Sökning: "object detection"

Visar resultat 1 - 5 av 406 uppsatser innehållade orden object detection.

  1. 1. Fault detection power of unit and system testing in Java open source projects

    Master-uppsats, Göteborgs universitet/Institutionen för data- och informationsteknik

    Författare :ANDREEA SULUGIU; [2021-07-06]
    Nyckelord :Software testing; unit test; system test; test categorization; bugs; project; thesis; fault detection;

    Sammanfattning : Testing is one of the most crucial steps in providing quality for software products.Two key and heavily used testing levels are unit and system testing, each level hav ing different benefits and drawbacks. For their testing process a software team needsto decide where the focus and effort should be put, often by creating a strategy fortesting. LÄS MER

  2. 2. Ocean Exploration with Artificial Intelligence

    Master-uppsats, Göteborgs universitet/Institutionen för data- och informationsteknik

    Författare :Sarah Al-Khateeb; Lisa Bodlak; [2021-07-06]
    Nyckelord :computer science; deep learning; generative adversarial networks; data augmentation; object detection; underwater image; computer vision;

    Sammanfattning : Large and diverse data is crucial to train object detection systems properly andachieve satisfactory prediction performance. However, in some areas, such as ma rine science, gathering sufficient data is challenging and sometimes even infeasible.Working with limited data can result in overfitting and poor performance. LÄS MER

  3. 3. RISK ESTIMATION FOR PERCEPTION FAILURES IN AUTOMATED DRIVING

    Master-uppsats, Göteborgs universitet/Institutionen för matematiska vetenskaper

    Författare :Love Nilsson; [2021-06-15]
    Nyckelord :;

    Sammanfattning : The failure of sensors to perceive the environment correctly is one of the primarysources of risk that needs to be quantified in the development of active safetyfeatures for autonomous vehicles. By extracting training data from the CARLAsimulator, an object detector was trained to simulate a perception system ofan autonomous vehicle. LÄS MER

  4. 4. Application of Machine Learning Algorithms for Post Processing of Reference Sensors

    Master-uppsats, Göteborgs universitet/Institutionen för data- och informationsteknik

    Författare :VASILIKI LAMPROUSI; [2021-04-01]
    Nyckelord :Object detection; machine learning; camera; sensors; semi-supervised learning;

    Sammanfattning : The Autonomous Drive (AD) systems and Advanced Driver Assistance Systems(ADAS) in the current and future generations of vehicles include a large numberof sensors which are used to perceive the vehicle’s surroundings. The productionsensors of these vehicles are verified and validated against reference data that areoriginated from high-accurate reference sensors that are placed in a reference roofbox at the top of the vehicle. LÄS MER

  5. 5. Svarstid vid konfrontationsbenämning för personer med multipel skleros och självupplevd anomi jämfört med en referensgrupp

    Magister-uppsats, Göteborgs universitet/Institutionen för neurovetenskap och fysiologi

    Författare :Benedetta Dei Campielisi; [2021-02-12]
    Nyckelord :OANB; multipel skleros; svarstid; benämningssvårighet; ordklass; OANB; multiple sclerosis; response time; naming difficulties; word class;

    Sammanfattning : In this study, differences in response time and number of correct responses in oral confrontation naming with the test An Object and Action Naming Battery were examined between 25 persons with multiple sclerosis who experienced anomia and 25 neurologically intact participants. The results showed significantly shorter response time and significantly more correct responses in the reference group. LÄS MER