单线圈检测器速度估计方法研究

Research on Method of Speed Estimation from Single Loop Detector

实时精确的交通速度对于交通管理系统来说是至关重要的。然而,最普遍的单线圈检测器却不能输出速度参数。提出了一种新的单线圈检测器速度估计的模糊神经网络方法。采用杭州公路实地数据对算法进行了验证,模型的速度估计结果与实际速度接近,与传统的g因子算法相比精度有显著地提高。这一方法可以有效地应用于交通管理系统速度的估计。

The real-time, accurate traffic speed is important for a successful traffic management sys-tem. Unfortunately, the most common form of traffic detector, the single loop detector, is incapable of providing speed measurements. A new method of speed estimation from single loop detector data is presen-ted by using fuzzy neural networks method. The algorithm of the proposed method is implemented and evaluated Using the field data from highway in Hangzhou City. Estimated speeds are compared with the ob-served speed data and also with results from g factor algorithm. The results show that the proposed me-thod has excellent estimation accuracy. So this method can be efficiently applied in traffic management sys-tem.