Motion Coherent Tracking Using Multi-label MRF Optimization

  • Authors:

  • David Tsai;Matthew Flagg;Atsushi Nakazawa;James M. Rehg

  • Affiliations:

  • Center for Behavior Imaging and the Computational Perception Laboratory, School of Interactive Computing, Georgia Institute of Technology, Atlanta, USA 30332;Center for Behavior Imaging and the Computational Perception Laboratory, School of Interactive Computing, Georgia Institute of Technology, Atlanta, USA 30332;Cybermedia Center, Osaka University, Toyonaka, Japan 560-0043;Center for Behavior Imaging and the Computational Perception Laboratory, School of Interactive Computing, Georgia Institute of Technology, Atlanta, USA 30332

  • Venue:
  • International Journal of Computer Vision
  • Year:
  • 2012

Quantified Score

Hi-index 0.00

Visualization

Abstract

We present a novel off-line algorithm for target segmentation and tracking in video. In our approach, video data is represented by a multi-label Markov Random Field model, and segmentation is accomplished by finding the minimum energy label assignment. We propose a novel energy formulation which incorporates both segmentation and motion estimation in a single framework. Our energy functions enforce motion coherence both within and across frames. We utilize state-of-the-art methods to efficiently optimize over a large number of discrete labels. In addition, we introduce a new ground-truth dataset, called Georgia Tech Segmentation and Tracking Dataset (GT-SegTrack), for the evaluation of segmentation accuracy in video tracking. We compare our method with several recent on-line tracking algorithms and provide quantitative and qualitative performance comparisons.