Powered by OpenAIRE graph
Found an issue? Give us feedback
image/svg+xml art designer at PLoS, modified by Wikipedia users Nina, Beao, JakobVoss, and AnonMoos Open Access logo, converted into svg, designed by PLoS. This version with transparent background. http://commons.wikimedia.org/wiki/File:Open_Access_logo_PLoS_white.svg art designer at PLoS, modified by Wikipedia users Nina, Beao, JakobVoss, and AnonMoos http://www.plos.org/ NTNU Openarrow_drop_down
image/svg+xml art designer at PLoS, modified by Wikipedia users Nina, Beao, JakobVoss, and AnonMoos Open Access logo, converted into svg, designed by PLoS. This version with transparent background. http://commons.wikimedia.org/wiki/File:Open_Access_logo_PLoS_white.svg art designer at PLoS, modified by Wikipedia users Nina, Beao, JakobVoss, and AnonMoos http://www.plos.org/
NTNU Open
Bachelor thesis . 2025
Data sources: NTNU Open
addClaim

Underwater Wildlife Monitoring Stations

Authors: Abrahamsen, Kato Mørland; Bjørkedal, Øyvind; Holtan, Hans Kristian; Robertsen, Steffen;

Underwater Wildlife Monitoring Stations

Abstract

With rising climate change, and more overfishing than ever, it becomes increasingly important to monitor marine wildlife. This thesis describes the development of an Underwater Wildlife Monitoring Station (UWMS), a system created to collect and transmit data containing fish properties autonomously. Ultimately the purpose of the UWMS is to be a part of a larger network of Internet of Underwater Things (IoUT), with real-time monitoring for research in underwater environments. The system consisted of an Intel RealSense D435 camera with depth measurements, a Khadas VIM3/4 Single-board Computer (SBC) as the processing unit, and a Seatrac X010 acoustic modem for data transmission inside of a waterproof enclosure. A YOLOv8 model with an accompanying computer vision algorithm was used to detect, classify and extract properties of fish. The processing occured in real-time, and data such as length, amount of fish in a school, and species were parsed for acoustic communication. The YOLO model was trained using the DeepFish and Norfisk datasets, chosen to reflect conditions and species it was likely to encounter. ROS2 was used to exchange data between the computer vision algorithm and the acoustic communication system locally. Field tests demonstrated the systems ability to capture images, calculate length estimations, and transmit data acoustically over short distances in realistic conditions. Based on this the UWMS could prove a modular, scalable and easily deployable marine monitoring tool for sustainable ocean research, if developed further.

Med økende klimaendringer og mer overfisking enn noensinne, blir det stadig viktigere å overvåke livet i havet. Denne rapporten tar for seg utviklingen av overvåkningstassjon for dyreliv undervann (UWMS), et system lagd for å samle og sende data om fiskens detaljer autonomt. På sikt er hensikten med UWMS å bli del av et større nettverk av undervanns systemer (IoUT), med sanntidsovervåkning for forskning i undervanns miljøer. Systemet var bygd opp av et Intel Realsense D435 kamera med dybdemåler, en Khadas VIM3/4 ettbrettsdatamaskin (SBC) som prossesseringsenhet, og Seatrac X010 akustisk modem for data transmisjon inni en vanntett innkapsling. En YOLOv8 model med en tilhørende algoritme for datasyn ble brukt for å detektere, klassifisere og hente ut egenskaper fra fisk. Prossesseringen foregikk i sanntid, og data som lengde, fiskemengde i en stim og fisketype ble parset for akustisk kommunikasjon. YOLO-modellen ble trent ved bruk av DeepFish og Norfisk datasettene, valgt for å gjenspeile forhold og arter den sannsynligvis ville møte. ROS2 ble brukt til å utveksle data lokalt mellom datasynsalgoritmen og det akustiske kommunikasjonssystemet. Felttester demonstrerte systemets evne til å ta bilder, beregne lengdeestimater og overføre data akustisk over korte avstander under realistiske forhold. Basert på dette kan UWMS vise seg å være et modulært, skalerbart og lett utplasserbart marint overvåkingsverktøy for bærekraftig havforskning, hvis det utvikles videre.

Country
Norway
  • BIP!
    Impact byBIP!
    selected citations
    These citations are derived from selected sources.
    This is an alternative to the "Influence" indicator, which also reflects the overall/total impact of an article in the research community at large, based on the underlying citation network (diachronically).
    0
    popularity
    This indicator reflects the "current" impact/attention (the "hype") of an article in the research community at large, based on the underlying citation network.
    Average
    influence
    This indicator reflects the overall/total impact of an article in the research community at large, based on the underlying citation network (diachronically).
    Average
    impulse
    This indicator reflects the initial momentum of an article directly after its publication, based on the underlying citation network.
    Average
Powered by OpenAIRE graph
Found an issue? Give us feedback
selected citations
These citations are derived from selected sources.
This is an alternative to the "Influence" indicator, which also reflects the overall/total impact of an article in the research community at large, based on the underlying citation network (diachronically).
BIP!Citations provided by BIP!
popularity
This indicator reflects the "current" impact/attention (the "hype") of an article in the research community at large, based on the underlying citation network.
BIP!Popularity provided by BIP!
influence
This indicator reflects the overall/total impact of an article in the research community at large, based on the underlying citation network (diachronically).
BIP!Influence provided by BIP!
impulse
This indicator reflects the initial momentum of an article directly after its publication, based on the underlying citation network.
BIP!Impulse provided by BIP!
0
Average
Average
Average
Green