基于InISAR像的目标识别方法

针对目标ISAR图像方位向坐标是多普勒频率，其分辨率和目标运动状态有关，如果不进行标定，直接利用ISAR像进行识别存在困难，该文提出了一种基于多特显点的InISAR成像方法，并利用极化映射，提取特征进行识别。该文利用ISAR图像中特显点的多普勒频率和横距的关系，对整幅ISAR像进行横向定标；InISAR像转换到极坐标格式下，提取具有旋转和尺度不变性的特征，对目标分类。详细分析了4个主要参数对成像和识别的影响，仿真实验结果验证了理论分析。

Radar Automatic Target Recognition Based on InISAR Images

The cross-range of ISAR image corresponds with the Doppler frequencies of scatterers, which is decided by the target motion. If the cross-range of ISAR image is not scaled, it is difficult to recognize by ISAR image. In this paper a novel method of interferometric ISAR imaging based on the dominant scatterers is proposed, then the features are extracted from the polar image that is obtained from InISAR image by the polar mapping. The extracted features have invariance with respect to rotation and scale. The effect of the four important parameters on imaging and recognition is discussed, the results of four experiments prove the theory analysis.