基于多任務復數因子分析模型的雷達高分辨距離像識別方法
doi: 10.11999/JEIT141591
基金項目:
國家自然科學基金(61271024, 61201296, 61322103)，高等學校博士學科點專項科研基金(20130203110013)和陜西省自然科學基礎研究計劃(2015JZ016)
Radar HRRP Target Recognition Method Based on Multi-task Learning and Complex Factor Analysis
Funds:
The National Natural Science Foundation of China (61271024, 61201296, 61322103)
-
摘要: 傳統(tǒng)的高分辨距離像(HRRP)統(tǒng)計識別方法大部分只使用雷達目標高分辨回波的幅值信息且需要大量的訓練樣本保證統(tǒng)計模型參數學習的精度。為了充分利用高分辨回波的相位信息，在雷達采樣率有限、訓練樣本數不足的條件下保證統(tǒng)計識別的性能，該文提出一種多任務學習(MTL)復數因子分析(CFA)模型，將數據描述推廣到復數域，將每個方位幀訓練樣本的統(tǒng)計建模視為單一的學習任務，各學習任務共享加載矩陣，利用貝塔伯努利(Beta-Bernoulli)稀疏先驗自適應地選擇各任務需要的因子，完成多任務的共同學習。基于實測數據的識別實驗顯示，與傳統(tǒng)的單任務學習(STL)因子分析模型相比，該文提出的多任務因子分析模型具有更低的模型復雜度且在小樣本條件下可以顯著提高識別性能。Abstract: Most traditional recognition methods for High Resolution Range Profile (HRRP) only utilize the amplitude information and need large number of training samples to obtain better estimation precision of model parameters. To utilize the phase information contained in the complex echoes and obtain better recognition performance with small training data and low sampling rate, a statistical model based on Multi-Task Leaning (MTL) and Complex Factor Analysis (CFA), referred to as MTL-CFA, is proposed in this paper. The MTL-CFA model directly describes the complex HRRP data. The statistical modeling of each training aspect-frame is considered as a single task, and all tasks share a common loading matrix. The factor number of each task is automatically determined via the Beta-Bernoulli sparse prior. Experimental results based on measured data show that the proposed model MTL-CFA can not only describe the observed data with lower order of model complexity, but also obtain satisfactory recognition accuracy with small training data, compared with the traditional Single- Task Learning (STL) based on FA models.
-
張瑞, 牛威 寇鵬. 基于樣本緊密度的雷達高分辨距離像識別方法研究[J]. 電子與信息學報, 2014, 36(3): 529-536. Zhang Rui, Niu Wei, and Kou Peng. Radar high resolution range profiles recognition based on the affinity[J]. Journal of Electronics Information Technology, 2014, 36(3): 529-536. 張學峰, 王鵬輝, 馮博, 等. 基于多分類器融合的雷達高分辨距離像目標識別與拒判新方法[J]. 自動化學報, 2014, 40(2): 348-356. Zhang Xue-feng, Wang Peng-hui, Feng Bo, et al.. A new method to improve radar HRRP recognition and outlier rejection performances based on classifier combination[J]. Acta Automatica Sinica, 2014, 40(2): 348-356. 張玉璽, 王曉丹, 姚旭, 等. 基于復數全極化HRRP的雷達目標識別[J]. 系統(tǒng)工程與電子技術, 2014, 36(2): 260-265. Zhang Yu-xi, Wang Xiao-dan, Yao Xu, et al.. Radar target recognition based on complex fully polarimeric HRRP[J]. Systems Engineering and Electronics, 2014, 36(2): 260-265. 潘勉, 王鵬輝, 杜蘭, 等. 基于 TSB-HMM 模型的雷達高分辨距離像目標識別方法[J]. 電子與信息學報, 2013, 35(7): 1547-1554. Pan Mian, Wang Peng-hui, Du Lan, et al.. Radar HRRP target recognition based on truncated stick-breaking hidden markov model[J], Journal of Electronics Information Technology, 2013, 35(7): 1547-1554. 姚莉娜, 吳艷敏, 崔光照. 基于隨機森林的雷達高分辨距離像目標識別新方法[J]. 鄭州大學學報(工學版), 2014, 35(4): 105-108. Yao Li-na, Wu Yan-min, and Cui Guang-zhao. New method of radar high resolution range image target recognition based on random forest[J]. Journal of Zhengzhou University (Engineering Science), 2014, 35(4): 105-108. Jacobs S P and OSullivan J A. Automatic target recognition using sequences of high resolution radar range profiles[J]. IEEE Transactions on Aerospace Electronic Systems, 2000, 36(2): 364-380. Du L, Liu H, and Bao Z. Radar HRRP statistical recognition: parametric model and model selection[J]. IEEE Transactions on Signal Processing, 2008, 56(5): 1931-1944. Du L, Liu H, and Bao Z. A two-distribution compounded statistical model for radar HRRP target recognition[J]. IEEE Transactions on Signal Processing, 2006, 54(6): 2226-2238. Du L, Liu H, and Bao Z. A novel feature vector using complex HRRP for radar target recognition[J]. Lecture Notes in Computer Science, 2007, 4491: 1303-1309. 王鵬輝, 杜蘭, 劉宏偉. 基于復高斯模型的雷達高分辨距離像目標識別新方法[J]. 光學學報, 2014, 34(2): 275-284. Wang Peng-hui, Du Lan, and Liu Hong-wei. A new method based on complex Gaussian models for radar high resolution range profile target recognition[J]. Acta Optica Sinica, 2014, 34(2): 275-284. 王鵬輝. 基于統(tǒng)計建模的雷達高分辨距離像目標識別方法研究[D]. [博士論文], 西安電子科技大學, 2012. Wang Peng-hui. Study of radar high resolution range profile target recognition based on statistical modeling[D]. [Ph.D dissertation], Xidian University, 2012. Xue Y, Liao X, and Carin L. Multi-task learning for classification with Dirichlet process priors[J]. The Journal of Machine Learning Research, 2007, 8: 35-63. Pan M, Du L, and Wang P. Multi-task hidden Markov modeling of spectrogram feature from radar high-resolution range profiles[J]. EURASIP Journal on Advances in Signal Processing, 2012(1): 1-17. Watanabe S. A widely applicable Bayesian information criterion[J]. The Journal of Machine Learning Research, 2013, 14(1): 867-897. Paisley J and Carin L. Nonparametric factor analysis with beta process priors[C]. Proceedings of the 26th ACM Annual International Conference on Machine Learning, 2009: 777-784. Ando T. Bayesian Model Selection and Statistical Modeling [M]. CRC Press, 2010, 43-96. Du L, Liu H, and Wang P. Noise robust radar HRRP target recognition based on multitask factor analysis with small training data size[J]. IEEE Transactions on Signal Processing, 2012, 60(7): 3546-3559. -
計量
- 文章訪問數: 1540
- HTML全文瀏覽量: 167
- PDF下載量: 448
- 被引次數: 0
下載:
