Browsing NTNU Open by Author "Mathiassen, John Reidar"
Now showing items 1-7 of 7
-
ASSIST: Accuracy-driven Sampling Strategies for Improved Supervised Training
Smedås, Halvor Bakken (Master thesis, 2021)Hvordan vi bruker treningstid har blitt viktigere med nevrale nettverkets stadig mer komplekse arkitekturer. Nyere forskning presenterer strategiske datautvelgingsmetoder som et alternativ til mini-batch SGD, som forenkler ... -
Automatic Quality Control of Salmon - Using Machine Learning Algorithms based on Input from a 3D Machine Vision System
Sture, Øystein (Master thesis, 2015)Quality control of Atlantic salmon is currently a task performed manually by human operators. To stay competitive in an increasingly global market, it becomes necessary to take advantage of technology to improve productivity ... -
Machine Vision for Defect Detection in Fisheries and Fish Processing Applications
Mathiassen, John Reidar (Doktoravhandlinger ved NTNU, 1503-8181; 2009:203, Doctoral thesis, 2009)The fisheries and fish processing industries have high labor costs. In part, this is due to visual inspection tasks, which are found in these industries, being so complex that humans are needed to do the inspection. One ... -
Robot learning with visual processing in arbitrarily sized, high resolution volumes
Dyrstad, Jonatan Sjølund (Doctoral theses at NTNU;2023:266, Doctoral thesis, 2023)Flexible robots, capable of manipulating objects in unstructured environments under changing conditions, will lead to a paradigm shift in automation. Such robotic solutions can potentially transform entire industries ... -
Robust Classification Approaches to Industrial Sorting of Herring Fractions
Guttormsen, Erik (Master thesis, 2015)Among the rest raw material produced during the filleting process of herring there are high value products such as roe and milt. As of today there has been little or no major effort to process these by-products at an ... -
Telemanipulation of NAO Robot Using Sixense STEM - Joint Control by External Analytic IK-Solver
Evjemo, Linn Danielsen (Master thesis, 2016)If it was possible to train robots to do new tasks instead of programming them directly, robots would be able to perform a greater variety of tasks that are usually carried out manually, both in industry and in society in ... -
Underwater recording and beamforming methods applicable for suppressing surface sounds from aquaculture facilities
Stene, Kristian Sørensen (Master thesis, 2020)Nylig økt fokus på produksjonseffektivitet og fiskevelferd har skapt behovet for ny teknologi for å overvåke statusen til fisk under forskjellige driftsforhold innen fiskeoppdett. Innspillinger av kjente retningsbestemte ...