Sökning: "CNN"

Visar resultat 1 - 5 av 380 uppsatser innehållade ordet CNN.

  1. 1. 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

  2. 2. Deep Learning for Iceberg Detection in Satellite Images

    Master-uppsats, Uppsala universitet/Institutionen för informationsteknologi

    Författare :Shuzhi Dong; [2021]
    Nyckelord :;

    Sammanfattning : The application of satellite images for ship and iceberg monitoring is essential in many ways in Arctic waters. Even though the detection of ships and icebergs in images is well established using Geoscience techniques, the discrimination between those two target classes still represents a challenge for operational scenarios. LÄS MER

  3. 3. Classification of EEG Data Using Convolutional Neural Networks and the Scaled Reassigned Spectrogram

    Kandidat-uppsats, Lunds universitet/Matematisk statistik

    Författare :Karin Pagels; [2021]
    Nyckelord :Mathematics and Statistics;

    Sammanfattning : Electroencephalography (EEG) is a medical technique for measuring brain activity through several channels connected to the scalp. Interpreting EEG data is a difficult problem because of the large amount of noise contained in the data. LÄS MER

  4. 4. Evaluation of 3D motion capture data from a deep neural network combined with a biomechanical model

    Master-uppsats, Linköpings universitet/Institutionen för medicinsk teknik; Linköpings universitet/Institutionen för medicinsk teknik

    Författare :Anna Rydén; Amanda Martinsson; [2021]
    Nyckelord :Human pose estimation; motion capture; deep neural network; CNN; MargiPose; biomechanical modelling; AnyBody modelling system;

    Sammanfattning : Motion capture has in recent years grown in interest in many fields from both game industry to sport analysis. The need of reflective markers and expensive multi-camera systems limits the business since they are costly and time-consuming. LÄS MER

  5. 5. Evaluation of In-Silico Labeling for Live Cell Imaging

    Uppsats för yrkesexamina på avancerad nivå, Umeå universitet/Institutionen för fysik

    Författare :Elsa Sörman Paulsson; [2021]
    Nyckelord :Deep learning; Machine Learning; Image analysis; CNN; cell; live cell imaging; supervised learning; AI; artificial intelligence; sartorius;

    Sammanfattning : Today new drugs are tested on cell cultures in wells to minimize time, cost, andanimal testing. The cells are studied using microscopy in different ways and fluorescentprobes are used to study finer details than the light microscopy can observe.This is an invasive method, so instead of molecular analysis, imaging can be used. LÄS MER