Underwater object classification using scattering transform of sonar signals
This work addresses the problem of classifying underwater objects like unexploded ordnance for sonar applications, but it is incremental as it applies an existing method to a new domain.
The paper tackled underwater object classification using sonar signals by applying the scattering transform, a nonlinear map based on CNNs, and achieved effective binary classification on both real UXO datasets and synthetic examples, with excellent performance due to quasi-invariance properties.
In this paper, we apply the scattering transform (ST), a nonlinear map based off of a convolutional neural network (CNN), to classification of underwater objects using sonar signals. The ST formalizes the observation that the filters learned by a CNN have wavelet like structure. We achieve effective binary classification both on a real dataset of Unexploded Ordinance (UXOs), as well as synthetically generated examples. We also explore the effects on the waveforms with respect to changes in the object domain (e.g., translation, rotation, and acoustic impedance, etc.), and examine the consequences coming from theoretical results for the scattering transform. We show that the scattering transform is capable of excellent classification on both the synthetic and real problems, thanks to having more quasi-invariance properties that are well-suited to translation and rotation of the object.