摘要
不同的交通信息采集方式由于其硬件和采集条件的不同,数据的适用范围和准确性也不同。在短时交通预测中,对于来自于不同检测器的交通流数据进行融合,并在数据融合的基础上进行区间速度的预测,可以有效地改善预测结果的准确性和可靠性。文中提出一种基于卡尔曼滤波的数据融合和区间速度预测方法。在对数据进行预处理和交通状态划分的基础上,根据不同的交通状态,进行多源交通数据融合和区间速度的预测。研究确定了卡尔曼滤波方法中的各个参数,并使用人工神经网络的方法求解状态转移矩阵。算法验证结果表明,速度预测的精度在90%以上。
Due to the variety of equipment and collection condition, different traffic data collection methods have their own application fields and different precision. Therefore, in order to acquire more reliable analysis results, the data from different detectors need to be fused in short-term traffic forecast. Moreover, the travel speed estimation should be carried out based on the data fusion results. The paper presented a short-term forecasting algorithm for travel speed based on Kalman filter data fusion. After the pretreatment and traffic states division, the multi-source data including microwave detector data, loop detector data and floating car data （FCD） were fused to estimate travel speed according to the different traffic states. This research determines parameters for Kalman filter, and computes the states transformation matrix with the artificial neural network （ANN）. The analysis result of model validation shows that the average accuracy of the travel speed forecasting algorithm is over 90 percents.
出处
《交通信息与安全》
2009年第3期74-77,共4页
Journal of Transport Information and Safety
基金
国家科技部科技支撑项目(批准号:2006BAG01A01)
北京市科委科技计划项目(批准号:D07050600440000)
北京工业大学校青基金项目(批准号:X1004011200802)资助
关键词
智能交通系统
交通数据处理
数据融合
交通预测
浮动车数据
卡尔曼滤波
人工神经网络
intelligent transportation system （ITS）
traffic data processing
data fusion
traffic forecasting
floating car data （FCD）
Kalman filter
artificial neural network （ANN）
