With its endless dark blue tone, the underwater world is filled with color, life, and beauty. It has many scientific imaging research opportunities. However, during the development of an underwater geolocation instrument based on polarization imaging sensors, we noticed that the underwater devices are all designed for cinematography applications. They are bulky and complicated, and they cannot satisfy the ever-changing scientific research needs. In this thesis, we report on the design of a compact, expandable underwater edge computing platform based on the Nvidia Jetson devices. This platform is capable of recording and processing more than 4 hours of footage underwater. With its modular design, the platform can support image sensors up to 70 mm/2.75" diagonal and virtually any lens. This platform opens up possibilities for researchers to perform underwater data collections, real-time machine learning inferences, and marine biology studies.
Use this login method if you
don't
have an
@illinois.edu
email address.
(Oops, I do have one)
IDEALS migrated to a new platform on June 23, 2022. If you created
your account prior to this date, you will have to reset your password
using the forgot-password link below.
