1 January 1987 Scene Segmentation For Autonomous Robotic Navigation Using Sequential Laser Projected Structured Light
Author Affiliations +
Proceedings Volume 0852, Mobile Robots II; (1987) https://doi.org/10.1117/12.968242
Event: Advances in Intelligent Robotics Systems, 1987, Cambridge, CA, United States
Abstract
Vision systems for mobile robots or autonomous vehicles navigating in an unknown terrain environment must provide a rapid and accurate method of segmenting the scene ahead into regions of pathway and background. A major distinguishing feature between the pathway and background is the three dimensional texture of these two regions. Typical methods of textural image segmentation are very computationally intensive, often lack the required robustness, and are incapable of sensing the three dimensional texture of various regions of the scene. A method is presented where scanned laser projected lines of structured light, viewed by a stereoscopically located single video camera, resulted in an image in which the three dimensional characteristics of the scene were represented by the discontinuity of the projected lines. This image was conducive to processing with simple regional operators to classify regions as pathway or background. Design of some operators and application methods, and demonstration on sample images are presented. This method provides rapid and robust scene segmentation capability that has been implemented on a microcomputer in near real time, and should result in higher speed and more reliable robotic or autonomous navigation in unstructured environments.
© (1987) COPYRIGHT Society of Photo-Optical Instrumentation Engineers (SPIE). Downloading of the abstract is permitted for personal use only.
C. David Brown, C. David Brown, Charles S. Ih, Charles S. Ih, Gonzalo R. Arce, Gonzalo R. Arce, David A. Fertell, David A. Fertell, } "Scene Segmentation For Autonomous Robotic Navigation Using Sequential Laser Projected Structured Light", Proc. SPIE 0852, Mobile Robots II, (1 January 1987); doi: 10.1117/12.968242; https://doi.org/10.1117/12.968242
PROCEEDINGS
9 PAGES


SHARE
Back to Top