Share Email Print
cover

Proceedings Paper

Extended target detection in complex background based on fractal theory
Author(s): Kun-hua Zhang; Qi-heng Zhang; Xuan Yang
Format Member Price Non-Member Price
PDF $14.40 $18.00

Paper Abstract

The man-made target detection in natural background based on fractal theory has many advantages compared to traditional detection methods. While using single fractal feature to detect target, particularly extended target, is not robust in practice. Combing fractal feature with fractal scale invariance, a novel algorithm for extended target detection in complex background was proposed in this paper. First, through analyzing the self-similarity of fractal surface, the fractal feature named area measurement was developed to preliminary extract the target and the edges of image. According to the preliminary extraction result and the characteristic of extended target, potential target regions were detected. Then, the function of fractal area measurement changing with scale was proposed. Giving adaptive threshold, the backgrounds in potential target regions were eliminated by fractal scale invariance. Finally, the background conglutination was removed through mathematical morphology method if required. Experimental results demonstrate that the algorithm can detect extended target in complex background correctly and reliably, and the shape details of the target is reserved perfectly.

Paper Details

Date Published: 20 May 2009
PDF: 4 pages
Proc. SPIE 7283, 4th International Symposium on Advanced Optical Manufacturing and Testing Technologies: Optical Test and Measurement Technology and Equipment, 728331 (20 May 2009); doi: 10.1117/12.828757
Show Author Affiliations
Kun-hua Zhang, Shenzhen Univ. (China)
Qi-heng Zhang, Institute of Optics and Electronics (China)
Xuan Yang, Shenzhen Univ. (China)


Published in SPIE Proceedings Vol. 7283:
4th International Symposium on Advanced Optical Manufacturing and Testing Technologies: Optical Test and Measurement Technology and Equipment
Yudong Zhang; James C. Wyant; Robert A. Smythe; Hexin Wang, Editor(s)

© SPIE. Terms of Use
Back to Top