摘要 为了增加水下高速目标的识别特征维度,优化识别效果,该文设计了一种基于目标辐射噪声高速特征量(High Speed Characteristic Quantity, HSCQ)的分类方法。首先,针对水下高速目标辐射噪声的DEMON(Detection of Envelope Modulation On Noise)谱特征进行分析,根据DEMON谱的频率可分性,定义了DEMON谱调制分布比(Modulation Distribution Ratio, MDR)。然后,根据水下高速目标辐射噪声的功率谱历程图直纹特征,应用图像边缘检测、线谱生长等理论进行特征提取,并分析了功率谱历程图的直纹特征量(Straight-line Characteristic Quantity of Spectrum, SCQS)。最后,根据2种特征量的实测信号分析结果,定义了目标辐射噪声的HSCQ,实现了一种新的水下高速目标分类方法。实测信号分析结果显示,采用MDR或SCQS进行单特征量分类,非高速目标的误报率分别为21.4%和16.3%;采用HSCQ进行分类,非高速目标的误报率仅为4.1%。
Abstract:In order to improve the result of underwater high speed vehicle classification, a classification method that is based on High Speed Characteristic Quantity (HSCQ) of vehicle radiated noise is designed. Firstly, analysis of Detection of Envelope Modulation On Noise (DEMON) spectrum of actual measured radiated noise is finished. The Modulation Distribution Ratio (MDR) of radiated noise is defined based on the separability of modulation frequency of DEMON spectrum. Then the spectrograms feature analysis and feature extraction of underwater high speed radiated noise are done based on image edge detection and edge growing. The Straight-line Characteristic Quantity of Spectrum (SCQS) of vehicle radiated noise is analyzed. Finally, considering the analysis results of two types of characteristic quantity, a new classification method of underwater high speed vehicle is realized and HSCQ of vehicle radiated noise is designed. The actual measured radiated noise analysis shows that, the false alarm rate of non-high speed vehicle is respectively 21.4% (only using MDR), 16.3% (only using SCQS), and 4.1% (using HSCQ).
王森,王余,王易川,李海涛 . 水下高速目标声谱图特征提取及分类设计[J]. 电子与信息学报, 2017, 39(11): 2684-2689.
WANG Sen, WANG Yu, WANG Yichuan, LI Haitao. Feature Extraction and Classification of Spectrum of Radiated Noise of Underwater High Speed Vehicle. JEIT, 2017, 39(11): 2684-2689.
YU Yue, SUN Zhenxin, and CHEN Yanhui. Guidance type identification based on cumulative azimuth variation of incoming torpedo[J]. Fire Control & Command Control, 2015, 40(10): 87-89.
SUN Xiangqian, FAN Zhan, and LI Qing. A method of target DOA estimation based on correlation integral and cross spectrum WVD[J]. Technical Acoustics, 2015, 34(1): 23-28. doi: 10.16300/j.cnki.1000-3630.2015.01.005.
ZHOU Dianbao, ZHANG Kui, and YI Hong. Estimation of course angle and distance for high speed underwater vehicles[J]. Torpedo Technology, 2007, 15(1): 38-41.
SUN Changcun, XING Guoqiang, and QU Zhaoyu. Doppler frequency estimation method of underwater high-speed small target[J]. Ship Electronic Engineering, 2015, 35(10): 162-165. doi: 10.3969/j.issn.1672-9730.2015.10.041.
LI Haitao, CHENG Yusheng, DAI Weiguo, et al. A method based on wavelet fractal and support vector machine for underwater target recognition[J]. Technical Acoustics, 2015, 34(3): 219-222. doi: 10.3969/j.issn.1000-3630.2015.03.006.
WU Yaozhen, YANG Yixin, YANG Long, et al. Underwater target recognition based on constant-beamwidth waveform fidelity and interference-suppression[J]. Journal of Northwestern Polytechnical University, 2015, 33(5): 843-848.
WU Guoqing, WANG Meigang, and CHEN Yaoming. Numerical prediction of envelope line spectrum intensity in underwater acoustic waveguide[J]. Acta Acustica, 2013, 37(4): 432-439.
WEN Hongtao, YANG Yanming, ZHOU Hongtao, et al. Classification and analysis on the ocean underwater acoustic detection signals[J]. Journal of Applied Oceanography, 2015, 34(2): 272-278. doi: 10.3936/j.issn.2095-4972.2015.02.017.
HUANG Wenbin, CHEN Yanhui, and XUE Changyou. Indices extraction and algorithm design for recognizing type of incoming torpedo[J]. Journal of Nanjing University of Science and Technology, 2011, 35(2): 199-203.
WANG Sen, GAO Xin, and CHENG Yusheng. A classification method of high speed underwater vehicle based on modulation statistics[J]. Technical Acoustics, 2014, 33(1): 61-64. doi: 10.3969/j.issn.1000-3630.2014.01.013.
HAI Shen and WANG Sen. Combination of Gaussian smoothing and edge detection of torpedo spectrum recognition method[J]. Computer Engineering and Applications, 2017, 53(3): 160-163. doi: 10.3778/j.issn.1002- 8331.1506-0021.
GONG Yanting, CHENG Xiaoxue, REN Hongmei, et al. Application of the saliency of spectrogram in audio recognition[J]. Journal of Hefei University of Technology, 2016, 39(1): 62-66.
[14]
SONG J, YANG Y, HUANG Z, et al. Effective multiple feature hashing for large-scale near-duplicate video retrieval[J]. IEEE Transactions on Multimedia, 2013, 15(8): 1997-2008.
MA Lixiang and ZENG Xiangyang. Study of underwater targets recognition based on audiovisual feature integration [J]. Technical Acoustics, 2015, 34(3): 209-213. doi: 10.3969/ j.issn.1000-3630.2015.03.004.
[16]
WU Y, YANG Y, TIAN F, et al. Robust target feature extraction based on modified cochlear filter analysis model[C]. IEEE International Conference on Signal Processing, Kunming, China, 2013: 1-5.
SHI Meihong, LI Qing, and ZHAO Xueqing, et al. A new approach for image edge detection based on conformal phase[J]. Journal of Electronics & Information Technology, 2015, 37(11): 2594-2600. doi: 10.11999/JEIT150364.
[18]
WONG Y P, SOH V C M, BAN K W, et al. Improved canny edges using ant colony optimization[C]. The Fifth International Conference on Computer Graphics, Imaging and Visualization, Penang, 2008: 197-202.