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 301–400 of 1,002
Deep Learning-Based Object Tracking in Satellite Videos: A comprehensive survey with a new dataset
Li, Y., Jiao, L., Huang, Z., Zhang, X., Zhang, R., Song, X., Tian, C., Zhang, Z., Liu, F., Yang, S., et al. (2022) · IEEE Geoscience and Remote Sensing Magazine · doi:10.1109/mgrs.2022.3198643 · Cited by 68
“MOSSE [35] successfully brings the correlation into the visual tracking study and makes CF-based tracking with multiple samples learning.”
MethodInfluentialIMAGING: In-Memory AlGorithms for Image processiNG
Haj-Ali, A., Ben-Hur, R., Wald, N., Ronen, R., & Kvatinsky, S. (2018) · IEEE Transactions on Circuits and Systems I Regular Papers · doi:10.1109/tcsi.2018.2846699 · Cited by 70
“, visual tracking, data compression and fast Fourier transform [25], [26].”
MethodReal-Time Drowsiness Detection Algorithm for Driver State Monitoring Systems
Baek, J.-W., Han, B.-G., Kim, K., Chung, Y.-S., & Lee, S. I. (2018) · International Conference on Ubiquitous and Future Networks · doi:10.1109/icufn.2018.8436988 · Cited by 63
“And we use Correlation Filter in order to improve the reliability of the face detection [7].”
MethodLuo, C., Sun, B., Yang, K., Lu, T., & Yeh, W. (2019) · Infrared Physics & Technology · doi:10.1016/j.infrared.2019.04.017 · Cited by 67
Multi-Correlation Filters With Triangle-Structure Constraints for Object Tracking
Ruan, W., Chen, J., Wu, Y., Wang, J., Liang, C., Hu, R., & Jiang, J. (2019) · IEEE Transactions on Multimedia · doi:10.1109/tmm.2018.2872897 · Cited by 66
“By exploiting the global and local appearances of the target to construct multiple CFs, the target location is estimated using the filters to jointly measure the correlation responses of the holistic candidate and its local parts within a search window over time, as shown in Fig.”
BackgroundMethodInfluentialSpatially Attentive Visual Tracking Using Multi-Model Adaptive Response Fusion
Zhang, J., Wu, Y. D., Feng, W., & Wang, J. (2019) · IEEE Access · doi:10.1109/access.2019.2924944 · Cited by 63
“Minimum the output sum of squared error (MOSSE) algorithm [23], proposed by Bolme et al.”
MethodAD-VAT+: An Asymmetric Dueling Mechanism for Learning and Understanding Visual Active Tracking
Zhong, F., Sun, P., Luo, W., Yan, T., & Wang, Y. (2019) · IEEE Transactions on Pattern Analysis and Machine Intelligence · doi:10.1109/tpami.2019.2952590 · Cited by 82
“, [1], [2], [3], [4], [5], [6] aims to solely propose a 2D bounding box of the target frame by frame, and does not actively take into consideration the camera-control.”
BackgroundSpatio-Temporal Semantic Segmentation for Drone Detection
Craye, C., & Ardjoune, S. (2019) · IEEE International Conference on Advanced Video and Signal Based Surveillance (AVSS) · doi:10.1109/avss.2019.8909854 · Cited by 62
“To this end, we turn the detections into tracks: for each bounding box Bi(t) at time t, we apply a MOSS tracking algorithm [2] to predict the position of the box in the frame at time t + 1.”
MethodMutation Sensitive Correlation Filter for Real-Time UAV Tracking with Adaptive Hybrid Label
Zheng, G., Fu, C., Ye, J., Lin, F., & Ding, F. (2021) · Proceedings - IEEE International Conference on Robotics and Automation/Proceedings · doi:10.1109/icra48506.2021.9561931 · Cited by 70
“[10] took the advantage of the peak to sidelobe ratio (PSR) for failure detection.”
BackgroundMethodStudy on Automatic Tracking System of Microwave Deicing Device for Railway Contact Wire
Du, G., Zhang, H., Yu, H., Peng, H., He, J., Cao, S., Wang, G., & Ma, L. (2024) · IEEE Transactions on Instrumentation and Measurement · doi:10.1109/tim.2024.3446638 · Cited by 75
“Bolme et al. [10] proposed a correlation filter tracking method based on deformable parts, which based on the coupling between the global filter and multiple partial filters.”
MethodFast RGB-T Tracking via Cross-Modal Correlation Filters
Zhai, S., Shao, P., Liang, X., & Wang, X. (2019) · Neurocomputing · doi:10.1016/j.neucom.2019.01.022 · Cited by 68
Cost-effective, Energy-efficient, and Scalable Storage Computing for Large-scale AI Applications
Do, J., Ferreira, V. C., Bobarshad, H., Torabzadehkashi, M., Rezaei, S., HeydariGorji, A., Souza, D., Goldstein, B. F., Santiago, L., Kim, M. S., et al. (2020) · ACM Transactions on Storage · doi:10.1145/3415580 · Cited by 71
“This enables, for example, tracking multiple objects of interest in a given scene, which is crucial for autonomous systems such as self-driving vehicles [6, 21, 31, 33, 34, 46, 65, 85].”
BackgroundMethodDeep Reinforcement Learning with Iterative Shift for Visual Tracking
Ren, L., Yuan, X., Lu, J., Yang, M., & Zhou, J. (2018) · Lecture notes in computer science · doi:10.1007/978-3-030-01240-3_42 · Cited by 64
“Then, the observation model may be evaluated on hundreds of these locations, as a correlation filtering in MOSSE [5] and KCF [20], or as a discriminative classification [11] or regression problem [16], which is demanding in computation.”
BackgroundMethodLearning target-focusing convolutional regression model for visual object tracking
Yuan, D., Fan, N., & He, Z. (2020) · Knowledge-Based Systems · doi:10.1016/j.knosys.2020.105526 · Cited by 62
Perry, B. J., & Guo, Y. (2021) · Measurement · doi:10.1016/j.measurement.2021.109222 · Cited by 61
Recent advances of target tracking applications in aquaculture with emphasis on fish
Mei, Y., Sun, B., Li, D., Yu, H., Qin, H., Liu, H., Yan, N., & Chen, Y. (2022) · Computers and Electronics in Agriculture · doi:10.1016/j.compag.2022.107335 · Cited by 64
Robust Shadow Tracking for Video SAR
Zhao, B., Han, Y., Wang, H., Tang, L., Liu, X., & Wang, T. (2020) · IEEE Geoscience and Remote Sensing Letters · doi:10.1109/lgrs.2020.2988165 · Cited by 63
“Minimum Output Sum of Squared Error (MOSSE) [14] is the pioneering work of DCF, which achieves a relatively good performance at a very high frame-rate (over 600 frames/s).”
BackgroundCollaborative Correlation Tracking
Zhu, G., Wang, J., Wu, Y., & Lu, H. (2015) · British Machine Vision Conference (BMVC) · doi:10.5244/c.29.184 · Cited by 64
“Person’s Correlation) by Galton in 1888 [5], it has been adopted to solve various computer vision problems, such as object detection and recognition [12, 20], pose detection [13], and object tracking [3].”
BackgroundMethodInfluentialIntelligent Cinematography: a review of AI research for cinematographic production
Azzarelli, A., Anantrasirichai, N., & Bull, D. (2025) · Artificial Intelligence Review · doi:10.1007/s10462-024-11089-3 · Cited by 63
Real-time tracking of low-resolution vehicles for wide-area persistent surveillance
Keck, M. A., Galup, L., & Stauffer, C. (2013) · Proceedings · doi:10.1109/wacv.2013.6475052 · Cited by 60
“In addition to the stitched imagery, the on-board system also provides metadata containing information like the GPS and INS gimbal information during image capture as well as the velocity and heading of the aircraft.”
BackgroundMulti-Object Tracking with Correlation Filter for Autonomous Vehicle
Zhao, D., Fu, H., Xiao, L., Wu, T., & Dai, B. (2018) · Sensors · doi:10.3390/s18072004 · Cited by 57
“Since the seminal work in [38], CF has made great progress, and most state-of-the-art CF trackers have begun to use deep CNN features [18].”
BackgroundSiamVGG: Visual Tracking using Deeper Siamese NetworksPreprint
Li, Y., Zhang, X., & Chen, D. (2019) · arXiv (Cornell University) · doi:10.48550/arxiv.1902.02804 · Cited by 76
“One typical example is a tracker called MOSSE [8], which can process up to 700 frames per second but it fails to provide acceptable accuracy and requires additional hand-crafted features to recognize the targeted object.”
BackgroundRecent Advances in Intelligent Processing of Satellite Video: Challenges, Methods, and Applications
Li, S., Sun, X., Gu, Y., Lv, Y., Zhao, M., Zhou, Z., Guo, W., Sun, Y., Wang, H., & Yang, J. B. (2023) · IEEE Journal of Selected Topics in Applied Earth Observations and Remote Sensing · doi:10.1109/jstars.2023.3296451 · Cited by 62
“criminative correlation filtering methods [23], [24], [25], [26] are the most representative.”
MethodQuantification of Esophageal Tumor Motion on Cine-Magnetic Resonance Imaging
Lever, F. M., Lips, I. M., Crijns, S. P. M., Reerink, O., van Lier, A. L. H. M. W., Moerland, M. A., van Vulpen, M., & Meijer, G. J. (2013) · International Journal of Radiation Oncology*Biology*Physics · doi:10.1016/j.ijrobp.2013.10.036 · Cited by 59
Visual Tracking via Spatially Aligned Correlation Filters Network
Zhang, M., Wang, Q., Xing, J., Gao, J. G., Peng, P., Hu, W., & Maybank, S. (2018) · Lecture notes in computer science · doi:10.1007/978-3-030-01219-9_29 · Cited by 59
“[3] introduced the CF into the visual tracking field, several extensions have been proposed to improve the tracking performance.”
BackgroundSea Mining Exploration With an UVMS: Experimental Validation of the Control and Perception Framework
Simetti, E., Campos, R., Vito, D. D., Quintana, J., Antonelli, G., García, R., & Turetta, A. (2020) · IEEE/ASME Transactions on Mechatronics · doi:10.1109/tmech.2020.3025973 · Cited by 58
Zhang, J., Liu, Y., Liu, H., & Wang, J. (2021) · Sensors · doi:10.3390/s21041129 · Cited by 58
“In recent years, discriminative correlation filter (DCF)-based trackers [5–7] have gained more and more attention from researchers due to their excellent performance.”
BackgroundMethodMulti-Features Integration Based Hyperspectral Videos Tracker
Zhang, Z., Qian, K., Du, J., & Zhou, H. (2021) · Workshop on Hyperspectral Image and Signal Processing: Evolution in Remote Sensing · doi:10.1109/whispers52202.2021.9484029 · Cited by 67
“Several popular algorithms contains the Minimum Output Sum of Squared Error Filter (MOSSE) tracker [3], Kernelized Correlation Filter (KCF) [4] and Spatial-Temporal Context (STC) [5].”
BackgroundMethodLin, W., Zhang, Y., Lu, J., Zhou, B., Wang, J., & Zhou, Y. (2014) · Neurocomputing · doi:10.1016/j.neucom.2014.12.044 · Cited by 58
“Although many tracking algorithms have been proposed [7–10,12,16,37], their performances are still less satisfactory due to the interferences from object occlusion or complex background.”
BackgroundReal-Time Correlation Tracking Via Joint Model Compression and Transfer
Wang, N., Zhou, W., Song, Y., Ma, C., & Li, H. (2020) · IEEE Transactions on Image Processing · doi:10.1109/tip.2020.2989544 · Cited by 62
“Correlation filters have been widely studied in visual tracking since the MOSSE method [3] was proposed by Bolme et al.”
MethodADTrack: Target-Aware Dual Filter Learning for Real-Time Anti-Dark UAV Tracking
Li, B., Fu, C., Ding, F., Ye, J., & Lin, F. (2021) · Proceedings - IEEE International Conference on Robotics and Automation/Proceedings · doi:10.1109/icra48506.2021.9561564 · Cited by 70
“Among various tracking methods, CF-based trackers [15]– [17] are popular mainly relying on: a) their fast element-wise product in Fourier domain, b) online trained filters which are favorably adaptive when object appearance undergoes abrupt variation.”
BackgroundMethodJoint Scale-Spatial Correlation Tracking with Adaptive Rotation Estimation
Zhang, M., Xing, J., Gao, J. G., Shi, X., Wang, Q., & Hu, W. (2015) · IEEE International Conference on Computer Vision Workshops · doi:10.1109/iccvw.2015.81 · Cited by 61
Particle filter re-detection for visual tracking via correlation filters
Yuan, D., Lu, X., Li, D., Liang, Y., & Zhang, X. (2018) · Multimedia Tools and Applications · doi:10.1007/s11042-018-6800-0 · Cited by 59
“Bolme et al. [9] introduced an adaptive correlation filter by minimizing the output sum of the squared error to make the tracking strategy simpler and more effective.”
BackgroundMethodInfluentialInfrared target tracking via weighted correlation filter
He, Y., Li, M., Zhang, J., & Yao, J. (2015) · Infrared Physics & Technology · doi:10.1016/j.infrared.2015.09.010 · Cited by 60
Convolutional Regression for Visual Tracking
Chen, K., & Tao, W. (2018) · IEEE Transactions on Image Processing · doi:10.1109/tip.2018.2819362 · Cited by 57
MFT: Long-Term Tracking of Every Pixel
Neoral, M., Šerých, J., & Matas, J. (2024) · IEEE Winter Conference on Applications of Computer Vision · doi:10.1109/wacv57701.2024.00669 · Cited by 85
“Historically, object tracking algorithms [3, 14, 31] estimated the location of an object spec-1 ified in the first frame by a bounding box output in every frame of the video sequence.”
BackgroundReal-time and robust object tracking in video via low-rank coherency analysis in feature space
Chen, C., Li, S., Qin, H., & Hao, A. (2015) · Pattern Recognition · doi:10.1016/j.patcog.2015.01.025 · Cited by 56
“Meanwhile, global tracking criteria derived from all previous frames are oftentimes used to facilitate current-frame tracking [22,23].”
BackgroundTrackingNet: A Large-Scale Dataset and Benchmark for Object Tracking in the WildPreprint
Müller, M., Bibi, A., Giancola, S., Alsubaihi, S., & Ghanem, B. (2018) · arXiv (Cornell University) · doi:10.48550/arxiv.1803.10794 · Cited by 160
“Also, the remarkable runtime performance is achieved by efficiently solving the underlying ridge regression problem in the Fourier domain [23].”
BackgroundMethodInfluentialLSOTB-TIR: A Large-Scale High-Diversity Thermal Infrared Single Object Tracking Benchmark
Liu, Q., Li, X., Yuan, D., Yang, C., Chang, X., & He, Z. (2023) · IEEE Transactions on Neural Networks and Learning Systems · doi:10.1109/tnnls.2023.3236895 · Cited by 61
Yang, L., Li, E., Long, T., Fan, J., & Liang, Z. (2018) · IEEE Sensors Journal · doi:10.1109/jsen.2018.2867581 · Cited by 55
“Here, the DCF and MOOSE algorithms are set as comparison experiments to verify the performance of KCF algorithm.”
MethodInfluentialBridging the Gap Between Detection and Tracking: A Unified Approach
Huang, L., Zhao, X., & Huang, K. (2019) · 2019 IEEE/CVF International Conference on Computer Vision (ICCV) · doi:10.1109/iccv.2019.00410 · Cited by 52
“, UMACE [41] and ASEF [6]) and later improved and adapted for tracking [5, 22, 23, 9, 8].”
BackgroundZhu, X., Wu, X., Xu, T., Feng, Z., & Kittler, J. (2020) · IEEE Transactions on Circuits and Systems for Video Technology · doi:10.1109/tcsvt.2020.2979480 · Cited by 60
“The pioneering solutions favoured plain models, for instance using grayscale features [11], [12],”
MethodSiamAtt: Siamese attention network for visual tracking
Yang, K., He, Z., Zhou, Z., & Fan, N. (2020) · Knowledge-Based Systems · doi:10.1016/j.knosys.2020.106079 · Cited by 59
“MOSSE tracker [7] converts complex convolution into element-wise multiplications by Fourier transform, which achieves a tracking speed of 700 frames per second.”
Real-Time Scalable Visual Tracking via Quadrangle Kernelized Correlation Filters
Ding, G., Chen, W., Zhao, S., Han, J., & Liu, Q. (2018) · IEEE Transactions on Intelligent Transportation Systems · doi:10.1109/tits.2017.2774778 · Cited by 54
“Zhang et al. [10] changed the Gaussian function in MOSSE to a Bayesian framework such that the contextual information can be incorporated into the filter learning.”
BackgroundMethodInfluentialAn Overview of Correlation-Filter-Based Object Tracking
Du, S., & Wang, S. (2021) · IEEE Transactions on Computational Social Systems · doi:10.1109/tcss.2021.3093298 · Cited by 57
ReCF: Exploiting Response Reasoning for Correlation Filters in Real-Time UAV Tracking
Lin, F., Fu, C., He, Y., Xiong, W., & Li, F. (2021) · IEEE Transactions on Intelligent Transportation Systems · doi:10.1109/tits.2021.3094654 · Cited by 56
When Correlation Filters Meet Convolutional Neural Networks for Visual Tracking
Ma, C., Xu, Y. X., Ni, B., & Yang, X. (2016) · IEEE Signal Processing Letters · doi:10.1109/lsp.2016.2601691 · Cited by 53
“We multiply each input feature channel by a cosine window [4], which helps not only to remove the boundary discontinuities of learning correlation filters, but also accelerate the convergence of the CNN model.”
BackgroundMethodAdaptive Discriminative Deep Correlation Filter for Visual Object Tracking
Han, Z., Wang, P., & Ye, Q. (2018) · IEEE Transactions on Circuits and Systems for Video Technology · doi:10.1109/tcsvt.2018.2888492 · Cited by 53
“Frequency domain calculation [9], kernel function [5], [6],”
BackgroundInfluentialObject Tracking in Hyperspectral-Oriented Video with Fast Spatial-Spectral Features
Chen, L., Zhao, Y., Yao, J., Chen, J., Li, N., Chan, J. C.-W., & Kong, S. G. (2021) · Remote Sensing · doi:10.3390/rs13101922 · Cited by 55
“[40] has been extended to many variants such as kernel correlation filters [41,42], long-term memory [43–45], multi-dimensional features [46,47], part-based strategies [48–50], scale es-”
BackgroundMethodMulti-modal visual tracking: Review and experimental comparison
Zhang, P., Wang, D., & Lu, H. (2024) · Computational Visual Media · doi:10.1007/s41095-023-0345-5 · Cited by 61
“In RGB tracking, several frameworks including Kalman filter (KF) [12, 13], particle filter (PF) [14, 15], sparse learning (SL) [16, 17], correlation filter (CF) [18, 19], and CNN [20, 21] have been involved to improve the tracking accuracy and speed.”
Gündoğdu, E., Koç, A., Solmaz, B., Hammoud, R. I., & Alatan, A. A. (2016) · IEEE/CVF Conference on Computer Vision and Pattern Recognition Workshops (CVPRW) · doi:10.1109/cvprw.2016.43 · Cited by 56
“State-of-theart methods such as support vector machines [17], sparse dictionary-based learning [3, 30, 27], saliency-based approaches [40] and correlation filters [5, 10, 18] have been applied in an online fashion for object tracking.”
BackgroundMethodInfluentialCorrelation Filter Learning Toward Peak Strength for Visual Tracking
Sui, Y., Wang, G., & Zhang, L. (2017) · IEEE Transactions on Cybernetics · doi:10.1109/tcyb.2017.2690860 · Cited by 58
“Recently, there is a significant interest in developing correlation filtering [3] based visual trackers.”
BackgroundMethodInfluentialDense structural learning for infrared object tracking at 200+ Frames per Second
Yu, X., Yu, Q., Shang, Y., & Zhang, H. (2017) · Pattern Recognition Letters · doi:10.1016/j.patrec.2017.10.026 · Cited by 53
Feature Alignment and Aggregation Siamese Networks for Fast Visual Tracking
Fan, J., Song, H., Zhang, K., Yang, K., & Liu, Q. (2020) · IEEE Transactions on Circuits and Systems for Video Technology · doi:10.1109/tcsvt.2020.2987601 · Cited by 54
“MOSSE [24], KCF [2], DSST [25], Staple [26], BACF [27].”
MethodGündoğdu, E., Özkan, H., Demir, H. S., Ergezer, H., Akagündüz, E., & Pakin, S. K. (2015) · IEEE/CVF Conference on Computer Vision and Pattern Recognition Workshops (CVPRW) · doi:10.1109/cvprw.2015.7301290 · Cited by 59
“For this reason, template based correlator trackers [4,10] are included in our comparative study due to their impressively efficient implementations.”
BackgroundMethodHistograms of oriented mosaic gradients for snapshot spectral image description
Chen, L., Zhao, Y., Chan, J. C.-W., & Kong, S. G. (2021) · ISPRS Journal of Photogrammetry and Remote Sensing · doi:10.1016/j.isprsjprs.2021.10.018 · Cited by 55
Visual Object Tracking in First Person Vision
Dunnhofer, M., Furnari, A., Farinella, G. M., & Micheloni, C. (2022) · International Journal of Computer Vision · doi:10.1007/s11263-022-01694-6 · Cited by 64
“Specifically, in the analysis we have included shortterm trackers [71] based on both correlation-filters with handcrafted features (MOSSE [11], DSST [24], KCF [47], Staple [6], BACF [53], DCFNet [103], STRCF [61], MCCTH [101]) and deep features (ECO [22], ATOM [23], DiMP [9], PrDiMP [25], KYS [10], KeepTrack [75]).”
BackgroundMethodInfluentialTemplate-guided frequency attention and adaptive cross-entropy loss for UAV visual tracking
Xue, Y., Guodong, J. I. N., Tao, S. H. E. N., Tan, L., & Lianfeng, W. A. N. G. (2023) · Chinese Journal of Aeronautics · doi:10.1016/j.cja.2023.03.048 · Cited by 53
Infrared Small Target Tracking Algorithm via Segmentation Network and Multistrategy Fusion
Kou, R., Wang, C., Yu, Y. K., Peng, Z., Huang, F., & Fu, Q. (2023) · IEEE Transactions on Geoscience and Remote Sensing · doi:10.1109/tgrs.2023.3286836 · Cited by 61
Real-Time Visual Tracking: Promoting the Robustness of Correlation Filter Learning
Sui, Y., Zhang, Z., Wang, G., Tang, Y., & Zhang, L. (2016) · Lecture notes in computer science · doi:10.1007/978-3-319-46484-8_40 · Cited by 59
“Recently, correlation filtering [1] has received much attention in visual tracking.”
BackgroundReal-Time Long-Term Tracking With Prediction-Detection-Correction
Liang, N., Wu, G., Kang, W., Wang, Z., & Feng, D. D. (2018) · IEEE Transactions on Multimedia · doi:10.1109/tmm.2018.2803518 · Cited by 54
Soft Facial Landmark Detection by Label Distribution Learning
Su, K., & Geng, X. (2019) · Proceedings of the AAAI Conference on Artificial Intelligence · doi:10.1609/aaai.v33i01.33015008 · Cited by 54
“, Logistic Regression (LR) (Saragih, Lucey, and Cohn 2011), Minimum Output Sum of Squared Errors (MOSSE) filters (Bolme et al. 2010).”
MethodRobust Visual Detection and Tracking Strategies for Autonomous Aerial Refueling of UAVs
Sun, S., Yin, Y., Wang, X., & Xu, D. (2019) · IEEE Transactions on Instrumentation and Measurement · doi:10.1109/tim.2019.2899476 · Cited by 55
Lan, K.-C., & Litscher, G. (2019) · Medicines · doi:10.3390/medicines6030087 · Cited by 55
“proposed the minimum output sum of squared error (MOSSE) based on the correlation filter [20].”
MethodFu, C., Ye, J., Xu, J., He, Y., & Lin, F. (2020) · IEEE Transactions on Geoscience and Remote Sensing · doi:10.1109/tgrs.2020.3030265 · Cited by 55
“[24], the DCF-based approaches have made great progress.”
BackgroundAberrance suppressed spatio-temporal correlation filters for visual object tracking
Elayaperumal, D., & Joo, Y. H. (2021) · Pattern Recognition · doi:10.1016/j.patcog.2021.107922 · Cited by 52
Real-Time Event-Triggered Object Tracking in the Presence of Model Drift and Occlusion
Guan, M., Wen, C., Shan, M., Ng, C.-L., & Zou, Y. Y. (2018) · IEEE Transactions on Industrial Electronics · doi:10.1109/tie.2018.2835390 · Cited by 54
“[2] initially apply the correlation filter to visual tracking by minimizing the total”
MethodMulti-object tracking with discriminant correlation filter based deep learning tracker
Yang, T., Cappelle, C., Ruichek, Y., & Bagdouri, M. E. (2019) · Integrated Computer-Aided Engineering · doi:10.3233/ica-180596 · Cited by 54
DeepPlayer-Track: Player and Referee Tracking With Jersey Color Recognition in Soccer
Naik, B. T., Hashmi, M. F., Geem, Z. W., & Bokde, N. D. (2022) · IEEE Access · doi:10.1109/access.2022.3161441 · Cited by 55
Detection and Tracking in Thermal Infrared Imagery
Berg, A. (2016) · Linköping University Electronic Press eBooks · doi:10.3384/lic.diva-126955 · Cited by 61
“A complete derivation is given in Bolme et al. (2010).”
BackgroundMethodInfluentialLiu, X., Yang, Y., Ma, C., Li, J., & Zhang, S. (2020) · Applied Sciences · doi:10.3390/app10155064 · Cited by 61
“[40] presented a minimum output sum of squared error (MOSSE) filter, which produced stable correlation filters when initialized using a single frame.”
Latent Constrained Correlation Filter
Zhang, B., Luan, S., Chen, C., Han, J., Wang, W., Perina, A., & Shao, L. (2017) · IEEE Transactions on Image Processing · doi:10.1109/tip.2017.2775060 · Cited by 50
A multiple feature fused model for visual object tracking via correlation filters
Yuan, D., Zhang, X., Liu, J., & Li, D. (2019) · Multimedia Tools and Applications · doi:10.1007/s11042-019-07828-2 · Cited by 50
“[7] propose the MOSSE tracker, correlation filters have been studied as a robust and”
Yang, J., Pan, Z., Wang, Z., Lei, B., & Hu, Y. (2023) · IEEE Transactions on Geoscience and Remote Sensing · doi:10.1109/tgrs.2023.3271645 · Cited by 56
Detecting and tracking all moving objects in wide-area aerial video
Pollard, T., & Antone, M. E. (2012) · 2009 IEEE Computer Society Conference on Computer Vision and Pattern Recognition Workshops · doi:10.1109/cvprw.2012.6239201 · Cited by 50
“Wide-area coverage, minimum resolution, and a moving sensor all create unique challenges, particularly when objects to be detected and tracked include pedestrians as well as vehicles.”
BackgroundSpatial-Temporal Context-Aware Tracking
Han, Y., Deng, C., Zhao, B., & Zhao, B. (2019) · IEEE Signal Processing Letters · doi:10.1109/lsp.2019.2895962 · Cited by 50
“To evaluate the effectiveness and robustness of the proposed STCAT framework, we validate it with five popular DCF based trackers (MOSSE [31], DCF [9], DSST [15], SAMF [32] and Staple [33]) and denote them as MOSSE-STCA, DCF-STCA, DSST-STCA, SAMF-STCA and Staple-STCA respectively.”
MethodRobust Visual Tracking via Constrained Multi-Kernel Correlation Filters
Huang, B., Xu, T., Jiang, S., Chen, Y., & Bai, Y. (2020) · IEEE Transactions on Multimedia · doi:10.1109/tmm.2020.2965482 · Cited by 51
“We employ 1-channel gray, 10-channel CN [5], 31-channel HOG [35] features, and the total 42-channel features are then multiplied by a Hann window [4] to enhance the robustness.”
Methodde Oliveira, Í. O., Laroca, R., Menotti, D., Fonseca, K. V. O., & Minetto, R. (2021) · IEEE Access · doi:10.1109/access.2021.3097964 · Cited by 50
“Therefore, in order to have more matching pairs, we used the MOSSE algorithm [55] to track a vehicle for m consecutive frames, and only for the matching pairs we used all its m frame occurrences to create new matching pairs.”
MethodDistractor-aware visual tracking using hierarchical correlation filters adaptive selection
Zhang, J., Liu, Y., Liu, H., Wang, J., & Zhang, Y. (2021) · Applied Intelligence · doi:10.1007/s10489-021-02694-8 · Cited by 50
“Bolme et al. proposed the Minimum Output Sum of Square Error (MOSSE) algorithm in 2010 [22], and introduced correlation filters into visual object tracking for the first time.”
MethodLearning residue-aware correlation filters and refining scale for real-time UAV tracking
Li, S., Liu, Y., Zhao, Q., & Feng, Z. (2022) · Pattern Recognition · doi:10.1016/j.patcog.2022.108614 · Cited by 54
Li, Y., Bian, C., & Chen, H. (2022) · IEEE Transactions on Geoscience and Remote Sensing · doi:10.1109/tgrs.2022.3204105 · Cited by 59
“squared error filter (MOSSE) [22] achieved a remarkable 112”
BackgroundRotation adaptive correlation filter for moving object tracking in satellite videos
Xuan, S., Li, S., Zhao, Z., Zhou, Z., Zhang, W., Tan, H., Xia, G.-S., & Gu, Y. (2021) · Neurocomputing · doi:10.1016/j.neucom.2021.01.058 · Cited by 51
Liu, Z., Zhong, Y., Wang, X., Shu, M., & Zhang, L. (2021) · IEEE Transactions on Geoscience and Remote Sensing · doi:10.1109/tgrs.2021.3111183 · Cited by 62
“1) Discriminative Correlation Filtering: DCF-based trackers are the most representative algorithms among the non-deep learning target tracking algorithms.”
MethodInfluentialChen, W., Zhang, K., & Liu, Q. (2016) · Neurocomputing · doi:10.1016/j.neucom.2016.06.048 · Cited by 49
Object Tracking Based on Satellite Videos: A Literature Review
Zhang, Z., Wang, C., Song, J., & Xu, Y. (2022) · Remote Sensing · doi:10.3390/rs14153674 · Cited by 49
Fast car Crash Detection in Video
Arceda, V. E. M., & Riveros, E. L. (2018) · Latin American Computer Conference (CLEI) · doi:10.1109/clei.2018.00081 · Cited by 47
“Then the features HOG [4] are extracted since the intensity level of each pixel of the image region, a cosine window [2] is applied for smoothing a boundary effects.”
MethodAn eye tracking based virtual reality system for use inside magnetic resonance imaging systems
Qian, K., Arichi, T., Price, A. N., Dall’Orso, S., Eden, J., Noh, Y., Rhode, K., Burdet, E., Neil, M. A. A., Edwards, A. D., et al. (2021) · Scientific Reports · doi:10.1038/s41598-021-95634-y · Cited by 47
Hand Gesture Recognition Algorithm Using SVM and HOG Model for Control of Robotic System
Huu, P. N., & Ngoc, T. P. (2021) · Journal of Robotics · doi:10.1155/2021/3986497 · Cited by 57
“There are many targeting algorithms for image processing such as BOOSTING [7], MIL, KCF [8], TLD, MEDIANFLOW [9], GOTURN [10], MOSSE [11], and CSRT [12, 13].”
MethodTracking by Joint Local and Global Search: A Target-Aware Attention-Based Approach
Wang, X., Tang, J., Luo, B., Wang, Y., Tian, Y., & Wu, F. (2021) · IEEE Transactions on Neural Networks and Learning Systems · doi:10.1109/tnnls.2021.3083933 · Cited by 50
Target-Aware Transformer for Satellite Video Object Tracking
Lai, P., Zhang, M., Cheng, G., Li, S., Huang, X., & Han, J. (2023) · IEEE Transactions on Geoscience and Remote Sensing · doi:10.1109/tgrs.2023.3339658 · Cited by 55
“Furthermore, discriminative correlation filter-based frameworks [39], [40], [41], [42], [43], [44], [45], [46], [47], [48] are also of significance for SOT, which learn a correlation filter in an online manner to construct a target-dependent model for discriminative tracking.”
Satellite Video Object Tracking Based on Location Prompts
Wang, J., Liu, F., Jiao, L., Gao, Y., Wang, H., Li, L., Chen, P., Liu, X., & Li, S. (2024) · IEEE Transactions on Circuits and Systems for Video Technology · doi:10.1109/tcsvt.2024.3358549 · Cited by 52
“In recent years, object tracking algorithms based on correlation filters such as MOSSE [1], CSK [2], and KCF [3] have played an important role in the field of object tracking due to their high tracking speed and accuracy.”
MethodHybrid soft computing approaches to content based video retrieval: A brief review
Bhaumik, H., Bhattacharyya, S., Nath, M. D., & Chakraborty, S. (2016) · Applied Soft Computing · doi:10.1016/j.asoc.2016.03.022 · Cited by 48
Zhao, J. K., Bao, Y., Guan, Z., Zuo, W., Li, J., & Li, H. (2019) · Structural Control and Health Monitoring · doi:10.1002/stc.2314 · Cited by 46
Zou, Y., Wei, X., & Chen, J. (2020) · Optics and Lasers in Engineering · doi:10.1016/j.optlaseng.2020.106140 · Cited by 46
BiCF: Learning Bidirectional Incongruity-Aware Correlation Filter for Efficient UAV Object Tracking
Lin, F., Fu, C., He, Y., Guo, F., & Tang, Q. (2020) · Proceedings - IEEE International Conference on Robotics and Automation/Proceedings · doi:10.1109/icra40945.2020.9196530 · Cited by 48
“In [7], the minimum output sum of squared error, i.”
BackgroundDeep Lesion Tracker: Monitoring Lesions in 4D Longitudinal Imaging Studies
Cai, J., Tang, Y., Yan, K., Harrison, A. P., Xiao, J. Z., Lin, G., & Lü, L. (2021) · 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/cvpr46437.2021.01491 · Cited by 60
“Visual object tracking is an active research topic in general computer vision [8, 35, 18, 54, 53, 6, 39, 51, 52].”
BackgroundTamargo, M. A., Nash, T. R., Fleischer, S., Kim, Y., Vila, O. F., Yeager, K. J., Summers, M., Zhao, Y., Lock, R. I., Chavez, M., et al. (2021) · ACS Biomaterials Science & Engineering · doi:10.1021/acsbiomaterials.1c01006 · Cited by 49
Learning Target-Oriented Dual Attention for Robust RGB-T Tracking
Yang, R., Zhu, Y., Wang, X., Li, C., & Tang, J. (2019) · 2019 IEEE International Conference on Image Processing (ICIP) · doi:10.1109/icip.2019.8803528 · Cited by 45
Selective Spatial Regularization by Reinforcement Learned Decision Making for Object Tracking
Guo, Q., Han, R., Feng, W., Chen, Z., & Wan, L. (2020) · IEEE Transactions on Image Processing · doi:10.1109/tip.2019.2955292 · Cited by 45
“In particular, CF is a notable tracking scheme that can learn a robust appearance model for the target online, based on which many successful real-time trackers have been constructed [9], [10], [15]–[17].”
BackgroundMethodInfluentialMobileTrack: Siamese efficient mobile network for high‐speed UAV tracking
Xue, Y., Jin, G., Shen, T., Tan, L., Yang, J., & Hou, X. (2022) · IET Image Processing · doi:10.1049/ipr2.12565 · Cited by 45
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.