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
Items 901–1,000 of 1,002
Noise-Aware Framework for Robust Visual Tracking
Li, S., Zhao, S., Cheng, B. H., & Chen, J. (2020) · IEEE Transactions on Cybernetics · doi:10.1109/tcyb.2020.2996245 · Cited by 18
Robust Object Tracking via Large Margin and Scale-Adaptive Correlation Filter
Li, J., Zhou, X., Chan, S., & Chen, S. (2017) · IEEE Access · doi:10.1109/access.2017.2778740 · Cited by 16
“[21] propose to model a tracker by learning a correlation filter which is optimized by minimizing the”
Enhancing the Robustness of Visual Object Tracking via Style Transfer
Amirkhani, A., Barshooi, A. H., & Ghahnavieh, A. E. (2021) · Computers, materials & continua/Computers, materials & continua (Print) · doi:10.32604/cmc.2022.019001 · Cited by 17
“Visual object tracking (VOT), which is a subset of computer vision systems, refers to the process of examining a region of an image in order to detect one/several targets and to estimate its/their positions in subsequent frames [1].”
BackgroundExploiting temporal coherence for self-supervised visual tracking by using vision transformer
Zhu, W., Wang, Z., Li, X., & Meng, J. H. (2022) · Knowledge-Based Systems · doi:10.1016/j.knosys.2022.109318 · Cited by 15
Chen, L., Li, G., Zhao, K., Zhang, G., & Zhu, X. (2023) · Cognitive Computation · doi:10.1007/s12559-023-10173-0 · Cited by 15
“In 2010, the minimum output sum of squared error (MOSSE) [6] algorithm was proposed, which was the first to introduce the concept of correlation filtering in visual target tracking.”
MethodSiamCA: Siamese visual tracking with customized anchor and target-aware interaction
Pan, S., Zhang, C., Li, Z., & Hu, L. (2023) · Expert Systems with Applications · doi:10.1016/j.eswa.2023.121763 · Cited by 16
Safaei, D., Sobhani, A., & Kiaei, A. A. (2023) · International Journal of Information Technology · doi:10.1007/s41870-023-01665-1 · Cited by 18
“The foundation of their work relies on the MOSSE tracker [32], a filter that introduced correlation filter technology to the visual tracking field through the Minimum Output Sum of Squared Error (MOSSE) filter [34].”
InfluentialSu, Z., Wan, G., Zhang, W., Guo, N., Wu, Y., Liu, J., Cong, D., Jia, Y., & Wei, Z. (2024) · Remote Sensing · doi:10.3390/rs16040724 · Cited by 15
“To increase the tracking speed, MOSSE [13] uses the fast Fourier transform (FFT), which converts the convolution operations in the real number domain to an element-wise multiplication in the Fourier domain, and this is performed to decrease the computational complexity.”
Hu, S., & Zhang, J. (2024) · Measurement · doi:10.1016/j.measurement.2024.114388 · Cited by 17
PPTtrack: Pyramid pooling based Transformer backbone for visual tracking
Wang, J., Yang, S., Wang, Y., & Yang, G. (2024) · Expert Systems with Applications · doi:10.1016/j.eswa.2024.123716 · Cited by 15
Human-Following Strategy for Orchard Mobile Robot Based on the KCF-YOLO Algorithm
Huang, Z., Ou, C., Guo, Z., Ye, L., & Li, J. (2024) · Horticulturae · doi:10.3390/horticulturae10040348 · Cited by 16
Parallel Architecture for Low Latency UAV Detection and Tracking Using Robotic Telescopes
Ojdanić, D., Naverschnigg, C., Sinn, A., Zelinskyi, D., & Schitter, G. (2024) · IEEE Transactions on Aerospace and Electronic Systems · doi:10.1109/taes.2024.3396418 · Cited by 17
Correlation filter based visual trackers for person pursuit using a low-cost Quadrotor
Haag, K., Dotenco, S., & Gallwitz, F. (2015) · International Conference on Innovations for Community Services (I4CS) · doi:10.1109/i4cs.2015.7294481 · Cited by 19
“Correlation filter based trackers exploit the observation that a complete correlation response can be calculated efficiently in the frequency domain using the fast Fourier transform (FFT) [9].”
BackgroundMethodMulti-channel correlation filters for human action recognition
Galoogahi, H. K., Sim, T., & Lucey, S. (2014) · Proceedings - International Conference on Image Processing · doi:10.1109/icip.2014.7025297 · Cited by 15
“It was discussed in [10] that this may increase the sensitivity to the noise or produce smooth peaks which are difficult to be accurately recognized/detected.”
BackgroundMethodInfluentialSelective Sampling Importance Resampling Particle Filter Tracking With Multibag Subspace Restoration
Jenkins, M. D., Barrie, P., Buggy, T., & Morison, G. (2016) · IEEE Transactions on Cybernetics · doi:10.1109/tcyb.2016.2631660 · Cited by 15
“Correlation filters theo retically perform the same operation but more efficiently by exploiting frequency domain techniques [21]–[23] to analy se the entire search region in one operation.”
BackgroundLearning Robust Gaussian Process Regression for Visual Tracking
Zheng, L., Tang, M., & Wang, J. (2018) · International Joint Conference on Artificial Intelligence · doi:10.24963/ijcai.2018/170 · Cited by 15
Discriminative tracking via supervised tensor learning
Xu, G., Khan, S., Zhu, H., Han, L., Ng, M. K., & Yan, H. (2018) · Neurocomputing · doi:10.1016/j.neucom.2018.05.108 · Cited by 16
Occlusion-Aware Correlation Particle Filter Target Tracking Based on RGBD Data
Zhai, Y., Song, P., Mou, Z., Chen, X.-X., & Liu, X. (2018) · IEEE Access · doi:10.1109/access.2018.2869766 · Cited by 19
“[10] proposed amethod of learning theminimum output sum of squared error (MOSSE) correlation filter on grayscale images.”
BackgroundYang, X., Zhu, R., Wang, J., & Li, Z. (2019) · Chinese Journal of Aeronautics · doi:10.1016/j.cja.2019.01.020 · Cited by 15
Robust visual tracking based on global-and-local search with confidence reliability estimation
Fang, Y., Ko, S., & Jo, G. (2019) · Neurocomputing · doi:10.1016/j.neucom.2019.08.005 · Cited by 16
Robust RGBD Tracking via Weighted Convolution Operators
Liu, W., Tang, X., & Zhao, C. (2020) · IEEE Sensors Journal · doi:10.1109/jsen.2020.2964019 · Cited by 19
Motion Guided Siamese Trackers for Visual Tracking
Wu, C., Zhang, Y., Zhang, Y., Zhang, W., Wang, H., Zhang, Y., & Sun, X. (2020) · IEEE Access · doi:10.1109/access.2020.2964269 · Cited by 15
“The pioneering study of the DCF-based tracker is [40].”
BackgroundMethodOcclusion detection and drift-avoidance framework for 2D visual object tracking
Karakostas, I., Mygdalis, V., Tefas, A., & Pitas, I. (2020) · Signal Processing Image Communication · doi:10.1016/j.image.2020.116011 · Cited by 21
Hierarchical correlation siamese network for real-time object tracking
Meng, Y., Deng, Z., Zhao, K., Xu, Y., & Liu, H. (2020) · Applied Intelligence · doi:10.1007/s10489-020-01992-x · Cited by 15
“On the basis of features represented by the trackers, visual object tracking can be divided into two categories: one is based on Correlation Filter (CF) [5–11] and the other is based on Deep Learning (DL) [7, 12–14].”
MethodMaltezos, E., Douklias, A., Dadoukis, A., Misichroni, F. D., Karagiannidis, L., Αντωνόπουλος, Μ., Voulgary, K., Ouzounoglou, E., & Amditis, A. (2021) · Computation · doi:10.3390/computation9020012 · Cited by 15
“Assessing qualitatively the experimental results on the RGB video datasets (OKUTAMA and UAV123), the Mosse tracker seems that achieves the best performance compared with the other trackers.”
MethodInfluentialDynamic Object Tracking for Self-Driving Cars Using Monocular Camera and LIDAR
Zhao, L., Wang, M., Su, S., Liu, T., & Yang, Y. M. (2020) · IEEE/RSJ International Conference on Intelligent Robots and Systems (IROS) · doi:10.1109/iros45743.2020.9341179 · Cited by 18
“Especially, the Correlation Filter rose to prominence as a particularly fast and effective strategy for tracking-by-detection [8].”
BackgroundIoU-guided Siamese region proposal network for real-time visual tracking
Zhou, L., He, Y. Q., Li, W., Mi, J., & Lei, B. (2021) · Neurocomputing · doi:10.1016/j.neucom.2021.05.111 · Cited by 15
Markerless gait estimation and tracking for postural assessment
Tay, C. Z., Lim, K. H., & Phang, J. T. S. (2022) · Multimedia Tools and Applications · doi:10.1007/s11042-022-12026-8 · Cited by 16
“∑ d w̃d = 1, w̃ d is the learned channel filter obtained from the update step and w̃ d is the channel detection reliability measured on the ratio between the second and first highest non-adjacent peaks in the channel response map [7].”
BackgroundLearning Dynamic Compact Memory Embedding for Deformable Visual Object Tracking
Yu, H., Zhu, P., Zhang, K., Wang, Y., Zhao, S., Wang, L., Zhang, T., & Hu, Q. (2022) · IEEE Transactions on Neural Networks and Learning Systems · doi:10.1109/tnnls.2022.3208605 · Cited by 18
“MOSSE [16] is the first attempt to learn the filter coefficients by ridge regression in the Fourier domain.”
BackgroundDFAT: Dynamic Feature-Adaptive Tracking
Zhang, W., Jiao, L., Liu, F., Yang, S., & Liu, J. (2022) · IEEE Transactions on Circuits and Systems for Video Technology · doi:10.1109/tcsvt.2022.3197145 · Cited by 15
“did the seminal work for DCF trackers in [46] where MOSSE was proposed by minimizing the sum of squared error filter.”
BackgroundBai, Y., Song, Y., Zhao, Y., Zhou, Y., Wu, X., He, Y., Zhang, Z., Yang, X., & Hao, Q. (2022) · Remote Sensing · doi:10.3390/rs14194756 · Cited by 15
A dynamic infrared object tracking algorithm by frame differencing
Wu, H., & Liu, G. (2022) · Infrared Physics & Technology · doi:10.1016/j.infrared.2022.104384 · Cited by 15
CoCoLoT: Combining Complementary Trackers in Long-Term Visual Tracking
Dunnhofer, M., & Micheloni, C. (2022) · Proceedings - International Conference on Pattern Recognition/Proceedings/International Conference on Pattern Recognition · doi:10.1109/icpr56361.2022.9956082 · Cited by 15
“Differently from such approaches, the FuCoLoT tracker [34] extended the discriminative correlation filter (DCFs) approach [35] to the long-term setting by optimizing multiple filters at different time scales to implement a short-term tracker and a long-term detector which predictions”
MethodTracking Small and Fast Moving Objects: A Benchmark
Zhang, Z., Wu, F., Qiu, Y., Liang, J., & Li, S. (2023) · Lecture notes in computer science · doi:10.1007/978-3-031-26293-7_33 · Cited by 17
Lin, J.-T., Peng, J., & Chai, J.-C. (2023) · IEEE Geoscience and Remote Sensing Letters · doi:10.1109/lgrs.2023.3272522 · Cited by 17
“T HE correlation filter (CF) was first proposed by Bolme et al. [1].”
MethodCheng, Z., Li, X., Liu, S., Ma, M., Liang, F., Zhao, D., & Wang, B. (2023) · IEEE Transactions on Antennas and Propagation · doi:10.1109/tap.2023.3309372 · Cited by 15
“To find a filter mapping the training inputs to the desired outputs, the MOSSE filter minimizes the sum of squared errors between the actual output and the desired image [34].”
BackgroundEmbedding CNN-Based Fast Obstacles Detection for Autonomous Vehicles
Hu, C., Wang, Y., Yu, G., Wang, Z., Ao, L., & Hu, Z. (2018) · SAE technical papers on CD-ROM/SAE technical paper series · doi:10.4271/2018-01-1622 · Cited by 16
Learning channel-aware deep regression for object tracking
Lu, X., Tang, F., Huo, H., & Fang, T. (2018) · Pattern Recognition Letters · doi:10.1016/j.patrec.2018.06.032 · Cited by 15
Robust Visual Tracking Using Multi-Frame Multi-Feature Joint Modeling
Zhang, P., Yu, S., Xu, J., You, X., Jiang, X., Jing, X., & Tao, D. (2018) · IEEE Transactions on Circuits and Systems for Video Technology · doi:10.1109/tcsvt.2018.2882339 · Cited by 15
“Finally, we compare K(MF)(2)JMT with several other representative CFTs, including MOSSE [49], SAMF [9], MUSTer [16] and the recently published CCOT [36], to reveal the properties of our proposed tracker among CFTs family and also illustrate future research directions for modern discriminative tracker design.”
MethodInfluentialOptical Flow in Deep Visual Tracking
Vihlman, M., & Visala, A. (2020) · Proceedings of the AAAI Conference on Artificial Intelligence · doi:10.1609/aaai.v34i07.6890 · Cited by 19
“MOSSE (Bolme et al. 2010) builds trackers directly from pixel values, whereas the kernelized correlation filter (Henriques et al.”
MethodA Bottom-Up and Top-Down Integration Framework for Online Object Tracking
Li, M., Peng, L., Wu, T., & Peng, Z. (2020) · IEEE Transactions on Multimedia · doi:10.1109/tmm.2020.2978623 · Cited by 15
“The raw pixel feature is firstly adopted in the DSST tracker [9] and CSK tracker [25].”
BackgroundMethodPart-Based Co-Difference Object Tracking Algorithm for Infrared Videos
Demir, H. S., & Adil, Ö. F. (2018) · Proceedings - International Conference on Image Processing · doi:10.1109/icip.2018.8451294 · Cited by 15
“The proposed method is compared against well-known recent methods CO-DIFF [2], TBOOST [I], STAPLE [9], MILTrack [10], ODFS [II], FCT [12], STRUCK [13], L1APG [14] and MOSSE [15] on this dataset.”
MethodImproved kernelized correlation filter tracking by using spatial regularization
Gao, L., Li, Y., & Ning, J. (2018) · Journal of Visual Communication and Image Representation · doi:10.1016/j.jvcir.2017.11.008 · Cited by 14
On the improvement of foreground–background model‐based object tracker
Hanif, M. S., Ahmad, S., & Khurshid, K. (2017) · IET Computer Vision · doi:10.1049/iet-cvi.2016.0487 · Cited by 14
Hu, X., Jiang, Y., Xia, X., Chen, C., Liu, W., Wan, P., Bin, K., & Zhong, P. (2025) · International Journal of Applied Earth Observation and Geoinformation · doi:10.1016/j.jag.2025.104586 · Cited by 27
Scene-Aware Adaptive Updating for Visual Tracking via Correlation Filters
Li, F., Zhang, S., & Qiao, X. (2017) · Sensors · doi:10.3390/s17112626 · Cited by 14
“Since correlation filters is applied to target tracking [15,17,23–27], the speed of discriminative tracking algorithms has improved qualitatively and can reach up to 100 frames per second [15,23,25].”
BackgroundMethodWang, B., Li, W., Zhang, B., Liu, Y., & Du, J. (2023) · IEEE Transactions on Circuits and Systems for Video Technology · doi:10.1109/tcsvt.2023.3325672 · Cited by 15
“Bolme et al. [38] pioneered the application of the CF in the field of visual online tracking, and they achieved remarkable speed ( ∼ 600 FPS) by utilizing fast Fourier transform (FFT) for accelerated computation.”
MethodViT Spatio-Temporal Feature Fusion for Aerial Object Tracking
Guo, C., Liu, K., Dong-hu, D., & Li, X. (2023) · IEEE Transactions on Circuits and Systems for Video Technology · doi:10.1109/tcsvt.2023.3326695 · Cited by 15
Recent advances in object tracking using hyperspectral videos: a survey
Qian, K., Shen, J., Wang, S., & Sun, W. (2023) · Multimedia Tools and Applications · doi:10.1007/s11042-023-17758-9 · Cited by 14
SDCS-CF: Saliency-driven localization and cascade scale estimation for visual tracking
Yang, P., Wang, Q., Dou, J., & Dou, L. (2023) · Journal of Visual Communication and Image Representation · doi:10.1016/j.jvcir.2023.104040 · Cited by 14
Visual tracking in camera-switching outdoor sport videos: Benchmark and baselines for skiing
Dunnhofer, M., & Micheloni, C. (2024) · Computer Vision and Image Understanding · doi:10.1016/j.cviu.2024.103978 · Cited by 16
Tracking Skiers from the Top to the Bottom
Dunnhofer, M., Sordi, L., Martinel, N., & Micheloni, C. (2024) · IEEE Winter Conference on Applications of Computer Vision · doi:10.1109/wacv57701.2024.00832 · Cited by 18
“In addition, we included the short-term trackers [54] MOSSE [7], KCF [39], and SiamRPN++ [49] for their general popularity, and MixFormer [19], OSTrack [84], FEAR [8], and SeqTrack [12] for their very recent demonstration of high accuracy.”
BackgroundMamba Adapter: Efficient Multi-Modal Fusion for Vision-Language Tracking
Shi, L., Zhong, B., Liang, Q., Hu, X., Mo, Z., & Song, S. (2025) · IEEE Transactions on Circuits and Systems for Video Technology · doi:10.1109/tcsvt.2025.3557570 · Cited by 23
Moorthy, S., Sakthivel, S. S. K., Arthanari, S., Jeong, J. H., & Joo, Y. H. (2025) · Journal of Visual Communication and Image Representation · doi:10.1016/j.jvcir.2025.104458 · Cited by 14
Visual object tracking: Review and challenges
Chen, Z., Peng, C., Liu, S., & Ding, W. (2025) · Applied Soft Computing · doi:10.1016/j.asoc.2025.113140 · Cited by 18
Correlation Filters for Detection of Cellular Nuclei in Histopathology Images
Ahmad, A., Asif, A., Rajpoot, N., Arif, M., & Minhas, F. (2017) · Journal of Medical Systems · doi:10.1007/s10916-017-0863-8 · Cited by 14
“In this study, we employ Minimum Output Sum of Squared Error (MOSSE) [28] and radial basis function (RBF) kernelized correlation filter (KCF) [30] for cells detection in histopathology images.”
BackgroundMethodInfluentialCorrelation filter tracker with siamese: A robust and real-time object tracking framework
Pan, G., Chen, G., Kang, W., & Hou, J. (2019) · Neurocomputing · doi:10.1016/j.neucom.2019.05.033 · Cited by 14
Target-Aware Correlation Filter Tracking in RGBD Videos
Kuai, Y., Wen, G., Li, D., & Xiao, J. (2019) · IEEE Sensors Journal · doi:10.1109/jsen.2019.2925821 · Cited by 19
“V ISUAL object tracking is a classical and rapidly evolving research topic in computer vision with many applications such as video surveillance [1], augmented reality [2], and human-computer interaction [3].”
BackgroundA new TLD target tracking method based on improved correlation filter and adaptive scale
Yang, X., Zhu, S., Xia, S., & Zhou, D. (2019) · The Visual Computer · doi:10.1007/s00371-019-01772-w · Cited by 14
“Bolme et al. first [11] proposed correlation filter-based tracking method, which designed a correlation filter consisting of the minimum output squared error.”
MethodVisual Tracking With Long-Short Term Based Correlation Filter
Yang, Y., Xing, W., Zhang, S., Gao, L., Yu, Q., Che, X., & Lu, W. B. (2020) · IEEE Access · doi:10.1109/access.2020.2968125 · Cited by 15
“[12], [13] with the discriminative power of deep features has become popular.”
BackgroundMethodDing, F., Fu, C., Li, Y., Jin, J., & Feng, C. (2020) · IEEE/RSJ International Conference on Intelligent Robots and Systems (IROS) · doi:10.1109/iros45743.2020.9341744 · Cited by 14
“An effective tracking failure monitoring mechanism and an efficient re-initialization method based on EdgeBoxes [21] collaboratively contribute to the smooth long-term tracking.”
BackgroundMethodInfluentialReview of recent advances in visual tracking techniques
M, J. R. S., & Augasta, M. G. (2021) · Multimedia Tools and Applications · doi:10.1007/s11042-021-10848-6 · Cited by 17
“Correlation filters have become popular by the pioneering study [7], which mainly attempts to minimize the sum of squared error between the desired correlation response and the circular correlation of the filter and the object patch.”
BackgroundMethodA Comparison of OpenCV Algorithms for Human Tracking with a Moving Perspective Camera
Haggui, O., Tchalim, M. A., & Magnier, B. (2021) · European Workshop on Visual Information Processing · doi:10.1109/euvip50544.2021.9483957 · Cited by 14
“Tracking algorithms described in section II, namely, CSRT, TLD, KCF, MOSSE, Boosting and particle filter are qualitatively and quantitatively compared.”
Influential2D vision-based tracking algorithm for general space non-cooperative objects
Zhou, D. X., Sun, G., Song, J., & Yao, W. (2021) · Acta Astronautica · doi:10.1016/j.actaastro.2021.07.023 · Cited by 14
Robust Visual Tracking via Multitask Sparse Correlation Filters Learning
Nai, K., Li, Z., Gan, Y., & Wang, Q. (2021) · IEEE Transactions on Neural Networks and Learning Systems · doi:10.1109/tnnls.2021.3097498 · Cited by 16
Deep Learning-Based Ground Target Detection and Tracking for Aerial Photography from UAVs
Wang, K., Meng, Z., & Wu, Z. (2021) · Applied Sciences · doi:10.3390/app11188434 · Cited by 15
“Tracking Score Based on Peak to Sidelobe Ratio (PSR) MOSSE proposed peak to sidelobe ratio (PSR) to determine tracking failure.”
MethodInfluentialFarhadmanesh, M., Marković, N., & Rashidi, A. (2022) · Transportation Research Record Journal of the Transportation Research Board · doi:10.1177/03611981221115087 · Cited by 14
“Among them, we used minimum output sum of squared error (MOSSE) that employs a fast computing solution to find the object’s new position (55).”
MethodUnderwater Formation System Design and Implement for Small Spherical Robots
Shi, L., Bao, P., Guo, S., Chen, Z., & Zhang, Z. (2022) · IEEE Systems Journal · doi:10.1109/jsyst.2022.3199574 · Cited by 15
“the leader–follower formation, the follower robot needs to track the leader robot in real time and the resource occupation should be finite, multiscale kernel correlation filtering algorithm (KCF) based on online learning [43], [44], [45], [46] was chosen as our algorithm framework.”
MethodLiu, J., Wang, Z., Cheng, D., Chen, W., & Chen, C. (2022) · Remote Sensing · doi:10.3390/rs14235937 · Cited by 14
“The peak to side-lobe ratio (PSR) [26] and average peak-to-correlation energy (APCE) [27] are utilized to evaluate the fluctuated degree of response y and the confidence level of the detected targets, which are given by (31) and (32), respectively, PSR = ymax − µs σs , (31) APCE = |ymax − ymin|2 mean ( ∑ w,h (yw,h − y…”
MethodInfluentialSiamese Graph Attention Networks for robust visual object tracking
Lu, J., Li, S., Guo, W., Zhao, M., Yang, J., Liu, Y., & Zhou, Z. (2023) · Computer Vision and Image Understanding · doi:10.1016/j.cviu.2023.103634 · Cited by 15
Correlational Image Modeling for Self-Supervised Visual Pre-Training
Li, W., Xie, J., & Loy, C. C. (2023) · 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/cvpr52729.2023.01450 · Cited by 20
Relation Learning Reasoning Meets Tiny Object Tracking in Satellite Videos
Yang, X., Jiao, L., Li, Y., Liu, X., Liu, F., Li, L., Chen, P., & Yang, S. (2024) · IEEE Transactions on Geoscience and Remote Sensing · doi:10.1109/tgrs.2024.3376669 · Cited by 20
“Correlation filter-based approaches have emerged since the proposition of MOOSE [37] and DCF [38], it achieves very promising results.”
MethodObject Detection and Tracking based on Recurrent Neural Networks
Zhang, Y., Ming, Y., & Zhang, R. (2018) · International Conference on Signal Processing · doi:10.1109/icsp.2018.8652389 · Cited by 17
“The tracking approaches based on Discriminative Correlation Filter (DCF) [16], including KCF [17], DeepSRDCF [18], C-COT [19] and ECO [20], learn a correlation filter to discriminate between the target and background appearance.”
MethodApplication of gcForest to visual tracking using UAV image sequences
Liu, F., & Anzhe, 杨. Y. (2019) · Multimedia Tools and Applications · doi:10.1007/s11042-019-07864-y · Cited by 15
“The tracking method based on correlation filtering really led the pace of tracking field last year, [5, 7, 26, 32, 40, 47] using a variety of correlation filtering improvements to improve the tracking speed and accuracy, indeed achieved the better performance.”
MethodKernel-Correlated Filtering Target Tracking Algorithm Based on Multi-Features Fusion
Yan, H., Xie, M., Wang, P., Zhang, Y., & Luo, C. (2019) · IEEE Access · doi:10.1109/access.2019.2921581 · Cited by 14
Visual object tracking with discriminative correlation filtering and hybrid color feature
Huang, Y., Zhao, Z., Wu, B., Mei, Z., Cui, Z., & Gao, G. (2019) · Multimedia Tools and Applications · doi:10.1007/s11042-019-07901-w · Cited by 14
“For example, gray feature [2, 16] is a common feature for visual object tracking.”
BackgroundVisual Object Tracking via Guessing and Matching
Song, K., Zhang, W., Lu, W., Zha, Z.-J., Ji, X., & Li, Y. (2019) · IEEE Transactions on Circuits and Systems for Video Technology · doi:10.1109/tcsvt.2019.2948600 · Cited by 14
“efficiency and competitive performance [4]–[7].”
SLAM-Based Multistate Tracking System for Mobile Human-Robot Interaction
Hempel, T., & Al-Hamadi, A. K. (2020) · Lecture notes in computer science · doi:10.1007/978-3-030-50347-5_32 · Cited by 14
Long-term target tracking combined with re-detection
Wang, J., Yang, H., Xu, N., Wu, C., Zhao, Z., Zhang, J., & Wu, D. O. (2021) · EURASIP Journal on Advances in Signal Processing · doi:10.1186/s13634-020-00713-3 · Cited by 15
“In the past few decades, the visual object tracking technology has made significant progress [1] [2] [3] [4] [5] [6] [7] [8] [9] [10].”
BackgroundMethodEACOFT: An energy-aware correlation filter for visual tracking
Liu, Q., Ren, J., Wang, Y., Wu, Y., Sun, H., & Zhao, H. (2020) · Pattern Recognition · doi:10.1016/j.patcog.2020.107766 · Cited by 14
“Experiments show that CF can effectively improve the accuracy and robustness of visual tracking [4],[14],[15].”
MethodLow-Cost, Computer Vision-Based, Prebloom Cluster Count Prediction in Vineyards
Jaramillo, J., Heuvel, J. E. V., & Petersen, K. H. (2021) · Frontiers in Agronomy · doi:10.3389/fagro.2021.648080 · Cited by 14
Liu, B., Chang, X., Yuan, D., & Yang, Y. (2021) · Knowledge-Based Systems · doi:10.1016/j.knosys.2021.107913 · Cited by 14
Two-stage multiple object detection using CNN and correlative filter for accuracy improvement
Kinasih, F. M. T. R., Machbub, C., Yulianti, L., & Rohman, A. S. (2023) · Heliyon · doi:10.1016/j.heliyon.2022.e12716 · Cited by 14
“A combination of MobileNet-SSD for object detection and KCF or MOSSE for object tracking was considered here.”
MethodReal-Time Robust Tracking for Motion Blur and Fast Motion via Correlation Filters
Xu, L., Luo, H., Hui, B., & Chang, Z. (2016) · Sensors · doi:10.3390/s16091443 · Cited by 15
“[12] to reap the appearance model of target.”
BackgroundTian, W., Chen, L. F., Zou, K., & Lauer, M. (2017) · IEEE Transactions on Intelligent Transportation Systems · doi:10.1109/tits.2017.2771410 · Cited by 15
“Leveraging the strength of structured SVMs, the correlation filter (CF) [19], [20] has”
BackgroundRemove Cosine Window From Correlation Filter-Based Visual Trackers: When and How
Li, F., Wu, X., Zuo, W., Zhang, D. D., & Zhang, L. (2020) · IEEE Transactions on Image Processing · doi:10.1109/tip.2020.2997521 · Cited by 14
“Since the pioneering work of MOSSE [1], many improvements have been made to CF trackers.”
BackgroundMethodInfluentialMaximum Margin Vector Correlation FilterPreprint
Boddeti, V. N., & Kumar, B. V. K. V. (2014) · arXiv (Cornell University) · doi:10.48550/arxiv.1404.6031 · Cited by 14
“Towards this end many CF designs [19][4][3], all of them assuming scalar features at every pixel, have been proposed which minimize the Mean Square Error (MSE) between the ideal desired correlation output for a true-class (or false-class) input image and the cross-correlation output of the training images with the fil…”
BackgroundCorrelation Filters Based on Strong Spatio-Temporal for Robust RGB-T Tracking
Luo, F., Zhou, M., & Fang, B. (2021) · Journal of Circuits Systems and Computers · doi:10.1142/s0218126622500414 · Cited by 13
UStark: underwater image domain-adaptive tracker based on Stark
Li, Y., Huo, W., Liu, Z., Wang, B., & Li, Y. (2022) · Journal of Electronic Imaging · doi:10.1117/1.jei.31.5.053012 · Cited by 13
“Blue (20) Yellow (7) Bright (7) Dark (11) Seabed (14) Green (13) Sea-desert (10) Cyan (11) Clear (13)”
Gravity Matching Algorithm Based on Correlation Filter
Zhao, S., Xiao, X., Deng, Z., & Shi, L. (2022) · IEEE Sensors Journal · doi:10.1109/jsen.2022.3228559 · Cited by 13
A Quantum Evolutionary Learning Tracker for Video
Zhang, R., Jiao, L., Li, L., Liu, X., Liu, F., & Yang, S. (2023) · IEEE Transactions on Evolutionary Computation · doi:10.1109/tevc.2023.3264641 · Cited by 14
Natural surface floaters in image-based river surface velocimetry: Insights from a case study
Trieu, H., Bergström, P., Sjödahl, M., Hellström, J. G. I., Andreasson, P., & Lycksam, H. (2024) · Flow Measurement and Instrumentation · doi:10.1016/j.flowmeasinst.2024.102557 · Cited by 13
Dynamic region-aware transformer backbone network for visual tracking
Wang, J., Yang, S., & Wang, Y. (2024) · Engineering Applications of Artificial Intelligence · doi:10.1016/j.engappai.2024.108329 · Cited by 15
Single target tracking in high-resolution satellite videos: a comprehensive review
Huang, X., Wang, D., Zhu, Q., Zheng, Y. F., & Guan, Q. (2024) · Geo-spatial Information Science · doi:10.1080/10095020.2024.2305912 · Cited by 15
“KCF (Henriques et al. 2014) is a classic approach as an extension to MOSSE (Bolme et al. 2010).”
Learning Deconvolutional Network for Object Tracking
Lu, X., Huo, H., Fang, T., & Zhang, H. (2018) · IEEE Access · doi:10.1109/access.2018.2820004 · Cited by 14
“The most representative approach is correlation filter based trackers [12], [41]–[44].”
BackgroundMulti-view correlation tracking with adaptive memory-improved update model
Li, G., Peng, M., Nai, K., Li, Z., & Li, K. (2019) · Neural Computing and Applications · doi:10.1007/s00521-019-04413-4 · Cited by 14
Real-time visual tracking using complementary kernel support correlation filters
Su, Z., Li, J., Chang, J., Du, B., & Xiao, Y. (2019) · Frontiers of Computer Science · doi:10.1007/s11704-018-8116-1 · Cited by 13
“Most CF based trackers [29, 30, 33, 36] use ridge regression or kernel ridge regression as predictors, and some recently proposed works [23, 25, 28] exploit the circulant property of dense samples to accelerate SVM based trackers.”
MethodSE-IYOLOV3: An Accurate Small Scale Face Detector for Outdoor Security
Deng, Z., Yang, R., Lan, R., Liu, Z., & Luo, X. (2020) · Mathematics · doi:10.3390/math8010093 · Cited by 17
“For example, the PCA method [6] is used to extract facial features; serial and parallel methods are used to combine the extracted facial features [7]; and the LBP pattern is widely used for face recognition [8–10].”
MethodPart alignment network for vehicle re-identification
Chen, Y., Ma, B., & Chang, H. (2020) · Neurocomputing · doi:10.1016/j.neucom.2020.08.016 · Cited by 13
Xu, X., Li, X., Zhao, H., Liu, M., Xu, A., & Ma, Y. (2021) · Measurement · doi:10.1016/j.measurement.2021.109386 · Cited by 14
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
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.