A mover detection method based on 2-D fuzzy entropy in SAR images

Author

Fei, Gao ; Rui, Zhou ; Jinping, Sun ; Zhenming, Yu

Author_Institution

Sch. of E.I.E, Beihang Univ., Beijing, China

fYear

2010

fDate

24-28 Oct. 2010

Firstpage

2218

Lastpage

2221

Abstract

In this paper, a new technique for the moving targets detection combining incoherent and coherent information of the Synthetic Aperture Radar (SAR) images is proposed based on the measure of a two-dimensional (2-D) fuzzy entropy principle. Firstly, it extracts incoherent and coherent information from images in pixel and builds a 2-D histogram. Secondly, according to 2-D fuzzy function, image pixels are fuzzy classified into two groups: changed and unchanged then 2-D fuzzy entropy is calculated. Finally, Differential Evolution (DE) algorithm is used to maximize the entropy and the optimal parameters of the fuzzy function are obtained, which procures effective moving target detection results.

Keywords

entropy; image classification; image motion analysis; object detection; radar imaging; synthetic aperture radar; 2D fuzzy entropy; 2D fuzzy function; 2D histogram; SAR images; differential evolution algorithm; fuzzy classification; image pixels; mover detection method; synthetic aperture radar; two dimensional fuzzy entropy; Charge coupled devices; Classification algorithms; Entropy; Equations; Histograms; Object detection; Pixel; 2-D fuzzy entropy; Differential Evolution algorithm; SAR image; change detecion; moving target detection;

fLanguage

English

Publisher

ieee

Conference_Titel

Signal Processing (ICSP), 2010 IEEE 10th International Conference on

Conference_Location

Beijing

Print_ISBN

978-1-4244-5897-4

Type

conf

DOI

10.1109/ICOSP.2010.5656957

Filename

5656957