Dynamic scene understanding for autonomous mobile robots
Burger, W.
Bhanu, B.
Honeywell Syst. & Res. Center, Minneapolis, MN ;
This paper appears in: Computer Vision and Pattern Recognition, 1988. Proceedings CVPR '88., Computer Society Conference on
Publication Date: 5-9 Jun 1988
On page(s): 736-741
Meeting Date: 06/05/1988 - 06/09/1988
Location: Ann Arbor, MI, USA
ISBN: 0-8186-0862-5
References Cited: 12
INSPEC Accession Number: 3248019
Digital Object Identifier: 10.1109/CVPR.1988.196316
Current Version Published: 2002-08-06
Abstract
An approach to the dynamic scene analysis is presented which
departs from previous work by emphasizing a qualitative strategy of
reasoning and modeling. Instead of refining a single quantitative
description of the observed environment over time, multiple qualitative
interpretations are maintained simultaneously. This offers superior
robustness and flexibility over traditional numerical techniques which
are often ill-conditioned and noise-sensitive. The main tasks of the
authors' approach are: (1) detect and classify the motion of individual
objects in the scene; (2) estimate the robot's egomotion; and (3) derive
the 3-D structure of the stationary environment. These three tasks
strongly depend on each other. First, the direction of heading (i.e.
translation) and rotation of the robot are estimated with respect to
stationary locations in the scene. The focus of expansion (FOE) is not
determined as particular image location, but as a region of possible
FOE-locations called the fuzzy FOE. From this information, a rule-based
system constructs and maintains a qualitative scene model. Results of
this approach for real and synthetic imagery are presented
Index
Terms
Available to subscribers and IEEE members.
References
Available to subscribers and IEEE members.
Citing Documents
Available to subscribers and IEEE members.
Cart
