基于Cesium平台中车辆的碰撞识别跟踪  

Collision Recognition and Tracking of Vehicles Based on Cesium Platform

作　　者：杨东远[1] 王瑞玺 Yang Dongyuan;Wang Ruixi(Tianjin research Institute For Water Transport Engineering,M.O.T,Tianjin 300456,China)

机构地区：[1]交通运输部天津水运工程科学研究院信息化中心,天津300456

出　　处：《计算机测量与控制》2018年第4期205-207,211,共4页Computer Measurement &Control

摘　　要：采用传统方法进行识别与跟踪,效果较差,无法得到精准车辆碰撞数据,提出了基于Cesium平台中车辆的碰撞识别与跟踪;针对车辆碰撞识别需先对样本进行训练,提取出正、负两种样本特征,利用离线车辆碰撞识别分类器识别尺度模块,并在Cesium平台下构建积分图,由此进行图像识别;针对车辆碰撞跟踪需进行阴影检测,根据获得的阴影区,排除非车辆碰撞阴影区,即完成车辆定位与验证;实验结果表明,该方法识别跟踪效果良好。The traditional method of identifying and tracking is not effective,and can not get precise vehicle collision data.A collision recognition and tracking based on Cesium platform is proposed.The vehicle collision recognition need to be conducted training on the positive and negative samples,extracted two kinds of sample characteristics,using off-line vehicle collision classifier recognition scale module,and construct the integral map in the Cesium platform,the image recognition;for vehicle collision tracking for shadow detection and shadow area according to the exclusion of non vehicle collision shadow,complete vehicle positioning and verification.According to the experimental results,the method of recognition and tracking is good.

关 键 词：Cesium平台 车辆碰撞 识别跟踪 3D虚拟 

分 类 号：TP391.41[自动化与计算机技术—计算机应用技术]