基于水平特征的车辆检测与跟踪  

Vehicle Detection and Tracking Based on Horizontal Features

作　　者：邢艳云[1] 于波[2] XING Yanyun;YU Bo(College of Automobile and Transportation,Tianjin University of Technology and Education,Tianjin 300222,China;Automotive Engineering Research Institute,China Automotive Technology and Research Center,Tianjin 300162,China)

机构地区：[1]天津职业技术师范大学汽车与交通学院,天津300222 [2]中国汽车技术研究中心汽车工程研究院,天津300162

出　　处：《汽车零部件》2021年第4期69-74,共6页Automobile Parts

基　　金：天津职业技术师范大学科研发展基金项目(KJ15-09)。

摘　　要：利用加权平均滤波算法对图像进行了滤波处理,去除部分噪声,利用Sobel算子的水平算子对图像的水平边缘进行增强处理,利用最大类间方差法对边缘增强后的图像进行图像分割;提出了利用车辆的水平特征中的列直方图和行直方图对车辆进行检测,根据检测结果得出该方法检测效果良好,即使是复杂环境下的车辆也能得到有效的识别,且对货车的识别效果良好;最后,利用限定感兴趣区域法对车辆进行跟踪,验证了识别方法与跟踪方法的有效性。The image was filtered by using the weighted average filter algorithm to eliminate the noise.Sobel operator s level operator was used to enhance the horizontal edge of image,and the Otsu method was used to segmentation the image.The vehicle histogram was used to detect the vehicle with horizontal histogram and row histogram.According to the detection results,this method has good detection effect,even in complex environment of the vehicle can also be effectively identified,and the recognition of the truck is also effective.Finally,the method of restricted interesting of region was used to track the vehicle,and the effectiveness of the recognition method and tracking method was verified.

关 键 词：最大类间方差法 水平边缘 直方图 检测 跟踪 

分 类 号：U463.85[机械工程—车辆工程]