ComputingComputer ScienceComputer VisionMachine VisionRobot VisionMarkov Chain Monte CarloMotion EstimationParticle FilteringTracking SystemsVisual TrackingMarkov Chain Monte Carlo InferenceMotion ModelsReal-time TrackingSamplingTarget Tracking
We propose a novel tracking framework called visual tracker sampler that tracks a target robustly by searching for the appropriate trackers in each frame. Since the real-world tracking environment varies severely over time, the trackers should be adapted or newly constructed depending on the current situation. To do this, our method obtains several samples of not only the states of the target but also the trackers themselves during the sampling process. The trackers are efficiently sampled using the Markov Chain Monte Carlo method from the predefined tracker space by proposing new appearance models, motion models, state representation types, and observation types, which are the basic important components of visual trackers. Then, the sampled trackers run in parallel and interact with each other while covering various target variations efficiently. The experiment demonstrates that our method tracks targets accurately and robustly in the real-world tracking environments and outperforms the state-of-the-art tracking methods.
22
Incremental Learning for Robust Visual Tracking
David A. Ross, Jongwoo Lim, Ruei-Sung Lin et al. · International Journal of Computer Vision · 2007 · 3.1K citations
Real-time tracking of non-rigid objects using mean shift
Dorin Comaniciu, Visvanathan Ramesh, Peter Meer · 2002 · 2.9K citations
Robust Fragments-based Tracking using the Integral Histogram
A. Adam, Ehud Rivlin, Ilan Shimshoni · 2006 · 1.4K citations