Sökning: "bilddata"

Visar resultat 21 - 25 av 50 uppsatser innehållade ordet bilddata.

  1. 21. Assisted Annotation of Sequential Image Data With CNN and Pixel Tracking

    Master-uppsats, KTH/Matematik (Avd.)

    Författare :Jenny Chan; [2021]
    Nyckelord :Assistant annotation; Object detection; Object tracking; Sequential data; Assisterande annotering; Objectdetektering; Objektspårning; Sekventiell data;

    Sammanfattning : In this master thesis, different neural networks have investigated annotating objects in video streams with partially annotated data as input. Annotation in this thesis is referring to bounding boxes around the targeted objects. LÄS MER

  3. 22. Data Augmentation for Safe 3D Object Detection for Autonomous Volvo Construction Vehicles

    Master-uppsats, KTH/Skolan för elektroteknik och datavetenskap (EECS)

    Författare :Xun Zhao; [2021]
    Nyckelord :Point Cloud; Data Augmentation; Data Annotation; 3D Object Detection; Generative Adversarial Network; Computer Vision.;

    Sammanfattning : Point cloud data can express the 3D features of objects, and is an important data type in the field of 3D object detection. Since point cloud data is more difficult to collect than image data and the scale of existing datasets is smaller, point cloud data augmentation is introduced to allow more features to be discovered on existing data. LÄS MER

  4. 23. Generate synthetic datasets and scenarios by learning from the real world

    Master-uppsats, KTH/Skolan för elektroteknik och datavetenskap (EECS)

    Författare :Paolo Berizzi; [2021]
    Nyckelord :Synthetic Data; Rendered Images; Computer Vision; Syntetiska data; återgivna bilder; datorsyn;

    Sammanfattning : The modern paradigms of machine learning algorithms and artificial intelligence base their success on processing a large quantity of data. Nevertheless, data does not come for free, and it can sometimes be practically unfeasible to collect enough data to train machine learning models successfully. LÄS MER

  5. 24. En jämförande studie av regulariserade neurala nätverk med tillämpning på bildklassificering

    Kandidat-uppsats, Göteborgs universitet/Institutionen för matematiska vetenskaper

    Författare :Eric Johansson; Björn Krook Willén; Aladdin Persson; Marcus Sajland; [2020-07-02]
    Nyckelord :;

    Sammanfattning : Denna rapport fokuserar på jämförelsen mellan olika regulariseringstekniker av artificiella neurala nätverk applicerade på klassificering av bilddata. Regulariseringsmetoderna som använts är L2-regularisering och dropout, och dessa har jämförts med icke-regulariserande neurala nätverk. LÄS MER

  7. 25. Synthesis of Tabular Financial Data using Generative Adversarial Networks

    Master-uppsats, KTH/Matematisk statistik

    Författare :Anton Karlsson; Torbjörn Sjöberg; [2020]
    Nyckelord :Generative Adversarial Networks; GAN; Generative Modeling; Tabular data; Financial data; Machine Learning; Statistical learning; Applied Mathematics; GANs; Generativa modeller; Tabulär data; Finansdata; Maskininlärning; Statistisk inlärning; Tillämpad Matematik;

    Sammanfattning : Digitalization has led to tons of available customer data and possibilities for data-driven innovation. However, the data needs to be handled carefully to protect the privacy of the customers. Generative Adversarial Networks (GANs) are a promising recent development in generative modeling. LÄS MER