Share Email Print

Optical Engineering

Software Architecture Of Machine Vision For Roving Robots
Author(s): Julius T. Tou
Format Member Price Non-Member Price
PDF $20.00 $25.00
cover GOOD NEWS! Your organization subscribes to the SPIE Digital Library. You may be able to download this paper for free. Check Access

Paper Abstract

This paper presents a comprehensive approach to the design of machine vision software for roving robots and autonomous vehicles. Various techniques are proposed for solving the important problems of directional guidance, obstacle avoidance, and object identification. Artificial intelligence and knowledge-base concepts form the basis of the vision system design. The principle of texture invariance is introduced for shadow analysis and discrimination. The idea of scene layout footprints and 3-D maps for landmarks is proposed as a means of orientation determination for the guidance and navigation of roving robots and autonomous vehicles. The vision system performs three phases of visual processing: the initialization phase, the "walking" phase, and the warning phase. The visual processing and interpretation are monitored by the knowledge access and inference routine.

Paper Details

Date Published: 1 March 1986
PDF: 8 pages
Opt. Eng. 25(3) 253428 doi: 10.1117/12.7973840
Published in: Optical Engineering Volume 25, Issue 3
Show Author Affiliations
Julius T. Tou, University of Florida (United States)

© SPIE. Terms of Use
Back to Top