VCIP 2003

Visual Communications and Image Processing 2003

Special Session on object-based video: extraction tools, evaluation metrics and applications

Motivation: The representation of video information in terms of its content is at the foundation of many multimedia applications, such as broadcasting, content-based information retrieval, interactive video, remote surveillance and entertainment. In particular, object-based representation consists in decomposing the video content into a collection of meaningful objects. This approach offers a broad range of capabilities in terms of access, manipulation and interaction with the visual content. The basic difference when compared with pixel-based procedures is that instead of processing individual pixels, image objects are used in the representation.
To exploit the benefits of object-based representation, multimedia applications need automatic techniques for extracting such objects from video data, a problem that still remains largely unsolved.

Aim of the special session: The goal of this special session is to bring together researchers who are working on different aspects of object-based video analysis and processing, ranging from object extraction to object-based applications. Areas of interest of the special session include (but are not limited to):

  • Video object segmentation
  • Video object tracking
  • Automatic and semiautomatic video object extraction
  • Semantic aspects in video object extraction
  • Performance evaluation metrics
  • Examples of object-based systems for Video Editing, Visual Surveillance, Augmented Reality, Video Coding, Universal Multimedia Access, Video Databases, Ambient Intelligence



  • "Object-based video: extraction tools, evaluation metrics and applications."
    A. Cavallaro and T. Ebrahimi,
    Signal Processing Institute, Swiss Federal Institute of Technology (EPFL)


  • "Real-time Video Object Segmentation using a depth camera."
    Eyal Ofek and Giora Yahav,
    3DV Systems Ltd., Yokneam, Israel, 20692

  • "Automatic Video Object Segmentation for MPEG-4."
    Wei Wei and King Ngi Ngan,
    School of Computer Engineering, Nanyang Technological University, Singapore


  • "A multi-metric evaluation protocol for video object extraction algorithms."
    Na Li (1) , Shipeng Li (2) , Wenyin Liu (3) , Chun Chen (1),
    (1) College of Computer Science, Zhejiang University, Hangzhou, China, (2) Microsoft Research Asia, Beijing, China, (3) Dept. of Computer Science, City University of Hong Kong, China

  • "Performance Measures for Video Object Segmentation and Tracking."
    Cigdem Eroglu Erdem (1), Bulent Sankur (1), A. Murat Tekalp (2),
    (1) Department of Electrical and Electronics Engineering, Bogazici University, Istanbul 80815, Turkey, (2) Department of Electrical and Computer Engineering, University of Rochester, Rochester, NY 14627, USA, and College of Engineering, Koc University, Rumelifeneri Yolu, Sariyer, Istanbul, Turkey


  • "Real-Time Segmentation of Video Objects for Mixed-Reality Interactive Applications."
    Xavier Marichal (1) and Toshiyuki Umeda (2)
    (1)Alterface S.A., Louvain la Neuve, Belgium, (2) Laboratoire de Telecommunications et Teledetection, Louvain-la-Neuve, Belgium

  • "Human detection and tracking for video surveillance applications in a low-density environment."
    Lionel Carminati (1), Jenny Benois-Pineau (1) and Marc Gelgon (2),
    (1) LaBRI, France, (2)IRIN/ATLAS INRIA research group, France

    Special session chair:
    Andrea Cavallaro
    Signal Processing Institute, Swiss Federal Institute of Technology (EPFL)

    Program Committee:
    Andrew Senior, IBM T.J. Watson Research Center
    Changick Kim, Epson Palo Alto Labs
    Fatih Porikli, Mitsubishi Electric Research Laboratories
    Touradj Ebrahimi, Swiss Federal Institute of Technology

    Special Session web site:

    Visual Communications and Image Processing 2003 web site: