On-Road Vehicle Detection Algorithm Based on Mathematical Morphology

Wireless magnetic sensor network is gradually used in the intelligent traffic detection system. However, the magnetic sensor is susceptible to the geomagnetic interference. The operation of electric railway systems, such as subways and light rail systems, generates geomagnetic interference signal. Most existing detection systems are prone to high false detection rates in the case of interference environment. This work proposes an on-road vehicle detection algorithm which can effectively eliminate interference signal. Based on mathematical morphology, we designed two filters for extracting the signals of moving and static vehicles from interfered magnetic signals. We have deployed an experiment system at the intersection nearby a subway. Experiment results show that the algorithm has an accuracy rate of more than 98% for vehicle detection.