Sidescan sonar

Automatic target recognition of unexploded ordnances in side scan sonar imagery has been a struggling task, due to the lack of publicly available side-scan sonar data. Real time image detection and classification algorithms have been implemented to combat this task, however, machine learning algorithms require a substantial amount of training data to properly detect specific targets. Transfer learning methods are used to replace the need of large datasets, by using a pre trained network on the side-scan sonar images. In the present study the implementation of a generative adversarial network is used to generate meaningful sonar imagery from a small dataset. The generated images are then added to the existing dataset to train an image detection and classification algorithm. The study looks to demonstrate that generative images can be used to aid in detecting objects of interest in side-scan sonar imagery.

Automatic target recognition capabilities in autonomous underwater vehicles has
been a daunting task, largely due to the noisy nature of sonar imagery and due to the lack
of publicly available sonar data. Machine learning techniques have made great strides in
tackling this feat, although not much research has been done regarding deep learning
techniques for side-scan sonar imagery. Here, a state-of-the-art deep learning object
detection method is adapted for side-scan sonar imagery, with results supporting a simple
yet robust method to detect objects/anomalies along the seabed. A systematic procedure
was employed in transfer learning a pre-trained convolutional neural network in order to
learn the pixel-intensity based features of seafloor anomalies in sonar images. Using this
process, newly trained convolutional neural network models were produced using
relatively small training datasets and tested to show reasonably accurate anomaly
detection and classification with little to no false alarms.

Many acoustic targets of interest contain features that are periodic in space. This thesis demonstrates that a chirp waveform, 2 kHz to 12 kHz, can detect repetitive structures with periods in the range of 0.125 m to 0.75 m. As aspect angle increases from 0 deg to 90 deg, a frequency shift in the range of 830 Hz to 4800 Hz will occur as the period decreases from 0.75 to 0.125 m. It follows that, spectral analysis can aid in target identification. A sonar propagation model has been developed to simulate the acoustic backscattered energy of a target with periodic characteristics in the presence of seafloor scattering. Examining the spectral components, with appropriate time gating, can achieve a gain of 7 dB at 3100 m.

A new method for calculating the direction-of-arrival (DOA), and thus the bathymetry of the seafloor, is presented. This method will calculate the DOA directly from the phase difference between the phase centers of the array. In parallel, a bathymetric sidescan sonar system originally built at Woods Hole and now here at Florida Atlantic University's Department of Ocean Engineering, was completed. Once this system was working, the above mentioned signal analysis regime will be implemented on actual data to test its validity.