A Mobile Target''s Detection and Analysis Method from SAR Image
一种SAR图像机动目标检测与分析方法

The Mobile target's detection and analysis from SAR(synthetic aperture radar) image is a key step of SAR ATR(automatic target recognition).An approach of the mobile target's detection and analysis from SAR image is proposed in this paper.After pre-processing of SAR image,Constant false alarm ratio(CFAR) algorithm based on the hypothesis that the intensity distribution of the clutter is exponential and morphological operation are applied to original SAR scene to get region-of-interest(ROIs),the CFAR detector is a rapid algorithm for detecting targets in clutter and the morphological operation can eliminate false alarms.Then the feature vector consist of 8 features for each target area is extracted to describe target in detail.Features are length,width,area,the position of centroid,azimuth,fractal dimension,rotational inertia and Mean bright.The experimental results show that this algorithm is fast in computing speed,and can get lots of useful information from target areas.Moreover,this algorithm has definite currency.