Cross-Correlation Based Efficient Technique For Vehicle Occupancy Detection using Magnetoresistive Sensors

Abstract

An efficient method to determine the occupancy state of a parking lot by determining the arrival and departure of vehicles from the perturbations in the magnetic field, is proposed. The method is based on cross-correlation of the magnetic field data with a suitable reference signal as template. The resulting correlation coefficient determines arrival and departure events and hence the occupancy state of parking lots. Results show that 2-axis magnetometer would suffice for accurate state-change detection. With threshold based conditions on the change in the signal, to determine when the correlation computation needs to be carried out, leads to efficient implementation of the algorithm in low-power sensor nodes. Investigation of placement location of the sensor nodes show that the sensor can be placed in between the parking lots, potentially reducing the number of required sensors to half the number of parking lots.