基于声谱图时间分辨率优化与残差空间金字塔网络的车辆识别  

Vehicle Recognition Based on Spectral-Temporal Resolution Optimization and Residual Spatial Pyramid Network

作　　者：刘伟娜 赵红东 史剑锋 张学志 赵一鸣 LIU Weina;ZHAO Hongdong;SHI Jianfeng;ZHANG Xuezhi;ZHAO Yiming(School of Electronic and Information Engineering,Hebei University of Technology,Tianjin 300401,China;P.R.China and National Key Laboratory of Electromagnetic Space Security,Tianjin 300308,China;Hebei Jinghe Electronic Technology Co.,Ltd.,Shijiazhuang 050200,Hebei,China)

机构地区：[1]河北工业大学电子信息工程学院,天津300401 [2]电磁空间安全全国重点实验室,天津300308 [3]河北晶禾电子技术股份有限公司,河北石家庄050200

出　　处：《计算机工程》2024年第12期376-385,共10页Computer Engineering

基　　金：天津市科技计划项目(企业科技特派员项目)(21YDTPJC00050);电磁空间安全全国重点实验室项目(2021JCJQLB055008)。

摘　　要：车辆分类是智能交通系统的关键技术之一,是道路交通监控系统的一个重要研究领域。由于声学传感器具有效率高、成本低、可昼夜工作、隐蔽性强等优势,因此基于车辆声音特征的车辆分类引起了研究人员的广泛关注。然而,现有研究中的车辆声音信号仅包含单一车辆,对于混合的双车辆声音信号的分类缺乏讨论。为此,设计一种网络模型对单车辆和双车辆共12种类别的噪声信号进行分类。针对声音频谱特征的固定分辨率并非最优的问题,基于网络训练得出的注意力得分和时间转换矩阵,控制噪声频谱时间大小,设计频谱时间分辨率优化模型。分类网络依据卷积递归神经网络(CRNN)架构,卷积网络部分(多尺度信号分析模块)参考高效空间金字塔模块对特征进行双分支融合处理,由于循环神经网络(RNN)等不利于并行化,运算速度慢,因此将因果时间卷积网络(TCN)转换为非因果循环TCN。在自制数据集中进行实验,结果表明,该模型的平均精度均值(mAP)达到0.98,远高于相当参数量下的CRNN网络,与MobileNetV3性能相当,但是相比MobileNetV3参数量减少了1.7×10^(6)。分析结果表明,所提模型适用于长时间声音信号处理任务,能提取深层次的特征。Vehicle classification is a key technology in intelligent transportation systems and a vital research area in road traffic monitoring systems.Owing to the advantages of acoustic sensors,such as high efficiency,low cost,round-the-clock operations,and strong concealment,vehicle classification based on vehicle sound characteristics has been extensively researched.However,existing vehicle sound signals only contain a single vehicle,with limited discussion on classifying mixed two-vehicle sound signals.To address this research gap,a network model is developed to classify noise signals from single and double vehicles.To address the issue of suboptimal fixed resolution in sound spectral features,a spectral time-resolution optimization model is designed using the attention score and frame warpage matrix obtained from network training.The classification network is based on a Convolutional Recurrent Neural Network(CRNN)architecture,with the convolutional component(multiscale signal reconstruction module)utilizing an efficient spatial pyramid for double-branch fusion.Since Recurrent Neural Network(RNN)and other cyclic networks are unsuitable for parallelization and have low operation speeds,the causal Time Convolutional Neural Network(TCN)is converted to a non-causal cyclic TCN.The mean Average Precision(mAP)of the model on the self-made dataset reaches 0.98,significantly outperforming the CRNN network with a comparable parameter count.Its performance is comparable to MobileNetV3 but with 1.7×10^(6) fewer parameters.Experimental results indicate that the designed model is effective for processing long-term sound signals and extracting deep features.

关 键 词：车辆识别 声音信号重建 卷积循环神经网络 高效空间金字塔模块 时间卷积神经网络 时间分辨率优化 

分 类 号：TP391[自动化与计算机技术—计算机应用技术]