摘要
提出一种基于字典学习的雷达高分辨距离像(HRRP)目标识别算法。该算法依据对测试样本的信噪比估计,可以自适应地确定测试阶段稀疏分解的稀疏度系数。相比于传统识别算法,文中算法对目标的识别性能更好,且对噪声的鲁棒性更强。另外,文中算法可以在只训练部分角域数据(不完备训练集)的条件下较好地识别全角域数据,可应用于HRRP数据库的扩展。基于实测数据的识别试验验证了该算法的有效性。
The dictionary learning based radar high-resolution range profile(HRRP) target recognition method is proposed in this paper. The method can adaptively select the sparse decomposition coefficients based on the estimated test noise level. Compared with the traditional HRRP recognition methods, the proposed algorithm has a higher recognition rate and is more robust to the test noise environment. Furthermore, this method can obtain satisfactory performance even with the limited HRRP training samples from partial target-aspect angles (i. e. , the training dataset is incomplete), thereby it can be used for HRRP dataset extension. The experiments based on measured HRRP data validate the proposed method.
出处
《电波科学学报》
EI
CSCD
北大核心
2012年第5期897-905,共9页
Chinese Journal of Radio Science
基金
国家自然科学基金(编号:60901067)
新世纪优秀人才支持计划(NCET-09-0630)
长江学者和创新团队发展计划(IRT0954)
全国优秀博士学位论文作者专项资金(FANEDD-201156)
中央高校基本科研业务费专项资金联合资助
关键词
雷达自动目标识别
高分辨距离像
稀疏表示
字典学习
K次奇异值分解算法
radar automatic target recognition
high-resolution range profile (HR- RP)
sparse representation
dictionary learning
K-SVD algorithm