Discriminative Scale Space Tracker (DSST)

Robust scale estimation is a challenging problem in visual object tracking. Most existing methods fail to handle large scale variations in complex image sequences. This paper presents a novel approach for robust scale estimation in a tracking-by-detection framework. The proposed approach works by learning discriminative correlation filters based on a scale pyramid representation. We learn separate filters for translation and scale estimation, and show that this improves the performance compared to an exhaustive scale search. Our scale estimation approach is generic as it can be incorporated into any tracking method with no inherent scale estimation.

The proposed Discriminative Scale Space Tracker (DSST) is the winner of the Visual Object Tracking (VOT) Challenge 2014, with 38 participating tracking methods.

Publications

Martin Danelljan, Gustav Häger, Fahad Khan, Michael Felsberg.
Discriminative Scale Space Tracking.
Transactions on Pattern Analysis and Machine Intelligence (TPAMI), 2017.

Martin Danelljan, Gustav Häger, Fahad Khan, Michael Felsberg.
Accurate Scale Estimation for Robust Visual Tracking.
In Proceedings of the British Machine Vision Conference (BMVC), 2014.

Extended abstract
Supplementary material
Poster

Code

Original Matlab code for the DSST [BMVC'14] and the fDSST [PAMI'17].
The fDSST scale filter is also integrated in our most recent ECO tracking framework (GitHub).

Raw Results

Raw result files for the OTB, Temple-Color and ALOV300++ datasets.

Video

Last updated: 2017-06-27