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 201–300 of 1,002
Robust visual tracking via co-trained Kernelized correlation filters
Zhang, L., & Suganthan, P. N. (2017) · Pattern Recognition · doi:10.1016/j.patcog.2017.04.004 · Cited by 101
Automated sewer pipe defect tracking in CCTV videos based on defect detection and metric learning
Wang, M., Kumar, S. S., & Cheng, J. C. P. (2020) · Automation in Construction · doi:10.1016/j.autcon.2020.103438 · Cited by 103
PG-Net: Pixel to Global Matching Network for Visual Tracking
Liao, B., Wang, C., Wang, Y., Wang, Y., & Yin, J. (2020) · Lecture notes in computer science · doi:10.1007/978-3-030-58542-6_26 · Cited by 109
“Existing tracking methods can be divided into: (i) correlation filter based [4, 15, 6] and (ii) deep learning based [2, 13, 18, 26–28, 38, 17].”
MethodObject Tracking by Reconstruction With View-Specific Discriminative Correlation Filters
Kart, U., Lukežič, A., Kristan, M., Kämäräinen, J., & Matas, J. (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.2019.00143 · Cited by 116
“DCF [4], Siamese deep nets [2], Mean shift [9], Lucas Kanade [27]),”
BackgroundFu, C., Li, B., Ding, F., Lin, F., & Lu, G. (2021) · IEEE Geoscience and Remote Sensing Magazine · doi:10.1109/mgrs.2021.3072992 · Cited by 103
Robust Estimation of Similarity Transformation for Visual Object Tracking
Li, Y., Zhu, J., Hoi, S. C. H., Song, W., Wang, Z., & Liu, H. (2019) · Proceedings of the AAAI Conference on Artificial Intelligence · doi:10.1609/aaai.v33i01.33018666 · Cited by 97
Automatic detection of fish and tracking of movement for ecology
Lopez‐Marcano, S., Jinks, E. L., Buelow, C. A., Brown, C. J., Wang, D., Kusý, B., Ditria, E. M., & Connolly, R. M. (2021) · Ecology and Evolution · doi:10.1002/ece3.7656 · Cited by 97
“Additionally, we benchmarked the performance of three object tracking architectures: minimum output sum of squared errors (MOSSE) (Bolme et al., 2010), sequential nonmaximum suppression (Seq- NMS) (Han et al., 2016), and Siamese mask (SiamMask) (Wang et al., 2019) by using movement data gathered…”
BackgroundMethodInfluentialMixFormer: End-to-End Tracking With Iterative Mixed Attention
Cui, Y., Jiang, C., Wu, G., & Wang, L. (2024) · IEEE Transactions on Pattern Analysis and Machine Intelligence · doi:10.1109/tpami.2024.3349519 · Cited by 117
Human Short Long-Term Cognitive Memory Mechanism for Visual Monitoring in IoT-Assisted Smart Cities
Wang, S., Liu, X., Liu, S., Muhammad, K., Heidari, A. A., Ser, J. D., & de Albuquerque, V. H. C. (2021) · IEEE Internet of Things Journal · doi:10.1109/jiot.2021.3077600 · Cited by 99
Infrastructure-Based Object Detection and Tracking for Cooperative Driving Automation: A Survey
Bai, Z., Wu, G., Qi, X., Liu, Y., Oguchi, K., & Barth, M. (2022) · IEEE Intelligent Vehicles Symposium · doi:10.1109/iv51971.2022.9827461 · Cited by 108
Adaptive Region Proposal With Channel Regularization for Robust Object Tracking
Lu, X., Ma, C., Ni, B., & Yang, X. (2019) · IEEE Transactions on Circuits and Systems for Video Technology · doi:10.1109/tcsvt.2019.2944654 · Cited by 96
“Our motivation relies on three observations from prior works [8], [10]–[14], [17], [23].”
BackgroundMethodLiu, S., Huang, S., Wang, S., Muhammad, K., Bellavista, P., & Ser, J. D. (2023) · Information Fusion · doi:10.1016/j.inffus.2023.02.005 · Cited by 99
HRSiam: High-Resolution Siamese Network, Towards Space-Borne Satellite Video Tracking
Shao, J., Du, B., Wu, C., Gong, M., & Liu, T. (2021) · IEEE Transactions on Image Processing · doi:10.1109/tip.2020.3045634 · Cited by 98
SatSOT: A Benchmark Dataset for Satellite Video Single Object Tracking
Zhao, M., Li, S., Xuan, S., Kou, L., Gong, S., & Zhou, Z. (2022) · IEEE Transactions on Geoscience and Remote Sensing · doi:10.1109/tgrs.2022.3140809 · Cited by 115
“The discriminative correlation filter methods became popular later due to the faster processing speed [30]–[36].”
MethodMaximum Margin Correlation Filter: A New Approach for Localization and Classification
Rodriguez, A., Boddeti, V. N., Kumar, B. V. K. V., & Mahalanobis, A. (2012) · IEEE Transactions on Image Processing · doi:10.1109/tip.2012.2220151 · Cited by 101
“The MOSSE [10] filter is also designed using Eq.”
InfluentialFang, Z., Zhou, S., Cui, Y., & Scherer, S. (2020) · IEEE Sensors Journal · doi:10.1109/jsen.2020.3033034 · Cited by 112
Robust Visual Tracking by Segmentation
Paul, M., Danelljan, M., Mayer, C., & Gool, L. V. (2022) · Lecture notes in computer science · doi:10.1007/978-3-031-20047-2_33 · Cited by 122
SPARK: Spatial-Aware Online Incremental Attack Against Visual Tracking
Guo, Q., Xie, X., Juefei-Xu, F., Ma, L., Li, Z., Xue, W., Feng, W., & Liu, Y. (2020) · Lecture notes in computer science · doi:10.1007/978-3-030-58595-2_13 · Cited by 116
“, MOSSE [1], KCF [4], BACF [3], STRCF [5], and ECO [2] with the perturbations generated from SiamRPN-AlexNet.”
MethodGoogle map aided visual navigation for UAVs in GPS-denied environment
Shan, M., Wang, F., Lin, F., Gao, Z. Y., Tang, Y. Z., & Chen, B. M. (2015) · IEEE International Conference on Robotics and Biomimetics (ROBIO) · doi:10.1109/robio.2015.7418753 · Cited by 102
Recent advances of single-object tracking methods: A brief survey
Zhang, Y., Wang, T., Liu, K., Zhang, B., & Chen, L. (2021) · Neurocomputing · doi:10.1016/j.neucom.2021.05.011 · Cited by 101
Bai, Z., Wu, G., Barth, M., Liu, Y., Sisbot, E. A., Oguchi, K., & Huang, Z. (2024) · IEEE Transactions on Intelligent Transportation Systems · doi:10.1109/tits.2024.3436012 · Cited by 114
“Dedicated object tracking [45] and speed estimation algorithms have been optimized to track objects reliably from a UAV with limited computational efforts.”
MethodLong-Term Visual Object Tracking Benchmark
Moudgil, A., & Gandhi, V. (2019) · Lecture notes in computer science · doi:10.1007/978-3-030-20890-5_40 · Cited by 95
Real-Time Obstacle Detection and Tracking for Sense-and-Avoid Mechanism in UAVs
Bharati, S. P., Wu, Y., Sui, Y., Padgett, C. W., & Wang, G. (2018) · IEEE Transactions on Intelligent Vehicles · doi:10.1109/tiv.2018.2804166 · Cited by 98
“Usually, a small test window is selected on the object that needs to be tracked [32].”
BackgroundMethodQian, K., Zhou, J. W., Xiong, F., Zhou, H., & Du, J. (2018) · Lecture notes in computer science · doi:10.1007/978-3-030-04375-9_26 · Cited by 100
SiamFPN: A Deep Learning Method for Accurate and Real-Time Maritime Ship Tracking
Shan, Y., Zhou, X., Liu, S., Zhang, Y., & Huang, K. (2020) · IEEE Transactions on Circuits and Systems for Video Technology · doi:10.1109/tcsvt.2020.2978194 · Cited by 94
A computer vision-based method for bridge model updating using displacement influence lines
Martini, A., Tronci, E. M., Feng, M. Q., & Leung, R. Y. (2022) · Engineering Structures · doi:10.1016/j.engstruct.2022.114129 · Cited by 93
Object Tracking in Vary Lighting Conditions for Fog Based Intelligent Surveillance of Public Spaces
Liu, G., Liu, S., Muhammad, K., Sangaiah, A. K., & Doctor, F. (2018) · IEEE Access · doi:10.1109/access.2018.2834916 · Cited by 91
“By learning separate DCFs, the translation and scale estimation were carried out.”
MethodInfluentialMulti-Regularized Correlation Filter for UAV Tracking and Self-Localization
Ye, J., Fu, C., Lin, F., Ding, F., An, S., & Lu, G. (2021) · IEEE Transactions on Industrial Electronics · doi:10.1109/tie.2021.3088366 · Cited by 96
Deep motion features for visual tracking
Gladh, S., Danelljan, M., Khan, F. S., & Felsberg, M. (2016) · Proceedings - International Conference on Pattern Recognition/Proceedings/International Conference on Pattern Recognition · doi:10.1109/icpr.2016.7899807 · Cited by 94
“raw image patches [1], [21], image histograms and Haar features [19], color [6], [20], or shape features [2], [4].”
BackgroundMethodInfluentialFast Online Tracking With Detection Refinement
Shen, J., Yu, D., Deng, L., & Dong, X. (2017) · IEEE Transactions on Intelligent Transportation Systems · doi:10.1109/tits.2017.2750082 · Cited by 86
“In contrast, MOSSE [14] reduces this requirement of large training data by introducing a regularized variant of ASEF, which is more suitable for visual tracking.”
BackgroundMethodInfluentialMulti-Drone-Based Single Object Tracking With Agent Sharing Network
Zhu, P., Zheng, J., Du, D., Wen, L., Sun, Y., & Hu, Q. (2020) · IEEE Transactions on Circuits and Systems for Video Technology · doi:10.1109/tcsvt.2020.3045747 · Cited by 97
Robotic seam tracking system combining convolution filter and deep reinforcement learning
Zou, Y., Chen, T., Chen, X., & Li, J. (2021) · Mechanical Systems and Signal Processing · doi:10.1016/j.ymssp.2021.108372 · Cited by 86
Heerkens, H. D., van Vulpen, M., van den Berg, C. A. T., Tijssen, R. H. N., Crijns, S. P. M., Molenaar, I. Q., van Santvoort, H. C., Reerink, O., & Meijer, G. J. (2014) · Radiotherapy and Oncology · doi:10.1016/j.radonc.2014.03.002 · Cited by 85
Bauer, Z., Dominguez, A., Cruz, E., Gomez‐Donoso, F., Orts‐Escolano, S., & Cazorla, M. (2019) · Pattern Recognition Letters · doi:10.1016/j.patrec.2019.03.008 · Cited by 92
Deep learning serves traffic safety analysis: A forward‐looking review
Razi, A., Chen, X., Li, H., Wang, H., Russo, B. J., Chen, Y., & Yu, H. (2022) · IET Intelligent Transport Systems · doi:10.1049/itr2.12257 · Cited by 98
A Simple and Robust Correlation Filtering Method for Text-Based Person Search
Suo, W., Sun, M., Niu, K., Gao, Y., Wang, P., Zhang, Y., & Wu, Q. (2022) · Lecture notes in computer science · doi:10.1007/978-3-031-19833-5_42 · Cited by 104
“[2] introduces the correlation filter into the Fourier domain and achieves fast and accurate tracking.”
BackgroundMulti-UAV Collaborative Absolute Vision Positioning and Navigation: A Survey and Discussion
Tong, P., Yang, X., Yang, Y., Liu, W., & Wu, P. (2023) · Drones · doi:10.3390/drones7040261 · Cited by 99
Zhou, Y., Pei, Y., Li, Z., Fang, L., Zhao, Y., & Yi, W. (2020) · Measurement · doi:10.1016/j.measurement.2020.107801 · Cited by 84
Real-time RGB-D Tracking with Depth Scaling Kernelised Correlation Filters and Occlusion Handling
Camplani, M., Hannuna, S., Mirmehdi, M., Damen, D., Paiement, A., Tao, L., & Burghardt, T. (2015) · British Machine Vision Conference (BMVC) · doi:10.5244/c.29.145 · Cited by 84
“Additionally, the reader should refer to the works presented in [2, 5, 9, 10] for a comprehensive view of correlation filters.”
BackgroundGuo, Y., Yang, D., & Chen, Z. (2019) · IEEE Journal of Selected Topics in Applied Earth Observations and Remote Sensing · doi:10.1109/jstars.2019.2933488 · Cited by 86
“It is the adoption of a kernel mechanism that mainly makes KCF slightly slower than our method by increasing more inverse fast Fourier transformation (IFFT) operations.”
BackgroundMethodInfluentialSiamBAG: Band Attention Grouping-Based Siamese Object Tracking Network for Hyperspectral Videos
Li, W., Hou, Z., Zhou, J. W., & Tao, R. (2023) · IEEE Transactions on Geoscience and Remote Sensing · doi:10.1109/tgrs.2023.3285802 · Cited by 101
“Hence, the resulted images are {X(:, [13], [15], [16]), X(:, [4], [7], [10]), X(:, [5], [6], [8]), X(:, [1], [3], [14]), X(:, [2], [9], [11]), and X(:, [7], [12], [15])}.”
BackgroundAction-Driven Visual Object Tracking With Deep Reinforcement Learning
Yun, S., Choi, J., Yoo, Y., Yun, K., & Choi, J. Y. (2018) · IEEE Transactions on Neural Networks and Learning Systems · doi:10.1109/tnnls.2018.2801826 · Cited by 84
“Tracking methods based on a correlation filter [5]–[9] have attracted attention due to their computational efficiency and competitive performance.”
Video Relation Detection with Spatio-Temporal Graph
Qian, X., Zhuang, Y., Li, Y., Xiao, S., Pu, S., & Xiao, J. (2019) · ACM International Conference on Multimedia (ACM MM) · doi:10.1145/3343031.3351058 · Cited by 98
“[5] learned a discriminative correlation filter to localize the target in a new frame.”
BackgroundUCT: Learning Unified Convolutional Networks for Real-Time Visual Tracking
Zhu, Z. D., Huang, G., Zou, W., Du, D., & Huang, C. (2017) · IEEE International Conference on Computer Vision Workshops · doi:10.1109/iccvw.2017.231 · Cited by 86
“The proposed standard UCT (with ResNet-101) and UCT-Lite (with ZF-Net) can track generic objects at 41 FPS and 154 FPS, respectively, which is of significance for realtime computer vision systems.”
MethodInfluentialDeep Object Tracking with Shrinkage Loss
Lu, X., Ma, C., Shen, J., Yang, X., Reid, I. D., & Yang, M. (2020) · IEEE Transactions on Pattern Analysis and Machine Intelligence · doi:10.1109/tpami.2020.3041332 · Cited by 91
“learns a mapping between input features and the target labels usually generated by a Gaussian function [28], [29].”
BackgroundSimilarity-Guided Layer-Adaptive Vision Transformer for UAV Tracking
Xue, C., Zhong, B., Liang, Q., Zheng, Y., Li, N., Xue, Y., & Song, S. (2025) · 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/cvpr52734.2025.00631 · Cited by 103
“DCF-based trackers are widely used in the field of UAV tracking for their high efficiency, but they hardly maintain robustness under challenging conditions due to poor representation ability of hand-crafted features [3, 14– 16, 27, 32, 40].”
Real-time categorization of driver's gaze zone using the deep learning techniques
Choi, I.-H., Hong, S. K., & Kim, Y.-G. (2016) · International Conference on Big Data and Smart Computing · doi:10.1109/bigcomp.2016.7425813 · Cited by 82
CDTB: A Color and Depth Visual Object Tracking Dataset and Benchmark
Lukežič, A., Kart, U., Käpylä, J., Durmush, A., Kämäräinen, J., Matas, J., & Kristan, M. (2019) · IEEE/CVF International Conference on Computer Vision (ICCV) · doi:10.1109/iccv.2019.01011 · Cited by 80
Efficient Algorithms for In-Memory Fixed Point Multiplication Using MAGIC
Haj-Ali, A., Ben-Hur, R., Wald, N., & Kvatinsky, S. (2018) · IEEE International Symposium on Circuits and Systems proceedings · doi:10.1109/iscas.2018.8351561 · Cited by 87
Real-time visual detection and tracking system for traffic monitoring
Fernández-Sanjurjo, M., Bosquet, B., Mucientes, M., & Brea, V. M. (2019) · Engineering Applications of Artificial Intelligence · doi:10.1016/j.engappai.2019.07.005 · Cited by 86
“when the tracking fails) as the PSR (Peak to Sidelobe Ratio) value [20], which measures the spread degree of the convolution operation of the correlation filter, is not a reliable measure.”
BackgroundMethodDeformable part-based tracking by coupled global and local correlation filters
Akın, O., Erdem, E., Erdem, A., & Mikolajczyk, K. (2016) · Journal of Visual Communication and Image Representation · doi:10.1016/j.jvcir.2016.04.018 · Cited by 82
“MOSSE is extended in [12] to deal with the scaling problem which makes use of scale- space pyramid representation.85 Another highly efficient solution was offered in CSK [9] in which circulant matrices are employed, allowing correlation filters to be kernelized.”
BackgroundInfluentialTemporally Identity-Aware SSD With Attentional LSTM
Chen, X., Yu, J., & Wu, Z. (2019) · IEEE Transactions on Cybernetics · doi:10.1109/tcyb.2019.2894261 · Cited by 83
“As a closely relevant field, object tracking requires the initial position to be known as a prior knowledge [35].”
BackgroundMethodFrame-Event Alignment and Fusion Network for High Frame Rate Tracking
Zhang, J., Wang, Y., Liu, W., Li, M., Bai, J., Yin, B., & Yang, 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/cvpr52729.2023.00943 · Cited by 113
“, correlation filter (CF) trackers [1, 4, 18, 33], and deep trackers [2, 26, 39, 55, 64, 65].”
BackgroundInspection of Imprint Defects in Stamped Metal Surfaces Using Deep Learning and Tracking
Block, S. A. B., da Silva, R. D., Dorini, L. B., & Minetto, R. (2020) · IEEE Transactions on Industrial Electronics · doi:10.1109/tie.2020.2984453 · Cited by 84
“One may refer to the original paper [10] for further details on MOSSE.”
BackgroundMethodInfluentialRobust visual tracking with correlation filters and metric learning
Yuan, D., Kang, W. M., & He, Z. (2020) · Knowledge-Based Systems · doi:10.1016/j.knosys.2020.105697 · Cited by 80
Small Target Tracking in Satellite Videos Using Background Compensation
Wang, Y., Wang, T., Zhang, G., Cheng, Q., & Wu, J. (2020) · IEEE Transactions on Geoscience and Remote Sensing · doi:10.1109/tgrs.2020.2978512 · Cited by 81
“[10] first applied correlation filtering to target tracking, its use has become widespread.”
Background3D Siamese Transformer Network for Single Object Tracking on Point Clouds
Hui, L., Wang, L., Tang, L., Lan, K., Xie, J., & Yang, J. (2022) · Lecture notes in computer science · doi:10.1007/978-3-031-20086-1_17 · Cited by 97
FuCoLoT – A Fully-Correlational Long-Term Tracker
Lukežič, A., Zajc, L. Č., Vojíř, T., Matas, J., & Kristan, M. (2019) · Lecture notes in computer science · doi:10.1007/978-3-030-20890-5_38 · Cited by 84
“Confident localization produces a well expressed local maximum in the correlation response rt, which can be measured by the peak-to-sidelobe ratio PSR(rt) [3] and by the peak absolute value max(rt).”
BackgroundMethodOutput Constraint Transfer for Kernelized Correlation Filter in Tracking
Zhang, B., Li, Z., Cao, X., Ye, Q., Chen, C., Shen, L., Perina, A., & Jill, R. (2017) · IEEE Transactions on Systems, Man, and Cybernetics: Systems · doi:10.1109/tsmc.2016.2629509 · Cited by 75
A comprehensive review on intelligent surveillance systems
Ibrahim, S. (2016) · Communications in Science and Technology · doi:10.21924/cst.1.1.2016.7 · Cited by 93
“This tracker extended the minimum output sum of squared errors (MOSSE) tracker [78] with robust scale estimation.”
MethodDual Model Learning Combined With Multiple Feature Selection for Accurate Visual Tracking
Zhang, J., Jin, X., Sun, J., Wang, J., & Li, K. (2019) · IEEE Access · doi:10.1109/access.2019.2908668 · Cited by 75
“[10] utilize the minimum output sum of squared error (MOSSE) to learn the correlation filters on the gray image sequence and achieve efficient computation.”
BackgroundMethodAdaptive Channel Selection for Robust Visual Object Tracking with Discriminative Correlation Filters
Xu, T., Feng, Z., Wu, X., & Kittler, J. (2021) · International Journal of Computer Vision · doi:10.1007/s11263-021-01435-1 · Cited by 79
“The origins of the approach can be traced back to Bolme et al. , who proposed the minimum output sum of squared error (MOSSE) filter (Bolme et al. 2010) to realise adaptive correlation filtering in the frequency domain.”
BackgroundLiu, S., Wang, S., Liu, X., Dai, J., Muhammad, K., Gandomi, A. H., Ding, W., Hijji, M., & de Albuquerque, V. H. C. (2022) · IEEE Internet of Things Journal · doi:10.1109/jiot.2022.3142115 · Cited by 77
Chen, Y., Yuan, Q., Tang, Y., Xiao, Y., He, J., & Zhang, L. (2023) · IEEE Transactions on Geoscience and Remote Sensing · doi:10.1109/tgrs.2023.3347950 · Cited by 92
“Some efforts, such as [36], [37], [38], [39], and [40] have been made in correlation filters with hand-crafted features such as intensity, color name [41], and histogram of oriented gradients [42].”
BackgroundPang, Y., & Ling, H. (2013) · IEEE/CVF International Conference on Computer Vision (ICCV) · doi:10.1109/iccv.2013.346 · Cited by 77
“These papers, such as recent studies in [9, 12, 21, 30, 31, 56, 63, 66, 70] to name a few, are therefore not included.”
BackgroundHierarchical Tracking by Reinforcement Learning-Based Searching and Coarse-to-Fine Verifying
Zhong, B., Bai, B., Li, J., Zhang, Y., & Fu, Y. (2018) · IEEE Transactions on Image Processing · doi:10.1109/tip.2018.2885238 · Cited by 76
“Sum of Squared Error (MOSSE) filter [7], the tracking performance of CF-based trackers has been persistently”
BackgroundMethodInfluentialReliable Re-Detection for Long-Term Tracking
Wang, N., Zhou, W., & Li, H. (2018) · IEEE Transactions on Circuits and Systems for Video Technology · doi:10.1109/tcsvt.2018.2816570 · Cited by 76
Visual Tracking Under Motion Blur
Ma, B., Huang, L., Shen, J., Shao, L., Yang, M., & Porikli, F. (2016) · IEEE Transactions on Image Processing · doi:10.1109/tip.2016.2615812 · Cited by 78
“Our approach is compared with 13 recent state-of-the-art tracking methods including Multi-Task Tracking (MTT) tracker [27], Kernelized Correlation Filters (KCF) [44], Discriminative Scale Space Tracker (DSST) [51], Struck [10], Color-attribute based tracker (CNT) [42], Circulant Structure tracker with Kernels (CSK) [3…”
MethodThe Thermal Infrared Visual Object Tracking VOT-TIR2016 Challenge Results
Felsberg, M., Kristan, M., Matas, J., Leonardis, A., Pflugfelder, R. P., Hager, G., Berg, A., Eldesokey, A., Ahlberg, J., Zajc, L. Č., et al. (2016) · Lecture notes in computer science · doi:10.1007/978-3-319-48881-3_55 · Cited by 74
“Seven trackers are based on the method of discriminative correlation filters (DCFs) [22,23] with various sets of image features: DSST2014 (A.”
MethodDS-KCF: a real-time tracker for RGB-D data
Hannuna, S., Camplani, M., Hall, J., Mirmehdi, M., Damen, D., Burghardt, T., Paiement, A., & Tao, L. (2016) · Journal of Real-Time Image Processing · doi:10.1007/s11554-016-0654-3 · Cited by 84
“Additionally, refer the works presented in [3, 9, 14, 22, 23] for a comprehensive overview of correlation filters.”
BackgroundVisual object tracking with adaptive structural convolutional network
Yuan, D., Li, X., He, Z., Liu, Q., & Lu, S. (2020) · Knowledge-Based Systems · doi:10.1016/j.knosys.2020.105554 · Cited by 73
Human trajectory prediction in crowded scene using social-affinity Long Short-Term Memory
Pei, Z., Qi, X., Zhang, Y., Ma, M., & Yang, Y.-H. (2019) · Pattern Recognition · doi:10.1016/j.patcog.2019.04.025 · Cited by 65
Robust Visual Tracking Revisited: From Correlation Filter to Template Matching
Liu, F., Gong, C., Huang, X., Zhou, T., Yang, J., & Tao, D. (2018) · IEEE Transactions on Image Processing · doi:10.1109/tip.2018.2813161 · Cited by 72
“[5], in which the filter h is learned by minimizing the total squared error between the actual output and the desired correlation output Y = yi }n i=1 on a set of sample patches X = { xi }n i=1.”
BackgroundMethodRetracted: Multiscale fast correlation filtering tracking algorithm based on a feature fusion model
Chen, Y., Wang, J., Liu, S., Chen, X., Xiong, J., Xie, J., & Yang, K. (2019) · Concurrency and Computation Practice and Experience · doi:10.1002/cpe.5533 · Cited by 72
“The IDFT of Equation (26) is used to obtain the response value yt of the candidate predicted position with rectangle box Zt: yt = F −1{Yt}.”
MethodInfluentialRetractedChen, Y., Tang, Y., Xiao, Y., Yuan, Q., Zhang, Y., Liu, F., He, J., & Zhang, L. (2024) · ISPRS Journal of Photogrammetry and Remote Sensing · doi:10.1016/j.isprsjprs.2024.03.013 · Cited by 82
“Subsequently, CSK (Henriques et al., 2012) modeled after MOSSE introduces the circular matrix and kernel trick to improve tracking performance.”
Can We Track Targets From Space? A Hybrid Kernel Correlation Filter Tracker for Satellite Video
Shao, J., Du, B., Wu, C., & Zhang, L. (2019) · IEEE Transactions on Geoscience and Remote Sensing · doi:10.1109/tgrs.2019.2922648 · Cited by 71
“Minimum output sum of squared error filter (MOSSE) is a milestone for correlation filter-based methods, which was the first to employ classical signal processing analysis to derive fast correlation filters [31].”
MethodSalient Region-Based Online Object Tracking
Lee, H., & Kim, D. (2018) · IEEE Winter Conference on Applications of Computer Vision · doi:10.1109/wacv.2018.00133 · Cited by 74
“Starting with [2, 22], several trackers have adopted the correlation filter for efficient learning of a target model and have achieved state-of-the art performance in tracking challenges [18].”
BackgroundZhou, Y., Wang, T., Hu, R., Su, H., Liu, Y., Liu, X., Suo, J., & Snoussi, H. (2019) · IEEE Transactions on Signal Processing · doi:10.1109/tsp.2019.2917812 · Cited by 73
“In fact, the tracker with high PSR score has a strong confidence of that the true location of the target is near to the tracker’s estimation.”
MethodInfluentialDeep learning-based visual detection of marine organisms: A survey
Wang, N., Chen, T., Liu, S., Wang, R., Karimi, H. R., & Lin, Y. (2023) · Neurocomputing · doi:10.1016/j.neucom.2023.02.018 · Cited by 69
Underwater multi-robot convoying using visual tracking by detection
Shkurti, F., Chang, W.-D., Henderson, P., Islam, J., Higuera, J. C. G., Li, J., Manderson, T., Xu, A., Dudek, G., & Sattar, J. (2017) · IEEE/RSJ International Conference on Intelligent Robots and Systems (IROS) · doi:10.1109/iros.2017.8206280 · Cited by 74
“Works such as [23], [24] use convolutional neural networks and rely on supervised learning to learn a generic set”
BackgroundSoft Computing based object detection and tracking approaches: State-of-the-Art survey
Kaushal, M., Khehra, B. S., & Sharma, A. (2018) · Applied Soft Computing · doi:10.1016/j.asoc.2018.05.023 · Cited by 71
Hu, Z., Yang, D., Zhang, K., & Chen, Z. (2020) · IEEE Journal of Selected Topics in Applied Earth Observations and Remote Sensing · doi:10.1109/jstars.2020.2971657 · Cited by 67
“The contributions of each response will be weighted by their qualities, which are measured by the peak-to-sidelobe ratio (PSR) [5].”
BackgroundMethodRobust Visual Object Tracking Via Adaptive Attribute-Aware Discriminative Correlation Filters
Zhu, X., Wu, X., Xu, T., Feng, Z., & Kittler, J. (2021) · IEEE Transactions on Multimedia · doi:10.1109/tmm.2021.3050073 · Cited by 74
Thermal Infrared Target Tracking: A Comprehensive Review
Yuan, D., Zhang, H., Shu, X., Liu, Q., Chang, X., He, Z., & Shi, G. (2023) · IEEE Transactions on Instrumentation and Measurement · doi:10.1109/tim.2023.3338701 · Cited by 90
“Bolme et al. [71] proposed MOSSE, which first applied correlation filtering to video tracking tasks; SRDCF [72] introduces space regularization to solve the boundary effect; kernelized correlation filter (KCF) [48] is used to solve the problem of template matching.”
MethodEvent-Based Face Detection and Tracking Using the Dynamics of Eye Blinks
Lenz, G., Ieng, S.-H., & Benosman, R. (2020) · Frontiers in Neuroscience · doi:10.3389/fnins.2020.00587 · Cited by 60
“We use a maximum threshold of the peak-to-sidelobe ratio (Bolme et al., 2010), which measures the strength of a correlation peak and can therefore be used to detect occlusions or tracking failure while being able to continue the online update when the subject reappears.”
Vision-Based Target-Following Guider for Mobile Robot
Zhang, M., Liu, X., Xu, D., Cao, Z., & Yu, J. (2019) · IEEE Transactions on Industrial Electronics · doi:10.1109/tie.2019.2893829 · Cited by 71
Real-Time Multiple Face Recognition using Deep Learning on Embedded GPU System
Saypadith, S., & Aramvith, S. (2018) · Asia-Pacific Signal and Information Processing Association Annual Summit and Conference (APSIPA ASC) · doi:10.23919/apsipa.2018.8659751 · Cited by 72
“A closely related approach, proposed by Bolme et al. [12], is based on finding an adaptive correlation filter by minimizing the output sum of squared error (MOSSE).”
MethodJoint Classification and Regression for Visual Tracking with Fully Convolutional Siamese Networks
Cui, Y., Guo, D., Shao, Y., Wang, Z., Shen, C., Zhang, L., & Chen, S. (2022) · International Journal of Computer Vision · doi:10.1007/s11263-021-01559-4 · Cited by 75
“The introduction of correlation filter methods (Bolme et al., 2010; Danelljan et al., 2016a; Henriques et al., 2014; Li et al., 2017; Zhang et al., 2017b; Liu et al., 2016) improves the tracking performance significantly in terms of both efficiency and accuracy.”
MethodReal-Time 3D Single Object Tracking With Transformer
Shan, J., Zhou, S., Cui, Y., & Fang, Z. (2022) · IEEE Transactions on Multimedia · doi:10.1109/tmm.2022.3146714 · Cited by 88
“Early 2D visual trackers mainly focused on correlation filtering [27]–[30].”
Background3D Part-Based Sparse Tracker with Automatic Synchronization and Registration
Bibi, A., Zhang, T., & Ghanem, B. (2016) · 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.2016.160 · Cited by 80
“Examples of discriminative trackers include multiple instance learning tracking (MIL) [5], ensemble tracking [4], support vector tracking [3], correlation filter based trackers [14, 13, 7, 6, 20, 18], multiple experts entropy minimization (MEEM) tracker [32] and other multi-object based trackers like the tracklet asso…”
BackgroundA scale-adaptive object-tracking algorithm with occlusion detection
Yuan, Y., Chu, J., Leng, L., Miao, J., & Kim, B. (2020) · EURASIP Journal on Image and Video Processing · doi:10.1186/s13640-020-0496-6 · Cited by 72
RPformer: A Robust Parallel Transformer for Visual Tracking in Complex Scenes
Gu, F., Lu, J., & Cai, C. (2022) · IEEE Transactions on Instrumentation and Measurement · doi:10.1109/tim.2022.3170972 · Cited by 84
Iftikhar, S., Asim, M., Zhang, Z., Muthanna, A., Chen, J., ELAffendi, M. A., Sedik, A., & El‐Latif, A. A. A. (2023) · Applied Sciences · doi:10.3390/app13063995 · Cited by 74
“In [14,15], fast fourier transform and kernel function were employed on a discriminative correlation filter-based detective to perform the complex computation in the frequency domain rather than in the spatial domain which optimized and enhanced the performance of the detecting model.”
MethodState-Aware Anti-Drift Object Tracking
Han, Y., Deng, C., Zhao, B., & Tao, D. (2019) · IEEE Transactions on Image Processing · doi:10.1109/tip.2019.2905984 · Cited by 66
“Using correlation filters for tracking started with MOSSE [13].”
MethodManifold Siamese Network: A Novel Visual Tracking ConvNet for Autonomous Vehicles
Gao, M., Jin, L., Jiang, Y., & Guo, B. (2019) · IEEE Transactions on Intelligent Transportation Systems · doi:10.1109/tits.2019.2930337 · Cited by 70
“While the fastest speed belongs to CSK [24], our tracker runs at 40 FPS and is slightly slower than the baseline CFNet.”
MethodResultA survey on online learning for visual tracking
Abbass, M. Y., Kwon, K.-C., Kim, N., Abdelwahab, S. A., El-Samie, F. E. A., & Khalaf, A. A. M. (2021) · The Visual Computer · doi:10.1007/s00371-020-01848-y · Cited by 64
“[67] added correlation filters (CFs) into the tracking process, and proposed the minimum output”
BackgroundKutschbach, T., Bochinski, E., Eiselein, V., & Sikora, T. (2017) · 2017 14th IEEE International Conference on Advanced Video and Signal Based Surveillance (AVSS) · doi:10.1109/avss.2017.8078517 · Cited by 66
“while different hypotheses for the same track i are denoted as x([1]) i ,x [2] i ,x [1,1] i ,x [2,1] i , .”
BackgroundKart, U., Kämäräinen, J., & Matas, J. (2019) · Lecture notes in computer science · doi:10.1007/978-3-030-11009-3_8 · Cited by 71
“Since the original idea of Discriminative Correlation Filter (DCF) for tracking [28, 16], many improvements have been proposed.”
BackgroundEnhanced robust spatial feature selection and correlation filter learning for UAV tracking
Wen, J., Chu, H., Lai, Z., Xu, T., & Shen, L. (2023) · Neural Networks · doi:10.1016/j.neunet.2023.01.003 · Cited by 64
Remote Sensing Object Tracking With Deep Reinforcement Learning Under Occlusion
Cui, Y., Hou, B., Wu, Q., Ren, B., Wang, S., & Jiao, L. (2021) · IEEE Transactions on Geoscience and Remote Sensing · doi:10.1109/tgrs.2021.3096809 · Cited by 71
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.