Radar object recognition by wavelet transform and neural network
Jozef Tkac, S. Spirko, L. Boka · 2002
This paper presents a method of radar object recognition by wavelet transform and neural network. Analysing range profiles by wavelet transform can show information about the tracked object more clearly. It also gives a method of constructing a feature vector for automatic recognition so that the dimension of the feature vector may be much smaller than the dimension of the primitive echo signal. A three-layer backpropagation neural network is used as recognisor. This problem is aimed at radar systems with the duration of the transmitted pulses longer than the size of the object.