基于加权稀疏表示分类的车辆识别  

Vehicle recognition based on weighted sparse representation based classification

作　　者：罗涛 冯玉田[1] 唐子成 毕超[1] Luo Tao;Feng Yutian;Tang Zicheng;Bi Chao(School of Communication and Information Engineering, Shanghai University, Shanghai 200444, Chin)

机构地区：[1]上海大学通信与信息工程学院

出　　处：《电子测量技术》2018年第6期27-31,共5页Electronic Measurement Technology

摘　　要：不同种类的车辆自动识别能够在很大程度上给人们提供便利,而通过声波来区分车辆的类型是可行的。由于声频信号和自然信号一样都具有稀疏性,稀疏表示分类（SRC）算法同样适用于车辆声频识别领域。但是SRC算法没有考虑样本的局部性,即没有考虑测试样本和每一个训练样本之间的相似性,从而导致识别效果不够优异。为了解决以上不足,提出了一种基于加权稀疏表示分类（WSRC）的声频传感器网络下车辆识别方法。通过对声频测试样本和各个声频训练样本之间的距离制定一个权重标准,并将其考虑进权重分配,以提高识别精度。实验结果表明,WSRC的识别精度相比于SRC有了明显的提高。同时,WSRC也明显优于SVM、k-NN这些常见分类算法,验证了WSRC在声频传感器网络下车辆识别的可行性。The automatic recognition of different types of vehicles can provide great convenience to people,and it is possible to distinguish the types of vehicles by sound waves.Since acoustic signals are sparse like natural signals,sparse representation based classification（SRC）algorithm is also suitable for the field of vehicle acoustic recognition.However,the SRC algorithm fails to consider the locality of the sample,that is,it does not consider the similarity between the test samples and each training sample,and thus the recognition effect is not excellent enough.In order to solve the problems above,a method of vehicle recognition based on weighted sparse representation based classification（WSRC）in acoustic sensor networks is proposed.A weight standard is set for the distance between the acoustic test sample and each of the acoustic training samples,and it is also considered into weight reassignment to improve the recognition accuracy.The experiments show that comparing to SRC,WSRC has obviously improved in recognition accuracy.At the same time,the performance of WSRC is also better than the common classification algorithms such as SVM and k-NN.Therefore,the feasibility of vehicle recognition in acoustic sensor networks with WSRC is verified.

关 键 词：加权稀疏表示分类 权重标准 声频传感器网络 车辆识别 

分 类 号：TP391.4[自动化与计算机技术—计算机应用技术] TN912.3[自动化与计算机技术—计算机科学与技术]