基于协同表示的声振传感器网络车辆分类识别

doi:10.16183/j.cnki.jsjtu.2018.01.016

摘要/Abstract

摘要： 针对使用单一信号分类的现有车辆识别技术的不足，提出了一种基于声音信号与振动信号协同表示的车辆分类识别方法.利用梅尔倒谱系数(MFCC)提取车辆的声音信号和振动信号特征，分别对提取的2种信号特征进行多任务训练分类，以获得多任务协同表示的重构误差并对其进行加权处理，得出被检测目标的分类识别结果.结果表明，所提出的车辆分类识别方法对于车辆目标具有较好的分类效果和较高的识别效率.

关键词: 车辆识别, 协同表示, 多任务分类, 特征提取, 重构误差

Abstract: Aiming at the defects of the current recognition methods using single signal, we propose a vehicle recognition method based on the collaboration representation of acoustical and vibrative signals. Firstly, Mel-frequency cepstral coefficients (MFCCs) are used to extract the acoustical and vibrative features of vehicles. Then, multitask training of classification is carried out separately by two kinds of signal features. Finally, the reconstruction error of multitask collaboration representation is obtained through the signal features and the target is classified according to the reconstruction error. Experiments indicate that this method has better classification effect and higher recognition efficiency, compared with the existing methods.

Key words: vehicle recognition, collaboration representation, multitask classification, feature extraction, reconstruction error

中图分类号:

TP 391

王瑞，刘宾，周天润，杨羽. 基于协同表示的声振传感器网络车辆分类识别[J]. 上海交通大学学报（自然版）, 2018, 52(1): 103-110.

WANG Rui,LIU Bin,ZHOU Tianrun,YANG Yu. Vehicle Recognition in Acoustic and Seismic Networks via Collaboration Representation[J]. Journal of Shanghai Jiaotong University, 2018, 52(1): 103-110.

参考文献

［1］钱志伟. 智能交通系统中车型识别的研究与应用［D］. 西安: 西安电子科技大学通信工程学院, 2011. ［2］张成. 基于图像特征的车型识别［D］. 南京:南京理工大学自动化学院, 2012. ［3］王慧斌, 卢蓉. 基于视频的车型特征提取及识别方法研究［J］. 微型电脑应用, 2010, 26(10): 50-53. WANG Huibin, LU Rong. The feature extraction and classification of verchile based on video［J］. Microcomputer Applications, 2010, 26(10): 50-53. ［4］MA W, MIAO Z, ZHANG Q. Vehicle classification based on multi-feature fusion［C］∥5th IET Internaaional Conference on Wireless, Mobile and Multimedia Networks (ICWMMN). Beijing: IET, 2013: 215-219. ［5］罗向龙,牛国宏, 吴潜蛟,等.基于经验模态分解和支持向量机的车型声频识别［J］. 应用声学, 2010, 29(3):178-183. LUO Xianglong, NIU Guohong, WU Qianjiao, et al. Vehicle recognition by acoustic signals based on EMD and SVM［J］. Applied Acoustics, 2010, 29(3): 178-183. ［6］SHARMA N, JAIRATH K A, SINGH B, et al. Detection of various vehicles using wireless seismeic sensor network［C］∥Inernational Conference on Advances in Mobile Network, Communication and its Application (MNCAPPS). Bangalore, India: IEEE, 2012: 149-155. ［7］KANDPAL M, KAKAR V K, VERMA G. Classification of ground vehicles using acoustic signal［C］∥International Conference on Signal Processing and Communication (ICSC). Noida, India: IEEE, 2013: 512-518. ［8］YANG S S, KIM Y G, CHOI H. Vehicle identification using discrete spectrums in wireless sensor networks［J］. Journal and Networks, 2008, 3(4): 51-63. ［9］王艳, 李文藻, 张意,等. 基于改进TESP算法的边防车辆类型声音识别［J］. 四川大学学报(工程科学版), 2014, 46(S2):122-127. WANG Yan, LI Wenzao, ZHANG Yi, et al. Vehicle sound signal recognition in border surveillance based on improved TESP algorithm［J］. Journal of Sichuan University (Engineering Science Edition), 2014, 46(S2): 122-127. ［10］毕超, 冯玉田, 李园辉,等. 基于HHT的声频传感器车辆分类识别［J］. 电声技术, 2016, 40(6): 48-52. BI Chao, FENG Yutian, LI Yuanhui, et al. Audio sensor vehicle classification recognition based on HHT［J］. Audio Engineering, 2016, 40(6): 48-52. ［11］LUO Y, FENG G, LIU J, et al. Vehicle identification technology of laser heterodyne spectral analysis of vibration characteristics［J］. Chinese Journal of Lasers, 2014, 9(1):13-15. ［12］LU C Y, MIN H, GUI J, et al. Face recognition via weighted sparse representation［J］. Journal of Visual Communication and Image Representation, 2013, 24(2): 111-116. ［13］KUMAR A, CHAN T S T. Robust ear identification using sparse representation of local texture descriptors［J］. Pattern Recognition, 2013, 46(1): 73-85. ［14］ZHANG X, LI M, ZUO L. New detection method for extended targets using sparse representation［J］. Journal of Xidian University (Natural Science), 2014, 41(3): 24-29. ［15］蒋建国, 金玉龙, 齐美彬,等. 基于稀疏表达残差的自然场景运动目标检测［J］. 电子学报, 2015, 43(9): 1738-1744. JIANG Jianguo, JIN Yulong, QI Meibin, et al. Moving target detection in natural scene based on sparse representation of residuals［J］. Acta Electronica Sinica, 2015, 43(9): 1738-1744. ［16］ZHANG L, YANG M, FENG X. Sparse representation or collaborative representation: Which helps face recognition?［C］∥IEEE International Conference on Computer Vision (ICCV). Ontario, Canada: IEEE, 2012: 471-478. ［17］SUN Y, DU L, WANG Y, et al. SAR automatic target recognition based on dictionary learning and joint dynamic sparse representation［J］. IEEE Geoscience & Remote Sensing Letters, 2016, 13(12): 1777-1781. ［18］王建仁, 魏龙, 段刚龙. 自适应残差加权的多元素协同表示分类算法［J］. 计算机系统应用, 2014, 23(5): 152-157. WANG Jianren, WEI Long, DUAN Ganglong. Adaptive weighted residuals multi-element collaborative representation classification approach［J］. Computer Systems & Applications, 2014, 23(5): 152-157. ［19］CHEN Y, ZHAO W, LI G, et al. Parametric sparse representation method for parameter estimation in SAR imaging［C］∥Iet International Radar Conference. Hangzhou, China: IET, 2015: 1-5. ［20］DUARTE M, HU Y H. Vehicle classification in distributed sensor networks［J］. Journal of Parallel and Distributed Computing, 2004, 64(7): 826-838. ［21］MEI X, LING H. Robust visual tracking and vehicle classification via sparse representation［J］. IEEE Transactions on Pattern Analysis and Machine Intelligence, 2011, 33(11): 2259-2272. ［22］COOLEY J W, TUKEY J W. An algorithm for the machine calculation of complex Fourier series［J］. Mathematics of Computation, 1965, 19: 297-301. ［23］CHITRA V P J, SUMALATHA M R. SVM-instance based approach to improve QoS parameters for time critical applications in WSN［C］∥Fourth International Conference on Advanced Computing (ICoAC). Chennai, India: IEEE, 2013: 1-6. ［24］GAO S, TSANG W H, CHIA L T. Kernel sparse representation for image classification and face recognition［C］∥European Conference on Computer Vision. Berlin, Germany: Springer, 2010:1-14. ［25］JIANG Z, LIN Z, DAVIS L S. Label consistent K-SVD: Learning a discriminative dictionary for recognition［J］. IEEE Trans Pattern Anal Mach Intell, 2013, 35(11): 2651-2664.

[1]	倪扬帆, 杨媛媛, 谢哲, 郑德重, 王卫东. 基于LSTM与注意力结构的肺结节多特征抽取方法[J]. 上海交通大学学报, 2022, 56(8): 1078-1088.
[2]	张晏合, 臧月进, 陈渤, 徐铭晟. 基于解耦表征变分自编码机的雷达目标识别算法[J]. 空天防御, 2022, 5(2): 87-93.
[3]	王微, 王冰, 胡雄, 孙德建. 基于在线改进符号序列熵与逻辑回归模型的岸桥起升减速箱在线退化评估[J]. 上海交通大学学报, 2021, 55(10): 1272-1280.
[4]	王俊, 王赛, 任俞明, 陈德红, 崔闪, 魏少明. 结合深度学习去噪和超分辨的SAR检测识别[J]. 空天防御, 2020, 3(3): 24-30.
[5]	颜波，张磊，褚学宁. 基于卷积神经网络的用户感知评估建模[J]. 上海交通大学学报, 2019, 53(7): 844-851.
[6]	商诺诺, 梁艳, 翟恒峰, 原浩娟. 一种高效的雷达信号全脉冲特征提取方法[J]. 空天防御, 2018, 1(4): 37-43.
[7]	吴倩红，韩蓓，冯琳，李国杰，江秀臣. “人工智能+”时代下的智能电网预测分析[J]. 上海交通大学学报（自然版）, 2018, 52(10): 1206-1219.
[8]	王嗣阳，许黎明，赖小平. 砂轮磨削过载判据及其快速诊断[J]. 上海交通大学学报（自然版）, 2015, 49(09): 1346-1352.
[9]	成谢锋,傅女婷. 心音身份识别综述[J]. 上海交通大学学报（自然版）, 2014, 48(12): 1745-1750.
[10]	王佳婧1，2，张树生1，何卫平1. 基于多信息融合的失效DPM码识别[J]. 上海交通大学学报（自然版）, 2014, 48(12): 1675-1680.
[11]	余焕伟，叶震，张志芬，陈华斌，陈善本. Al-Mg合金钨极气体保护焊接电弧的光谱特征提取方法[J]. 上海交通大学学报（自然版）, 2013, 47(11): 1655-1660.
[12]	郝圣桥，许黎明，沈伟，王建楼. 电液伺服阀状态在线特征提取和异常检测方法 [J]. 上海交通大学学报（自然版）, 2010, 44(12): 1747-1752.