基于TSB-HMM模型的雷达高分辨距离像目标识别方法

针对雷达高分辨距离像(HRRP)的识别问题，该文提出了一种基于时域特征的截断Stick-Breaking过程隐马尔可夫模型(TSB-HMM)，并建立了基于TSB-HMM模型的分层识别算法，利用TSB-HMM模型结合时域特征和功率谱特征对HRRP进行分层识别。实测数据的实验结果表明，该方法是一种有效的雷达HRRP识别方法，分层识别的算法可极大提高目标的平均识别率。特别是在训练样本数极少的情况下，TSB-HMM模型仍能获得较好的识别性能。

Radar HRRP Target Recognition Based on Truncated Stick-breaking Hidden Markov Model

To improve the performance of radar High-Resolution Range Profile (HRRP) target recognition, a new Truncated Stick-Breaking Hidden Markov Model (TSB-HMM) based on time domain feature is proposed. Moreover, a hierarchical classification scheme based on TSB-HMM is employed, which utilizes both time domain feature and power spectral density feature of HRRPs for hierarchical recognition. Experimental results based on measured data show that the TSB-HMM is an effective method for radar HRRP recognition, and the hierarchical classification scheme can largely enhance the average recognition rate. Furthermore, the proposed method can obtain satisfactory recognition performances even with very limited training data.