Video Object Segmentation Using Graphs

  • Authors:
  • Salvador B. Mármol;Nicole M. Artner;Adrian Ion;Walter G. Kropatsch;Csaba Beleznai

  • Affiliations:
  • PRIP, Vienna University of Technology, Austria and Andalusian Research Group FQM-296: "Computational Topology and Applied Mathematics", Spain;Austrian Research Centers GmbH - ARC, Smart Systems Division, Vienna, Austria;PRIP, Vienna University of Technology, Austria;PRIP, Vienna University of Technology, Austria;Austrian Research Centers GmbH - ARC, Smart Systems Division, Vienna, Austria

  • Venue:
  • CIARP '08 Proceedings of the 13th Iberoamerican congress on Pattern Recognition: Progress in Pattern Recognition, Image Analysis and Applications
  • Year:
  • 2008

Quantified Score

Hi-index 0.00

Visualization

Abstract

This paper presents an approach for video object segmentation. The main idea of our approach is to generate a planar, triangulated, and labeled graph that describes the scene, foreground objects and background. With the help of the Kanade-Lucas-Tomasi Tracker, corner points are tracked within a video sequence. Then the movement of the points adaptively generates a planar triangulation. The triangles are labeled as rigid, articulated, and separatingdepending on the variation of the length of their edges.