A New SVM Algorithm and AMR Sensor Based Vehicle Classification

This paper proposes a new and efficient vehicle classification system base on support vector machine (SVM) algorithm and anisotropic magnetoresistive (AMR) sensor. The main point is that the AMR sensors detect the change of earth magnetic field which will be disturbed differently by different types of passing traffic vehicle. The characteristics of AMR sensor output model of the sample data, SVM learning classification algorithm, kernel function and model parameters are analyzed in detail. The results of our experiments show that this vehicle classification system base on AMR sensor and SVM algorithm is effective and efficient.