关键词: 脉冲超宽带雷达, 距离-多普勒图, 自适应特征选择网络, 地面目标识别

Abstract: Aiming at the problem that Impulse Radio Ultra-Wideband Radar (IR-UWBR) has insufficient target recognition ability under the challenges of small sample conditions and complex detection scenes, a moving target recognition method based on range-Doppler map and adaptive feature selection network (RDAFSN) is proposed. The IR-UWBR Doppler information extraction model is established based on the analysis of the law of IR-UWBR receiving echo signals in the slow time dimension. At the same time, the characteristics of the moving target range-Doppler map, which has large differences in image spatial features due to complex background information and many target types, are deeply analyzed, and the RDAFSN target recognition model based on coordinate soft threshold denoising module and spatial adaptive down sampling layer is constructed. Experimental results show that this method can effectively improve the classification ability of moving targets under small sample conditions, and has good recognition effects on similar targets in different scenes. Compared with CNN-BiLSTM-DNN and image coding deep network commonly used for ground target recognition, the recognition accuracy is improved by 3.64% and 7.53% respectively.

Key words: pulse ultra-wideband radar, range-doppler map, adaptive feature selection network, ground target recognition