摘要
车型识别技术是智能运输系统的核心。针对目前车型识别方法的不足,提出了一种基于车辆声音和震动信号相融合的车型识别方法。用BCS算法提取声震信号的特征,并在特征级融合形成特征向量,以此作为训练样本对支持向量机的分类器进行训练。对两种车型的声音和震动数据进行处理的结果表明,基于特征级融合的声震信号能够准确识别不同的车型,识别准确率达到86%以上,是一种有效的车型识别方法。
Vehicle identification technology is the core of the intelligent transportation management systems. Aiming at the defects of the current recognition methods, this paper proposes a vehicle identification method based on the fusion of acoustic and seismic signals. The BCS algorithm is used to extract features of signals, then fused eigenvectors on feature-level is formed to use as training samples of SVM classifier. The results of data processing for acoustic and seismic signals of two kinds of vehicles show that it can accurately identify various vehicles with the acoustic and seismic signals based on feature level fusion, the recognition rate is 86%, and it is an effective method for vehicle recognition.
出处
《微型机与应用》
2015年第11期79-82,共4页
Microcomputer & Its Applications
关键词
车型识别
声震信号
特征融合
支持向量机
vehicle recognition
acoustic and seismic signals
feature fusion
SVM