A Novel Approach Research on Low Altitude Passive Acoustic Target Recognition Based on ICA and HMM

摘要

An approach is proposed to classifying simultaneous multiple low altitude targets in battlefield. Based on Independent Component Analysis (ICA), the mixed signal is separated into several single and pure signals, and the noise is removed from the acoustic signal. Mel-frequency Cepstrum Coefficients (MFCC) which responses the characteristic of the sound more aggressively is extracted as characteristic parameters in the system. For the Hidden Markov Models (HMM), in order to work better performance in representing the time-variant signal, the HMM are employed to simulate the model change of the sound signals as the with time going. K-means algorithm is used as clustering MFCC to produce training and identifying eigenvector. Simulation results indicate that this approach's is effective in target recognition.