Share Email Print
cover

Proceedings Paper

Real-time vision system using multiple-feature extraction for the Toro robot
Author(s): Joan Climent; Antoni Grau
Format Member Price Non-Member Price
PDF $14.40 $18.00
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 vision system developed for the guidance of a mobile robot. This robot emulates the behavior of a bull in a corrida. A camera is placed at the front of the robot, this means, for the first time, we look at the scene from the point of view of the bull. Due to the difficulty in understanding how bull vision works our model is restricted to the most known features about bull behavior in front of corrida scenes. For this reason, we restrict the bull vision to two different topics: high sensitivity to red color, and constant attention to moving objects. We emulate this model using two image processors. The first performs color segmentation, the second performs motion segmentation. The information obtained is used as feedbacks of the mobile robot. Our approach for view planning is to first simplify the 3-D decision making problem into a 2-D problem. The architecture of our real-time vision system and its implementation are described in detail.

Paper Details

Date Published: 17 August 1994
PDF: 4 pages
Proc. SPIE 2357, ISPRS Commission III Symposium: Spatial Information from Digital Photogrammetry and Computer Vision, (17 August 1994); doi: 10.1117/12.182832
Show Author Affiliations
Joan Climent, Univ. Politecnica de Catalunya (Spain)
Antoni Grau, Univ. Politecnica de Catalunya (Spain)


Published in SPIE Proceedings Vol. 2357:
ISPRS Commission III Symposium: Spatial Information from Digital Photogrammetry and Computer Vision
Heinrich Ebner; Christian Heipke; Konrad Eder, Editor(s)

© SPIE. Terms of Use
Back to Top