摘要
提出了一种结合功率变换的高距离分辨率雷达像预处理新方法。根据时域——频域能量等价性,利用奇异值分解形成一种频域特征模板。在用这种模板针对MSTAR中的3类雷达目标实测数据进行的识别实验中,获得了较高的正确识别率。
the paper introduces a novel pre-processing method for automatic target recognition (ATR) based on high resolution range profiles (HRRP). According to the energy equivalence of temporal domain and frequency domain, the paper introduces a frequency domain eigen-template making use of singular value decomposition. Experimental results based on the MSTAR (Moving and Stationary Target Acquisition and Recognition) public data set are provided to illustrate the performance of the proposed method.
出处
《信号处理》
CSCD
2003年第1期28-32,共5页
Journal of Signal Processing
基金
国家自然科学基金项目(69902009)
中科院自动化所模式识别国家重点实验室开放课题