Visual object tracking using adaptive correlation filters
The DOI matches its Crossref record; 18 of the 19 references it cites were found in a registry or an index.
Abstract
Although not commonly used, correlation filters can track complex objects through rotations, occlusions and other distractions at over 20 times the rate of current state-of-the-art techniques. The oldest and simplest correlation filters use simple templates and generally fail when applied to tracking. More modern approaches such as ASEF and UMACE perform better, but their training needs are poorly suited to tracking. Visual tracking requires robust filters to be trained from a single frame and dynamically adapted as the appearance of the target object changes. This paper presents a new type of correlation filter, a Minimum Output Sum of Squared Error (MOSSE) filter, which produces stable correlation filters when initialized using a single frame. A tracker based upon MOSSE filters is robust to variations in lighting, scale, pose, and nonrigid deformations while operating at 669 frames per second. Occlusion is detected based upon the peak-to-sidelobe ratio, which enables the tracker to pause and resume where it left off when the object reappears.
Overview
Integrity signals
Registry
Cites
Statistics
Verification
Claims the paper makes
Citations
Cites
Breiman, L. (1996) · Machine Learning · doi:10.1007/bf00058655 · Cited by 16,325 · cited 1×
“Motivation for averaging comes from Bootstrap Aggregation [5] where the output of weak classifiers can be averaged to produce a much stronger classifier.”
BackgroundPress, W. H., Teukolsky, S. A., Vetterling, W. T., & Flannery, B. P. (1994) · Cited by 15,411
Incremental Learning for Robust Visual Tracking
Ross, D. A., Lim, J., Lin, R.-S., & Yang, M.-H. (2008) · International Journal of Computer Vision · doi:10.1007/s11263-007-0075-7 · Cited by 3,061 · cited 7×
“Recent examples include: Incremental Visual Tracking (IVT) [17], Robust Fragmentsbased Tracking (FragTrack) [1], Graph Based Discriminative Learning (GBDL) [19], and Multiple Instance Learning (MILTrack) [2].”
BackgroundMethodInfluentialVisual tracking with online Multiple Instance Learning
Babenko, B., Yang, M.-H., & Belongie, S. (2009) · 2009 IEEE Conference on Computer Vision and Pattern Recognition · doi:10.1109/cvpr.2009.5206737 · Cited by 1,770 · cited 6×
“Recent examples include: Incremental Visual Tracking (IVT) [17], Robust Fragmentsbased Tracking (FragTrack) [1], Graph Based Discriminative Learning (GBDL) [19], and Multiple Instance Learning (MILTrack) [2].”
BackgroundMethodInfluentialRobust Fragments-based Tracking using the Integral Histogram
Adam, A., Rivlin, E., & Shimshoni, I. (2006) · 2006 IEEE Computer Society Conference on Computer Vision and Pattern Recognition - Volume 1 (CVPR'06) · doi:10.1109/cvpr.2006.256 · Cited by 1,397 · cited 7×
“Recent examples include: Incremental Visual Tracking (IVT) [17], Robust Fragmentsbased Tracking (FragTrack) [1], Graph Based Discriminative Learning (GBDL) [19], and Multiple Instance Learning (MILTrack) [2].”
BackgroundMethodInfluentialRobust online appearance models for visual tracking
Jepson, A. D., Fleet, D. J., & El-Maraghi, T. F. (2003) · IEEE Transactions on Pattern Analysis and Machine Intelligence · doi:10.1109/tpami.2003.1233903 · Cited by 922
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 · cited 1×
“In the 1980’s and 1990’s, many variants of correlation filters, including Synthetic Discriminant Functions (SDF) [7, 6], Minimum Variance Synthetic Discriminant Functions (MVSDF) [9], Minimum Average Correlation Energy (MACE) [11], Optimal Tradeoff Filters (OTF) [16], and Minimum Squared Error Synthetic Discriminant F…”
MethodMultivariant technique for multiclass pattern recognition
Hester, C. F., & Casasent, D. (1980) · Applied Optics · doi:10.1364/ao.19.001758 · Cited by 385 · cited 3×
“In [12], it was found that the hard constraints of SDF based filters like MACE caused issues with distortion Naive UMACE ASEF MOSSE INPUT FILTER OUTPUT Figure 2 .”
MethodUnconstrained correlation filters
Mahalanobis, A., Vijaya Kumar, B. V. K., Song, S., Sims, S. R. F., & Epperson, J. F. (1994) · Applied Optics · doi:10.1364/ao.33.003751 · Cited by 293 · cited 2×
“In fact, the optimization problem in Equation 3 is almost identical to optimization problems presented in [10] and [12].”
MethodUnified synthetic discriminant function computational formulation
Casasent, D. (1984) · Applied Optics · doi:10.1364/ao.23.001620 · Cited by 292 · cited 3×
“In [12], it was found that the hard constraints of SDF based filters like MACE caused issues with distortion Naive UMACE ASEF MOSSE INPUT FILTER OUTPUT Figure 2 .”
Method
Research works printed but not linked: 2
- messerschmitt, 2006, Stationary points of a real-valued function of a complex variable
- savvides, 2002, Face verification using correlation filters, AIAT
Cited by
High-Speed Tracking with Kernelized Correlation Filters
Henriques, J. F., Caseiro, R., Martins, P., & Batista, J. (2015) · IEEE Transactions on Pattern Analysis and Machine Intelligence · doi:10.1109/tpami.2014.2345390 · Cited by 5,753
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
“conducted in Fourier domain and is then widely used in the tracking community [5, 14].”
MethodLearning 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
“[2] proposed a fast correlation tracker with a minimum output sum of squared error (MOSSE) filter, which runs in hundreds of frames per second.”
BackgroundECO: 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
“The standard approach in DCF based tracking is to update the model in each frame [4, 9, 20].”
BackgroundSiamRPN++: Evolution of Siamese Visual Tracking With Very Deep Networks
Li, B., Wu, W., Wang, Q., Zhang, F., Xing, J., & Yan, J. (2019) · 2019 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR) · doi:10.1109/cvpr.2019.00441 · Cited by 2,607
“[3] introduces the Convolution Theorem from the signal processing field into visual tracking and transforms the object template matching problem into a correlation operation in the frequency domain.”
Method
Metadata
- Authors
- Bolme, D., Beveridge, J. R., Draper, B. A., & Lui, Y. M.
- Affiliations
- Colorado State University (US)
- Venue
- 2010 IEEE Computer Society Conference on Computer Vision and Pattern Recognition
- Publisher
- IEEE
- Published
- 2010-06
- Pages
- 2544-2550
- ISSN
- 1063-6919 (ISSN-L)
- OpenAlex
- W1964846093
- Cited by
- 3,406
- References
- 19
- Citations by year
- 2026: 78 · 2025: 165 · 2024: 246 · 2023: 327 · 2022: 391 · 2021: 442 · 2020: 433 · 2019: 493 · 2018: 372 · 2017: 206 · 2016: 118 · 2015: 71 · 2014: 36 · 2013: 16 · 2012: 8
- FWCI
- 7.68
- Type
- conference paper
- Language
- en
- Open access
- closed
- Locations
- IEEE Computer Society Conference on Computer Vision and Pattern Recognition/Proceedings - IEEE Computer Society Conference on Computer Vision and Pattern Recognition/Proceedings (publishedVersion)
- 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 › Infrared Target Detection Methodologies
- Keywords
- visual object tracking, correlation filter, occlusion detection, peak-to-sidelobe ratio, non-rigid deformation, real-time 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
How to cite
Cite CoChat for the checks on this page, and the paper for its own findings.
- This page
- CoChat. (2026). Citation check: Visual object tracking using adaptive correlation filters. https://app.cochat.ai/papers/10.1109/cvpr.2010.5539960
- The paper
- Bolme, D., Beveridge, J. R., Draper, B. A., & Lui, Y. M. (2010). Visual object tracking using adaptive correlation filters. 2010 IEEE Computer Society Conference on Computer Vision and Pattern Recognition. https://doi.org/10.1109/cvpr.2010.5539960
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.