Morphological 3-D segmentation using laser structured light

摘要

Segmentation methods were developed for images of the scene illuminated by sequentially scanned, laser projected, structured light. The structured light, viewed by a stereoscopically located, single video camera, resulted in an image in which the regional three-dimensional characteristics of the scene were represented by corresponding distortion of the structure of the projected light. In addition, an extension of the segmentation process yields a three-dimensional planar fit of regions of interest in the scene. The results are pertinent to the application of machine vision to the guidance of robots and autonomous vehicles along pathways without special markings.< <ETX xmlns:mml="http://www.w3.org/1998/Math/MathML" xmlns:xlink="http://www.w3.org/1999/xlink">&gt;</ETX>