Title :
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
fDate :
31 Aug.-4 Sept. 2004
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;
Conference_Titel :
Signal Processing, 2004. Proceedings. ICSP '04. 2004 7th International Conference on
Print_ISBN :
0-7803-8406-7
DOI :
10.1109/ICOSP.2004.1441476
