Directional fractal dimension and its application in moving target detection

Author

Lidi, Wang ; Shabai, Huang ; Zelin, Shi

Author_Institution

Shenyang Inst. of Autom., Chinese Acad. of Sci., Beijing, China

Volume

2

fYear

2004

fDate

31 Aug.-4 Sept. 2004

Firstpage

946

Abstract

In the paper, a kind of definition of directional fractal dimension is proposed, a method based on the directionally deformable neighborhood to compute the parameter of directional fractal dimension is given and its effectiveness is proved by experiments in moving target detection. We can compute the directional fractal parameter by selecting the suitable pixels in the deformable neighborhood according to the image texture with directional feature. Then the position of the target can be confirmed by the difference between the target and the background in the directional fractal parameter. Compared with traditional fractal dimension, directional fractal dimension has some characteristics as accurate detection and fast computation.

Keywords

fractals; image recognition; image texture; random functions; target tracking; directional feature; directional fractal dimension; image processing; image texture; moving target detection; parameter computation; Boats; Face detection; Fractals; Image analysis; Image edge detection; Image processing; Image recognition; Object detection; Target recognition; Target tracking;

fLanguage

English

Publisher

ieee

Conference_Titel

Signal Processing, 2004. Proceedings. ICSP '04. 2004 7th International Conference on

Print_ISBN

0-7803-8406-7

Type

conf

DOI

10.1109/ICOSP.2004.1441476

Filename

1441476