• Deep learning in Dynamic Imager - A convolutional neural network module 

      Slettevold, Johan Nikolai (Master thesis, 2018)
      This thesis investigates the extent of which deep learning methods can be used for automatic detection of salmon in images. It also investigates the extent of which a module with deep learning functionality can be integrated ...
    • DeepPrivacy: A GAN-based framework for image anonymization 

      Hukkelås, Håkon (Master thesis, 2019)
      Samle data fra selvkjørende biler uten å anonymisere personlig informasjon er ulovlig etter introduksjonen av Personvernforordningen (GDPR) i 2018. For å samle data for å trene og validere maskinlæringsmodeller, må vi ...
    • DeepPrivacy: A Generative Adversarial Network for Face Anonymization 

      Hukkelås, Håkon; Lindseth, Frank; Mester, Rudolf (Chapter, 2019)
      We propose a novel architecture which is able to automatically anonymize faces in images while retaining the original data distribution. We ensure total anonymization of all faces in an image by generating images exclusively ...
    • Direct Visual Odometry on a GPU 

      Christensen, Matias (Master thesis, 2019)
      Denne masteroppgaven dekker implementasjonen av DVO (Direct Visual Odometry) algoritmen på en GPGPU (General-purpose Graphical Processing Unit). DVO er en direkte visuell odometri algoritme som er i stand til å estimere ...
    • End-to-end steering angle prediction and object detection using convolutional neural networks 

      Grimnes, Øyvind Kjeldstad (Master thesis, 2017)
      Artificial neural networks have enabled a new generation of autonomous vehicles. Public datasets can possibly be used to build networks capable of predicting steering angles and detect objects for self-driving vehicles. ...
    • End-to-End Steering Angle Prediction for Autonomous Vehicles 

      Kastet, Anna; Neset, Ragnhild Cecilie (Master thesis, 2018)
      In recent years, convolutional neural networks (CNNs) have been applied to several autonomous driving tasks in an end-to-end manner with promising results. As these kinds of systems are given the freedom to self-optimise ...
    • Enhanced Ultrasound Interpretation for Use in Neurological Navigation: Developing a Learning Platform for Enhanced Ultrasound Enterpretation 

      Lislebø, Even; Bjørnstad, Halvor G (Master thesis, 2015)
      Ultrasound (US) is widely used in medical imaging and boasts several advan- tages over other image modalities such as magnetic resonance imaging (MRI) and X-ray computed tomography (CT). Apart from being free of harmful ...
    • Face Recognition for Access Control Using Deep Neural Networks on Mobile Devices 

      Zakariassen, Line (Master thesis, 2018)
      The Telenor-NTNU AI Lab would like to use facial detection as access control for their Lab. A proposed way of doing this is to mount a mobile device, like a tablet, outside the lab and run a facial recognition application ...
    • Fully-Automatic Coronary Artery Segmentation using Deep Convolutional Autoencoders 

      Jacobsen, Frode (Master thesis, 2018)
      Automatic semantic segmentation of medical images is an important tool in aiding clinical experts in diagnosing diseases. The large volume of data produced in medical imaging modalities such as CT and MRI, and the inherent ...
    • GPU-Based Airway Tree Segmentation and Centerline Extraction 

      Smistad, Erik (Master thesis, 2012)
      Lung cancer is one of the deadliest and most common types of cancer inNorway. Early and precise diagnosis is crucial for improving the survivalrate. Diagnosis is often done by extracting a tissue sample in the lung throughthe ...
    • HD-Maps in Autonomous Driving 

      Gran, Christoffer Wilhelm (Master thesis, 2019)
      Bilindustrien går i en autonom retning, og mange av de største teknologifirmaene i verden investerer ressurser i utvikling innenfor dette området. Norsk teknisk-vitenskapelige universitet (NTNU) startet i 2018 sitt eget ...
    • ImageCL and Other Techniques and Tools for Optimizing Applications Utilizing Heterogeneous Computing 

      Falch, Thomas Løfsgaard (Doctoral theses at NTNU;2018:92, Doctoral thesis, 2018)
      Several technological and economic trends have recently caused a rise in the use and adoption of systems with heterogeneous and parallel hardware. These systems include different computing devices with different architectures, ...
    • Improved Bronchoscopy by new image guided Approach 

      Reynisson, Páll Jens (Doctoral theses at NTNU;2018:81, Doctoral thesis, 2018)
      Navigation in bronchoscopy has developed into a feasible approach for lung diagnostics since introduced in 1998. The concept combines computer generated models from patient CT data with position and orientation tracking ...
    • Improved Distance Weighted GPU-based 3D Ultrasound Reconstruction Methods 

      Øygard, Tord (Master thesis, 2014)
      Ultrasound is a flexible medical imaging modality with many uses, one ofthem being intra-operative imaging for use in navigation. In order to obtainthe highest possible spatial resolution and avoiding big, clunky 3D ...
    • Improved Distance Weighted GPU-based 3D Ultrasound Reconstruction Methods 

      Øygard, Tord (Master thesis, 2014)
      Ultrasound is a flexible medical imaging modality with many uses, one of them being intra-operative imaging for use in navigation. In order to obtain the highest possible spatial resolution and avoiding big, clunky 3D ...
    • Interaksjonsløs VR 

      Grytten, Lars Henrik (Master thesis, 2019)
      Denne oppgaven forsøkte å finne ut hvilket potensial interaksjonsløs VR har innen utdanning. For å utforske dette ble oppfattet tilfredshet, oppslukthet og autonomi undersøkt. En prototype av en interaksjonsløs VR-applikasjon ...
    • Kransarterie segmentering ved bruk av dyp læring 

      Jostad, Trude (Master thesis, 2019)
      En metode for diagnostisering av hjerte-karsykdommer er å måle FFR (fractional flow reserve), som innebærer et lite kirurgisk inngrep. Ved å ekstrahere den geometriske strukturen av hjertets kransarterier fra CT bilder ...
    • Laboratory test of Single Landmark registration method for ultrasound-based navigation in laparoscopy using an open-source platform 

      Perez de Frutos, Javier; Hofstad, Erlend Fagertun; Solberg, Ole Vegard; Tangen, Geir Arne; Lindseth, Frank; Langø, Thomas; Elle, Ole Jacob; Mårvik, Ronald (Journal article; Peer reviewed, 2018)
      Purpose Test the feasibility of the novel Single Landmark image-to-patient registration method for use in the operating room for future clinical trials. The algorithm is implemented in the open-source platform CustusX, a ...
    • Learning Algorithms in Virtual Reality as Part of a Virtual University 

      Windsrygg, Sindre (Master thesis, 2019)
      I utdanning kan ny teknologi gi bedre forhold for læring. Virtuell virkelighet (Virtual Reality) har de siste årene blitt veldig populært hovedsakelig i spillindustrien, men har også begynt å bli brukt som et verktøy av ...
    • Lobster Watchdog 

      Melsom, Adrian Siim; Johansen, Tobias (Master thesis, 2019)
      Hummeroppdrett er et område som ikke har benyttet seg av teknologi som maskinlæring og er svært lite automatisert. Prosesser som fôring krever store mengder manuelt arbeid. Fasiliteter på land er lite skalerbare, der dagens ...