Weakly-Calibrated Stereo Perception for Rover Navigation - Robotics Institute Carnegie Mellon University

Weakly-Calibrated Stereo Perception for Rover Navigation

L. Robert, M. Buffa, and Martial Hebert
Conference Paper, Proceedings of (ICCV) International Conference on Computer Vision, pp. 46 - 51, June, 1995

Abstract

Presents a vision system for autonomous navigation based on stereo perception without 3D reconstruction. This approach uses weakly calibrated stereo images, i.e. images for which only the epipolar geometry is known. The vision system first rectifies the images, matches selected points between the two images, and then computes the relative elevation of the points relative to a reference plane as well as the images of their projections on this plane. We have integrated this vision module into a complete navigation system. In this system, the relative elevation is used as a shape indicator in order to compute appropriate steering directions everytime a new stereo pair is processed. We have conducted initial experiments in unstructured, outdoor environments with an wheeled rover.

BibTeX

@conference{Robert-1995-13788,
author = {L. Robert and M. Buffa and Martial Hebert},
title = {Weakly-Calibrated Stereo Perception for Rover Navigation},
booktitle = {Proceedings of (ICCV) International Conference on Computer Vision},
year = {1995},
month = {June},
pages = {46 - 51},
}