Vessel Classification through Convolutional Neural Networks using Passive Sonar Spectrogram Images

Lucas P. Cinelli, Gabriel S. Chaves, Markus V. S. Lima

DOI: 10.14209/sbrt.2018.340

Evento: XXXVI Simpósio Brasileiro de Telecomunicações e Processamento de Sinais (SBrT2018)

Keywords: convolutional neural networks classification machine learning security surveillance image processing passive sonar spectrograms

Abstract

Vessel classification is an extremely important task for coastal areas security and surveillance. Currently, this task relies on Synthetic Aperture Radar (SAR) images but gathering these images is expensive and often prohibitive. In this paper, we propose using spectrograms containing characteristic sound noise records of each vessel acquired from a single passive sonar device as an input to a convolutional neural network, which performs the classification. The main advantage of our method is its simplicity and low cost development due to the nature of this kind of data. Furthermore, our proposal can be used alongside other SAR-image-based method, potentially improving results of the overall classifier.

Download