融合目标轮廓和阴影轮廓的SAR图像目标识别

An SAR ATR Based on Fusion of Target Contour and Shadow Contour

针对合成孔径雷达图像目标识别问题,在基于图像成像模型分析基础上,提出了一种融合SAR目标轮廓和阴影轮廓的目标识别算法。首先提出了一种基于去控制标记符的SAR图像分割算法,得到SAR图像目标轮廓和阴影轮廓,然后用这2种轮廓融合,用傅立叶描述子将二维数据转为一维数据,最后用基于串接准则的融合算法得到识别结果,进行SAR目标识别。基于MSTAR的实验结果验证了本算法的有效性。实验结果证明:目标轮廓和阴影轮廓的结合,除反映本身包含的局部空间结构信息外,还能反映SAR目标的高度信息,较单一轮廓特征,是一种更为稳健的特征。

Automatic target recognition（ATR） using Synthetic Aperture Radar（SAR） imagery is investigated in this paper.According to the imaging model of SAR image,a SAR ATR based on fusion of target contour and shadow contour is proposed.Firstly,this paper presents a SAR image segmentation method based on marker-controlled,by using which the target contour and the shadow contour of SAR image are obtained.Then,fusion recognition is performed by using these two kinds of contours.The effectiveness of the proposed algorithm is verified by experimental results on MSTAR.The experiments verify that the fusion of these two kinds of contours contains not only the structural information of target but also the height information of SAR target.Compared with the feature of the target contour or the shadow contour when they are used separately,the feature of the fusion of them is more steady.