|
|
|
| Study on Target Detection of SAR Image Using Improved Fractal Feature |
| Cheng De-bao①; Hu Feng-ming②③; Yang Ru-liang② |
①School of Economics and Management, Beihang University, Beijing 100191, China; ②Institute of Electronics, Chinese Academy of Sciences, Beijing 100190, China;
③Graduate University of the Chinese Academy of Sciences, Beijing 100190, China |
|
|
|
|
Abstract The improved fractal feature of each pixel can be extracted based on the filtered image using the exponential wavelet at one scale and energy functions. This paper studies the method of the improved fractal feature for SAR images target detection. The results of target detections using the improved fractal feature are compared with that using the method of Extended Fractal (EF) for SAR images in the simple and complex backgrounds respectively. Results state the method using the improved fractal feature can not only detect all size-fixed targets but also have lower false alarm rates, spatial resolution of the detected targets are higher and the locations of the detected targets are more accurate in both of the backgrounds, but worse false alarm rates in complex background than in the simple background using the improved fractal feature.
|
|
Received: 13 April 2008
|
|
|
|
|
|
|
|
|
2009, Vol. 31 
