S. Schenker, Editor(s)

© SPIE. Terms of Use
Back to Top