High-Speed Tracking with Kernelized Correlation Filters
Top Cited Papers
- 1 August 2014
- journal article
- research article
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Transactions on Pattern Analysis and Machine Intelligence
- Vol. 37 (3), 583-596
- https://doi.org/10.1109/tpami.2014.2345390
Abstract
The core component of most modern trackers is a discriminative classifier, tasked with distinguishing between the target and the surrounding environment. To cope with natural image changes, this classifier is typically trained with translated and scaled sample patches. Such sets of samples are riddled with redundancies—any overlapping pixels are constrained to be the same. Based on this simple observation, we propose an analytic model for datasets of thousands of translated patches. By showing that the resulting data matrix is circulant, we can diagonalize it with the discrete Fourier transform, reducing both storage and computation by several orders of magnitude. Interestingly, for linear regression our formulation is equivalent to a correlation filter, used by some of the fastest competitive trackers. For kernel regression, however, we derive a new kernelized correlation filter (KCF), that unlike other kernel algorithms has the exact same complexity as its linear counterpart. Building on it, we also propose a fast multi-channel extension of linear correlation filters, via a linear kernel, which we call dual correlation filter (DCF). Both KCF and DCF outperform top-ranking trackers such as Struck or TLD on a 50 videos benchmark, despite running at hundreds of frames-per-second, and being implemented in a few lines of code (Algorithm 1). To encourage further developments, our tracking framework was made open-source.Keywords
Other Versions
Funding Information
- FCT (PTDC/EEA-CRO/122812/2010, SFRH/BD75459/2010, SFRH/BD74152/2010, SFRH/BPD/90200/2012)
This publication has 25 references indexed in Scilit:
- Multi-channel Correlation FiltersPublished by Institute of Electrical and Electronics Engineers (IEEE) ,2013
- Beyond Hard Negative Mining: Efficient Detector Learning via Block-Circulant DecompositionPublished by Institute of Electrical and Electronics Engineers (IEEE) ,2013
- Event Retrieval in Large Video Collections with Circulant Temporal EncodingPublished by Institute of Electrical and Electronics Engineers (IEEE) ,2013
- Correlation Filters for Object AlignmentPublished by Institute of Electrical and Electronics Engineers (IEEE) ,2013
- Online Object Tracking: A BenchmarkPublished by Institute of Electrical and Electronics Engineers (IEEE) ,2013
- Distribution fields for trackingPublished by Institute of Electrical and Electronics Engineers (IEEE) ,2012
- Efficient Additive Kernels via Explicit Feature MapsIEEE Transactions on Pattern Analysis and Machine Intelligence, 2012
- Average of Synthetic Exact FiltersPublished by Institute of Electrical and Electronics Engineers (IEEE) ,2009
- Beyond sliding windows: Object localization by efficient subwindow searchPublished by Institute of Electrical and Electronics Engineers (IEEE) ,2008
- Support vector trackingIEEE Transactions on Pattern Analysis and Machine Intelligence, 2004