Please use this identifier to cite or link to this item: http://hdl.handle.net/1959.3/69507

Download PDF (Published version) (Adobe Acrobat PDF, -1 bytes)

Title

Land cover boundary extraction in rural aerial videos

Author(s)

Majidi, Babak;  Bab-Hadiashar, Alireza

Abstract

In this paper a new approach to finding and tracking various land cover boundaries such as rivers, agricultural fields, channels and roads for use in visual navigation system of an unmanned aerial vehicle is presented. We use a combination of statistical estimation and optimization techniques for extraction of dominant boundaries in noisy aerial images. A set of perceptual grouping restrictions is used to connect the acquired piecewise boundaries and to find the heading direction of the main boundary. The results are further refined by applying a set of texture and colour cues and eliminating any false hypothesis. Our results show our method outperforms single feature object tracking algorithms in this application.

Publication type

Conference paper

Research centre

Swinburne University of Technology. Faculty of Engineering and Industrial Sciences

Source

Proceedings of the IAPR Conference on Machine Vision Applications (MVA 2007), Tokyo, Japan, 16-18 May 2007, Vol. 18, pp. 311-314

Publication year

2007

Keyword(s)

Aerial images;  Aerial videos;  Land cover boundaries;  Perceptual grouping;  Rural areas;  Statistical estimation;  Unmanned aerial vehicles;  Visual navigation system

Publisher

Seiki Tsushinsya

ISBN

9784901122078

Publisher URL

http://www.mva-org.jp/Proceedings/2007CD/

Copyright

Copyright © 2007 by MVA Conference Committee. The published version is reproduced for non-commercial use only in accordance with the copyright policy of the publisher (http://www.mva-org.jp/mva2007/Copyright2007.pdf).

Full text

Peer reviewed