Files in this item



application/pdfSP20-ECE499-Thesis-Liang, Zuodong.pdf (5MB)
(no description provided)PDF


Title:Design of a compact underwater imaging and geolocalization platform with edge computing capability
Author(s):Liang, Zuodong
Contributor(s):Gruev, Viktor
underwater navigation
edge computing
Abstract: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.
Issue Date:2020-05
Date Available in IDEALS:2020-06-11

This item appears in the following Collection(s)

Item Statistics