Rational Orthogonal Wavelet Pulse and Feature Extraction Method Based on Auditory Frequency Cepstral Coefficient for Underwater Target Localization

Underwater target localization has always been a challenging and important research topic in underwater acoustic sensing, especially when the underwater target is moving. This paper uses three pulse signals for system design: continuous wave, linear frequency modulated signal and rational orthogonal wavelet signal. We use a geometric underwater channel model to generate a database of underwater signals with specified geometric parameters of ocean environments to simulate the ocean. The received pulses signal are converted into feature maps as the classifier's input. In this paper, Short-time Fourier transform, Mel-frequency cepstral coefficient, Gammatone frequency cepstral coefficient and Perceptual linear prediction coefficient are applied to construct different feature maps. The classifier uses a lightweight CNN model. Experiments demonstrate the superiority of wavelet pulse signals in underwater target localization. The multipath effect will also contribute to underwater acoustic sensing.