Vehicle Classification Algorithm based on Binary Proximity Magnetic Sensors and Neural Network

To improve the classification accuracy, a new algorithm is developed with binary proximity magnetic sensors and back propagation neural networks. In this scheme, we use the low cost and high sensitive magnetic sensors that detect the magnetic field distortion when vehicle pass by it and estimate vehicle length with the geometrical characteristics of binary proximity networks, and finally classify vehicles via neural networks. The inputs to the neural networks are the vehicle length, velocity and the sequence of features vector set, and the output is predefined vehicle category. Simulation and on-road experiment obtains the high recognition rate of 93.61%. It verified that this scheme enhances the vehicle classification with high accuracy and solid robustness.