Interactive tools for constructing and browsing structures for movie films

ABSTRACT

This paper presents a prototype for constructing, browsing and using structures for movie films based on content image analysis only. The goal of the structuring is to facilitate the user's access to the video content (non-linear navigation, etc.). Our prototype provides for the “editor user” advanced tools for structuring the video at its low-level (e.g. shots, key-frames) and high-level structures (e.g. groups of objects, scenes). Also, it provides for the “end user” flexible interfaces for browsing and using constructed video structures. Against the previous version of this prototype [1], we mainly improved the matching and the clustering of segmented objects. Also, constructing and browsing the high-level scene structure are now available.

REFERENCES

• 1: S. Benayoun, H. Bernard, P. Bertolino, M. Gelgon, C. Schmid, and F. Spindler. Structuration de videos pour des interfaces de consultation avancdes. In CORESA 98 - Journees d'etudes et d'echanges COmpression et REpresentation des Signaux Audiovisuels., June 1998.
• 2: Marc Gelgon , Patrick Bouthemy, A region-level graph labeling approach to motion-based segmentation, Proceedings of the 1997 Conference on Computer Vision and Pattern Recognition (CVPR '97), p.514, June 17-19, 1997
• 3: R. Hammoud, L. Chen, and F. Fontaine. An extensible spatial-temporal model for semantic video segmentation. In First Int. Forum on Multimedia and Image Processing, Anchorage, Alaska, 1998.
• 4: R. Hammoud and D. G. Kouam. A mixed classification approach of shots for constructing scene structure for movie films. In Irish Machine Vision and Image Precessing Conference, The Queen's University of Belfast, Northern Ireland, 31 August-2 Septembre 2000.
• 5: R. Hammoud and R. Mohr. Building and browsing hyper-videos: a content variation modeling solution. Pattern Analysis and Applications, 2000. Special Issue on Image Indexation, Submitted. In Irish Machine Vision and Image Precessing Conference, Belfast, Northern Ireland, 31 August-2 Septembre 2000.
• 6: It. Hammoud and 1%. Mohr. Mixture densities for video objects recognition. In International Conference on Pattern Recognition, Barcelona, Spain, 3-8 September 2000. Technical report, INRIA, March 2000. http://www.inria.fr/RRRT/RR-3905.html.

INDEX TERMS

Primary Classification:
  H. Information Systems
  H.5 INFORMATION INTERFACES AND PRESENTATION (I.7)
      H.5.1 Multimedia Information Systems
          Subjects: Video (e.g., tape, disk, DVI)

Additional Classification:
  H. Information Systems
  H.5 INFORMATION INTERFACES AND PRESENTATION (I.7)
      H.5.2 User Interfaces (D.2.2, H.1.2, I.3.6)
          Subjects: Interaction styles (e.g., commands, menus, forms, direct manipulation)

  I. Computing Methodologies
  I.3 COMPUTER GRAPHICS
      I.3.6 Methodology and Techniques
          Subjects: Interaction techniques

General Terms:
Design, Human Factors, Management, Performance, Theory

Keywords:
groups/scenes, interactive videos, video structuring