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 501–600 of 1,002
Ma, S., Zhao, B., Hou, Z., Yu, W., Pu, L., & Yang, X. (2023) · Expert Systems with Applications · doi:10.1016/j.eswa.2023.122131 · Cited by 37
Yu, T., Mo, B., Liu, F., Qi, H., & Liu, Y. (2019) · Infrared Physics & Technology · doi:10.1016/j.infrared.2019.02.012 · Cited by 35
Beyond SOT: Tracking Multiple Generic Objects at Once
Mayer, C., Danelljan, M., Yang, M., Ferrari, V., Gool, L. V., & Kuznetsova, A. (2024) · IEEE Winter Conference on Applications of Computer Vision · doi:10.1109/wacv57701.2024.00668 · Cited by 49
“Generic Object Tracking refers to the task of tracking potentially multiple user-defined target objects of arbitrary classes specified by a user-specified bounding box in the initial video frame.”
BackgroundLiu, Z., Zhong, Y., Ma, G., Wang, X., & Zhang, L. (2024) · IEEE Transactions on Geoscience and Remote Sensing · doi:10.1109/tgrs.2024.3483072 · Cited by 44
Zero-Aliasing Correlation Filters for Object Recognition
Fernandez, J. A., Boddeti, V. N., Rodríguez, A., & Kumar, B. V. K. V. (2014) · IEEE Transactions on Pattern Analysis and Machine Intelligence · doi:10.1109/tpami.2014.2375215 · Cited by 35
Learning Scale-Adaptive Tight Correlation Filter for Object Tracking
Zhang, S., Lu, W. B., Xing, W., & Zhang, L. (2018) · IEEE Transactions on Cybernetics · doi:10.1109/tcyb.2018.2868782 · Cited by 35
“[31] proposed a minimum output sum of a squared error filter for tracking, which first models the appearance adaptively by learning the correlation filter but does not make full use of the spatial constraints.”
BackgroundContent-Related Spatial Regularization for Visual Object Tracking
Han, R., Guo, Q., & Feng, W. (2018) · IEEE International Conference on Multimedia and Expo (ICME) · doi:10.1109/icme.2018.8486487 · Cited by 34
“Recently, correlation filters (CF) tracking [2, 3], being one of the best tracking frameworks, has shown continuous performance improvement in terms of accuracy and robustness on various benchmarks [1, 4].”
BackgroundLearning Soft-Consistent Correlation Filters for RGB-T Object Tracking
Wang, Y., Li, C., & Tang, J. (2018) · Lecture notes in computer science · doi:10.1007/978-3-030-03341-5_25 · Cited by 43
Using FTOC to track shuttlecock for the badminton robot
Chen, W., Liao, T., Li, Z., Lin, H., Xue, H., Zhang, L., Guo, J., & Cao, Z. (2019) · Neurocomputing · doi:10.1016/j.neucom.2019.01.023 · Cited by 34
Coral Identification and Counting with an Autonomous Underwater Vehicle
Modasshir, M., Rahman, S., Youngquist, O., & Rekleitis, I. M. (2018) · IEEE International Conference on Robotics and Biomimetics (ROBIO) · doi:10.1109/robio.2018.8664785 · Cited by 38
“The MOSSE [33] tracker exploited adaptive correlation filter.”
MethodMultiple Object Trackers in OpenCV: A Benchmark
Dardagan, N., Brđanin, A., Džigal, D., & Akagić, A. (2021) · IEEE International Symposium on Industrial Electronics (ISIE) · doi:10.1109/isie45552.2021.9576367 · Cited by 42
“Minimum Output Sum of Squared Error (MOSSE) Visual object tracking using adaptive correlation filters [18] 2010 (2319) 5.”
MethodAdaptive spatial-temporal surrounding-aware correlation filter tracking via ensemble learning
Moorthy, S., & Joo, Y. H. (2023) · Pattern Recognition · doi:10.1016/j.patcog.2023.109457 · Cited by 34
Coloring Channel Representations for Visual Tracking
Danelljan, M., Hager, G., Khan, F. S., & Felsberg, M. (2015) · Lecture notes in computer science · doi:10.1007/978-3-319-19665-7_10 · Cited by 34
“Recently, the discriminative correlation filter [3] based trackers have received much research attention thanks to their accuracy, simplicity and speed.”
BackgroundVisual tracking via exemplar regression model
Ma, X., Liu, Q., He, Z., Zhang, X., & Chen, W.-S. (2016) · Knowledge-Based Systems · doi:10.1016/j.knosys.2016.05.028 · Cited by 32
“Among the achievements in visual tracking research, the discriminative approaches [1, 2, 3, 4, 5, 6, 7, 8, 9] provide an online mechanism that adapts appearance variations of the target, and achieve better results than their generative rivals [10, 11, 12, 13] on some hard sequences [14].”
BackgroundMethodInfluentialApplying Detection Proposals to Visual Tracking for Scale and Aspect Ratio Adaptability
Huang, D., Luo, L., Chen, Z., Wen, M., & Zhang, C. (2016) · International Journal of Computer Vision · doi:10.1007/s11263-016-0974-6 · Cited by 33
“DSST (Danelljan et al. 2014a) combines two separate correlation filters together, a MOSSE based filter for target translation estimation and an one-dimensional correlation filter for scale estimation.”
MethodInfluentialOnline Scale Adaptive Visual Tracking Based on Multilayer Convolutional Features
Wang, X., Hou, Z., Yu, W., Jin, Z., Zha, Y., & Qin, X. (2017) · IEEE Transactions on Cybernetics · doi:10.1109/tcyb.2017.2768570 · Cited by 32
“2) We construct a scale filter of the target based on correlation filter (CF) [16], [17] method.”
MethodInfluentialDeep motion and appearance cues for visual tracking
Danelljan, M., Bhat, G., Gladh, S., Khan, F. S., & Felsberg, M. (2018) · Pattern Recognition Letters · doi:10.1016/j.patrec.2018.03.009 · Cited by 33
Kerman: A Hybrid Lightweight Tracking Algorithm to Enable Smart Surveillance as an Edge Service
Nikouei, S. Y., Chen, Y., Song, S., & Faughnan, T. R. (2019) · IEEE Consumer Communications and Networking Conference · doi:10.1109/ccnc.2019.8651791 · Cited by 32
Anwar, A., Lin, W., Deng, X., Qiu, J., & Gao, H. (2018) · IEEE Transactions on Industrial Electronics · doi:10.1109/tie.2018.2881948 · Cited by 32
“Furthermore, the frames per second of these algorithms is also low except that of MOSSE tracker, which gives an equally competing frame rate.”
MethodMining Spatial-Temporal Similarity for Visual Tracking
Zhang, Y., Gao, X., Chen, Z., Zhong, H., Xie, H., & Yan, C. C. (2020) · IEEE Transactions on Image Processing · doi:10.1109/tip.2020.2981813 · Cited by 35
“A remarkable advancement of the search method in visual tracking community lies in the correlation filter, which densely samples a large region surrounding the previous target [2], [7].”
BackgroundMethodInfluentialLearning dynamic regression with automatic distractor repression for real-time UAV tracking
Fu, C., Ding, F., Li, Y., Jin, J., & Feng, C. (2020) · Engineering Applications of Artificial Intelligence · doi:10.1016/j.engappai.2020.104116 · Cited by 32
Time-Dynamic Estimates of the Reliability of Deep Semantic Segmentation Networks
Maag, K., Rottmann, M., & Gottschalk, H. (2020) · IEEE International Conference on Tools with Artificial Intelligence (ICTAI) · doi:10.1109/ictai50040.2020.00084 · Cited by 43
“Another approach for tracking-by-detection uses adaptive correlation filters that model the targets appearance, the tracking is then performed via convolution with the filters [20].”
MethodA Collaborative Learning Tracking Network for Remote Sensing Videos
Li, X., Jiao, L., Zhu, H., Liu, F., Yang, S., Zhang, X., Wang, S., & Qu, R. (2022) · IEEE Transactions on Cybernetics · doi:10.1109/tcyb.2022.3182993 · Cited by 34
“While discriminant models, such as tracking learning detection (TLD) [9], struck [10], MOSSE [11] usually compare the difference of object and background simultaneously through a discriminant function.”
BackgroundWang, S., Qian, K., & Chen, P. (2022) · Workshop on Hyperspectral Image and Signal Processing: Evolution in Remote Sensing · doi:10.1109/whispers56178.2022.9955025 · Cited by 38
“proposed the fast Minimum Output Sum of Squared Error (MOSSE) tracker [9], which uses gray-scale features and achieves a high speed.”
Intelligent Video Analytics for Human Action Recognition: The State of Knowledge
Kulbacki, M., Segen, J., Chaczko, Z., Rozenblit, J. W., Kulbacki, M., Klempous, R., & Wojciechowski, K. W. (2023) · Sensors · doi:10.3390/s23094258 · Cited by 35
Shah, S. H. H., Karlsen, A., Solberg, M., & Hameed, I. A. (2023) · Expert Systems with Applications · doi:10.1016/j.eswa.2023.122482 · Cited by 33
Single Object Trackers in OpenCV: A Benchmark
Brdjanin, A., Dardagan, N., Džigal, D., & Akagić, A. (2020) · International Conference on Innovations in Intelligent Systems and Applications (INISTA) · doi:10.1109/inista49547.2020.9194647 · Cited by 35
“Minimum uutput :Sum ot :squared Visual object tracking using adaptive correlation filters [13] 2010 (1839) Error (MOSSE) 5.”
MethodSparse Learning-Based Correlation Filter for Robust Tracking
Zhang, W., Jiao, L., Li, Y., & Liu, J. (2020) · IEEE Transactions on Image Processing · doi:10.1109/tip.2020.3039392 · Cited by 31
Vision-based People Counting for Attendance Monitoring System
Le, M. C., Le, M.-H., & Duong, M.-T. (2020) · International Conference on Green Technology and Sustainable Development (GTSD) · doi:10.1109/gtsd50082.2020.9303117 · Cited by 34
“Compared to other tracking methods, tracking filters created by MOSSE [12] are better at differentiating between tracking targets and background, and more robust to changes in targets’ appearance.”
MethodVisual tracking via dynamic saliency discriminative correlation filter
Gao, L., Liu, B., Fu, P., Xu, M., & Li, J. (2021) · Applied Intelligence · doi:10.1007/s10489-021-02260-2 · Cited by 32
“Figure 1b shows the training sample set after affine transformation by calculating the peak-to-sidelobe ratio(PSR) [5].”
MethodInfluentialZhang, J., Yuan, T., He, Y., & Wang, J. (2022) · Neural Computing and Applications · doi:10.1007/s00521-021-06771-4 · Cited by 32
“firstly proposed the Minimum Output Sum of Square Error (MOSSE) [34] filters for object tracking.”
Global Instance Tracking: Locating Target More Like Humans
Hu, S., Zhao, X., Huang, L., & Huang, K. (2022) · IEEE Transactions on Pattern Analysis and Machine Intelligence · doi:10.1109/tpami.2022.3153312 · Cited by 42
“As the first model to utilize the correlation filter framework in object tracking, MOSSE [24] considers this task as a regularized least-squares problem and reformulates its closed-form solution, achieving reliable tracking performance at 700 fps.”
MethodAd 2 Attack: Adaptive Adversarial Attack on Real-Time UAV Tracking
Fu, C., Li, S., Yuan, X., Ye, J., Cao, Z., & Ding, F. (2022) · Proceedings - IEEE International Conference on Robotics and Automation/Proceedings · doi:10.1109/icra46639.2022.9812056 · Cited by 39
Dynamic feature fusion with spatial-temporal context for robust object tracking
Nai, K., Li, Z., & Wang, H. (2022) · Pattern Recognition · doi:10.1016/j.patcog.2022.108775 · Cited by 35
Deep Siamese Network With Motion Fitting for Object Tracking in Satellite Videos
Ruan, L., Guo, Y., Yang, D., & Chen, Z. (2022) · IEEE Geoscience and Remote Sensing Letters · doi:10.1109/lgrs.2022.3158652 · Cited by 31
Achieving Adaptive Visual Multi-Object Tracking with Unscented Kalman Filter
Zhang, G., Yin, J., Deng, P., Sun, Y., Zhou, L., & Zhang, K. (2022) · Sensors · doi:10.3390/s22239106 · Cited by 32
Survey of connected automated vehicle perception mode: from autonomy to interaction
Shangguan, W., Du, Y., Guo, C. L., Liu, D., & Shu, W. W. (2018) · IET Intelligent Transport Systems · doi:10.1049/iet-its.2018.5239 · Cited by 31
“CF algorithm tracks the targets by calculating the partial maximum response in candidate areas using adaptive CF [35].”
MethodA Two-Stream Siamese Neural Network for Vehicle Re-Identification by Using Non-Overlapping Cameras
de Oliveira, Í. O., Fonseca, K. V. O., & Minetto, R. (2019) · Proceedings - International Conference on Image Processing · doi:10.1109/icip.2019.8803810 · Cited by 31
“Therefore, we used the MOSSE tracker [21] to extract the N first occurrences of each license plate (see Fig 4).”
MethodDiscriminative Fusion Correlation Learning for Visible and Infrared Tracking
Yun, X., Sun, Y., Yang, X., & Lu, N. (2019) · Mathematical Problems in Engineering · doi:10.1155/2019/2437521 · Cited by 31
“The target human in the visible sequence encounters similar background disturbance (i.e., bikes), which causes the ODFS, MOSSE, fDSST, TSKF, and MVMKF trackers to drift away from the target.”
MethodInfluentialUnifying Motion and Appearance Cues for Visual Tracking via Shared Queries
Xue, C., Zhong, B., Liang, Q., Xia, H., & Song, S. (2024) · IEEE Transactions on Circuits and Systems for Video Technology · doi:10.1109/tcsvt.2024.3486347 · Cited by 44
“As the seminal work of CF-based tracking methods, MOSSE [15] employs a filtering template to perform correlation operations with candidate regions for locating targets.”
Visual object tracking via enhanced structural correlation filter
Chen, K., Tao, W., & Han, S. (2017) · Information Sciences · doi:10.1016/j.ins.2017.02.012 · Cited by 34
“Recently, correlation filter-based trackers have become the most popular algorithms among the visual object tracking community [5, 9, 10, 15, 16, 35].”
BackgroundRobust infrared target tracking using discriminative and generative approaches
Asha, C. S., & Narasimhadhan, A. V. (2017) · Infrared Physics & Technology · doi:10.1016/j.infrared.2017.05.022 · Cited by 32
A novel adaptive kernel correlation filter tracker with multiple feature integration
Liu, Z., Lian, Z., & Li, Y. (2017) · Proceedings - International Conference on Image Processing · doi:10.1109/icip.2017.8296747 · Cited by 30
“Since our tracker belongs to discriminative trackers, we restrict our review to those trackers close to our work, such as TLD [9], Struck [10], CSK [2], MOSSE [1], KCF [3], DSST [4], SAMF [5], etc.”
BackgroundMethodInfluentialA New Dataset and Performance Evaluation of a Region-Based CNN for Urban Object Detection
Dominguez-Sanchez, A., Cazorla, M., & Orts‐Escolano, S. (2018) · Electronics · doi:10.3390/electronics7110301 · Cited by 31
Feng, M., Song, K., Wang, Y., Liu, J., & Yan, Y. (2020) · Journal of Visual Communication and Image Representation · doi:10.1016/j.jvcir.2020.102881 · Cited by 34
Fire smoke detection based on target-awareness and depthwise convolutions
Zhao, Y., Zhang, H., Zhang, X., & Chen, X. (2021) · Multimedia Tools and Applications · doi:10.1007/s11042-021-11037-1 · Cited by 30
“…as follows: The total computational cost of depthwise separable convolutions is defined as follows: The computation reduction according to depthwise and pointwise streamline combinations can be obtained as follows: In TADT, the cross-correlation filter [2] is applied to speed up the computations.”
MethodAn Enhanced SiamMask Network for Coastal Ship Tracking
Yang, X., Wang, Y., Wang, N., & Gao, X. (2021) · IEEE Transactions on Geoscience and Remote Sensing · doi:10.1109/tgrs.2021.3122330 · Cited by 37
“In the past, object tracking mostly used the correlation filter method [5], minimum output sum of squared error (MOSSE), which is robust to variations in lighting, scale, posture, and nonrigid deformations while operating at 669 frames per second.”
MethodVideo SAR Moving Target Tracking Using Joint Kernelized Correlation Filter
Zhong, C., Ding, J., & Zhang, Y. (2022) · IEEE Journal of Selected Topics in Applied Earth Observations and Remote Sensing · doi:10.1109/jstars.2022.3146035 · Cited by 31
Moving Object Detection and Tracking by Event Frame from Neuromorphic Vision Sensors
Zhao, J. B., Ji, S., Cai, Z., Zeng, Y., & Wang, Y. (2022) · Biomimetics · doi:10.3390/biomimetics7010031 · Cited by 30
“[27] propose the minimum output sum of squared error (MOSSE) filter.”
BackgroundJoint Correlation and Attention Based Feature Fusion Network for Accurate Visual Tracking
Yang, Y., & Gu, X. (2023) · IEEE Transactions on Image Processing · doi:10.1109/tip.2023.3251027 · Cited by 31
Correlation filters based on temporal regularization and background awareness,
Zhao, J.-W., Lu, Y., & Zhou, Z.-H. (2020) · Computers & electrical engineering · doi:10.1016/j.compeleceng.2020.106757 · Cited by 26
Moorthy, S., & Joo, Y. H. (2023) · Neural Networks · doi:10.1016/j.neunet.2023.08.019 · Cited by 29
Siamese network ensemble for visual tracking
Jiang, C., Xiao, J., Xie, Y., Tillo, T., & Huang, K. (2017) · Neurocomputing · doi:10.1016/j.neucom.2017.10.043 · Cited by 31
Efficient Visual Tracking With Stacked Channel-Spatial Attention Learning
Rahman, M. M., Fiaz, M., & Jung, S. K. (2020) · IEEE Access · doi:10.1109/access.2020.2997917 · Cited by 31
“This situation has altered somewhat with the introduction of the minimum output sum of squared error (MOSSE) [10] filter, which allows adaptive training schemes to perform robust and efficient object tracking.”
BackgroundInfluentialVision-Based Target Detection and Tracking System for a Quadcopter
Wu, S., Li, R., Shi, Y., & Liu, Q. (2021) · IEEE Access · doi:10.1109/access.2021.3074413 · Cited by 32
“Due to their impressive robustness and real-time capabilities, discriminative correlation filter (DCF-)based trackers [13], [14] have gained sustained attention.”
BackgroundAnti-Distractor Active Object Tracking in 3D Environments
Xi, M., Zhou, Y., Chen, Z., Zhou, W., & Li, H. (2021) · IEEE Transactions on Circuits and Systems for Video Technology · doi:10.1109/tcsvt.2021.3107153 · Cited by 36
Learning object-uncertainty policy for visual tracking
He, X., & Chen, C. Y. (2021) · Information Sciences · doi:10.1016/j.ins.2021.09.002 · Cited by 29
Ma, L., Luo, X., Hong, H., Zhang, Y., Wang, L., & Wu, J. (2022) · Applied Intelligence · doi:10.1007/s10489-022-04014-0 · Cited by 29
“We first filter out regions unrelated to foreground features, via the correlation filtering technology [2] to illuminate the discriminant regions associated with the foreground and enhance the distinction between foreground and background regions.”
MethodZhao, D., Zhu, X., Zhang, Z., Arun, P. V., Cao, J., Wang, Q., Zhou, H., Jiang, H., Hu, J., & Qian, K. (2023) · Signal Processing · doi:10.1016/j.sigpro.2023.109033 · Cited by 31
PVT++: A Simple End-to-End Latency-Aware Visual Tracking Framework
Li, B., Huang, Z., Ye, J., Li, Y., Scherer, S., Zhao, H., & Fu, C. (2023) · IEEE/CVF International Conference on Computer Vision (ICCV) · doi:10.1109/iccv51070.2023.00918 · Cited by 33
“Visual trackers basically fall into two paradigms, respectively based on discriminative correlation filters [4, 27, 15, 13] and Siamese networks [2, 34, 64, 33, 23, 58].”
Robust fusion for RGB-D tracking using CNN features
Wang, Y., Wei, X., Shen, H., Ding, L., & Wan, J. (2020) · Applied Soft Computing · doi:10.1016/j.asoc.2020.106302 · Cited by 29
Real-time Target Tracking Based on PCANet-CSK Algorithm
Hu, Z., Wang, X., Xu, K., & Dong, P. (2019) · doi:10.1145/3374587.3374607 · Cited by 29
“Our idea of scale updating is from DSST[14], which is expanded based on MOSSE algorithm[13].”
MethodHotMoE: Exploring Sparse Mixture-of-Experts for Hyperspectral Object Tracking
Sun, W., Tan, Y., Li, J., Hou, S., Li, X., Shao, Y., Wang, Z., & Song, B. (2025) · IEEE Transactions on Multimedia · doi:10.1109/tmm.2025.3535339 · Cited by 34
Co-difference based object tracking algorithm for infrared videos
Demir, H. S., & Çetin, A. E. (2016) · Proceedings - International Conference on Image Processing · doi:10.1109/icip.2016.7532394 · Cited by 28
“EXPERIMENTS We compared the proposed co-difference based tracking algorithm with various state-of-the-art trackers: COV [5], TBOOST [2], MILTrack [8], ODFS [9], FCT [10], STRUCK [11], L1APG [12], MOSSE [13], CRC [14] and IVT [15].”
MethodKernel correlation filters for visual tracking with adaptive fusion of heterogeneous cues
Bai, B., Zhong, B., Ouyang, G., Wang, P., Liu, X., Chen, Z., & Wang, C. (2018) · Neurocomputing · doi:10.1016/j.neucom.2018.01.068 · Cited by 28
Real-Time Underwater Fish Tracking Based on Adaptive Multi-Appearance Model
Li, X., Wei, Z., Huang, L., Nie, J., Zhang, W., & Wang, L. (2018) · Proceedings - International Conference on Image Processing · doi:10.1109/icip.2018.8451469 · Cited by 32
“propose to learn a Minimum Output Sum of Squared Error (MOSSE) filter to estimate the target translation for tracking [10].”
BackgroundRobust Visual Tracking via Hierarchical Particle Filter and Ensemble Deep Features
Li, S., Zhao, S., Cheng, B. H., Zhao, E., & Chen, J. (2018) · IEEE Transactions on Circuits and Systems for Video Technology · doi:10.1109/tcsvt.2018.2889457 · Cited by 29
Correlation Filter Selection for Visual Tracking Using Reinforcement Learning
Xie, Y., Xiao, J., Huang, K., Thiyagalingam, J., & Zhao, Y. (2018) · IEEE Transactions on Circuits and Systems for Video Technology · doi:10.1109/tcsvt.2018.2889488 · Cited by 29
“Discriminative correlation filter (CF)-based trackers [1]–[5] achieve a good trade-off between accuracy and speed by efficiently solving a ridge regression problem in Fourier frequency domain.”
MethodCascaded Correlation Refinement for Robust Deep Tracking
Ge, S., Zhang, C., Li, S., Zeng, D., & Tao, D. (2020) · IEEE Transactions on Neural Networks and Learning Systems · doi:10.1109/tnnls.2020.2984256 · Cited by 33
Multi-Hierarchical Independent Correlation Filters For Visual Tracking
Bai, S., He, Z., Dong, Y., & Bai, H. (2020) · IEEE International Conference on Multimedia and Expo (ICME) · doi:10.1109/icme46284.2020.9102759 · Cited by 30
“[21] propose a CF tracker by learning a minimum output sum of squared error (MOSSE) for target appearance, which is able to run in high speed.”
BackgroundMulti-Metric Re-Identification for Online Multi-Person Tracking
Nodehi, H., & Shahbahrami, A. (2021) · IEEE Transactions on Circuits and Systems for Video Technology · doi:10.1109/tcsvt.2021.3059250 · Cited by 32
Kent, T. A., Kim, S., Kornilowicz, G., Yuan, W., Hartmann, M. J. Z., & Bergbreiter, S. (2021) · IEEE Robotics and Automation Letters · doi:10.1109/lra.2021.3062816 · Cited by 28
Correlation Filters Based on Multi-Expert and Game Theory for Visual Object Tracking
Ma, S., Zhao, Z., Hou, Z., Zhang, L., Yang, X., & Pu, L. (2022) · IEEE Transactions on Instrumentation and Measurement · doi:10.1109/tim.2022.3178482 · Cited by 35
Memory Network With Pixel-Level Spatio-Temporal Learning for Visual Object Tracking
Zhou, Z., Zhou, X., Chen, Z., Guo, P., Liu, Q., & Zhang, W. (2023) · IEEE Transactions on Circuits and Systems for Video Technology · doi:10.1109/tcsvt.2023.3272319 · Cited by 32
“Online-learning based methods [20], [21], [22], [23], [24] utilize updated correlation filter to locate the object.”
MethodToothbrush motion analysis to help children learn proper tooth brushing
Marcon, M., Sarti, A., & Tubaro, S. (2016) · Computer Vision and Image Understanding · doi:10.1016/j.cviu.2016.03.009 · Cited by 28
Learning Multi-Domain Convolutional Network for RGB-T Visual Tracking
Zhang, X., Zhang, X., Du, X., Zhou, X., & Yin, J. (2018) · International Congress on Image and Signal Processing (CISP) · doi:10.1109/cisp-bmei.2018.8633180 · Cited by 34
“The tracking method based on the correlation filter[12] attracts many researchers’ attention because of its speed and good effect.”
MethodAn accelerated correlation filter tracker
Xu, T., Feng, Z., Wu, X., & Kittler, J. (2019) · Pattern Recognition · doi:10.1016/j.patcog.2019.107172 · Cited by 36
“MOSSE was proposed to achieve fast object tracking via correlation, with the objective of minimising the sum of squared errors.”
MethodInfluentialSAR Ground Moving Target Refocusing by Combining mRe³ Network and TVβ-LSTM
Zhou, Y., Shi, J., Wang, C., Hu, Y. G., Zhou, Z., Yang, X., Zhang, X., & Wei, S. (2020) · IEEE Transactions on Geoscience and Remote Sensing · doi:10.1109/tgrs.2020.3033656 · Cited by 28
BoLTVOS: Box-Level Tracking for Video Object SegmentationPreprint
Voigtlaender, P., Luiten, J., & Leibe, B. (2019) · arXiv (Cornell University) · doi:10.48550/arxiv.1904.04552 · Cited by 29
“All of these methods work by searching within a local window of the previous prediction using a template cross-correlation [2, 16, 30] followed by an RPN detector.”
MethodSakthivel, S. S. K., Moorthy, S., Arthanari, S., Jeong, J. H., & Joo, Y. H. (2024) · Mathematics · doi:10.3390/math12142279 · Cited by 27
“Inspired by [7], the authors in [12] proposed a CSK tracker which replaces the sum of squared error with a circulant structure of kernels.”
A Multi Object Tracking Framework Based on YOLOv8s and Bytetrack Algorithm
Wang, Y., & Mariano, V. Y. (2024) · IEEE Access · doi:10.1109/access.2024.3450370 · Cited by 32
“Early MOT algorithms [1], [2], [3], [4], [5], [6] mainly used human-designed features to conduct inter-frame target association, and the available target information was limited.”
BackgroundRobust Object Tracking With Discrete Graph-Based Multiple Experts
Li, J., Deng, C., Xu, R. Y. D., Tao, D., & Zhao, B. (2017) · IEEE Transactions on Image Processing · doi:10.1109/tip.2017.2686601 · Cited by 27
Robust Tracking and Redetection: Collaboratively Modeling the Target and Its Context
Liu, C., Liu, P., Zhao, W., & Tang, X. (2017) · IEEE Transactions on Multimedia · doi:10.1109/tmm.2017.2760633 · Cited by 27
“The training requirement had rendered the use of correlation filters for online tracking inappropriate until the proposal of the minimum-output sum of squared error [28], which uses FFT to expedite training.”
MethodDeep Location-Specific Tracking
Yang, L., Liu, R., Zhang, D. D., & Zhang, L. (2017) · ACM International Conference on Multimedia (ACM MM) · doi:10.1145/3123266.3123381 · Cited by 28
“In recent years, the Discriminative Correlation Filters (DCF) based methods [5, 8, 10, 19, 19] have achieved good results in terms of accuracy and speeds.”
MethodTehsin, S., Rehman, S. U., Saeed, M. O. B., Riaz, F., Hassan, A., Abbas, M., Young, R. C. D., & Alam, M. S. (2017) · IEEE Access · doi:10.1109/access.2017.2762354 · Cited by 27
“Correlation filters have been widely used in numerous domains including Pattern Recognition, Signal Processing and Image Processing for various applications such as automatic target recognition (ATR) [1]–[5], biometric recognition [6]–[8] and object tracking [9], [10].”
MethodExtraction and analysis of microscopic traffic data in disordered heterogeneous traffic conditions
Amrutsamanvar, R., Muthurajan, B., & Vanajakshi, L. (2019) · Transportation Letters · doi:10.1080/19427867.2019.1695563 · Cited by 27
Moorthy, S., & Joo, Y. H. (2020) · Information Sciences · doi:10.1016/j.ins.2020.09.060 · Cited by 27
A 500-Fps Pan-Tilt Tracking System With Deep-Learning-Based Object Detection
Jiang, M., Shimasaki, K., Hu, S., Senoo, T., & Ishii, I. (2021) · IEEE Robotics and Automation Letters · doi:10.1109/lra.2020.3048653 · Cited by 28
Liu, Y., Liao, Y., Lin, C., Jia, Y., Li, Z., & Yang, X. (2022) · Remote Sensing · doi:10.3390/rs14030777 · Cited by 28
Unified seam tracking algorithm via three-point weld representation for autonomous robotic welding
Yu, S., Guan, Y., Hu, J., Hong, J., Zhu, H., & Zhang, T. (2023) · Engineering Applications of Artificial Intelligence · doi:10.1016/j.engappai.2023.107535 · Cited by 27
An Analysis and Method for Contrast Enhancement Turbulence Mitigation
Gibson, K. B., & Nguyen, T. Q. (2014) · IEEE Transactions on Image Processing · doi:10.1109/tip.2014.2328180 · Cited by 27
“[11] to estimate the global motion parameter g .”
BackgroundTransfer learning-based discriminative correlation filter for visual tracking
Huang, B., Xu, T., Li, J., Shen, Z., & Chen, Y. (2019) · Pattern Recognition · doi:10.1016/j.patcog.2019.107157 · Cited by 28
High speed long-term visual object tracking algorithm for real robot systems
Jiang, M., Li, R., Liu, Q., Shi, Y., & Tlelo‐Cuautle, E. (2021) · Neurocomputing · doi:10.1016/j.neucom.2020.12.113 · Cited by 29
Detection-Based Object Tracking Applied to Remote Ship Inspection
Xie, J., Stensrud, E., & Skramstad, T. (2021) · Sensors · doi:10.3390/s21030761 · Cited by 29
“html) already provides APIs for several popular trackers including Boosting [24], CSRT [11], GOTURN [25], KCF [26], MedianFlow [27], MIL [28], MOSSE [29], and TLD [30].”
MethodInfluential3D Siamese Voxel-to-BEV Tracker for Sparse Point CloudsPreprint
Hui, L., Wang, L., Cheng, M., Xie, J., & Yang, J. J. (2021) · arXiv (Cornell University) · doi:10.48550/arxiv.2111.04426 · Cited by 80
“As a pioneer, MOSSE [4] presents stable correlation filters for visual tracking.”
MethodOne lens optical correlation: application to face recognition
Jridi, M., Napoléon, T., & Alfalou, A. (2018) · Applied Optics · doi:10.1364/ao.57.002087 · Cited by 27
Fast and object-adaptive spatial regularization for correlation filters based tracking
Zhang, P., Guo, Q., & Feng, W. (2019) · Neurocomputing · doi:10.1016/j.neucom.2019.01.060 · Cited by 26
Nikouei, S. Y., Chen, Y., Song, S., Choi, B., & Faughnan, T. R. (2019) · IEEE Transactions on Services Computing · doi:10.1109/tsc.2019.2916416 · Cited by 28
Hierarchical Spatiotemporal Context-Aware Correlation Filters for Visual Tracking
Wang, W., Zhang, K., Lv, M., & Wang, J. (2020) · IEEE Transactions on Cybernetics · doi:10.1109/tcyb.2020.2964757 · Cited by 27
Real Time Object Tracking for Intelligent Vehicle
Dewangan, D. K., & Sahu, S. P. (2020) · International Conference on Power, Control and Computing Technologies (ICPC2T) · doi:10.1109/icpc2t48082.2020.9071478 · Cited by 26
“This has limitation of tracking the targeted object that has in rotation in frame, to deal with such issues minimum output sum of squared error filter is used [18].”
Method
Metadata
- Authors
- Bolme, D., Beveridge, J. R., Draper, B. A., & Lui, Y. M.
- Affiliations
- Colorado State University (US)
- Venue
- 2010 IEEE Computer Society Conference on Computer Vision and Pattern Recognition
- Publisher
- IEEE
- Published
- 2010-06
- Pages
- 2544-2550
- ISSN
- 1063-6919 (ISSN-L)
- OpenAlex
- W1964846093
- Cited by
- 3,406
- References
- 19
- Citations by year
- 2026: 78 · 2025: 165 · 2024: 246 · 2023: 327 · 2022: 391 · 2021: 442 · 2020: 433 · 2019: 493 · 2018: 372 · 2017: 206 · 2016: 118 · 2015: 71 · 2014: 36 · 2013: 16 · 2012: 8
- FWCI
- 7.68
- Type
- conference paper
- Language
- en
- Open access
- closed
- Locations
- IEEE Computer Society Conference on Computer Vision and Pattern Recognition/Proceedings - IEEE Computer Society Conference on Computer Vision and Pattern Recognition/Proceedings (publishedVersion)
- Topics
- Physical Sciences › Computer Science › Computer Vision and Pattern Recognition › Video Surveillance and Tracking Methods
- Physical Sciences › Computer Science › Computer Vision and Pattern Recognition › Advanced Image and Video Retrieval Techniques
- Physical Sciences › Computer Science › Computer Vision and Pattern Recognition › Infrared Target Detection Methodologies
- Keywords
- visual object tracking, correlation filter, occlusion detection, peak-to-sidelobe ratio, non-rigid deformation, real-time tracking
About these checks
Registry, retraction, Cites and statistics results are computed, not judged, with one exception: a printed reference that no index lists is read once by a model before it counts as a citation error. Claims are extracted by a model and kept only when their quote appears verbatim in the text; each cited source is then checked, with a model’s help, for whether it says what the claim relies on. Those verdicts can be wrong — read the claim’s quote and the cited source before relying on one.
Statistics and arithmetic are recomputed, not judged.
Confidence bands are shown only for fields calibrated on our annotated test set. None is calibrated yet, so no band is shown.
What counts as a claim ›How we measure confidence ›How we check this ›
Are you an author, or do you see a problem with this page? Request a review
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.