With the rapid development of underwater sensor techniques, using acoustic techniques to
obtain and analyze underwater images is an effective approach due to the superior nature of …

Research on the automatic analysis of sonar images has focused on classical, ie non deep
learning based, approaches for a long time. Over the past 15 years, however, the application …

Deep learning has been recently shown to improve performance in the domain of synthetic
aperture sonar (SAS) image classification. Given the constant resolution with a range of …

Circular synthetic aperture sonars (CSAS) capture multiple observations of a scene to
reconstruct high-resolution images. We can characterize resolution by modeling CSAS …

The value of transferring convolutional neural networks (CNNs) trained with synthetic
aperture sonar (SAS) imagery is demonstrated in the context of an underwater unexploded …

The benefit of using multiple representations of data in the context of convolutional neural
networks (CNNs) is demonstrated. We present three variations on this theme of multiple …

Seabed characterization consists in the study of the physical and biological properties of the
of ocean floors. Sonar is commonly employed to capture the acoustic backscatter reflected …

Automatic target recognition (ATR) for 3D synthetic aperture sonar (SAS) imagery is an
intrinsic challenge in highly cluttered ocean environments, especially for objects partially or …

As many more nations actively transition their mine countermeasures (MCM) capability
towards autonomous systems, the NATO Centre for Maritime Research and Experimentation …

Deep learning has been recently shown to improve performance in the domain of synthetic
aperture sonar (SAS) image classification over existing shallow learning solutions. Given the …