Python implementation of DSST tracking algorithm based on KCF tracker.
In [Baseline 3], the DSST scale estimation algorithm is added to the original KCF Tracker. Based on the python implementation of KCF Tracker, see [Baseline 2], the code of DSST is translated from C++ and added to the KCF in python.
Some implementations of KCF and DSST algorithms.
C++ KCF Tracker: Original C++ implementation of Kernelized Correlation Filter (KCF) [1, 2].
KCF tracker in Python: Python implementation of KCF Tracker.
KCF-DSST: C++ implementation of Discriminative Scale Space Tracker (DSST) [3].
[1] J. F. Henriques, R. Caseiro, P. Martins, J. Batista, "High-Speed Tracking with Kernelized Correlation Filters", TPAMI 2015.
[2] J. F. Henriques, R. Caseiro, P. Martins, J. Batista, "Exploiting the Circulant Structure of Tracking-by-detection with Kernels", ECCV 2012.
[3] M. Danelljan, G. Häger, F. Shahbaz Khan, and M. Felsberg. "Accurate scale estimation for robust visual tracking". In Proceedings of the British Machine Vision Conference (BMVC), 2014.