摘要
车型识别是智能交通系统的关键技术之一,具有重要应用价值。针对车辆噪声信号的复杂性,提出了一种基于相位信息和能量信息融合的车型分类方法。通过耳蜗滤波器组将车辆噪声信号分解成窄带信号,为了避免相位卷绕问题,利用傅里叶变换性质结合相位一阶导数估计窄带信号的瞬时频率并提取瞬时频率特征。该特征能够有效地完成车型分类,通过将瞬时频率特征和对数能量联合,进一步提高了分类准确率。
Vehicle recognition is one of the key technologies of intelligent transportation system and has important application value.Aiming at the complexity of vehicle noise signal,a vehicle classification method based on phase information and energy information fusion was proposed.The vehicle noise signal was decomposed into narrow-band signals by cochlear filter banks.To avoid phase wrapping problem,the instantaneous frequency of narrow-band signals was estimated by combining the Fourier transform property with the first derivative of phase,and the instantaneous frequency(IF)feature was extracted.This feature can effectively complete vehicle classification.By combining IF feature with logarithmic energy,the classification accuracy is further improved.
作者
陈建新
尹雪飞
陈克安
CHEN Jianxin;YIN Xuefei;CHEN Ke’an(School of Electronics and Information,Northwestern Polytechnical University,Xi’an 710129,China;School of Marine Technology,Northwestern Polytechnical University,Xi’an 710072,China)
出处
《应用声学》
CSCD
北大核心
2020年第1期97-103,共7页
Journal of Applied Acoustics
基金
国家自然科学基金项目(11574249)
关键词
车型分类
耳蜗滤波器组
瞬时频率
对数能量
Vehicle classification
Cochlear filter bank
Instantaneous frequency
Logarithmic energy
