Low-Power and High-Perceptibility Underwater Drone Implementation for Inshore Aquaculture

Tian Song (), Takafumi Katayama (), Takashi Shimamoto () and Xiantao Jiang ()
Additional contact information
Tian Song: Graduate School of Technology, Industrial and Social Sciences, Tokushima University
Takafumi Katayama: Graduate School of Technology, Industrial and Social Sciences, Tokushima University
Takashi Shimamoto: Graduate School of Technology, Industrial and Social Sciences, Tokushima University
Xiantao Jiang: Shanghai Maritime University

A chapter in Advances and New Trends in Environmental Informatics, 2025, pp 105-121 from Springer

Abstract: Abstract In this work, a total solution is proposed for a typical underwater drone with high quality and low power consumption dedicated to inshore aquaculture. The proposed method introduced a high-perceptibility underwater image correction algorithm using a structural similarity evaluation to improve the video quality and object detection accuracy. The proposed algorithm considered real-time performance and low-power consumption by redesigning a compact model. It also employed automatic mixed precision (AMP) to effectively reduce the computational redundancy. An efficient implementation is also introduced using a low-cost GPU board, namely Jetson Xavier NX. The proposed implementation demonstrates improved object detection performance with a processing speed up to 60 fps.

Keywords: Underwater drone; Inshore aquaculture; Object detection; Low power implementation (search for similar items in EconPapers)
Date: 2025
References: Add references at CitEc
Citations:

There are no downloads for this item, see the EconPapers FAQ for hints about obtaining it.

Related works:
This item may be available elsewhere in EconPapers: Search for items with the same title.

Export reference: BibTeX RIS (EndNote, ProCite, RefMan) HTML/Text

Persistent link: https://EconPapers.repec.org/RePEc:spr:prochp:978-3-031-85284-8_7

Ordering information: This item can be ordered from
http://www.springer.com/9783031852848

DOI: 10.1007/978-3-031-85284-8_7

Access Statistics for this chapter

More chapters in Progress in IS from Springer
Bibliographic data for series maintained by Sonal Shukla () and Springer Nature Abstracting and Indexing ().