A study on modern deep learning detection algorithms for automatic target recognition in sidescan sonar images

Steiniger, Yannik; Groen, J.; Stoppe, Jannis; Kraus, Dieter; Meisen, Tobias

doi:10.1121/2.0001470

Cited by 3 publications

(1 citation statement)

References 0 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Reflections off the surface of the ocean and the seafloor, as well as clutter like fish, rocks and bubbles add noise and echoes that greatly impede clarity [1]. Robustly defining and selecting features for underwater signals is necessary for automatic target recognition tasks [2][3][4][5][6].…”

Section: Introductionmentioning

confidence: 99%

Convolutional Autoencoding of Small Targets in the Littoral Sonar Acoustic Backscattering Domain

Linhardt

Gupta

Bays

2022

JMSE

View full text Add to dashboard Cite

Automated target recognition is an important task in the littoral warfare domain, as distinguishing mundane objects from mines can be a matter of life and death. This is initial work towards the application of convolutional autoencoding to the littoral sonar space, with goals of disentangling the reflection noise prevalent in underwater acoustics and allowing recognition of the shape and material of targets. The autoencoders were trained on magnitude Fourier transforms of the TREX13 dataset. Clusters in the encoding space representing the known variable of measurement distance between the target and the sensor were found. An encoding vector space of around 16 dimensions appeared sufficient, and the space was shown to generalize well to unseen data.

show abstract