Planning Multiple Observations for Specular Object Recognition - Robotics Institute Carnegie Mellon University

Planning Multiple Observations for Specular Object Recognition

K. D. Gremban and Katsushi Ikeuchi
Conference Paper, Proceedings of (ICRA) International Conference on Robotics and Automation, Vol. 2, pp. 599 - 604, May, 1993

Abstract

The most prominent features of specular objects are the specularities, which are highly variable and dependent on local object geometry. In order to unambiguously recognize specular objects, more information is required. An approach for specular object recognition that relies on the use of multiple observations from different viewpoints to resolve any ambiguity in scene interpretation is presented. The results show that the multiple observation strategy can be very accurate, and is in fact limited only by the accuracy with which decisions can be made about individual observations.

BibTeX

@conference{Gremban-1993-13487,
author = {K. D. Gremban and Katsushi Ikeuchi},
title = {Planning Multiple Observations for Specular Object Recognition},
booktitle = {Proceedings of (ICRA) International Conference on Robotics and Automation},
year = {1993},
month = {May},
volume = {2},
pages = {599 - 604},
}