High-Speed Tracking with Kernelized Correlation Filters
Open accessThe DOI matches its Crossref record; 39 of the 43 references it cites were found in a registry or an index.
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.
Overview
The claims and statistics of this paper haven’t been checked yet.
Free: it reads the open-access text and checks the first 5 claims that cite a source we can check. Create a free account to check every claim.
Integrity signals
Registry
Cites
Statistics
Verification
Claims the paper makes
The claims and statistics of this paper haven’t been checked yet.
Free: it reads the open-access text and checks the first 5 claims that cite a source we can check. Create a free account to check every claim.
Claims other papers make about this one
Each is checked against this paper’s own text: does it say what the citing paper says it does?
The source backs part of the claim, not all of it — or backs it for a different population, condition or comparison.
In the citing paper
“This method also gained the research community's attention because of its exceptional performance in terms of accuracy and computational cost.”
From Multiple Cues-Based Robust Visual Object Tracking Method (2022) · cites this paper as [17]
Experimental — accuracy not yet measuredThe cited source says what the claim attributes to it.
In the citing paper
“Kernelized correlation filter(KCF) based tracking schemes have shown good performance in recent years.”
From Multiple Cues-Based Robust Visual Object Tracking Method (2022) · cites this paper as [17]
The cited source says what the claim attributes to it.
In the citing paper
“Interestingly, a single image is quiet enough to provide dense sampling to train the model in this method.”
From Multiple Cues-Based Robust Visual Object Tracking Method (2022) · cites this paper as [17]
The cited source says what the claim attributes to it.
In the citing paper
“In this method, all the input image/patch circularly shifted versions are used as training data.”
From Multiple Cues-Based Robust Visual Object Tracking Method (2022) · cites this paper as [17]
The cited source says what the claim attributes to it.
In the citing paper
“Using the kernel trick over this data significantly decreases the computational cost.”
From Multiple Cues-Based Robust Visual Object Tracking Method (2022) · cites this paper as [17]
1 more claim about this paper
Create a free account to see every claim other papers make about this one.
Self-check
Percentages, sums and reported differences re-computed from the paper’s own numbers.
The self-check needs the paper’s full text.
Citations
Cites
Learning with Kernels: Support Vector Machines, Regularization, Optimization, and Beyond
Schölkopf, B., & Smola, A. J. (2001) · The MIT Press eBooks · doi:10.7551/mitpress/4175.001.0001 · Cited by 11,703
Object Detection with Discriminatively Trained Part-Based Models
Felzenszwalb, P. F., Girshick, R. B., McAllester, D., & Ramanan, D. (2010) · IEEE Transactions on Pattern Analysis and Machine Intelligence · doi:10.1109/tpami.2009.167 · Cited by 9,853
Learning With Kernels: Support Vector Machines, Regularization, Optimization, and Beyond
Williams, C. K. I. (2003) · Journal of the American Statistical Association · doi:10.1198/jasa.2003.s269 · Cited by 4,281
Online Object Tracking: A Benchmark
Wu, Y., Lim, J., & Yang, M.-H. (2013) · 2013 IEEE Conference on Computer Vision and Pattern Recognition · doi:10.1109/cvpr.2013.312 · Cited by 4,138
Visual object tracking using adaptive correlation filters
Bolme, D., Beveridge, J. R., Draper, B. A., & Lui, Y. M. (2010) · 2010 IEEE Computer Society Conference on Computer Vision and Pattern Recognition · doi:10.1109/cvpr.2010.5539960 · Cited by 3,406
Kalal, Z., Mikolajczyk, K., & Matas, J. (2012) · IEEE Transactions on Pattern Analysis and Machine Intelligence · doi:10.1109/tpami.2011.239 · Cited by 3,285
Exploiting the Circulant Structure of Tracking-by-Detection with Kernels
Henriques, J. F., Caseiro, R., Martins, P., & Batista, J. (2012) · Lecture Notes in Computer Science · doi:10.1007/978-3-642-33765-9_50 · Cited by 2,310
Self-citationLearning with Kernels: Support Vector Machines, Regularization, Optimization, and Beyond
(2005) · IEEE Transactions on Neural Networks · doi:10.1109/tnn.2005.848998 · Cited by 2,225
Robust object tracking with online multiple instance learning
Babenko, B., Yang, M.-H., & Belongie, S. (2011) · IEEE Transactions on Pattern Analysis and Machine Intelligence · doi:10.1109/tpami.2010.226 · Cited by 2,007
Fast Feature Pyramids for Object Detection
Dollar, P., Appel, R., Belongie, S., & Perona, P. (2014) · IEEE Transactions on Pattern Analysis and Machine Intelligence · doi:10.1109/tpami.2014.2300479 · Cited by 1,955
Struck: Structured output tracking with kernels
Hare, S., Saffari, A., & Torr, P. H. S. (2011) · 2011 International Conference on Computer Vision · doi:10.1109/iccv.2011.6126251 · Cited by 1,831
Digital Image Processing: An Algorithmic Introduction using Java
Burger, W., & Burge, M. J. (2008) · Texts in Computer Science · doi:10.1007/978-1-84628-968-2 · Cited by 1,540
Visual Tracking: An Experimental Survey
(2014) · IEEE Transactions on Pattern Analysis and Machine Intelligence · doi:10.1109/tpami.2013.230 · Cited by 1,513
Real-Time Compressive Tracking
Zhang, K., Zhang, L., & Yang, M.-H. (2012) · Lecture Notes in Computer Science · doi:10.1007/978-3-642-33712-3_62 · Cited by 1,427
Semi-supervised On-Line Boosting for Robust Tracking
Grabner, H., Leistner, C., & Bischof, H. (2008) · Lecture Notes in Computer Science · doi:10.1007/978-3-540-88682-2_19 · Cited by 1,089
Avidan, S. (2004) · IEEE Transactions on Pattern Analysis and Machine Intelligence · doi:10.1109/tpami.2004.53 · Cited by 1,040
Toeplitz and Circulant Matrices: A Review
Gray, R. M. (2005) · now publishers, Inc. eBooks · doi:10.1561/9781933019680 · Cited by 759
Multiple kernels for object detection
Vedaldi, A., Gulshan, V., Varma, M., & Zisserman, A. (2009) · 2009 IEEE 12th International Conference on Computer Vision · doi:10.1109/iccv.2009.5459183 · Cited by 757
Efficient Additive Kernels via Explicit Feature Maps
Vedaldi, A., & Zisserman, A. (2012) · IEEE Transactions on Pattern Analysis and Machine Intelligence · doi:10.1109/tpami.2011.153 · Cited by 688
Beyond sliding windows: Object localization by efficient subwindow search
Lampert, C. H., Blaschko, M. B., & Hofmann, T. (2008) · 2008 IEEE Conference on Computer Vision and Pattern Recognition · doi:10.1109/cvpr.2008.4587586 · Cited by 683
Recent advances and trends in visual tracking: A review
Yang, H., Shao, L., Zheng, F., Wang, L., & Song, Z. (2011) · Neurocomputing · doi:10.1016/j.neucom.2011.07.024 · Cited by 607
Minimum average correlation energy filters
Mahalanobis, A., Vijaya Kumar, B. V. K., & Casasent, D. (1987) · Applied Optics · doi:10.1364/ao.26.003633 · Cited by 598
Distribution fields for tracking
Sevilla-Lara, L., & Learned-Miller, E. (2012) · 2012 IEEE Conference on Computer Vision and Pattern Recognition · doi:10.1109/cvpr.2012.6247891 · Cited by 513
Saffari, A., Leistner, C., Santner, J., Godec, M., & Bischof, H. (2009) · 2009 IEEE 12th International Conference on Computer Vision Workshops, ICCV Workshops · doi:10.1109/iccvw.2009.5457447 · Cited by 481
Combining efficient object localization and image classification
Harzallah, H., Jurie, F., & Schmid, C. (2009) · 2009 IEEE 12th International Conference on Computer Vision · doi:10.1109/iccv.2009.5459257 · Cited by 295
Multi-channel Correlation Filters
Galoogahi, H. K., Sim, T., & Lucey, S. (2013) · 2013 IEEE International Conference on Computer Vision · doi:10.1109/iccv.2013.381 · Cited by 266
Efficient additive kernels via explicit feature maps
Vedaldi, A., & Zisserman, A. (2010) · 2010 IEEE Computer Society Conference on Computer Vision and Pattern Recognition · doi:10.1109/cvpr.2010.5539949 · Cited by 257
Average of Synthetic Exact Filters
Bolme, D. S., Draper, B. A., & Beveridge, J. R. (2009) · 2009 IEEE Conference on Computer Vision and Pattern Recognition · doi:10.1109/cvpr.2009.5206701 · Cited by 176
Correlation Filters for Object Alignment
Boddeti, V. N., Takeo Kanade, A., & Kumar, B. V. K. V. (2013) · IEEE Computer Society Conference on Computer Vision and Pattern Recognition/Proceedings - IEEE Computer Society Conference on Computer Vision and Pattern Recognition/Proceedings · doi:10.1109/cvpr.2013.297 · Cited by 134
Event Retrieval in Large Video Collections with Circulant Temporal Encoding
Revaud, J., Douze, M., Schmid, C., & Jegou, H. (2013) · 2013 IEEE Conference on Computer Vision and Pattern Recognition · doi:10.1109/cvpr.2013.318 · Cited by 133
Online robust image alignment via iterative convex optimization
Wu, Y., Shen, B., & Ling, H. (2012) · IEEE Computer Society Conference on Computer Vision and Pattern Recognition/Proceedings - IEEE Computer Society Conference on Computer Vision and Pattern Recognition/Proceedings · doi:10.1109/cvpr.2012.6247878 · Cited by 130
Beyond Hard Negative Mining: Efficient Detector Learning via Block-Circulant Decomposition
Henriques, J. F., Carreira, J., Caseiro, R., & Batista, J. P. (2013) · IEEE/CVF International Conference on Computer Vision (ICCV) · doi:10.1109/iccv.2013.343 · Cited by 111
Self-citationKernel Correlation Filter Based Redundant Class-Dependence Feature Analysis (KCFA) on FRGC2.0 Data
Xie, C., Savvides, M., & Kumar, B. V. K. V. (2005) · Lecture notes in computer science · doi:10.1007/11564386_4 · Cited by 42
Average of Synthetic Exact Filters
Bolme, D. S., Draper, B. A., & Beveridge, J. R. (2009) · IEEE Computer Society Conference on Computer Vision and Pattern Recognition/Proceedings - IEEE Computer Society Conference on Computer Vision and Pattern Recognition/Proceedings · doi:10.1109/cvprw.2009.5206701 · Cited by 33
Exploiting spatial overlap to efficiently compute appearance distances between image windows.
Alexe, B., Petrescu, V., & Ferrari, V. (2011) · Edinburgh Research Explorer (University of Edinburgh) · Cited by 17
Fast FFT-based distortion-invariant kernel filters for general object recognition
Patnaik, R., & Casasent, D. P. (2008) · Proceedings of SPIE, the International Society for Optical Engineering/Proceedings of SPIE · doi:10.1117/12.805411 · Cited by 14
Kernel Based Synthetic Discriminant Function for Object Recognition
Jeong, K.-H., Pokharel, P. P., Xu, J., Han, S., & Príncipe, J. C. (2006) · IEEE International Conference on Acoustics Speech and Signal Processing · doi:10.1109/icassp.2006.1661388 · Cited by 10
Analysis of kernel distortion-invariant filters
Casasent, D. P., & Patnaik, R. (2007) · Proceedings of SPIE, the International Society for Optical Engineering/Proceedings of SPIE · doi:10.1117/12.734820 · Cited by 6
Distortion-invariant kernel correlation filters for general object recognition
Patnaik, R. (2009) · Cited by 2
Research works printed but not linked: 3
- davis, 0, Circulant Matrices
- rifkin, 0, Regularized least-squares classification, Nato Sci Ser Sub Ser III
- gonzalez, 0, Digital Image Processing
Cited by
Fully-Convolutional Siamese Networks for Object Tracking
Bertinetto, L., Valmadre, J., Henriques, J. F., Vedaldi, A., & Torr, P. H. S. (2016) · Lecture Notes in Computer Science · doi:10.1007/978-3-319-48881-3_56 · Cited by 4,546
Self-citationWu, Y., Lim, J., & Yang, M.-H. (2015) · IEEE Transactions on Pattern Analysis and Machine Intelligence · doi:10.1109/tpami.2014.2388226 · Cited by 3,371
High Performance Visual Tracking with Siamese Region Proposal Network
Li, B., Yan, J., Wu, W., Zhu, Z., & Hu, X. (2018) · 2018 IEEE/CVF Conference on Computer Vision and Pattern Recognition · doi:10.1109/cvpr.2018.00935 · Cited by 3,023
Learning Multi-domain Convolutional Neural Networks for Visual Tracking
Nam, H., & Han, B. (2016) · 2016 IEEE Conference on Computer Vision and Pattern Recognition (CVPR) · doi:10.1109/cvpr.2016.465 · Cited by 2,806
ECO: Efficient Convolution Operators for Tracking
Danelljan, M., Bhat, G., Khan, F. S., & Felsberg, M. (2017) · 2017 IEEE Conference on Computer Vision and Pattern Recognition (CVPR) · doi:10.1109/cvpr.2017.733 · Cited by 2,805
Metadata
- Authors
- Henriques, J. F., Caseiro, R., Martins, P., & Batista, J.
- Affiliations
- University of Coimbra (PT)
- Venue
- IEEE Transactions on Pattern Analysis and Machine Intelligence
- Published
- 2015-03-01
- Volume
- 37
- Issue
- 3
- Pages
- 583-596
- ISSN
- 0162-8828 (ISSN-L)
- 2160-9292
- OpenAlex
- W2154889144
- Cited by
- 5,753
- References
- 43
- Citations by year
- 2026: 164 · 2025: 285 · 2024: 406 · 2023: 510 · 2022: 614 · 2021: 718 · 2020: 712 · 2019: 846 · 2018: 690 · 2017: 472 · 2016: 240 · 2015: 92
- FWCI
- 240.92
- Type
- journal article
- Language
- en
- Open access
- green
- arxiv.org
- Locations
- IEEE Transactions on Pattern Analysis and Machine Intelligence (publishedVersion)
- PubMed (publishedVersion)
- arXiv (Cornell University) (submittedVersion)
- arXiv (Cornell University)
- Funders
- FCT (PTDC/EEA-CRO/122812/2010, SFRH/BD75459/2010, SFRH/BD74152/2010, SFRH/BPD/90200/2012)
- Topics
- Physical Sciences › Computer Science › Computer Vision and Pattern Recognition › Video Surveillance and Tracking Methods
- Physical Sciences › Computer Science › Computer Vision and Pattern Recognition › Advanced Image and Video Retrieval Techniques
- Physical Sciences › Computer Science › Computer Vision and Pattern Recognition › Advanced Neural Network Applications
- Keywords
- object tracking, kernelized correlation filter, correlation filter, circulant matrices, discrete Fourier transform, kernel regression, discriminative classifiers, high-speed tracking
About these checks
Registry, retraction, Cites and statistics results are computed, not judged, with one exception: a printed reference that no index lists is read once by a model before it counts as a citation error. Claims are extracted by a model and kept only when their quote appears verbatim in the text; each cited source is then checked, with a model’s help, for whether it says what the claim relies on. Those verdicts can be wrong — read the claim’s quote and the cited source before relying on one.
Statistics and arithmetic are recomputed, not judged.
Confidence bands are shown only for fields calibrated on our annotated test set. None is calibrated yet, so no band is shown.
What counts as a claim ›How we measure confidence ›How we check this ›
Are you an author, or do you see a problem with this page? Request a review
Data sources
Bibliographic data: Semantic Scholar, OpenAlex, Crossref.
Contains information from the Semantic Scholar Academic Graph Datasets, made available under the ODC Attribution License (ODC-BY 1.0).
Semantic Scholar’s data is described in: Kinney, R., et al. (2023). The Semantic Scholar Open Data Platform. arXiv:2301.10140.