SAR图像机动目标的多尺度间隙度特征及其鉴别处理算法

The Multi-scale Lacunarity Feature of Mobile Targets in SAR Imagery and the Discriminating Algorithm

提出了一种新的基于多尺度间隙度特征的高分辨率SAR图像机动目标鉴别算法,用以去除检测阶段的自然杂波虚警。给出了间隙度特征的物理概念,以及二值化图像和SAR灰度图像的间隙度计算方法,并基于多尺度间隙度特征实现SAR图像车辆目标鉴别处理。最后,利用MSTAR数据库中的车辆目标和自然地物数据验证了该算法,结果显示该特征具有较好的鉴别性能。

A new algorithm is developed to discriminate mobile target from natural clutter in high-resolution SAR imagery with multi-scale lacunarity feature in this paper. The concept of lacunarity is introduced, and the different methods are proposed to calculate the lacunarity in the binary image and gray image. And then, the multi-scale lacunarity are used discriminate the vehicle target. Finally, the MSTAR data with vehicle targets and natural terrains are used to validate the above algorithm, and the performance of this algorithm is good.