BROWSE
Detail
Conference Paper
Dynamic Markov Random Field Model for Visual Tracking
Cited 1 time in 
Share 
Share
- Authors
- Daehwan Kim, Ki-Hong Kim, Gil-Haeng Lee, Daijin Kim
- Issue Date
- 2012-10
- Citation
- European Conference on Computer Vision (ECCV) 2012 (LNCS 7585), v.7585, pp.203-212
- Publisher
- Springer
- Language
- English
- Type
- Conference Paper
- Abstract
- We propose a new dynamic Markov random field (DMRF) model to track a heavily occluded object. The DMRF model is a bidirectional graph which consists of three random variables: hidden, observation, and validity. It temporally prunes invalid nodes and links edges among valid nodes by verifying validities of all nodes. In order to apply the proposed DMRF model to the object tracking framework, we use an image block lattice model exactly correspond to nodes and edges in the DMRF model and utilize the mean-shift belief propagation (MSBP). The proposed object tracking method using the DMRF surprisingly tracks a heavily occluded object even if the occluded region is more than 70~80%. Experimental results show that the proposed tracking method gives good tracking performance even on various tracking image sequences(ex. human and face) with heavy occlusion. © 2012 Springer-Verlag.
- KSP Keywords
- Belief Propagation, Heavy occlusion, Image sequences, Markov random field model, Mean-shift(MS), Object Tracking, Occluded object, Random variables, Tracking Performance, Tracking method, Visual tracking