Maneuvering Target Tracking Based on Wavelet Neural Network

Wavelet neural network (WNN) is such a network that combines wavelet transform with conventional neural networks. It takes nonlinear wavelet bases as hidden nodes activation to replace nonlinear activation function in neural networks. A new maneuvering target tracking method based on WNN is proposed. The structure of multi-resolution WNN fitting for maneuvering target tracking is constructed. It does not need modeling and computing quantity doesn´t increase with the number of target models. Simulation results show that the algorithm can track maneuvering target exactly, meanwhile, it has better tracking performance than BP neural networks.