Sökning: "point cloud features"

Visar resultat 1 - 5 av 11 avhandlingar innehållade orden point cloud features.

  1. 1. Applications of Diversity and the Self-Attention Mechanism in Neural Networks

    Författare :Axel Berg; Matematik LTH; []
    Nyckelord :NATURVETENSKAP; NATURAL SCIENCES; NATURVETENSKAP; NATURAL SCIENCES; point cloud; self-attention; keyword spotting; deep learning; computer vision; machine learning; label diversity;

    Sammanfattning : This thesis covers three contributions in applications of neural networks. The first is related to diversity and ensemble learning, while the other two cover novel applications of the self-attention mechanism. An important aspect of training a neural network is the choice of objective function. LÄS MER

  3. 2. Holistic Grasping: Affordances, Grasp Semantics, Task Constraints

    Författare :Martin Hjelm; Danica Kragic; Markus Vincze; KTH; []
    Nyckelord :NATURVETENSKAP; NATURAL SCIENCES; robotics; robotic grasping; grasping; cognition; embodied cognition; computer vision; machine learning; artificial intelligence; AI; Gaussian process; Gaussian process latent variable model; GPLVM; 3D vision; point cloud features; robotik; manipulation; datorseende; maskininlärning; artificiell intelligens; kognition; Computer Science; Datalogi;

    Sammanfattning : Most of us perform grasping actions over a thousand times per day without giving it much consideration, be it from driving to drinking coffee. Learning robots the same ease when it comes to grasping has been a goal for the robotics research community for decades. LÄS MER

  4. 3. Ice clouds in satellite observations and climate models

    Författare :Salomon Eliasson; Corinna Hoose; Luleå tekniska universitet; []
    Nyckelord :TEKNIK OCH TEKNOLOGIER; ENGINEERING AND TECHNOLOGY; Rymdteknik; Space Technology;

    Sammanfattning : This thesis concerns the microphysical properties of clouds made up of ice particles, called ice clouds. Ice clouds are strong modulators of the outgoing longwave radiation and incoming shortwave radiation, yet our knowledge on several key ice cloud properties, which govern the magnitude and sign of the net contribution to the Earth’s atmospheric radiation budget, is inadequate. LÄS MER

  5. 4. Applications in Monocular Computer Vision using Geometry and Learning : Map Merging, 3D Reconstruction and Detection of Geometric Primitives

    Författare :David Gillsjö; Matematik LTH; []
    Nyckelord :NATURVETENSKAP; NATURAL SCIENCES; Scene Completion; Deep Learning; Bayesian Neural Network; Room Layout Estimation; Line Segment Detection; Polygon Detection; Graph Neural Network; Map Merging; Structure from Motion; Minimal Solvers; Wireframe Estimation;

    Sammanfattning : As the dream of autonomous vehicles moving around in our world comes closer, the problem of robust localization and mapping is essential to solve. In this inherently structured and geometric problem we also want the agents to learn from experience in a data driven fashion. LÄS MER

  7. 5. Ice clouds in satellite observations and climate models

    Författare :Salomon Eliasson; Tristan L’Ecuyer; Luleå tekniska universitet; []
    Nyckelord :TEKNIK OCH TEKNOLOGIER; ENGINEERING AND TECHNOLOGY; Rymdteknik; Space Technology;

    Sammanfattning : Ice clouds have an important role in climate. They are strong modulators of the outgoing longwave radiation and the incoming shortwave radiation and are an integral part of the hydrological cycle. However, our knowledge about them is inadequate. LÄS MER