基于CFAR级联的SAR图像舰船目标检测算法

SAR图像舰船目标检测在军事监视和海洋环境监管等方面有着重要的意义。针对SAR图像的特点,提出了一种基于全局CFAR检测与局部CFAR检测级联的舰船目标检测算法。在全局CFAR检测中,通过海杂波特性拟合优选海杂波统计模型,以较高的虚警率筛选潜在的目标点;在局部CFAR检测中,以潜在目标点的连通区域为单位,通过检测窗口的选取、背景像素的确定和海杂波拟合等步骤以后,以较低的虚警率确定目标。最后,通过条件扩张算法和目标像素聚类完善船只细节。实验结果表明,文中算法在保证良好的检测性能的同时,具有检测效率高、舰船细节完整等优点,为舰船目标鉴别和信息提取提供了良好的保障,更加符合实际应用需求。

An Algorithm of Ship Target Detection in SAR Images Based on Cascaded CFAR

Ship target detection in SAR images has an important meaning on military surveillance and environmental supervision. According to the characteristics of SAR image, an algorithm of ship target detection in SAR images is proposed based on a two stage CFAR cascaded of global CFAR and local CFAR. In the global CFAR detection, sea clutter distribution is determined by sea clutter feature, and potential target pixels are sorted out at a high false alarm rate. In the local CFAR detection, each connected region of potential target pixels, after steps of the selection of detecting window, the decision of background pixels and the fitting of sea clutter, is confirmed at a low false alarm rate. Finally, ship details are improved by using conditional dilation and target pixel clustering. The experimental results show that the algorithm proposed in this paper can get higher detection efficiency and more complete ship details, with guaranteed good detection performance, and provides a good precondition for ship target discrimination and information extraction, more satisfies application demands of SAR images.