An Antiinterference Traffic Speed Estimation System With Wireless Magnetic Sensor Network

Abstract

Wireless magnetic sensor networks (WMSNs) provide a low-power, low-cost solution for traffic information acquisition. Systems used for traffic speed estimation based on WMSNs have been well studied only when the geomagnetic field has not interfered. However, the widely developed electric rail transit systems, such as subways, light rails, and high-speed rail systems, produce magnetic field radiation that interferes with the geomagnetic field. So it is imperative to filter out noise in order to increase the detection accuracy. This article proposes a system for traffic speed estimation which can effectively eliminate the geomagnetic background interference. A morphological filter is designed for removing the interference and extracting the magnetic signatures of vehicles. The speed estimation is implemented based on the signatures reidentification. Experimental results verify that the proposed system is more accurate than existing systems.