摘要
当前道路前方车辆识别成为了智能网联汽车领域的研究热点,针对前车识别效率低的问题,基于机器视觉原理和车辆尾部类似于人脸的特点,通过研究和提取局部二值模式特征,并结合支持向量机分类方法,采用LBP特征谱的统计直方图作为特征向量用于分类识别,从而有效地实现了对前方车辆的识别与跟踪。基于Ubuntu 14.04操作系统和OpenCV 3.1版本的计算机视觉平台进行了算法实现和测试。结果表明:在不同车速工况下,本文算法运行时间短、识别率高,基本满足多场景下的前车识别条件。
At present,vehicle recognition in front of the road has become a research hotspot in the field of intelligent networked vehicles.Aiming at the problem of low recognition efficiency of the vehicle in front,based on the principle of machine vision and the features of the vehicle tail similar to human face,by studying and extracting LBP(Local Binary Pattern)features,Combined with SVM(Support Vector Machine)classification method,the statistical histogram of LBP feature spectrum is used as feature Vector for classification recognition,so as to effectively realize the recognition and tracking of vehicles ahead.Finally,the algorithm is implemented and tested based on Ubuntu 14.04 operating system and OpenCV 3.1 computer vision platform.The results show that the proposed algorithm has short running time and high recognition rate under different speed conditions,and basically meets the conditions of vehicle ahead recognition in multiple scenes.
作者
杨传江
曹景胜
袁增千
范博文
YANG Chuanjiang;CAO Jingsheng;YUAN Zengqian;FAN Bowen(College of Automobile and Traffic Engineering, Liaoning University of Technology, Jinzhou 121001, China)
出处
《重庆理工大学学报（自然科学）》
CAS
北大核心
2022年第6期81-87,共7页
Journal of Chongqing University of Technology：Natural Science
基金
辽宁省自然科学基金项目(20180550020)。
关键词
智能网联汽车
前车识别
LBP特征
SVM分类
intelligent connected vehicles
vehicle recognition
LBP feature
SVM classification
