Share Email Print
cover

Proceedings Paper

Fractal active contour model for segmenting the boundary of man-made target in nature scenes
Author(s): Min Li; Yandong Tang; Lidi Wang; Zelin Shi
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

In this paper, a novel geometric active contour model based on the fractal dimension feature to extract the boundary of man-made target in nature scenes is presented. In order to suppress the nature clutters, an adaptive weighting function is defined using the fractal dimension feature. Then the weighting function is introduced into the geodesic active contour model to detect the boundary of man-made target. Curve driven by our proposed model can evolve gradually from the initial position to the boundary of man-made target without being disturbed by nature clutters, even if the initial curve is far away from the true boundary. Experimental results validate the effectiveness and feasibility of our model.

Paper Details

Date Published: 23 February 2006
PDF: 6 pages
Proc. SPIE 6150, 2nd International Symposium on Advanced Optical Manufacturing and Testing Technologies: Optical Test and Measurement Technology and Equipment, 615053 (23 February 2006); doi: 10.1117/12.676837
Show Author Affiliations
Min Li, Shenyang Institute of Automation (China)
Chinese Academy of Sciences (China)
Yandong Tang, Shenyang Institute of Automation (China)
Lidi Wang, Shenyang Institute of Automation (China)
Chinese Academy of Sciences (China)
Zelin Shi, Shenyang Institute of Automation (China)


Published in SPIE Proceedings Vol. 6150:
2nd International Symposium on Advanced Optical Manufacturing and Testing Technologies: Optical Test and Measurement Technology and Equipment
Xun Hou; Jiahu Yuan; James C. Wyant; Hexin Wang; Sen Han, Editor(s)

© SPIE. Terms of Use
Back to Top