Share Email Print

Proceedings Paper

Obstacle detection algorithms for rotorcraft navigation
Author(s): Nitin Pande; Ying Huang; Anand Narasimhamurthy; Octavia I. Camps; Rangachar Kasturi
Format Member Price Non-Member Price
PDF $17.00 $21.00

Paper Abstract

Wires can be hardly visible and thus present a serious hazard to rotorcrafts flying at low altitudes. Vision systems capable of detecting wires in time to avoid collisions must be able to find in the input images curves less than one or two pixels wide. This paper describes a study on the performance of wire detection using a sub-pixel edge detector algorithm proposed by Steger. This algorithm was tested on a set of images synthetically generated by combining real outdoor images with computer generated wire graphics. Its performance was evaluated both, at the pixel and the wire levels. It was observed that the algorithm performs well, provided that the wires are not too thin (or distant) and that some post processing is performed to remove false alarms due to clutter.

Paper Details

Date Published: 16 July 2002
PDF: 11 pages
Proc. SPIE 4713, Enhanced and Synthetic Vision 2002, (16 July 2002); doi: 10.1117/12.474418
Show Author Affiliations
Nitin Pande, The Pennsylvania State Univ. (United States)
Ying Huang, The Pennsylvania State Univ. (United States)
Anand Narasimhamurthy, The Pennsylvania State Univ. (United States)
Octavia I. Camps, The Pennsylvania State Univ. (United States)
Rangachar Kasturi, The Pennsylvania State Univ. (United States)

Published in SPIE Proceedings Vol. 4713:
Enhanced and Synthetic Vision 2002
Jacques G. Verly, Editor(s)

© SPIE. Terms of Use
Back to Top