Multi-template Scale-Adaptive Kernelized Correlation Filters

Adel Bibi, Bernard Ghanem

Research output: Chapter in Book/Report/Conference proceedingConference contribution

32 Scopus citations


This paper identifies the major drawbacks of a very computationally efficient and state-of-the-art-tracker known as the Kernelized Correlation Filter (KCF) tracker. These drawbacks include an assumed fixed scale of the target in every frame, as well as, a heuristic update strategy of the filter taps to incorporate historical tracking information (i.e. simple linear combination of taps from the previous frame). In our approach, we update the scale of the tracker by maximizing over the posterior distribution of a grid of scales. As for the filter update, we prove and show that it is possible to use all previous training examples to update the filter taps very efficiently using fixed-point optimization. We validate the efficacy of our approach on two tracking datasets, VOT2014 and VOT2015.
Original languageEnglish (US)
Title of host publication2015 IEEE International Conference on Computer Vision Workshop (ICCVW)
PublisherInstitute of Electrical and Electronics Engineers (IEEE)
Number of pages8
ISBN (Print)9781467397117
StatePublished - Feb 16 2016

Bibliographical note

KAUST Repository Item: Exported on 2020-10-01


Dive into the research topics of 'Multi-template Scale-Adaptive Kernelized Correlation Filters'. Together they form a unique fingerprint.

Cite this