PERSONAL Sign in with your SPIE account to access your personal subscriptions or to use specific features such as save to my library, sign up for alerts, save searches, etc.
The underwater realm lacks GPS signal penetration, making passive navigation challenging. To overcome these hurdles, we've developed an underwater geolocalization technique that solely utilizes polarization data. This method leverages the underwater scattering phenomenon, which largely depends on the positions of the sun or moon. By training a deep neural network with over 10 million images gathered over two years, we have achieved an impressive accuracy of approximately 60 km with this approach.
Viktor Gruev
"Polarization-based underwater geolocalization with machine-learning algorithms", Proc. SPIE 13050, Polarization: Measurement, Analysis, and Remote Sensing XVI, 1305008 (10 June 2024); https://doi.org/10.1117/12.3012870
ACCESS THE FULL ARTICLE
INSTITUTIONAL Select your institution to access the SPIE Digital Library.
PERSONAL Sign in with your SPIE account to access your personal subscriptions or to use specific features such as save to my library, sign up for alerts, save searches, etc.
The alert did not successfully save. Please try again later.
Viktor Gruev, "Polarization-based underwater geolocalization with machine-learning algorithms," Proc. SPIE 13050, Polarization: Measurement, Analysis, and Remote Sensing XVI, 1305008 (10 June 2024); https://doi.org/10.1117/12.3012870