Magnetic Sensor-Based Multi-Vehicle Data Association

Sensors have been playing an increasingly important role in smart cities. Using small roadside magnetic sensors provides a cost-efficient method for monitoring vehicle traffic. However, there are significant challenges associated with vehicle data misalignment due to the timing-offsets between sensors and missed or increased data because of vehicle lane-changing. In this paper, we propose a novel traffic information acquisition and vehicle state estimation scheme using multiple road magnetic sensors. To efficiently solve the multi-sensor registration problem in the presence of timing-offset, we develop a linear discrimination analysis method to achieve vehicle separation and classification. To handle the situation of lane-changing, we propose a data smoothing technique based on a multi-hypotheses tracker that exploits vehicle correlation. The road density effect on the probability of correct data association is investigated, with numerical and experimental results provided. The results show that our proposed scheme can effectively detect vehicles with a 95.5% accuracy rate. It also outperforms some other speed sensing methods in terms of the vehicle speed estimation accuracy.