基于中心矩特征的空间目标识别方法

目标的雷达散射截面（RCS）包含了丰富的目标类别信息，有效地利用目标RCS特征对空间目标的雷达识别具有重要的意义。该文利用空间目标回波的距离维信号来进行识别。中心矩特征具有平移不变性，是一种简单有效的波形特征提取算法。文中首先提取中心矩作为特征向量，再采用Fisher判据进一步进行特征压缩，最后利。用支撑矢量机（SVM）分类算法实现识别。基于实测数据的仿真实验结果表明，该方法具有较好的识别性能和推广能力。

Space Target Recognition Based on Central Moment Feature

The radar cross section of target contains abundant information for target classification, effective use of the property of target's radar cross section has great importance on radar automatic space target recognition. A computationally efficient method for space target recognition is proposed in the paper. The central moments features, with translation-invariant property, are extracted for recognition. A multi-class support vector machine(SVM) classifier is designed to classify space objects based on the selected central moments features by using Fisher linear discriminant criterion. The experimental comparisons based on measured data show that the proposed method achieves good classification performance with its lower computational complexity.