Joint Tracking and Segmentation of Objects Using Graph Cuts

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.

• Type: Conference
• Year: 2007
• Where: ACIVS
• Authors: Aurélie Bugeau, Patrick Pérez
• Keywords: ACIVS 2007, Algorithms, Computer Vision, Energy Function, Observations