Moving target classification is an important issue in wireless sensors. The wild environment makes it a difficult problem for the acoustic signals. In this paper, a new classification method for moving targets in the wild is proposed based on microphone array and linear sparse auto-encoder (LSAE). Firstly, the acoustic signals of moving targets are enhanced by delay-and-sum (DS) beamformer in the narrawband way for the simplicity.

In this paper, a practical method is proposed for a moving target's fundamental frequency (MTFF) extraction from its acoustic signal. This method is developed for the application of motion parameters estimation. Starting from the analysis of the target frequency model and the acoustic Doppler model, the characteristics of moving target's signal are discussed. Based on the signatures of target's acoustic signal, a new approximate greatest common divisor (AGCD) method is developed to obtain an initial fundamental frequency (IFF). Then, the corresponding harmonic number associated with the IFF is determined by maximizing an objective function formulated as an impulse-train-weighted symmetric average magnitude sum function (SAMSF) of the observed signal.