DeepLofargram: A Deep Learning based Fluctuating Dim Frequency Line Detection and Recovery

TL;DR

This paper introduces DeepLofargram, a deep learning approach using convolutional neural networks to detect and recover fluctuating dim frequency lines in lofargrams, significantly surpassing human perception and previous methods.

Contribution

The paper presents a novel deep neural network architecture with multi-task learning for simultaneous detection and recovery of fluctuating frequency lines in lofargrams.

Findings

Achieves detection performance at -24dB on average

Surpasses human visual perception in line detection

Significantly outperforms previous state-of-the-art methods

Abstract

This paper investigates the problem of dim frequency line detection and recovery in the so-called lofargram. Theoretically, time integration long enough can always enhance the detection characteristic. But this does not hold for irregularly fluctuating lines. Deep learning has been shown to perform very well for sophisticated visual inference tasks. With the composition of multiple processing layers, very complex high level representation that amplify the important aspects of input while suppresses irrelevant variations can be learned. Hence we propose a new DeepLofargram, composed of deep convolutional neural network and its visualization counterpart. Plugging into specifically designed multi-task loss, an end-to-end training jointly learns to detect and recover the spatial location of potential lines. Leveraging on this deep architecture, the performance boundary is -24dB on average, and -26dB for some. This is far beyond the perception of human visual and significantly improves the state-of-the-art.