给出了一种结合幂变换的高分辨率距离像（High Resolution Range Profile,简称HRRP）的预处理新方法，根据时域－频域能量等价性，利用功率平均形成一种频域平均模板。基于美国MSTAR（Moving and Stationary Target Acquisition and Recognition)实测数据的实验结果证明了新方法的有效性。

A novel preprocessing method is given for automatic target recognition (ATR) based on high range resolution profiles (HRRPs). According to the energy equivalence of temporal domain and frequency domain, a frequency domain template formation scheme via power averaging is introduced. Experimental results based on the MSTAR (Moving and Stationary Target Acquisition and Recognition) public data sets demonstrate the performance of the proposed method.

TN957.51

国家自然科学基金项目 (6 990 2 0 0 9,6 0 2 72 0 4 9)，教育部优秀青年教师资助计划，中科院自动化所模式识别国家重点 实验室开放课题