Razvoj simulatora za testiranje metoda estimacije biomase riba u morskim uzgojnim kavezima

master's thesis

• Title (english): Development of a simulator for testing methods for estimation of fish biomass in marine fish cages
• Author: Marko Rezo
• Mentor: Zdenko Kovačić (mentor)
• Committee member: Zdenko Kovačić (predsjednik povjerenstva)
• Committee member: Matko Orsag (član povjerenstva)
• Committee member: Goran Vasiljević (član povjerenstva)
• Granter: University of Zagreb; Faculty of Electrical Engineering and Computing; Zagreb
• Defense date and country: 2022-02-24, Croatia
• Scientific / art field, discipline and subdiscipline: TECHNICAL SCIENCES; Computing

Abstract

U ovom radu bavimo se problemom estimacije biomase ribe u morskim ribogojilištima korištenjem heterogenog robotskog sustav koji se sastoji od bespilotnih letjelica i podvodnih vozila. Fotografije iz zraka dobivene pomoću bespilotnih letjelica tijekom hranjenja ribe predstavljaju ulazne podatke za procjenu broja riba te time i količine biomase u kavezu. S obzirom na nedostupnost pravih slika i podataka o pripadajućem broju ribe izrađen je simulator kojim su stvoreni sintetički podaci za obradu i izračun parametara aproksimacijskih funkcija. Rezultati dobiveni aproksimativnom metodom za procjenu broja riba na temelju obrade dobivenih slika u virtualnom dobiveni pokazuju da je ovaj problem iznimno složen. Potrebna je daljnja analiza uzgojnih kaveza po dubini i testiranje na stvarnim podacima.

Abstract (english)

In this paper, we deal with the problem of estimating fish biomass in marine fish farms using heterogeneous a robotic system consisting of drones and underwater vehicles. Aerial photographs obtained by drones during fish feeding are input data for estimating the number of fish and thus the amount of biomass in the cage. Given the unavailability of real images and data on the number of fish in those images, a simulator was created with which is possible to create synthetic data for processing and calculating the parameters of approximative functions. Results obtained by an approximate method for estimating the number of fish based on the processing of the obtained images in the virtual obtained show that this problem is extremely complex. Further depth analysis of breeding cages and testing on real data is required.

• Keywords: uzgoj morske ribe; heterogeni robotski sustavi; brojanje ribe; estimacija biomase riba; sintetički podaci
• Keywords (english): marine fish farming; heterogeneous robotics systems; fish counting; fish biomass estimation; synthetic data
• Language: croatian
• URN:NBN: urn:nbn:hr:168:473937
• Study programme: Title: Computing; Study programme type: university; Study level: graduate; Academic / professional title: magistar/magistra inženjer/inženjerka računarstva (magistar/magistra inženjer/inženjerka računarstva)
• Type of resource: Text
• File origin: Born digital
• Access conditions: Closed access
• Created on: 2023-01-13 10:41:21