基于机器视觉的车辆检测  

Vehicle Detection Based on Machine Vision

作　　者：杜学峰 高越 杨伟[1] 张勇[1] DU Xuefeng;GAO Yue;YANG Wei;ZHANG Yong(Chang’an University,College of Automobile,Shaanxi Xi'an 710064)

机构地区：[1]长安大学汽车学院,陕西西安710064

出　　处：《汽车实用技术》2021年第15期48-50,共3页Automobile Applied Technology

摘　　要：自动驾驶技术中,障碍物的识别是其中很重要的一环。文章设计了一种基于OpenCV技术的本车前方车辆的识别系统,其采用了单目摄像机进行图像输入,使用计算机完成图像预处理,然后训练级联分类器以识别车辆,文章采用Adaboost算法进行训练[1]。将处理好的图像导入车辆分类器,即可完成对前方车辆的识别。经过实验,本系统具有良好的实时性和可靠性。Obstle identification is a very important part in automatic driving technology.In this paper,a recognition system of the vehicle in front of the vehicle based on OpenCV technology is designed.The monocular camera is used for image input,the computer is used to complete image preprocessing,and then the cascade classifier is trained to identify the vehicle.In this paper,the Adaboost algorithm is used for training[1].The processed image is imported into the vehicle classifier to complete the recognition of the vehicle in front.Through the experiment,the system has good real-time performance and reliability.

关 键 词：OPENCV ADABOOST算法 自动驾驶 车辆检测 

分 类 号：U495[交通运输工程—交通运输规划与管理]