Abstract

Substantial research has been directed toward the use of machine vision in the problem of the guidance of robots and autonomous vehicles along pathways that are not designated by special markings of some kind. Morphologically based processing of images of laser projected, scanned structured light is applied to segment and define a 3-D scene. The structured light, viewed by a stereoscopically located, single video camera, results in an image in which the regional 3-D characteristics of the scene are represented by corresponding distortion of the structure of the projected light. The segmentation methods are based on this region-specific distortion in the image of the structured light. In addition, an extension of the segmentation process yields a 3-D planar fit of the region of interest in the scene.

© 1988 Optical Society of America