Blar i NTNU Open på forfatter "Stahl, Annette"

Viser treff 41-60 av 105

    • Experimental validation of camera-based maritime collision avoidance for autonomous urban passenger ferries 

      Helgesen, Øystein Kaarstad; Thyri, E.H.; Brekke, Edmund Førland; Stahl, Annette; Breivik, Morten (Peer reviewed; Journal article, 2023)
      Maritime collision avoidance systems rely on accurate state estimates of other objects in the environment from a tracking system. Traditionally, this understanding is generated using one or more active sensors such as ...

    • Experimental validation of camera-based maritime collision avoidance for autonomous urban passenger ferries 

      Helgesen, Øystein Kaarstad; Thyri, Emil Hjelseth; Brekke, Edmund Førland; Stahl, Annette; Breivik, Morten (Peer reviewed; Journal article, 2023)
      Abstract: Maritime collision avoidance systems rely on accurate state estimates of other objects in the environment from a tracking system. Traditionally, this understanding is generated using one or more active sensors ...

    • Feature-based pose estimation of ships in monocular camera images 

      Lauvsnes, Marthe (Master thesis, 2020)
      En metode for å beregne orienteringen til et fartøy basert på en sekvens av bilder blir presentert. Metoden blir demonstrert både på syntetiske bilder fra et simulert miljø og ekte bilder fra Trondheim havn. OpenCV blir ...

    • Few-Shot Open World Learner 

      Teigen, Andreas Langeland; Saad, Aya; Stahl, Annette; Mester, Rudolf (Peer reviewed; Journal article, 2021)
      Computer vision based recognition systems in dynamically changing environments require continuously updating datasets with novel detected categories while maintaining equally high performance on previously established ...

    • Few-shot open world learning 

      Teigen, Andreas Langeland (Master thesis, 2020)
      Datasynsystemer blir i økende grad tatt i bruk ute i dagligdags- og feltarbeidsapplikasjoner. Denne overgangen fra kontrollerte lab-omgivelser til den vide verden byr derimot på flere nye problemer. I stedet for kun å møte ...

    • Fusing Shape and Color for High-Speed Visual Tracking 

      Jensen, Martin Schei (Master thesis, 2017)
      In a computer vision system, one must often assume that the system will encounter objects it has never seen before. A component that is able to track such objects is therefore an integral part of a complete computer vision ...

    • Heterogeneous multi-sensor tracking for an autonomous surface vehicle in a littoral environment 

      Helgesen, Øystein Kaarstad; Vasstein, Kjetil; Brekke, Edmund Førland; Stahl, Annette (Peer reviewed; Journal article, 2022)
      Sensor fusion plays a key part in autonomous surface vehicles, however, the high cost of sensors makes the barrier of entry in this research field quite high. In this work, we present a complete system for sensor fusion ...

    • Hole Detection in Aquaculture Net Cages from Video Footage 

      Madshaven, Arild; Schellewald, Christian; Stahl, Annette (Peer reviewed; Journal article, 2021)
      Frequent inspection of salmon cage integrity is essential to early detect and prevent the possible escape of farmed salmon—minimizing the risk of any negative impact for the remaining wild stock of salmon. Current ...

    • Image Segmentation of Corrosion Damages in Industrial Inspections using State-of-the-Art Neural Networks 

      Fondevik, Simen Keiland (Master thesis, 2020)
      Denne masteroppgaven studerer avanserte bildesegmenteringsalgoritmer for automatisk korrosjonsskade-segmentering. Automatisk bildeanalyse er nødvendig for å prosessere all data som samles inn med dronebaserte industrielle ...

    • Implications of single-stage deep learning networks in real-time zooplankton identification 

      Ansari, Sadaf; Desai, Dattesh V.; Saad, Aya; Stahl, Annette (Peer reviewed; Journal article, 2023)
      Zooplankton are key ecological components of the marine food web. Currently, laboratory-based methods of zooplankton identification are manual, time-consuming, prone to human error and require expert taxonomists. Therefore, ...

    • Improved Maritime Vessel Detection in Camera Images using Bag-of-Visual-Words 

      Kolsgaard, Amalie (Master thesis, 2022)
      Autonome fartøy er avhengig av intelligente beslutningsalgoritmer basert på maskinlæring. En stor fordel innen maskinlæring er at dype nettverk utvikler seg mot å bli kraftfulle verktøy innen objekt deteksjon. Dype nettverk ...

    • Irregularity Detection in Net Pens Exploiting Computer Vision 

      Schellewald, Christian; Stahl, Annette (Peer reviewed; Journal article, 2022)
      Protecting the remaining wild salmon stock in Norway is of utmost importance and requires that farmed salmon cannot escape from aquaculture sites. As holes in net-cages are responsible for a large fraction of the escaped ...

    • Iterative Closest Point with Minimal Free Space Constraints 

      Haugo, Simen; Stahl, Annette (Chapter; Peer reviewed, 2020)
      The Iterative Closest Point (ICP) method is widely used for fitting geometric models to sensor data. By formulating the problem as a minimization of distances evaluated at observed surface points, the method is computationally ...

    • Kamerabasert Posisjoneringssystem for Fly og Helikopter 

      Birkeland, Peder Hogstad (Master thesis, 2019)
      Denne masteroppgaven tar for seg arbeidet med a utvikle og teste et kamerabasert sensorsystem ˚ for posisjonering av fly og helikoptre i samarbeid med Forsvarets Forskningsinstitutt (FFI). Systemet som er utviklet bestar ...

    • LiDAR-Inertial SLAM System for Tunnel Navigation of an Autonomous Road Roller 

      Wroldsen, Sjur Grønnevik (Master thesis, 2021)
      Autonom drift kan redusere menneskelig utsettelse mot farlige miljøer. Det kan også forbedre tids- og kostnadseffektiviteten ved at en menneskelig operator kan operere flere autonome kjøretøyer på en gang uten å være fysisk ...

    • Low Altitude Georeferencing for Imaging Sensors in Maritime Tracking 

      Helgesen, Øystein Kaarstad; Brekke, Edmund Førland; Stahl, Annette; Engelhardtsen, Øystein (Peer reviewed; Journal article, 2020)
      This paper presents a method for georeferencing low-altitude camera sensors, both infrared and electro-optical, in a maritime context. Accurate georeferencing require very high precision for the object pixel coordinates ...

    • Maritime Tracking with Georeferenced Multi-Camera Fusion 

      Helgesen, Øystein Kaarstad; Stahl, Annette; Brekke, Edmund Førland (Peer reviewed; Journal article, 2023)
      Cameras form an essential part of any autonomous surface vehicle’s sensor package, both for COLREGs compliance to detect light signals and for identifying and tracking other vessels. Due to limited fields of view compared ...

    • Minimal Free Space Constraints for Implicit Distance Bounds 

      Haugo, Simen; Stahl, Annette (Chapter; Peer reviewed, 2020)
      A general approach for fitting implicit models to sensor data is to optimize an objective function measuring the quality of the fit. The objective function often involves evaluating the model’s implicit function at several ...

    • Mixed box palletizing; a suggestion to detect and pack unknown sized objects in bins using point clouds and genetic algorithms 

      Vasdal, Edvard Rauø (Master thesis, 2019)
      Palletering av bokser er gjort med roboter i mange år. Det er en enkel oppgave å velge en boks og stable den på en pall. Men hvis boksen har ukjent størrelse og posisjoner, er løsningen til dette problemet ikke triviell. ...

    • Modellforsøk med dukbasert avlusing Beskrivelse av gjennomføringen av modellforsøk i Hirtshals - Foreløpig rapport 

      Volent, Zsolt; Birkevold, Jens; Stahl, Annette (Research report, 2014)
      Det er avgjørende å ha god kontroll på volumet under en avlusing, for å kunne beregne innblanding av lusemidler, slik at en oppnår ønsket behandlingskonsentrasjon. En for høy konsentrasjon kan skade fisken, og for lav ...