A New Method for Classification of Events in Noisy Hydrophone Data

In this paper a new method for classifying events in noisy hydrophone data is developed. The method takes an image processing approach to the 1D hydrophone data by first converting it into a log-frequency spectrogram image (cepstrum). This image is then filtered by reconstructing it based on mutual information (MI) criteria of the dominant orientation map. The features of the reconstructed cepstrum are then enhanced using a combination of edge-tracking and noise smoothing. Feature classification on the processed cepstrum is performed using a least-squares support vector machine (LS-SVM). The method showed event detection sensitivity in excess of 99% for rare events such as whale calls from noisy hydrophone recordings from the NEPTUNE Canada project, with in excess of 97% specificity and 98% overall accuracy. With relatively low computational cost and high accuracy, the proposed method is useful for automated long-term monitoring of a wide variety of marine mammals and human related activities from hydrophone data.