• 3D Object Detection for Autonomous Driving Using Real and Simulated Data 

      Brekke, Åsmund; Vatsendvik, Fredrik (Master thesis, 2019)
      Selvkjørende biler har blitt et populært tema det siste tiåret, både grunnet bredere offentlig interesse i kunstig intelligens og imponerende resultater oppnådd av forskninsinstitusjoner og private selskaper som Google, ...
    • 3D Object Detection for Autonomous Driving Using Real and Simulated Data 

      Brekke, Åsmund; Vatsendvik, Fredrik (Master thesis, 2019)
      Selvkjørende biler har blitt et populært tema det siste tiåret, både grunnet bredere offentlig interesse i kunstig intelligens og imponerende resultater oppnådd av forskninsinstitusjoner og private selskaper som Google, ...
    • 3D ultrasound reconstruction algorithms from analog and digital data 

      Solberg, Ole Vegard; Lindseth, Frank; Bø, Lars Eirik; Muller, Sebastien; Meland, Janne Beate Lervik; Tangen, Geir Arne; Hernes, Toril A. Nagelhus (Journal article; Peer reviewed, 2010)
      Freehand 3D ultrasound is increasingly being introduced in the clinic for diagnostics and image-assisted interventions. Various algorithms exist for combining 2D images of regular ultrasound probes to 3D volumes, being ...
    • A machine learning approach for jaundice detection using color corrected smartphone images 

      Falk, Håvard Hagen; Jensen, Oliver Damsgaard (Master thesis, 2018)
      Neonatal jaundice and the associated yellow skin discoloration is caused by hyperbilirubinemia, a condition in which there is too much bilirubin in the blood. In 2010, the failure to treat jaundice resulted in 114,000 ...
    • A mobile application for booking autonomous vehicles - Combining the sharing economy and self-driving cars 

      Mathisen, Hanne (Master thesis, 2018)
      Fully autonomous vehicles eliminate the human driver of cars by taking care of all driving tasks. The cars can view 360 degrees of their surroundings and make decisions based on them, which can optimize traffic and fuel ...
    • A mobile game/app for enhanced ultrasound interpretation 

      Khosravifard, Mina (Master thesis, 2014)
      Ultrasound imaging is widely used imaging modality. Ultrasound has many advantages: it is supporting continuous realtime imaging in 2D or 3D, relatively inexpensive, non invasive, and free of harmful radiation. Beside those ...
    • A new GPU-based Hybrid Approach to 3D Ultrasound Reconstruction - Quality Reconstruction with Top-End Performance in FAST 

      Fagerli, Ruben Håskjold (Master thesis, 2016)
      Ultrasound imaging is a versatile, portable, and low cost medical imaging modality. It produces real-time data from a local area in the scanned person, or object, useful in use cases such as intra-operative imaging. Freehand ...
    • A Serious Game for Medical Image Interpretation 

      Tønnessen, Martin Schiller (Master thesis, 2016)
      It is now quite common to use different types of image modalities such as ultrasound and MRI in the practise of medicine. However, the different modalities require experience and practice. A study of the potential behind ...
    • Accelerating Training of Deep Reinforcement Learning-based Autonomous Driving Agents Through Comparative Study of Agent and Environment Designs 

      Vergara, Marcus Loo (Master thesis, 2019)
      In this thesis, we will be investigating the current landscape of state-of-the-art methods using deep reinforcement learning for the purposes of training self-driving cars. Autonomous driving has garnered the interest of ...
    • Airway segmentation and centerline extraction from thoracic CT - Comparison of a new method to state of the art commercialized methods 

      Reynisson, Pall Jens; Scali, Marta; Smistad, Erik; Hofstad, Erlend Fagertun; Leira, Håkon Olav; Lindseth, Frank; Hernes, Toril A. Nagelhus; Amundsen, Tore; Sorger, Hanne; Langø, Thomas (Peer reviewed; Journal article, 2015)
      Introduction Our motivation is increased bronchoscopic diagnostic yield and optimized preparation, for navigated bronchoscopy. In navigated bronchoscopy, virtual 3D airway visualization is often used to guide a bronchoscopic ...
    • An educational game for enhanced medical imaging interpretation skills 

      Dalby, Kristoffer Andreas; Tørnvall, Fredrik Borgen (Master thesis, 2017)
      In the field of medicine, medical imaging is a tool of significance. It is a noninvasive diagnostic method and an instrument for guiding surgical equipment inside the patient. There exist different types of image modalities ...
    • Automatic Intraoperative Correction of Brain Shift for Accurate Neuronavigation 

      Iversen, Daniel Høyer; Wein, Wolfgang; Lindseth, Frank; Unsgård, Geirmund; Reinertsen, Ingerid (Journal article; Peer reviewed, 2018)
      Background Unreliable neuronavigation owing to inaccurate patient-to-image registration and brain shift is a major problem in conventional magnetic resonance imaging–guided neurosurgery. We performed a prospective ...
    • Autonomous Vehicle Control: End-to-end Learning in Simulated Environments 

      Haavaldsen, Hege; Aasbø, Max Michael Johnsen (Master thesis, 2019)
      I de siste årene er det gjort betydelige fremskritt mot et kjøretøys evne til å operere autonomt. En ende-til-ende-tilnærming forsøker å oppnå autonom kjøring ved hjelp av en enkel, omfattende komponent. Nylige gjennombrudd ...
    • Color Calibration on Human Skin Images 

      Amani, Mahdi; Falk, Håvard Hagen; Jensen, Oliver Damsgaard; Vartdal, Gunnar; Aune, Anders; Lindseth, Frank (Chapter, 2019)
      Many recent medical developments rely on image analysis, however, it is not convenient nor cost-efficient to use professional image acquisition tools in every clinic or laboratory. Hence, a reliable color calibration is ...
    • Color Calibration on Human Skin Images 

      Amani, Mahdi; Falk, Håvard Hagen; Jensen, Oliver Damsgaard; Vartdal, Gunnar; Aune, Anders; Lindseth, Frank (Journal article; Peer reviewed, 2019)
      Many recent medical developments rely on image analysis, however, it is not convenient nor cost-efficient to use professional image acquisition tools in every clinic or laboratory. Hence, a reliable color calibration is ...
    • Computer Vision and Deep Learning in Autonomous Drones 

      Pike, Markus Teigen (Master thesis, 2017)
      In this thesis we want to create a deep learning based object detection solution that is able to run locally on an autonomous drone. The goal of the drone is to herd a group of ground robots correctly within the International ...
    • Computer Vision and Deep Learning on Mobile Devices 

      Hansen, Tobias (Master thesis, 2018)
      Deep learning has advanced the field of computer-based image classification algorithms within a range of different fields. These algorithms are computational demanding, requiring a minimum level of computational power. The ...
    • Cross modality guided liver image enhancement of CT using MRI 

      Naseem, Rabia; Alaya Cheikh, Faouzi; Beghdadi, Azeddine; Elle, Ole Jakob; Lindseth, Frank (Peer reviewed; Journal article, 2019)
      Low contrast Computed Tomographic (CT) images often hamper the diagnosis of critical tumors found in various human organs. Contrast enhancement schemes play significant role in improving the visualization of these structures. ...
    • Deep Convolutional Encoder-Decoder Networks for Digital Rock Porosity Segmentation 

      Andresen, Markus; Johansen, Simen Nordby (Master thesis, 2019)
      Digital rock physics (DRP) er en moderne metode for å karakterisere de fysiske egenskapene til ulike typer stein. Ved å modellere korn-, flerfaset- og porevolum i forksjellige bergarter, kan en assistere institusjoner med ...
    • Deep Convolutional Encoder-Decoder Networks for Digital Rock Porosity Segmentation 

      Andresen, Markus; Johansen, Simen Nordby (Master thesis, 2019)
      Digital rock physics (DRP) er en moderne metode for å karakterisere de fysiske egenskapene til ulike typer stein. Ved å modellere korn-, flerfaset- og porevolum i forksjellige bergarter, kan en assistere institusjoner med ...