Tracking Deformable Parts via Dynamic Conditional Random Fields
This addresses robust object tracking in videos for applications like surveillance, but it appears incremental as it builds on existing conditional random field frameworks.
The paper tackled tracking objects with severe appearance changes like deformation and occlusion by proposing a dynamic graph model that integrates object detection priors and an occlusion handling mechanism. The method outperformed state-of-the-art trackers on challenging video sequences.
Despite the success of many advanced tracking methods in this area, tracking targets with drastic variation of appearance such as deformation, view change and partial occlusion in video sequences is still a challenge in practical applications. In this letter, we take these serious tracking problems into account simultaneously, proposing a dynamic graph based model to track object and its deformable parts at multiple resolutions. The method introduces well learned structural object detection models into object tracking applications as prior knowledge to deal with deformation and view change. Meanwhile, it explicitly formulates partial occlusion by integrating spatial potentials and temporal potentials with an unparameterized occlusion handling mechanism in the dynamic conditional random field framework. Empirical results demonstrate that the method outperforms state-of-the-art trackers on different challenging video sequences.