Automatic Vehicle Classification Based on Video with BP Neural Networks

The classification and statistics of the vehicles type in the road section are important parameters for the traffic management and control. The paper put forward the vehicle classification using image invariant moment and BP neural networks. First of all, road background is rebuild according to the serials images, and the background differences are used to segment vehicle region, invariant moment features are extracted for each vehicle region. The invariant moment features of vehicle will be the input of BP neural networks with three layers, and the vehicle type is classified according to the output of the BP neural networks. The test has verified the validity of this method.