Motion Coherent Tracking Using Multi-label MRF Optimization
- First Online:
- Cite this article as:
- Tsai, D., Flagg, M., Nakazawa, A. et al. Int J Comput Vis (2012) 100: 190. doi:10.1007/s11263-011-0512-5
- 1.5k Downloads
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.
KeywordsVideo object segmentation Visual tracking Markov random field Motion coherence Combinatoric optimization Biotracking
(AVI 10.8 MB)