Tracking by Sampling Trackers .pdf

Tracking by Sampling Trackers .pdf - Tracking by Sampling...

Info icon This preview shows pages 1–2. Sign up to view the full content.

Tracking by Sampling Trackers Junseok Kwon and Kyoung Mu Lee Department of EECS, ASRI, Seoul National University, 151-742, Seoul, Korea uni007B paradis0, kyoungmu uni007D , Abstract 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 sev- eral samples of not only the states of the target but also the trackers themselves during the sampling process. The track- ers are efficiently sampled using the Markov Chain Monte Carlo method from the predefined tracker space by propos- ing new appearance models, motion models, state repre- sentation types, and observation types, which are the basic important components of visual trackers. Then, the sam- pled trackers run in parallel and interact with each other while covering various target variations efficiently. The ex- periment demonstrates that our method tracks targets accu- rately and robustly in the real-world tracking environments and outperforms the state-of-the-art tracking methods. 1. Introduction It is a challenging problem to track a target in the real- world tracking environment where different types of vari- ations such as illumination, shape, occlusion, or motion changes occur at the same time [ 23 ]. Recently, sev- eral tracking methods solved the problem and successfully tracked targets in the real-world environment [ 2 , 6 , 8 , 10 , 11 , 12 , 14 , 17 , 18 , 21 ]. Among them, one of promising methods is the visual tracking decomposition (VTD), which utilizes a set of multiple trackers and runs them simulta- neously and interactively [ 11 ]. The method assumes that, given a fixed number of trackers, at least one tracker can deal with target variations at each time. However, this as- sumption is insufficient to cope with the complicated real- world tracking environment. Since generally the tracking environment severely varies from frame to frame, trackers should not be fixed but should be generated dynamically depending on the current tracking environment. This paper focuses on how to construct appropriate trackers automati- T r a c k e r s p a c e A p p e a r a n c e m o d e l M o t i o n m o d e l S t a t e r e p r e s e n t a t i o n O b s e r v a t i o n (a) Tracker space (b) Tracking results Figure 1. Visual tracker sampler (a) The figure describes our four-dimensional tracker space, in which the axes are the appear- ance model, motion model, state representation type, and obser- vation type. A tracker is determined by sampling a point in the tracker space, where each circle represents a different tracker. (b) Our visual tracker sampler tracks the target robustly in the chal- lenging matrix sequence by choosing appropriate trackers adap- tively during the tracking process.
Image of page 1

Info icon This preview has intentionally blurred sections. Sign up to view the full version.

Image of page 2
This is the end of the preview. Sign up to access the rest of the document.

{[ snackBarMessage ]}

What students are saying

  • Left Quote Icon

    As a current student on this bumpy collegiate pathway, I stumbled upon Course Hero, where I can find study resources for nearly all my courses, get online help from tutors 24/7, and even share my old projects, papers, and lecture notes with other students.

    Student Picture

    Kiran Temple University Fox School of Business ‘17, Course Hero Intern

  • Left Quote Icon

    I cannot even describe how much Course Hero helped me this summer. It’s truly become something I can always rely on and help me. In the end, I was not only able to survive summer classes, but I was able to thrive thanks to Course Hero.

    Student Picture

    Dana University of Pennsylvania ‘17, Course Hero Intern

  • Left Quote Icon

    The ability to access any university’s resources through Course Hero proved invaluable in my case. I was behind on Tulane coursework and actually used UCLA’s materials to help me move forward and get everything together on time.

    Student Picture

    Jill Tulane University ‘16, Course Hero Intern