摘要
通过数据融合技术确定车辆实际运行轨迹,本文首先基于三角形相似原理和图形透视原理建立了通过视频图像提取车辆轨迹的模型.在分析视频数据与GPS数据优缺点的基础上,提出利用视频数据标定GPS数据状态的数据融合方法.为了能够标定视频检测器未覆盖的路段的GPS数据状态,提出了标志速度方法.利用融合的车辆实际轨迹,能够实现在线评价线控协调方案的效果,解决了已有需要假设条件评价线控协调方案性能方法的不足.
The paper explores the real vehicle trajectory through data fusion method.First,it formulates a vehicle trajectory extraction model of video data based on the triangle similarity theory and image perspective theory.Then,based on analyzing the advantage and disadvantage of video data and GPS data,the paper puts forward a data fusion method in which the video data is used to identify the GPS data status.To solve the problem that some links are lack of video data,the paper presents characteristic speed method.With the real vehicle trajectory which is obtained via data fusion method,the performance of signal coordination strategy is evaluated on-line and the traditional evaluating method based on some assumed traffic parameters is improved.
出处
《交通运输系统工程与信息》
EI
CSCD
2011年第5期61-67,共7页
Journal of Transportation Systems Engineering and Information Technology
基金
国家自然科学基金项目(71071024
70701006)
教育部科研重点项目(145)
教育部公路工程重点实验室开放基金(kfj100206)
湖南省教育厅科研重点项目(09A003)
长沙市科技局重点项目(K1001010-11)