Sökning: "object learning"

Visar resultat 1 - 5 av 323 uppsatser innehållade orden object learning.

  1. 1. Interactionwise Semantic Awareness in Visual Relationship Detection

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

    Författare :Pagliarini Giovanni; Imtiaz Azfar; [2020-11-06]
    Nyckelord :Deep Learning; Natural Language Processing; Computer Vision; Visual Relationship Detection; Object Detection;

    Sammanfattning : Visual Relationship Detection (VRD) is a relatively young research area, where thegoal is to develop prediction models for detecting the relationships between objectsdepicted in an image. A relationship is modeled as a subject-predicate-object triplet,where the predicate (e.g an action, a spatial relation, etc. LÄS MER

  2. 2. Geo-temporal Online Analysis of Traffic Rule Violations

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

    Författare :Adam Davidsson; Dyako Fatih; Simon Larsson; Jesper Naarttijärvi; Daniel Nilsson; Marcus Svensson; [2020-10-30]
    Nyckelord :Traffic rule violations; Risk estimation; Privacy preservation; Computer vision; Deep learning neural net;

    Sammanfattning : Due to inattention and not complying with traffic regulations, human error accounts forroughly 94% of all traffic accidents. To counter this, the need to develop systems that canidentify traffic rule violations and calculate the risk of collisions. The information reportedcan then be used to implement preventive measures. LÄS MER

  3. 3. Augmented Reality in the Museum: Creating and Evaluating an AR Mobile Application in an Exhibition

    Master-uppsats, Göteborgs universitet/Institutionen för litteratur, idéhistoria och religion

    Författare :Frida Berntson; [2020-09-08]
    Nyckelord :museum; augmented reality; utställning; besökarupplevelse; applikation; digital humaniora; 3d;

    Sammanfattning : The purpose of this thesis is to map the process of making an AR application using 3D models for a museum, and study visitors’ experience of the application and investigate if the application generates a more meaningful experience compared to not using the application. The mix of digital production and empirical study of the created technology is a new way of investigating digital cultural heritage. LÄS MER

  4. 4. Kille: Learning Objects and Spatial Relations with Kinect

    Master-uppsats, Göteborgs universitet / Institutionen för filosofi, lingvistik och vetenskapsteori

    Författare :Erik de Graaf; [2020-08-26]
    Nyckelord :grounding; spatial relations; object learning;

    Sammanfattning : In order for humans to have meaningful interactions with a robotic system, this system should be capable of grounding semantic representations to their real-world representations, learn spatial relationships andcommunicate using spoken human language. End users need to be able to query the system what objects it already has knowledge of, for more efficient learning. LÄS MER

  5. 5. Detecting Offside Position using 3D Reconstruction

    Master-uppsats, Lunds universitet/Matematik LTH

    Författare :Axel Delbom; [2020]
    Nyckelord :Deep learning; football; offside detection; Mathematics and Statistics;

    Sammanfattning : With the increased number of technical innovations in soccer and the progress in the field of AI, this thesis investigates the possibilities to detect if a player is in offside position using deep learning and video recordings from soccer games. A method to create a 3D reconstruction of the players in the scene is proposed and evaluated. LÄS MER