Joint Tracking and Segmentation of Objects using Graph Cuts.

Aurélie Bugeau (1) , Patrick Pérez (1)

1 VISTA - Vision spatio-temporelle et active

This paper presents a new method to both track and segment objects in videos. It includes predictions and observations inside an energy function that is minimized with graph cuts. The min-cut/max-flow algorithm provides a segmentation as the global minimum of the energy function, at a modest computational cost. Simultaneously, our algorithm associates the tracked objects to the observations during the tracking. It thus combines “detect-before-track” tracking algorithms and segmentation methods based on color/motion distributions and/or temporal consistency. Results on real sequences are presented in which the robustness to partial occlusions and to missing observations is shown.

Domaines: Vision par ordinateur et reconnaissance de formes [cs.CV]

Aurélie Bugeau, Patrick Pérez. Joint Tracking and Segmentation of Objects using Graph Cuts.. ACIVS'07 Proceedings of the 9th international conference on Advanced concepts for intelligent vision systems, 2007, Netherlands. ⟨hal-00551593⟩