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 101–200 of 1,002
Zhang, M., Shi, R., & Yang, Z. (2020) · Safety Science · doi:10.1016/j.ssci.2020.104658 · Cited by 192
Anti-UAV: A Large-Scale Benchmark for Vision-Based UAV Tracking
Jiang, N., Wang, K., Peng, X., Yu, X., Wang, Q., Xing, J., Li, G., Guo, G., Ye, Q., Jiao, J., et al. (2023) · IEEE Transactions on Multimedia · doi:10.1109/tmm.2021.3128047 · Cited by 181
“[91]–[99] and CF-based trackers [53]–[56], [58], [64], [81]– [88], [90] are used for comparison under Protocol I and have been briefly described below.”
MethodRobust Visual Tracking via Hierarchical Convolutional Features
Ma, C., Huang, J.-B., Yang, X., & Yang, M.-H. (2019) · IEEE Transactions on Pattern Analysis and Machine Intelligence · doi:10.1109/tpami.2018.2865311 · Cited by 208
“To remove the boundary discontinuities, we weight the extracted feature channels of each convolutional layer by a cosine box filter [30].”
BackgroundMethodInfluentialCN-Celeb: A Challenging Chinese Speaker Recognition Dataset
Fan, Y., Kang, J. W., Li, L. T., Li, K. C., Chen, H. L., Cheng, S. T., Zhang, P. Y., Zhou, Z. Y., Cai, Y. Q., & Wang, D. (2020) · ICASSP 2020 - 2020 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP) · doi:10.1109/icassp40776.2020.9054017 · Cited by 186
“We used the ArcFace face recognition system [18] to perform the comparison; (3) Apply the MOSSE face tracking system [19] to produce face streams.”
MethodVideo Object Segmentation with Joint Re-identification and Attention-Aware Mask Propagation
Li, X., & Loy, C. C. (2018) · Lecture Notes in Computer Science · doi:10.1007/978-3-030-01219-9_6 · Cited by 207
Visual Object Tracking with Discriminative Filters and Siamese Networks: A Survey and Outlook
Javed, S., Danelljan, M., Khan, F. S., Khan, M. H., Felsberg, M., & Matas, J. (2022) · IEEE Transactions on Pattern Analysis and Machine Intelligence · doi:10.1109/tpami.2022.3212594 · Cited by 175
“The target is then detected in consecutive frames by convolving the trained filter via the Fast Fourier Transform (FFT) [10], [53].”
BackgroundMethodInfluentialEnd-to-End Active Object Tracking and Its Real-World Deployment via Reinforcement Learning
Luo, W., Sun, P., Zhong, F., Liu, W., Zhang, T., & Wang, Y. (2019) · IEEE Transactions on Pattern Analysis and Machine Intelligence · doi:10.1109/tpami.2019.2899570 · Cited by 235
“cess in real-time object tracking [17], [18].”
Learning Deep Multi-Level Similarity for Thermal Infrared Object Tracking
Liu, Q., Li, X., He, Z., Fan, N., Yuan, D., & Wang, H. (2021) · IEEE Transactions on Multimedia · doi:10.1109/tmm.2020.3008028 · Cited by 193
“For instance, TBOOST [3] ensembles several MOSSE filters [4] using a continuously switching”
MethodDevelopment of UAV-Based Target Tracking and Recognition Systems
Wang, S., Jiang, F., Zhang, B., Ma, R., & Hao, Q. (2020) · IEEE Transactions on Intelligent Transportation Systems · doi:10.1109/tits.2019.2927838 · Cited by 192
“The performance evaluation results and corresponding computing platforms of 6 top methods are acquired from related literature [26], [56], [59]–[62], [67].”
MethodSynthetic Data Generation for End-to-End Thermal Infrared Tracking
Zhang, L., Gonzalez-Garcia, A., van de Weijer, J., Danelljan, M., & Khan, F. S. (2019) · IEEE Transactions on Image Processing · doi:10.1109/tip.2018.2879249 · Cited by 183
“[8] was restricted to a single feature channel (grayscale image).”
BackgroundTracking by Natural Language Specification
Li, Z., Tao, R., Gavves, E., Snoek, C. G. M., & Smeulders, A. W. M. (2017) · 2017 IEEE Conference on Computer Vision and Pattern Recognition (CVPR) · doi:10.1109/cvpr.2017.777 · Cited by 177
“Many modern trackers rely on discriminative correlation filters [4, 12, 7].”
SiamAPN++: Siamese Attentional Aggregation Network for Real-Time UAV Tracking
Cao, Z., Fu, C., Ye, J., Li, B., & Li, Y. (2021) · 2021 IEEE/RSJ International Conference on Intelligent Robots and Systems (IROS) · doi:10.1109/iros51168.2021.9636309 · Cited by 173
“Previously, CF-based trackers have attracted much attention since MOSSE [17].”
BackgroundLearning Adaptive Attribute-Driven Representation for Real-Time RGB-T Tracking
Zhang, P., Wang, D., Lu, H., & Yang, X. (2021) · International Journal of Computer Vision · doi:10.1007/s11263-021-01495-3 · Cited by 184
“Numerous frameworks, including correlation filter Bolme et al. 2010; Danelljan et al. 2017; Li and Zhu 2014; Danelljan et al. 2017”
MethodSpatial and semantic convolutional features for robust visual object tracking
Zhang, J., Jin, X., Sun, J., Wang, J., & Sangaiah, A. K. (2020) · Multimedia Tools and Applications · doi:10.1007/s11042-018-6562-8 · Cited by 191
“In 2010, Bolme et al. [4] first proposed to learn a filter by using minimum output sum of squared error (MOSSE), which was an early application of correlation filter in the field of object tracking.”
BackgroundMethodVisual Tracking Using Attention-Modulated Disintegration and Integration
Choi, J., Chang, H. J., Jeong, J., Demiris, Y., & Choi, J. Y. (2016) · 2016 IEEE Conference on Computer Vision and Pattern Recognition (CVPR) · doi:10.1109/cvpr.2016.468 · Cited by 189
“The correlation filter can be trained quickly based on the property of the circulant matrix in the Fourier domain, so the trackers show high performance with low computational load [2].”
BackgroundMeta-tracker: Fast and Robust Online Adaptation for Visual Object Trackers
Park, E., & Berg, A. C. (2018) · Lecture Notes in Computer Science · doi:10.1007/978-3-030-01219-9_35 · Cited by 184
Visual object tracking based on residual network and cascaded correlation filters
Zhang, J., Sun, J., Wang, J., & Yue, X.-G. (2021) · Journal of Ambient Intelligence and Humanized Computing · doi:10.1007/s12652-020-02572-0 · Cited by 187
“used original image content to gain the target model called the MOSSE tracking method (Bolme et al. 2010).”
MethodXu, H., Zhang, Y., Zhou, B., Wang, L., Yao, X., Meng, G., & Shen, S. (2022) · IEEE Transactions on Robotics · doi:10.1109/tro.2022.3182503 · Cited by 159
“The images I extracted from the original image by VINS-Fisheye are also utilized for visual object tracking, as the function MOSSETrackers in Alg.”
MethodInfluentialCorrelation Tracking via Joint Discrimination and Reliability Learning
Sun, C., Wang, D., Lu, H., & Yang, M.-H. (2018) · 2018 IEEE/CVF Conference on Computer Vision and Pattern Recognition · doi:10.1109/cvpr.2018.00058 · Cited by 189
SCSTCF: Spatial-Channel Selection and Temporal Regularized Correlation Filters for visual tracking
Zhang, J., Feng, W., Yuan, T., Wang, J., & Sangaiah, A. K. (2022) · Applied Soft Computing · doi:10.1016/j.asoc.2022.108485 · Cited by 180
Quadruplet Network With One-Shot Learning for Fast Visual Object Tracking
Dong, X., Shen, J., Wu, D., Guo, K., Jin, X., & Porikli, F. (2019) · IEEE Transactions on Image Processing · doi:10.1109/tip.2019.2898567 · Cited by 167
“Recently, a lot of real-time (more than 30 fps) methods [3], [5], [6], [8], [13], [14], [19], [21], [25], [39], [44] and nearly real-time (more than 20 fps) methods [8], [16], [17], [33] are proposed for visual object tracking.”
MethodLearning Multi-Task Correlation Particle Filters for Visual Tracking
Zhang, T., Xu, C., & Yang, M.-H. (2019) · IEEE Transactions on Pattern Analysis and Machine Intelligence · doi:10.1109/tpami.2018.2797062 · Cited by 173
“Correlation filters have recently been introduced into visual tracking and shown to perform well in terms of speed and accuracy [1], [2], [3], [4], [6], [7], [8], [9], [10], [11], [12].”
Hyperparameter Optimization for Tracking with Continuous Deep Q-Learning
Dong, X., Shen, J., Wang, W., Liu, Y., Shao, L., & Porikli, F. (2018) · 2018 IEEE/CVF Conference on Computer Vision and Pattern Recognition · doi:10.1109/cvpr.2018.00061 · Cited by 161
“Tracker with heat-map: Our hyperparameter framework can be directly applied to the tracker with heat-map, thus we give several real-time related works including some deep learning trackers [3, 48, 16] and recent correlation filter based trackers [5, 19, 9, 10, 34, 58, 2, 12, 52, 24, 14].”
MethodUllah, A., Muhammad, K., Ding, W., Palade, V., Haq, I. U., & Baik, S. W. (2021) · Applied Soft Computing · doi:10.1016/j.asoc.2021.107102 · Cited by 166
“This problem primarily occurs when Naïve filtering is used in MOSSE [69], and in the proposed framework a Peak-to-Sidelobe Ratio filtering (MOSSE PSR) instead of Naïve filters.”
MethodVisual Object Tracking by Hierarchical Attention Siamese Network
Shen, J., Tang, X., Dong, X., & Shao, L. (2020) · IEEE Transactions on Cybernetics · doi:10.1109/tcyb.2019.2936503 · Cited by 167
“For example, [52] used the pixel values for correlation filter tracking and [54] applied PCA processing on frames for tracking.”
MethodAutomatic Individual Pig Detection and Tracking in Pig Farms
Zhang, L., Gray, H. E., Ye, X., Collins, L., & Allinson, N. M. (2019) · Sensors · doi:10.3390/s19051188 · Cited by 182
“Since the MOSSE [29] was first introduced for adaptive tracking using DCF, a series of improvements [28,30,31] have been made to this tracker to achieve more accurate, robust and efficient tracking.”
MethodObject Tracking in Satellite Videos by Improved Correlation Filters With Motion Estimations
Xuan, S., Li, S., Han, M., Wan, X., & Xia, G.-S. (2020) · IEEE Transactions on Geoscience and Remote Sensing · doi:10.1109/tgrs.2019.2943366 · Cited by 162
“The correlation filter called the minimum output sum of squared error (MOSSE) was applied to object tracking for the first time in [28].”
MethodStructural Correlation Filter for Robust Visual Tracking
Liu, S., Zhang, T., Cao, X., & Xu, C. (2016) · 2016 IEEE Conference on Computer Vision and Pattern Recognition (CVPR) · doi:10.1109/cvpr.2016.467 · Cited by 165
“encode target appearance by learning an adaptive correlation filter [5].”
BackgroundCorrelation-Guided Attention for Corner Detection Based Visual Tracking
Du, F., Liu, P., Zhao, W., & Tang, X. (2020) · 2020 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR) · doi:10.1109/cvpr42600.2020.00687 · Cited by 159
“There are two main kinds of tracker in current use: correlation filter (CF)-based trackers [4, 16, 9, 5] and Siamese network-based trackers [1, 37, 24].”
Effective template update mechanism in visual tracking with background clutter
Liu, S., Liu, D., Muhammad, K., & Ding, W. (2021) · Neurocomputing · doi:10.1016/j.neucom.2019.12.143 · Cited by 165
Distilled Siamese Networks for Visual Tracking
Shen, J., Liu, Y., Dong, X., Lu, X., Khan, F. S., & Hoi, S. C. H. (2021) · IEEE Transactions on Pattern Analysis and Machine Intelligence · doi:10.1109/tpami.2021.3127492 · Cited by 177
“The initial work of [5] exploited the properties of cir-”
BackgroundToward human activity recognition: a survey
Saleem, G., Bajwa, U. I., & Raza, R. H. (2022) · Neural Computing and Applications · doi:10.1007/s00521-022-07937-4 · Cited by 180
Decentralized Visual-Inertial-UWB Fusion for Relative State Estimation of Aerial Swarm
Xu, H., Wang, L., Zhang, Y., Qiu, K., & Shen, S. (2020) · Proceedings - IEEE International Conference on Robotics and Automation/Proceedings · doi:10.1109/icra40945.2020.9196944 · Cited by 185
“The detection results of 2-D boundingboxs are combined with MOSSE trackers [17] to provide the tracking results with a higher frequency.”
MethodMulti-kernel Correlation Filter for Visual Tracking
Tang, M., & Feng, J. (2015) · 2015 IEEE International Conference on Computer Vision (ICCV) · doi:10.1109/iccv.2015.348 · Cited by 160
“Fast Evaluation in Training All correlation filter based tracking algorithms [4, 15, 17, 7] consider the training samples, xi, to be generated through cyclically shifting a base sample.”
BackgroundMethodInfluentialCross-Modal Pattern-Propagation for RGB-T Tracking
Wang, C., Xu, C., Cui, Z., Zhou, L., Zhang, T., Zhang, X., & Yang, J. J. (2020) · 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/cvpr42600.2020.00709 · Cited by 197
“MOSSE [2] firstly used adaptive filter for visual tracking, then numerous correlation filter based trackers sprung up and performed excellent in the yield of visual object tracking.”
MethodLearning Adaptive Spatial-Temporal Context-Aware Correlation Filters for UAV Tracking
Yuan, D., Chang, X., Li, Z., & He, Z. (2022) · ACM Transactions on Multimedia Computing, Communications, and Applications · doi:10.1145/3486678 · Cited by 159
“Tracking methods under the DCF framework have obtained significantly more efficiency than other trackers [20, 24, 35, 40, 74] and have thus attracted the attention of many researchers [4, 25, 28, 29, 41, 68, 69].”
BackgroundMethodTarget Response Adaptation for Correlation Filter Tracking
Bibi, A., Mueller, M. F., & Ghanem, B. (2016) · Lecture notes in computer science · doi:10.1007/978-3-319-46466-4_25 · Cited by 166
Good Features to Correlate for Visual Tracking
Gundogdu, E., & Alatan, A. A. (2018) · IEEE Transactions on Image Processing · doi:10.1109/tip.2018.2806280 · Cited by 155
BranchOut: Regularization for Online Ensemble Tracking with Convolutional Neural Networks
Han, B., Sim, J., & Adam, H. (2017) · 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.2017.63 · Cited by 172
“[3] have introduced a minimum output sum of squared error (MOSSE) filter for visual tracking.”
Vision-Aided Multi-UAV Autonomous Flocking in GPS-Denied Environment
Yazhe, T., Hu, Y., Cui, J., Liao, F. Y., Lao, M., Lin, F., & Teo, R. (2018) · IEEE Transactions on Industrial Electronics · doi:10.1109/tie.2018.2824766 · Cited by 169
“This paper designs a tracking system on the basis of minimum output sum of squared error (MOSSE) [19] since it provides the”
MethodVisual object tracking: A survey
Chen, F., Wang, X., Zhao, Y., Lv, S., & Niu, X. (2022) · Computer Vision and Image Understanding · doi:10.1016/j.cviu.2022.103508 · Cited by 174
Adaptive Correlation Filters with Long-Term and Short-Term Memory for Object Tracking
Ma, C., Huang, J.-B., Yang, X., & Yang, M.-H. (2018) · International Journal of Computer Vision · doi:10.1007/s11263-018-1076-4 · Cited by 156
Recurrently Target-Attending Tracking
Cui, Z., Xiao, S., Feng, J., & Yan, S. (2016) · 2016 IEEE Conference on Computer Vision and Pattern Recognition (CVPR) · doi:10.1109/cvpr.2016.161 · Cited by 144
“In particular, correlation filter (CF) based methods [4, 11, 13, 28, 33, 23] arouse increasing interest due to their excellent efficiency and robustness.”
BackgroundMethodTracking in Aerial Hyperspectral Videos Using Deep Kernelized Correlation Filters
Uzkent, B., Rangnekar, A., & Hoffman, M. J. (2018) · IEEE Transactions on Geoscience and Remote Sensing · doi:10.1109/tgrs.2018.2856370 · Cited by 158
A Robust Parallel Object Tracking Method for Illumination Variations
Liu, S., Liu, G., & Zhou, H. (2018) · Mobile Networks and Applications · doi:10.1007/s11036-018-1134-8 · Cited by 156
“Bolme et al. [13] proposed a target tracking algo-rithm by learning a minimum output sum of squared error (MOSSE) correlation filter on a gray scale image.”
BackgroundAnnotating Objects and Relations in User-Generated Videos
Shang, X., Di, D., Xiao, J., Cao, Y., Yang, X., & Chua, T. (2019) · International Conference on Multimedia Retrieval · doi:10.1145/3323873.3325056 · Cited by 152
“We determine that a interval is accurately approximated if max t ∈T {vIoU(tf , tb )} > 0.5, (1) where vIoU is the voluminal Intersection-over-Union between the two trajectories, and KCF [8] and MOSSE [1] tracker are used in our implementation.”
BackgroundMethodInfluentialSaliency-Associated Object Tracking
Zhou, Z., Pei, W., Li, X., Wang, H., Zheng, F., & He, Z. (2021) · IEEE/CVF International Conference on Computer Vision (ICCV) · doi:10.1109/iccv48922.2021.00972 · Cited by 169
“In the initial definition [4], the size of main lobe Ψ for arbitrary similarity maps is pre-defined as a fixed value.”
BackgroundInfluentialLiu, S., Liu, X., Wang, S., & Muhammad, K. (2020) · Neural Computing and Applications · doi:10.1007/s00521-020-05021-3 · Cited by 154
“[11] used affine transformation and Gaussian distribution of samples to construct an adaptive correlation filter.”
MethodComprehensive Underwater Object Tracking Benchmark Dataset and Underwater Image Enhancement With GAN
Panetta, K. A., Kezebou, L., Oludare, V., & Agaian, S. С. (2021) · IEEE Journal of Oceanic Engineering · doi:10.1109/joe.2021.3086907 · Cited by 165
“Some of the trackers are from the OTB benchmark, and others are more recent deep learning-based tracking algorithms including BACF [14], BOOSTING [60], CCOT [48], CFWCR [61], CSR-DCF [52], DCF [44], ECO [11], fDSST [45], KCF [10], MDNet [49], MEDIANFLOW [62], MIL [42], MOSSE [63], SiamMask [64], SiamRPN++ [65], STAPLE…”
MethodUnified Transformer Tracker for Object Tracking
Ma, F., Shou, M. Z., Zhu, L., Fan, H., Xu, Y., Yang, Y., & Yan, Z. (2022) · 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/cvpr52688.2022.00858 · Cited by 177
“[7] proposes a minimum output sum of square error (MOSSE) filter.”
BackgroundMonocular Quasi-Dense 3D Object Tracking
Hu, H.-N., Yang, Y.-H., Fischer, T., Darrell, T., Yu, F., & Sun, M. (2023) · IEEE Transactions on Pattern Analysis and Machine Intelligence · doi:10.1109/tpami.2022.3168781 · Cited by 128
“Early methods [31], [32], [33] track objects based on correlation filters.”
MethodHandcrafted and Deep Trackers: Recent Visual Object Tracking Approaches and Trends
Fiaz, M., Mahmood, A., Javed, S., & Jung, S. K. (2019) · ACM Computing Surveys · doi:10.1145/3309665 · Cited by 155
“In later years, the development of Minimum Output of Sum of Squared Error (MOSSE) filter [15], which allows for efficient adaptive training, changed the situation.”
BackgroundDynamic Saliency-Aware Regularization for Correlation Filter-Based Object Tracking
Feng, W., Han, R., Guo, Q., Zhu, J., & Wang, S. (2019) · IEEE Transactions on Image Processing · doi:10.1109/tip.2019.2895411 · Cited by 143
A Systematic Review of Drone Based Road Traffic Monitoring System
Bisio, I., Garibotto, C., Haleem, H., Lavagetto, F., & Sciarrone, A. (2022) · IEEE Access · doi:10.1109/access.2022.3207282 · Cited by 139
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
“Yet, on large datasets this does not impact the overall efficiency, since it is only applied to a short-list of videos with the highest scores.”
BackgroundCorrelation Filters with Weighted Convolution Responses
He, Z., Fan, Y., Zhuang, J., Dong, Y., & Bai, H. (2017) · IEEE International Conference on Computer Vision Workshops · doi:10.1109/iccvw.2017.233 · Cited by 138
“[4] proposed the MOSSE tracker, which used the grey-scale image to extract single channel feature with high speed.”
BackgroundMethodAnti-UAV: A Large Multi-Modal Benchmark for UAV TrackingPreprint
Jiang, N., Wang, K., Peng, X., Yu, X., Wang, Q., Xing, J., Li, G., Zhao, J. C., Guo, G., & Han, Z. (2021) · arXiv (Cornell University) · doi:10.48550/arxiv.2101.08466 · Cited by 186
“OV OC FM SV LI TC LR All All TCeasy TCmed TChard TCall MOSSE [49] 8.”
BackgroundA multi-view model for visual tracking via correlation filters
Li, X., Liu, Q., He, Z., Wang, H., Zhang, C., & Chen, W.-S. (2016) · Knowledge-Based Systems · doi:10.1016/j.knosys.2016.09.014 · Cited by 131
Du, B., Sun, Y., Cai, S., Wu, C., & Du, Q. (2017) · IEEE Geoscience and Remote Sensing Letters · doi:10.1109/lgrs.2017.2776899 · Cited by 130
“In general, a tracking algorithm can be categorized as either being a generative model [9]–[12] or a discriminative model [13]–[20] based on its representation schemes.”
BackgroundMethodMultiple Object Tracking With Attention to Appearance, Structure, Motion and Size
Karunasekera, H., Wang, H., & Zhang, H. (2019) · IEEE Access · doi:10.1109/access.2019.2932301 · Cited by 129
“learning and detecting); Correlation filter (CF) based tracking [4] and kernelized correlation filter (KCF) based tracking [5] (by extending the linear filter into non-linear”
MethodHou, Z., Li, W., Zhou, J. W., & Tao, R. (2022) · IEEE Transactions on Geoscience and Remote Sensing · doi:10.1109/tgrs.2022.3215431 · Cited by 137
“based tracker that does not require training [16], [17] in”
BackgroundCorrelation Filters for Object Alignment
Boddeti, V. N., Kanade, T., & Kumar, B. V. K. V. (2013) · 2013 IEEE Conference on Computer Vision and Pattern Recognition · doi:10.1109/cvpr.2013.297 · Cited by 125
“The proposed vector correlation filter (VCF) with HOG features can accommodate significant within-class variations while being discriminative against background clutter.”
Correlation Particle Filter for Visual Tracking
Zhang, T., Liu, S., Xu, C., Liu, B., & Yang, M.-H. (2018) · IEEE Transactions on Image Processing · doi:10.1109/tip.2017.2781304 · Cited by 127
“Recently, tracking methods based on correlation filters have been proved to be able to achieve fairly high speed and robust performance [1], [2], [23]–[33].”
BackgroundMethodSiamese Transformer Pyramid Networks for Real-Time UAV Tracking
Xing, D., Evangeliou, N., Τσουκαλάς, Α., & Tzes, A. P. (2022) · IEEE Winter Conference on Applications of Computer Vision · doi:10.1109/wacv51458.2022.00196 · Cited by 143
Learning Support Correlation Filters for Visual Tracking
Zuo, W., Wu, X., Lin, L., Zhang, L., & Yang, M. (2018) · IEEE Transactions on Pattern Analysis and Machine Intelligence · doi:10.1109/tpami.2018.2829180 · Cited by 132
Advances techniques of the structured light sensing in intelligent welding robots: a review
Yang, L., Liu, Y., & Peng, J. (2020) · The International Journal of Advanced Manufacturing Technology · doi:10.1007/s00170-020-05524-2 · Cited by 126
“With the fast development of machine learning and computer vision, the tracking precision and speed of object tracking have been greatly improved [69–72].”
BackgroundUnsupervised Deep Representation Learning for Real-Time Tracking
Wang, N., Zhou, W., Song, Y., Ma, C., Liu, W., & Li, H. (2020) · International Journal of Computer Vision · doi:10.1007/s11263-020-01357-4 · Cited by 136
“The discriminative correlation filters (DCFs) [2, 19,10,21,42,55,38] handle the visual tracking task by solving a ridge regression task using densely sampled candidates.”
BackgroundMethodInfluentialCN-Celeb: Multi-genre speaker recognition
Li, L., Liu, R., Kang, J., Fan, Y. B., Cui, H., Cai, Y., Vipperla, R., Zheng, T. F., & Wang, D. (2022) · Speech Communication · doi:10.1016/j.specom.2022.01.002 · Cited by 162
Hedging Deep Features for Visual Tracking
Qi, Y., Zhang, S., Qin, L., Huang, Q., Yao, H., Lim, J., & Yang, M. (2018) · IEEE Transactions on Pattern Analysis and Machine Intelligence · doi:10.1109/tpami.2018.2828817 · Cited by 127
“[28] develop the minimum output sum of squared error method to learn robust filters where intensity features are used for object representation.”
BackgroundMethodDeep Meta Learning for Real-Time Target-Aware Visual Tracking
Choi, J., Kwon, J., & Lee, K. M. (2019) · 2019 IEEE/CVF International Conference on Computer Vision (ICCV) · doi:10.1109/iccv.2019.00100 · Cited by 109
“Recently, correlation filters have gained great popularity among the visual tracking methods since the seminal works of [3] and [20] due to their simplicity and computational efficiency in the Fourier frequency domain.”
BackgroundCompact Transformer Tracker with Correlative Masked Modeling
Song, Z., Luo, R., Yu, J., Chen, Y. P., & Yang, W. H. (2023) · Proceedings of the AAAI Conference on Artificial Intelligence · doi:10.1609/aaai.v37i2.25327 · Cited by 163
Dual Deep Network for Visual Tracking
Chi, Z., Li, H., Lu, H., & Yang, M. (2017) · IEEE Transactions on Image Processing · doi:10.1109/tip.2017.2669880 · Cited by 125
An object tracking framework with recapture based on correlation filters and Siamese networks
Zhang, J., Sun, J., Wang, J., Li, Z., & Chen, X. (2022) · Computers & Electrical Engineering · doi:10.1016/j.compeleceng.2022.107730 · Cited by 121
Towards Real-World Visual Tracking With Temporal Contexts
Cao, Z., Huang, Z., Pan, L., Zhang, S., Liu, Z., & Fu, C. (2023) · IEEE Transactions on Pattern Analysis and Machine Intelligence · doi:10.1109/tpami.2023.3307174 · Cited by 136
“firstly proposed the MOSSE filter [14], there are many works trying to boost the tracking performance of DCF-based trackers [15], [16], [17], [18].”
BackgroundAutomatic Feeding Control for Dense Aquaculture Fish Tanks
Atoum, Y., Srivastava, S., & Liu, X. (2014) · IEEE Signal Processing Letters · doi:10.1109/lsp.2014.2385794 · Cited by 131
“Based on the per-frame results obtained from both the fish activity classification and the feed detection, a continuous decision is made on whether to stop or continue the feeding.”
MethodAn Experimental Survey on Correlation Filter-based TrackingPreprint
Chen, Z., Hong, Z., & Tao, D. (2015) · arXiv (Cornell University) · doi:10.48550/arxiv.1509.05520 · Cited by 135
“Only after the proposal of Minimum Output Sum of Squared Error (MOSSE) [15] filter, this situation has been changed.”
BackgroundMethodInfluentialTrTr: Visual Tracking with TransformerPreprint
Zhao, M., Okada, K., & Inaba, M. (2021) · arXiv (Cornell University) · doi:10.48550/arxiv.2105.03817 · Cited by 140
“This has been achieved by the previously dominant Discriminative Correlation Filter (DCF) paradigms [5, 17, 22, 11, 43] and the most recent Siamese-network-based trackers [2, 20, 51, 55, 53].”
MethodSiam R-CNN: Visual Tracking by Re-Detection
Voigtlaender, P., Luiten, J., Torr, P. H. S., & Leibe, B. (2020) · 2020 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR) · doi:10.1109/cvpr42600.2020.00661 · Cited by 115
Integrating Boundary and Center Correlation Filters for Visual Tracking with Aspect Ratio Variation
Li, F., Yao, Y., Li, P., Zhang, D., Zuo, W., & Yang, M.-H. (2017) · 2017 IEEE International Conference on Computer Vision Workshops (ICCVW) · doi:10.1109/iccvw.2017.234 · Cited by 113
“Recently, correlation filter (CF)-based approaches have received considerable attention in visual tracking [3, 14, 7].”
BackgroundLSOTB-TIR: A Large-Scale High-Diversity Thermal Infrared Object Tracking Benchmark
Liu, Q., Li, X., He, Z., Li, C., Li, J., Zhou, Z., Yuan, D., Li, J., Yang, K., Fan, N., et al. (2020) · ACM International Conference on Multimedia (ACM MM) · doi:10.1145/3394171.3413922 · Cited by 131
“[53] propose to online learn a robust intensity histogram based appearancemodel using adaptive Kalman filtering, while TBOOST [24] maintains a dynamic MOSSE filter [7] set using a continuously switching mechanism according to appearance variation.”
MethodHOICLIP: Efficient Knowledge Transfer for HOI Detection with Vision-Language Models
Ning, S., Qiu, L., Liu, Y., & He, X. (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/cvpr52729.2023.02251 · Cited by 166
“as assistive robots, visual surveillance and video analysis [3,4,9,11].”
BackgroundChen, Y., Wang, J., Xia, R., Zhang, Q., Cao, Z., & Yang, K. (2019) · Journal of Ambient Intelligence and Humanized Computing · doi:10.1007/s12652-018-01171-4 · Cited by 114
“2017), Correlation Filter algorithm (Bolme et al. 2010; Ma et al. 2015), Structured SVM algorithm (Wang et al.”
MethodRetractedAugmented Ship Tracking Under Occlusion Conditions From Maritime Surveillance Videos
Chen, X., Xu, X., Yang, Y., Wu, H., Tang, J., & Zhao, J. (2020) · IEEE Access · doi:10.1109/access.2020.2978054 · Cited by 117
“visual ship tracking task by transforming the initial ship image sequences into frequency domain [6].”
BackgroundDeep Learning in Visual Tracking: A Review
Jiao, L., Wang, D., Bai, Y., Chen, P., & Liu, F. (2021) · IEEE Transactions on Neural Networks and Learning Systems · doi:10.1109/tnnls.2021.3136907 · Cited by 131
“ing module [139], [140] are one of the important methods to solve the tracking task.”
MethodDeformable Parts Correlation Filters for Robust Visual Tracking
Lukežič, A., Zajc, L. Č., & Kristan, M. (2017) · IEEE Transactions on Cybernetics · doi:10.1109/tcyb.2017.2716101 · Cited by 116
Xia, R., Chen, Y., & Ren, B. (2022) · Journal of King Saud University - Computer and Information Sciences · doi:10.1016/j.jksuci.2022.02.004 · Cited by 128
Wang, C., Zhang, L., Xie, L., & Yuan, J. (2018) · Proceedings of the AAAI Conference on Artificial Intelligence · doi:10.1609/aaai.v32i1.11710 · Cited by 114
Object Saliency-Aware Dual Regularized Correlation Filter for Real-Time Aerial Tracking
Fu, C., Xu, J., Lin, F., Guo, F., Liu, T., & Zhang, Z. (2020) · IEEE Transactions on Geoscience and Remote Sensing · doi:10.1109/tgrs.2020.2992301 · Cited by 111
“In recent years, discriminative correlation filter (DCF)based tracking methods have gained enormous popularity and shown impressive computational efficiency in addition to adequate tracking accuracy [7].”
BackgroundMethodOnboard Real-Time Aerial Tracking With Efficient Siamese Anchor Proposal Network
Fu, C., Cao, Z., Li, Y., Ye, J., & Feng, C. (2021) · IEEE Transactions on Geoscience and Remote Sensing · doi:10.1109/tgrs.2021.3083880 · Cited by 137
“[17] propose the minimum output sum of squared error (MOSSE) filter, showing the potential of a DCF-based framework.”
BackgroundThe Thermal Infrared Visual Object Tracking VOT-TIR2015 Challenge Results
Felsberg, M., Berg, A., Hager, G., Ahlberg, J., Kristan, M., Matas, J., Leonardis, A., Zajc, L. Č., Fernandez, G., Vojır, T., et al. (2015) · IEEE International Conference on Computer Vision Workshops · doi:10.1109/iccvw.2015.86 · Cited by 122
“For the translation filter, the intensity features employed in the MOSSE tracker is combined with a pixel-dense representation of HOG-features.”
BackgroundMethodInfluentialSiamese attentional keypoint network for high performance visual tracking
Gao, P., Yuan, R.-Y., Wang, F., Xiao, L., Fujita, H., & Zhang, Y. (2019) · Knowledge-Based Systems · doi:10.1016/j.knosys.2019.105448 · Cited by 111
“Thanks to the circular shifting of training samples and fast learning correlation filters in the Fourier frequency domain, DCF demonstrates superior computational efficiency and fairly good tracking accuracy and has attracted increasing attention since MOSSE [5]first exploited it.”
BackgroundTransVG++: End-to-End Visual Grounding With Language Conditioned Vision Transformer
Deng, J., Yang, Z., Liu, D., Chen, T., Zhou, W., Zhang, Y., Li, H., & Ouyang, W. (2023) · IEEE Transactions on Pattern Analysis and Machine Intelligence · doi:10.1109/tpami.2023.3296823 · Cited by 136
“RCCF [6] formulates the visual grounding problem as a correlation filtering process [39], [40], and picks the peak value of the correlation heatmap as the center of target objects.”
BackgroundUltra-wideband aided fast localization and mapping system
Wang, C., Zhang, H., Nguyen, T.-M., & Xie, L. (2017) · IEEE/RSJ International Conference on Intelligent Robots and Systems (IROS) · doi:10.1109/iros.2017.8205968 · Cited by 114
“The concept of PSR will also be used for the key-frame refinement in Section II-D.”
BackgroundInfluentialClassifying ASD children with LSTM based on raw videos
Li, J., Zhong, Y., Han, J., Ouyang, G., Li, X., & Liu, H. (2019) · Neurocomputing · doi:10.1016/j.neucom.2019.05.106 · Cited by 109
A Comprehensive Review for Typical Applications Based Upon Unmanned Aerial Vehicle Platform
Han, Y., Liu, H., Wang, Y., & Liu, C. (2022) · IEEE Journal of Selected Topics in Applied Earth Observations and Remote Sensing · doi:10.1109/jstars.2022.3216564 · Cited by 112
Balamuralidhar, N., Tilon, S., & Nex, F. (2021) · Remote Sensing · doi:10.3390/rs13040573 · Cited by 104
“With the Fourier transform and the synthetic target extracted, the MOSSE filter was initialized using the following formula [69]: where H ∗ is the complex conjugate of the filter; F i and G i are the fourier transform and the synthetically generated target of the template in the ith frame, respectively; and F ∗ i is the…”
BackgroundMethodInfluentialHigh-Speed Tracking with Multi-kernel Correlation Filters
Tang, M., Yu, B., Zhang, F., & Wang, J. (2018) · 2018 IEEE/CVF Conference on Computer Vision and Pattern Recognition · doi:10.1109/cvpr.2018.00512 · Cited by 103
Pan, Z. Y., Liu, S., Sangaiah, A. K., & Muhammad, K. (2018) · Journal of Parallel and Distributed Computing · doi:10.1016/j.jpdc.2018.06.012 · Cited by 105
ROI Pooled Correlation Filters for Visual Tracking
Sun, Y., Sun, C., Wang, D., He, Y., & Lu, H. (2019) · 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.2019.00593 · Cited by 108
“The correlation filter algorithm in visual tracking can be dated back to the MOSSE tracker [2], which takes the single-channel gray-scale image as input.”
MethodTracking Objects From Satellite Videos: A Velocity Feature Based Correlation Filter
Shao, J., Du, B., Wu, C., & Zhang, L. (2019) · IEEE Transactions on Geoscience and Remote Sensing · doi:10.1109/tgrs.2019.2916953 · Cited by 104
“derive fast correlation filters [32].”
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.