Unsupervised video object segmentation by spatiotemporal graphical model

@article{Guo2015UnsupervisedVO,
  title={Unsupervised video object segmentation by spatiotemporal graphical model},
  author={Lijun Guo and Ting-Ting Cheng and Yuanjie Huang and Jieyu Zhao and Rong Zhang},
  journal={Multimedia Tools and Applications},
  year={2015},
  volume={76},
  pages={1037-1053}
}
We propose a novel spatiotemporal graphical model for unsupervised video object segmentation. The core of our model is a layered-CRF (conditional random field) that contains two layers, i.e., pixel layer and supervoxel layer. First, the heat diffusion based segmentation and salient region detection is integrated to obtain the segmentation results of the first frame. The results are used as input seeds to train dual probabilistic models of each object class. In the spatiotemporal layered-CRF… CONTINUE READING