基于时频域特征融合的IR-UWB穿墙雷达人体行为识别方法

Human behavior recognition method of IR-UWB through wall radar based on time-frequency domain feature fusion

冲激脉冲(impulse radio,IR)超宽带(ultra-wideband,UWB)穿墙雷达因其良好的穿透性和距离分辨率在穿墙人体行为识别领域具有重要作用,但是常规识别方法仅采用单域特征对行为模式进行描述,识别准确率不高。针对这一问题,提出基于时频域特征融合的IR-UWB穿墙雷达人体行为识别算法。首先,通过杂波抑制及距离补偿方法获取高信噪比的人体行为距离像。其次,基于距离像提取目标时域特征,与频域特征进行融合,构建数据集。最后,基于支持向量机(support vector machine,SVM)算法对人体行为进行识别。实验结果表明,所提算法对于IR-UWB穿墙雷达人体行为识别能够达到95%的准确率。

The impulse radio(IR)ultra-wideband(UWB)through wall radar plays an important role in the field of through wall human behavior recognition due to its good penetration and range resolution.However,the conventional recognition method,only uses single domain feature to describe the behavior pattern,and the recognition accuracy is not high.Aiming at this problem,an IR-UWB through wall radar human behavior recognition algorithm is proposed based on time-frequency domain feature fusion.Firstly,the human behavior range image with high signal-to-noise ratio is obtained by clutter suppression and distance compensation methods.Secondly,the time domain features of the target are extracted based on the range image.It is fused with frequency domain features to build data set.Finally,human behavior is identified based on support vector machine(SVM)algorithm.Experimental results show that the proposed algorithm can achieve 95%accuracy for human behavior recognition with IR-UWB through wall radar.