Logo des Repositoriums

Auflistung nach Autor:in "Eberts, Markus"

1 - 2 von 2
  • Textdokument
    Deep Convolutional Neural Networks for Pose Estimation in Image-Graphics Search
    (INFORMATIK 2017, 2017) Eberts, Markus; Ulges, Adrian
    Deep Convolutional Neural Networks (CNNs) have recently been highly successful in various image understanding tasks, ranging from object category recognition over image classification to scene segmentation. We employ CNNs for pose estimation in a cross-modal retrieval system, which -given a photo of an object -allows users to retrieve the best match from a repository of 3D models. As our system is supposed to display retrieved 3D models from the same perspective as the query image (potentially with virtual objects blended over), the pose of the object relative to the camera needs to be estimated. To do so, we study two CNN models. The first is based on end-to-end learning, i.e. a regression neural network directly estimates the pose. The second uses transfer learning with a very deep CNN pre-trained on a large-scale image collection. In quantitative experiments on a set of 3D models and real-world photos of chairs, we compare both models and show that while the end-to-end learning approach performs well on the domain it was trained on (graphics) it suffers from the capability to generalize to a new domain (photos). The transfer learning approach on the other hand handles this domain drift much better, resulting in an average angle deviation from the ground truth angle of about 14 degrees on photos.
  • Konferenzbeitrag
    Interaktive Lehrvideos mit AMIGO
    (DeLFI 2018 - Die 16. E-Learning Fachtagung Informatik, 2018) Eberts, Markus; Ulges, Adrian
    Die an der Hochschule RheinMain entwickelte Video-Lernplattform AMIGO bietet Lernenden reichhaltige Interaktionsmöglichkeiten mit Videos: So kann z. B. sekundengenau nach Schlagworten gesucht und zwischen den Folien eines Vortrags geblättert werden. Die hierfür erforderliche Indexierung erfolgt vollautomatisch durch eine visuelle Verknüpfung von Video und Lehrmaterial mittels eines Bildmatching-Verfahrens. Die Plattform verzeichnet aktuell ca. 1070 Nutzer und 293 Stunden Videomaterial zu 30 Veranstaltungen. Studentisches Feedback sowie ein automatisches Benutzer-Tracking weisen insbesondere das Blättern zwischen Folien als besonders hilfreich aus.