Sökning: "Christoffer Möckelind"

Hittade 2 uppsatser innehållade orden Christoffer Möckelind.

  1. 1. Improving deep monocular depth predictions using dense narrow field of view depth images

    Master-uppsats, KTH/Robotik, perception och lärande, RPL

    Författare :Christoffer Möckelind; [2018]
    Nyckelord :Deep learning; Monocular; Depth estimation; Narrow field of view; RGB; RGBD; Noicy depth; Dense depth; Narrow depth; Sparse depth;

    Sammanfattning : In this work we study a depth prediction problem where we provide a narrow field of view depth image and a wide field of view RGB image to a deep network tasked with predicting the depth for the entire RGB image. We show that by providing a narrow field of view depth image, we improve results for the area outside the provided depth compared to an earlier approach only utilizing a single RGB image for depth prediction. LÄS MER

  3. 2. The effects of Deep Belief Network pre-training of a Multilayered perceptron under varied labeled data conditions

    Kandidat-uppsats, KTH/Skolan för datavetenskap och kommunikation (CSC)

    Författare :Marcus Larsson; Christoffer Möckelind; [2016]
    Nyckelord :;

    Sammanfattning : Sometimes finding labeled data for machine learning tasks is difficult. This is a problem for purely supervised models like the Multilayered perceptron(MLP). A Discriminative Deep Belief Network(DDBN) is a semi-supervised model that is able to use both labeled and unlabeled data. LÄS MER