基于压缩感知的道路交通参数修复方法研究

The Recovery Algorithm for Road Traffic Parameters Based on Compressive Sensing

为了解决交通路网中的道路交通检测器大面积发生故障时道路交通参数数据的缺失或异常问题,本文提出了一种基于压缩感知的道路交通参数修复方法.首先对道路交通参数矩阵进行分解和逼近;然后在道路交通参数矩阵进行分解和逼近的基础上,利用压缩感知的理论及方法进行道路交通参数修复,并对基于压缩感知进行道路交通参数修复的过程中所涉及的主要参数进行分析和设定;最后依据实例对基于压缩感知的道路交通参数数据修复算法进行验证.选取北京市典型快速路对该算法进行验证,结果证明,基于压缩感知的道路交通参数数据的修复方法具有高精度,在实际应用中是可行的.

To solve the road traffic parameters data problems （data invalid or data deletion） when a part of traffic states detectors in the road network break down, an algorithm based on compressive sensing is presented to repair traffic parameters of the road traffic network in this paper. Firstly, the road traffic parameters data are decomposed and approximated. Then the road traffic parameters recovery approach is presented based on compressive sensing, and the parameters setting referred in this road traffic parameters estimation approach based on compressive sensing is discussed. Finally, one typical road network in Beijing is adopted for the experiments analysis. The results show that this traffic states data recovery approach based on compressive sensing is feasible and can achieve a high accuracy.