A vehicle detection algorithm based on wireless magnetic sensor networks

With the explosively increase of automobiles, the traffic congestion problem becomes more and more severe. This paper proposes a vehicle detection algorithm, named Peak-Valley Algorithm (PVA), based on the Wireless Sensor Networks (WSN). By measuring the disturbance of the Earth´s magnetic field, when a vehicle passes through a Honeywell 3-axis sensor, the vehicle can be detected. A large number of experimental data have been collected and analyzed. The system can perform in real-time with detection accuracy as high as 98.68% for vehicles. Especially, it can effectively solve the fluctuation problem caused by temperature drift in the baseline tracking method.