direkt zum Inhalt springen

direkt zum Hauptnavigationsmenü

Sie sind hier

TU Berlin

Inhalt des Dokuments

Multimedia Applications

Lupe

The Communication Systems Group of the TU Berlin, led by Prof. Dr. Thomas Sikora, employed their results of multimedia analysis and processing in a couple of innovative multimedia applications and was involved in many national and international funded projects related to multimedia applications. The following list gives an overview of research areas we are involved in:

  • 2D-to-3D conversion of videos (automatic and interactive)
  • Geo-tagging in social networks
  • Genre detection in TV broadcast
  • Security in public transportation systems
  • Information exploitation of forensic data
  • Security at big events using drones
  • Privacy protection in video data
  • etc.

    Research Activities

    DeepStereoBrush: Interactive Depth Map Creation

    Bild

    In this paper, we introduce a novel interactive depth map creation approach for image sequences which uses depth scribbles as input at user-defined keyframes. These scribbled depth values are then propagated within these keyframes and across the entire sequence using a 3-dimensional geodesic distance transform (3D-GDT). In order to further improve the depth estimation of the intermediate frames, we make use of a con-volutional neural network (CNN) in an unconventional manner. Our process is based on online learning which allows us to specifically train a disposable network for each sequence individually using the user generated depth at keyframes along with corresponding RGB images as training pairs. mehr zu: DeepStereoBrush: Interactive Depth Map Creation

    Multimodal Geo-tagging in Social Media Websites using Hierarchical Spatial Segmentation

    Bild
    FG NUE

    These days the sharing of photographs and videos is very popular in social networks. Many of these social media web- sites such as Flickr, Facebook and Youtube allows the user to manually label their uploaded videos with geo-information using a interface for dragging them into the map. However, the manually labelling for a large set of social media is still borring and error-prone. For this reason we present a hierarchical, multi-modal approach for estimating the GPS information. Our approach makes use of external resources like gazetteers to extract toponyms in the metadata and of visual and textual features to identify similar content. mehr zu: Multimodal Geo-tagging in Social Media Websites using Hierarchical Spatial Segmentation

    Related Publications

    2019

    2018

    2015

    2014

    2013

    • Kai Ide, Ivo Keller, Thomas Sikora
      Consensus-Based Multiview Texturing and Depth-Map Completion
      20th IEEE International Conference on Image Processing, Melbourne, Australia, 15.09.2013 - 18.09.2013
      Details BibTeX
    • Frederik Zilly, Christian Riechert, Marcus Müller, Peter Eisert, Thomas Sikora, Peter Kauff
      Real-time generation of multi-view video plus depth content using mixed narrow and wide baseline
      Journal of Visual Communication and Image Representation, Elsevier, vol. Volume 24,, no. Issue 8, 10.07.2013, pp. ???
      ISSN 1047-3203
      Details BibTeX
    • Tobias Senst, Volker Eiselein, Atta Badii, Mathieu Einig, Ivo Keller,Thomas Sikora
      A decentralized Privacy-sensitive Video Surveillance Framework
      IEEE International Conference on Digital Signal Processing (DSP 2013), Greece, Santorini, 01.07.2013 - 03.07.2013
      DOI:10.1109/ICDSP.2013.6622765
      Details BibTeX
    • Carlos Vazquez, Liang Zhang, Filippo Speranza, Nils Plath, and Sebastian Knorr
      2D-to-3D Video Conversion: Overview and Perspectives
      in Emerging Technologies for 3D Video: Creation, Coding, Transmission and Rendering, Frédéric Dufaux, Béatrice Pesquet-Popescu, Marco Cagnazzo (ed(s).), Wiley, 2013
      Details BibTeX
    • Nils Plath, Sebastian Knorr, Lutz Goldmann, Thomas Sikora
      Adaptive Image Warping for Hole Prevention in 3D View Synthesis
      IEEE Transactions on Image Processing, Special Issue on 3D Video Representation, Compression and Rendering, IEEE, to appear, 2013
      Details BibTeX

    2012

    • Kai Ide, Thomas Sikora
      Real-Time Active Multiview 3D Reconstruction
      International Conference on Computer Vision in Remote Sensing, Xiamen University, Xiamen, China, 16.12.2012 - 18.12.2012
      Details BibTeX
    • Sebastian Knorr, Kai Ide, Matthias Kunter, and Thomas Sikora
      THE AVOIDANCE OF VISUAL DISCOMFORT AND BASIC RULES FOR PRODUCING “GOOD 3D” PICTURES
      SMPTE Motion Imaging Journal, Society of Motion Picture & Television Engineers, October 2012, pp. 72-79
      Details BibTeX

    2011

    • Sebastian Knorr
      High-quality 2D to 3D Conversion of Feature Films (invited lecture)
      Industrial Workshop EMC2, The Future of 3D Media, Berlin, Germany, 14.11.2011
      Details BibTeX
    • Sebastian Knorr, Kai Ide, Matthias Kunter, Thomas Sikora
      Basic rules for good 3D and the avoidance of visual discomfort in stereoscopic vision
      International Broadcasting Convention (IBC), Amsterdam, 08.09.2011 - 13.09.2011
      Details BibTeX
    • Tobias Senst, Michael Pätzold, Rubén Heras Evangelio, Volker Eiselein, Ivo Keller, Thomas Sikora
      On Building Decentralized Wide-Area Surveillance Networks based on ONVIF
      Workshop on Multimedia Systems for Surveillance (MMSS) in conjunction with 8th IEEE International Conference on Advanced Video and Signal-Based Surveillance, volume 2011, Klagenfurt, Austria, 30.08.2011 - 02.09.2011, pp. 420--423
      ISBN: 978-1-4577-0844-2 DOI: 10.1109/AVSS.2011.6027365
      Details BibTeX
    • Sebastian Knorr
      2D-to-3D conversion and basic rules for good 3D (invited lecture)
      Media-Tech Showcase & Conference, Hamburg, Germany, 03.05.2011
      Details BibTeX
    • Liang Zhang, Carlos Vázquez, Sebastian Knorr
      3D-TV Content Creation: Automatic 2D-to-3D Video Conversion (invited)
      IEEE Transactions on Broadcasting, Special Issue on 3D-TV, vol. 57, no. 2, 28.03.2011, pp. 372 - 383
      Received the Scott Helt Memorial Award for the best paper published in the IEEE Transactions on Broadcasting in 2011.
      Details BibTeX
    • Sebastian Knorr
      2D-to-3D conversion: market overview, conversion workflow and basic rules for good 3D (invited lecture)
      Media-Tech Showcase & Conference, Macao, China, 15.03.2011
      Details BibTeX

    2010

    • Kai Ide, Thomas Sikora
      Adaptive Parallax For 3D Television
      3DTV Conference 2010, Capture, Transmission and Display of 3D Video, Tampere, Finland, 07.06.2010 - 09.06.2010
      ISBN: 978-1-4244-6378-7
      Details BibTeX
    • Sebastian Knorr
      Überblick über aktuelle Verfahren zur 2D-3D-Filmkonvertierung (lecture)
      24. Fachtagung der FKTG: Film und Fernsehen - zwischen 3D u. 4G, Fernseh- und Kinotechnische Gesellschaft e.V., 19.05.2010
      Details BibTeX

    2009

    2008

    2007

    2006

    2005

    2004

    2002

    2000

    • Sila Ekmekci
      Encoding and Reconstruction of Incomplete 3D Video Objects
      Special Issue of IEEE Transactions on Circuits and Systems for Video Technology, vol. 10, no. 7, October 2000, pp. 1198-1207
      Details BibTeX

    1999

    • Sila Ekmekci, Jens-Rainer Ohm
      "Incomplete 3D Representation" and View Synthesis for Video Objects Captured by Multiple Cameras
      Proceedings Picture Coding Symposium PCS 99, Portland, Oregon, USA, April 1999, pp. 81-86
      Details BibTeX

    Zusatzinformationen / Extras