Share Email Print

Proceedings Paper

Neural-based system for obstacle detection and scene reconstruction
Author(s): Andrea Zanela; Sergio Taraglio
Format Member Price Non-Member Price
PDF $14.40 $18.00

Paper Abstract

A stereo vision based obstacle detection system is presented. The matching process on the input stereogram is performed as an optimisation of an energy functional through a variational approach yielding dense disparity maps. The energy minimisation is implemented by a Cellular Neural Network. The state of the art of the hardware implementation of the system is presented. Some experiments on the use of the system in outdoors applications are shown. These tests demonstrate the feasibility of an obstacle detection system for an autonomous surveillance robotic platform. The real time characteristics of the hardwired version of the algorithm will allow the temporal, and spatial, integration of data, with a considerable reduction in other otherwise unavoidable data noise.

Paper Details

Date Published: 23 June 2000
PDF: 10 pages
Proc. SPIE 4023, Enhanced and Synthetic Vision 2000, (23 June 2000); doi: 10.1117/12.389342
Show Author Affiliations
Andrea Zanela, ENEA, C.R. Casaccia (Italy)
Sergio Taraglio, ENEA, C.R. Casaccia (Italy)

Published in SPIE Proceedings Vol. 4023:
Enhanced and Synthetic Vision 2000
Jacques G. Verly, Editor(s)

© SPIE. Terms of Use
Back to Top