预测特征误差映射及其在多基地水下目标识别中的应用
|
摘要
针对水下多基地目标识别问题,提出了基于特征预测和误差映射的多基地融合识别算法。推导并简化了基于贝叶斯公式的多基地目标识别条件概率公式,利用BP神经网络对最后一个节点的特征向量进行预测,并计算得到预测值与实际值误差的概率密度,将其与前面每个节点的条件概率累乘,以得到目标识别的条件概率。将利用特征预测计算条件概率的方法从单个节点推广到多个节点上,同时针对误差概率分布模型不准确的问题,提出了利用混合高斯分布模型代替单高斯概率分布模型的改进方法。对每个目标重复此过程,取结果最大值对应的目标类别为最后的识别结果.在消声水池开展多基地模拟实验,对四类目标进行识别,在一定声呐节点数目及信噪比条件下,与单基地声呐相比,多基地目标融合识别得到的识别正确率最大可提高40%,采用改进方法以后,识别正确率得到进一步提高。
The method based on feature prediction and error mapping is used to conduct multi-static target identification. The target identification conditional probability is obtained through the Bayes rule. And the formula equation is simplified. The prediction feature of the last receiver is obtained by BP(Back Propagation) neural network, and the prediction error probabilistic is calculated using the Gaussian mixture model. The improved scheme expands the method using feature prediction and error mapping to calculate the conditional probability of multi sonar nodes and replaces the single Gaussian model with the Gaussian mixture model to solve the problem of inaccuracy of error probability distribution model. Then the multiplied result by the identification probability of each former receiver is used to obtain the conditional probability of the target type. The procedure is repeated for every target, and the target type corresponding to the maximum probability is the type of target to be identified. Multi-static simulation experiment is conducted in anechoic tank, and the above method is employed to identify four types of targets. In the condition of certain sonar numbers and signal-to-noise ratio, compared with mono-static sonar system, after employing the multi-static fusion recognition method, the identification rate of multi-static sonar system is increased by 40% and the identification rate is increased more after the method is improved.
The method based on feature prediction and error mapping is used to conduct multi-static target identification. The target identification conditional probability is obtained through the Bayes rule. And the formula equation is simplified. The prediction feature of the last receiver is obtained by BP(Back Propagation) neural network, and the prediction error probabilistic is calculated using the Gaussian mixture model. The improved scheme expands the method using feature prediction and error mapping to calculate the conditional probability of multi sonar nodes and replaces the single Gaussian model with the Gaussian mixture model to solve the problem of inaccuracy of error probability distribution model. Then the multiplied result by the identification probability of each former receiver is used to obtain the conditional probability of the target type. The procedure is repeated for every target, and the target type corresponding to the maximum probability is the type of target to be identified. Multi-static simulation experiment is conducted in anechoic tank, and the above method is employed to identify four types of targets. In the condition of certain sonar numbers and signal-to-noise ratio, compared with mono-static sonar system, after employing the multi-static fusion recognition method, the identification rate of multi-static sonar system is increased by 40% and the identification rate is increased more after the method is improved.
引文
1 Ai X F, Li Y Z, Wang X S et al:Some results on characteristics of bistatic high-range resolution profiles for targetclassification. IET Radar Sonar Navig., 2012; 6(5):379-388
2 Ai X F, Zou X H, Yang J H et al. Feature extraction of rotating target based on bistatic micro-doppler analysis.IEEE CIE Radar Conference, 2011:609-612
3 Azimi-Sadjadi M R, Yao D, Huang Q et al. Underwater target classification using wavelet packets and neural networks. IEEE Trans. Neural Networks, 2000; 11(3):784-794
4 李晓良,胡程,曾涛.多极化前向散射RCS分析及其对目标分类识别的影响.电子与信息学报,2010; 32(9):2191-2196
5 陈新亮,胡程,曾涛.一种基于前向散射雷达的车辆目标自动识别方法.中国科学:信息科学,2012; 42(11):1471-1480
6 Grimmett D J. Automatic identification of specular detections in multistatic sonar systems. IEEE Oceans, Biloxi,MS, USA, 2009
7 Houston B H, Carin L. Threat detection, classification, and identification. Naval Research Laboratory, Award number:N0001407WX207 75
8 Fawcett J, Myers V, Hopkin D et al. Multiaspect classification of sidescan sonar images:Four different approaches to fusing single-aspect information. IEEE J. Oceanic Eng.,2010; 35(4):863-876
9 Azimi-Sadjadi M R, Yao D, Huang Q et al. Underwater target classification using wavelet packets and neural networks. IEEE Trans. Neural Networks, 2000; 11(3):784-794
10 Salazar J, Robinson M, Azimi-Sadjadi M R. Multi-aspect pattern classification using predictive networks and error mapping. Neural Networks, 2002, IJCNN'02, Honolulu,USA, 2002:1842-1847
11 Priya K. Bharadwaj P K, Runkle P R, Carin L. Targetidentification with wave-based matched pursuits and hidden Markov models. IEEE Trans. Antennas Propag.,1999; 47(10):1543-1554
12 Zhang R, Li G, Clemente C et al. Multi-aspect microDoppler signatures for attitude-independent L/N quotient estimation and its application to helicopter classification.IET Radar Sonar Navig., 2017; 11(4):701-708
13 Roberts P L D, Jaffe J S, Trivedi M M. Broadband acoustic classification of marine fish:A machine learning framework and comparative analysis. IEEE J. Oceanic Eng., 2011;36(1):90-104
14 Robinson M, Azimi-Sadjadi M R, Salazar J. Multi-aspect target discrimination using hidden Markov models and neural networks. IEEE Trans. Neural Networks, 2005;16(2):447-459
15 曾接贤,季康.基于多特征融合的多视点飞机目标识别算法.南昌航空大学学报:自然科学版,2016; 30(2):8-15
16 Cui Z, Cao Z, Yang J et al. A hierarchical propelled fusion strategy for SAR automatic target recognition. EURASIP J. Wireless Commun. Networking, 2013:39
17 张小风.双/多基地声呐定位及目标特性研究.博士学位论文,西安:西北工业大学,2003:1-2
18 赵俊渭,丁玮,阎宜生,赵日昌,王荣庆,王之程.收发分置水下目标声散射特性的实验研究.声学学报,1997; 22(2):123-131
19 邹吉武.多基地声呐关键技术研究.博士学位论文,哈尔滨:哈尔滨工程大学,2012:3-4
20 边肇祺,张学工等.模式识别.北京:清华大学出版社,2000:9-13
21 ZHANG Yong, HU Ruimin. Speech wideband extension based on Gaussian mixture model. Chinese Journal of Acoustics, 2009; 28(4):362-377
22 张琳,黄敏.基于EMD与切片双谱的轴承故障诊断方法.北京航空航天大学学报,2010; 36(3):287-290
23 艾玲梅,王珏.基于双谱分析和支持向量机的手震颤加速度信号识别.电子学报,2008; 36(11):2165-2170
24 刘传武,张智军,豆仁福.基于时域双谱特征的雷达目标识别.数据采集与处理,2009; 24(6):709-713
25 马元锋,陈克安,王娜,郑文.听觉模型输出谱特征在声目标识别中的应用.声学学报,2009; 34(2):142-150
2 Ai X F, Zou X H, Yang J H et al. Feature extraction of rotating target based on bistatic micro-doppler analysis.IEEE CIE Radar Conference, 2011:609-612
3 Azimi-Sadjadi M R, Yao D, Huang Q et al. Underwater target classification using wavelet packets and neural networks. IEEE Trans. Neural Networks, 2000; 11(3):784-794
4 李晓良,胡程,曾涛.多极化前向散射RCS分析及其对目标分类识别的影响.电子与信息学报,2010; 32(9):2191-2196
5 陈新亮,胡程,曾涛.一种基于前向散射雷达的车辆目标自动识别方法.中国科学:信息科学,2012; 42(11):1471-1480
6 Grimmett D J. Automatic identification of specular detections in multistatic sonar systems. IEEE Oceans, Biloxi,MS, USA, 2009
7 Houston B H, Carin L. Threat detection, classification, and identification. Naval Research Laboratory, Award number:N0001407WX207 75
8 Fawcett J, Myers V, Hopkin D et al. Multiaspect classification of sidescan sonar images:Four different approaches to fusing single-aspect information. IEEE J. Oceanic Eng.,2010; 35(4):863-876
9 Azimi-Sadjadi M R, Yao D, Huang Q et al. Underwater target classification using wavelet packets and neural networks. IEEE Trans. Neural Networks, 2000; 11(3):784-794
10 Salazar J, Robinson M, Azimi-Sadjadi M R. Multi-aspect pattern classification using predictive networks and error mapping. Neural Networks, 2002, IJCNN'02, Honolulu,USA, 2002:1842-1847
11 Priya K. Bharadwaj P K, Runkle P R, Carin L. Targetidentification with wave-based matched pursuits and hidden Markov models. IEEE Trans. Antennas Propag.,1999; 47(10):1543-1554
12 Zhang R, Li G, Clemente C et al. Multi-aspect microDoppler signatures for attitude-independent L/N quotient estimation and its application to helicopter classification.IET Radar Sonar Navig., 2017; 11(4):701-708
13 Roberts P L D, Jaffe J S, Trivedi M M. Broadband acoustic classification of marine fish:A machine learning framework and comparative analysis. IEEE J. Oceanic Eng., 2011;36(1):90-104
14 Robinson M, Azimi-Sadjadi M R, Salazar J. Multi-aspect target discrimination using hidden Markov models and neural networks. IEEE Trans. Neural Networks, 2005;16(2):447-459
15 曾接贤,季康.基于多特征融合的多视点飞机目标识别算法.南昌航空大学学报:自然科学版,2016; 30(2):8-15
16 Cui Z, Cao Z, Yang J et al. A hierarchical propelled fusion strategy for SAR automatic target recognition. EURASIP J. Wireless Commun. Networking, 2013:39
17 张小风.双/多基地声呐定位及目标特性研究.博士学位论文,西安:西北工业大学,2003:1-2
18 赵俊渭,丁玮,阎宜生,赵日昌,王荣庆,王之程.收发分置水下目标声散射特性的实验研究.声学学报,1997; 22(2):123-131
19 邹吉武.多基地声呐关键技术研究.博士学位论文,哈尔滨:哈尔滨工程大学,2012:3-4
20 边肇祺,张学工等.模式识别.北京:清华大学出版社,2000:9-13
21 ZHANG Yong, HU Ruimin. Speech wideband extension based on Gaussian mixture model. Chinese Journal of Acoustics, 2009; 28(4):362-377
22 张琳,黄敏.基于EMD与切片双谱的轴承故障诊断方法.北京航空航天大学学报,2010; 36(3):287-290
23 艾玲梅,王珏.基于双谱分析和支持向量机的手震颤加速度信号识别.电子学报,2008; 36(11):2165-2170
24 刘传武,张智军,豆仁福.基于时域双谱特征的雷达目标识别.数据采集与处理,2009; 24(6):709-713
25 马元锋,陈克安,王娜,郑文.听觉模型输出谱特征在声目标识别中的应用.声学学报,2009; 34(2):142-150