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 401–500 of 1,002
A3Track: Achieving Precise Target Tracking in Aerial Images With Receptive Field Alignment
Xu, L., Xu, C., Cheng, W., Yang, W. T., & Xia, G.-S. (2023) · IEEE Transactions on Geoscience and Remote Sensing · doi:10.1109/tgrs.2023.3335359 · Cited by 45
“The correlation filter-based method is initially proposed by Mosse [14], and subsequent methods, such as CSK [15], DCF [16], and KCF [17], have adopted cyclic shifting for dense sampling.”
MethodMotion-Aware Correlation Filter-Based Object Tracking in Satellite Videos
Lin, B., Zheng, J., Xue, C., Fu, L., Li, Y., & Shen, Q. (2024) · IEEE Transactions on Geoscience and Remote Sensing · doi:10.1109/tgrs.2024.3350988 · Cited by 74
“…sharpness and fluctuation of the response R can be represented by two indicators, i.e., the peak value max ( R ) and Visualization for a representative occlusion scenario, including response maps, tracking results, and curve of tracking uncertainty. the peak-to-sidelobe ratio [5] of R , PSR ( R ) .”
BackgroundMethodZhao, D., Hu, B., Jiang, W., Zhong, W., Arun, P. V., Cheng, K., Zhao, Z., & Zhou, H. (2025) · Optics and Lasers in Engineering · doi:10.1016/j.optlaseng.2025.109124 · Cited by 45
Symbiotic Tracker Ensemble Toward A Unified Tracking Framework
Gao, Y., Ji, R., Zhang, L., & Hauptmann, A. G. (2014) · IEEE Transactions on Circuits and Systems for Video Technology · doi:10.1109/tcsvt.2014.2302366 · Cited by 45
“2302366 monitoring, as well as large area imagery monitoring [2]–[4].”
BackgroundImage Alignment for Panorama Stitching in Sparsely Structured Environments
Meneghetti, G., Danelljan, M., Felsberg, M., & Nordberg, K. (2015) · Lecture notes in computer science · doi:10.1007/978-3-319-19665-7_36 · Cited by 45
“[3], called MOSSE, uses grayscale patches for learning and detection, and thus only considers luminance information.”
BackgroundMethodInfluentialManifold Regularized Correlation Object Tracking
Hu, H., Ma, B., Shen, J., & Shao, L. (2017) · IEEE Transactions on Neural Networks and Learning Systems · doi:10.1109/tnnls.2017.2688448 · Cited by 49
“But this paper did not receive enough attention until an adaptive correlation filter-based tracking method [27].”
MethodLin, F., Fu, C., He, Y., Guo, F., & Tang, Q. (2020) · IEEE Transactions on Circuits and Systems for Video Technology · doi:10.1109/tcsvt.2020.3023440 · Cited by 46
S2SiamFC: Self-supervised Fully Convolutional Siamese Network for Visual Tracking
Sio, C. H., Ma, Y.-J., Shuai, H.-H., Chen, J.-C., & Cheng, W.-H. (2020) · ACM International Conference on Multimedia (ACM MM) · doi:10.1145/3394171.3413611 · Cited by 56
“Visual tracking [4, 11, 17, 39, 63] is still one of the most active and important research areas in computer vision, which aims to predict the location of an arbitrary target in the consecutive frames precisely by a given initial location ( e,g., a bounding box annotation).”
BackgroundZhu, J., Zhang, C., Lu, Z., & Li, X. (2021) · Measurement · doi:10.1016/j.measurement.2021.109847 · Cited by 46
MBLT: Learning Motion and Background for Vehicle Tracking in Satellite Videos
Zhang, W., Jiao, L., Liu, F., Li, L., Liu, X., & Liu, J. (2021) · IEEE Transactions on Geoscience and Remote Sensing · doi:10.1109/tgrs.2021.3109028 · Cited by 48
“In 2010, since Bolme et al. [20] proposed MOSSE, CF has attracted more and more attention, such as circulant matrix [24], kernel function [8], boundary penalty [27], context patches suppression [10], sparse response [11] and so on.”
MethodInfluentialKrenzer, A., Makowski, K., Hekalo, A., Fitting, D., Troya, J., Zoller, W. G., Hann, A., & Puppe, F. (2022) · BioMedical Engineering OnLine · doi:10.1186/s12938-022-01001-x · Cited by 46
“It works only with grayscale images, and colored images will be converted internally [52].”
BackgroundDashNet: A Hybrid Artificial and Spiking Neural Network for High-speed Object TrackingPreprint
Yang, Z., Wu, Y., Wang, G., Yang, Y., Li, G., Deng, L., Zhu, J., & Shi, L. (2019) · arXiv (Cornell University) · doi:10.48550/arxiv.1909.12942 · Cited by 47
“Starting from the MOSSE tracker [14],”
Ship Detection and Tracking in Inland Waterways Using Improved YOLOv3 and Deep SORT
Jie, Y., Leonidas, L., Mumtaz, F., & Ali, M. (2021) · Symmetry · doi:10.3390/sym13020308 · Cited by 44
“The two challenges introduced by our algorithm have been depicted again in the improved Deep Sort; there, larger processing time of 53 s and memory usage of 1.68 GB was demonstrated contrary to the existing techniques such as MOSSE and MIL which used about 22 s and 1.4 GB memory size.”
MethodInfluentialEANTrack: An Efficient Attention Network for Visual Tracking
Gu, F., Lu, J., Cai, C., Zhu, Q., & Ju, Z. (2023) · IEEE Transactions on Automation Science and Engineering · doi:10.1109/tase.2023.3319676 · Cited by 48
“…almost all mainstream tracking approaches employ convolutional neural networks [8], [33], [43], including correlation filtering-based trackers [1], [12], [20], [23], [33], [63], [64], [65], [66], [67], [68] and Siamese-based trackers [2], [8], [9], [10], [11], [14], [15], [16], [17], [18], [19].”
BackgroundMethodInfluentialMulti-template Scale-Adaptive Kernelized Correlation Filters
Bibi, A., & Ghanem, B. (2015) · IEEE International Conference on Computer Vision Workshops · doi:10.1109/iccvw.2015.83 · Cited by 47
“The extracted feature vector is multiplied by a Hanning window, as described in [7].”
BackgroundMethodInfluentialChoi, I.-H., Jeong, C.-H., & Kim, Y.-G. (2016) · Applied Sciences · doi:10.3390/app6050137 · Cited by 44
“In the present study, DB-ASM utilizes the Minimum Output Sum of Squared Error (MOSSE) filter [17] for the local feature detection because it is known to be fast and reliable.”
MethodCorrelation Filter-Based Visual Tracking for UAV with Online Multi-Feature Learning
Fu, C., Lin, F., Li, Y., & Chen, G. (2019) · Remote Sensing · doi:10.3390/rs11050549 · Cited by 44
“[22] derived a fast correlation filter, i.”
Real-Time Driver Drowsiness Detection using Computer Vision
Jain, M., Bhagerathi, B., & N, S. C. (2021) · International Journal of Engineering and Advanced Technology · doi:10.35940/ijeat.a3159.1011121 · Cited by 52
Visual tracking using spatio-temporally nonlocally regularized correlation filter
Zhang, K., Li, X., Song, H., Liu, Q., & Lian, W. (2018) · Pattern Recognition · doi:10.1016/j.patcog.2018.05.017 · Cited by 45
DAL: A Deep Depth-Aware Long-term Tracker
Qian, Y., Yan, S., Lukežič, A., Kristan, M., Kämäräinen, J., & Matas, J. (2021) · Proceedings - International Conference on Pattern Recognition/Proceedings/International Conference on Pattern Recognition · doi:10.1109/icpr48806.2021.9412984 · Cited by 71
“[13] inspired the visual tracking community of how visual tracking is addressed by DCF in a mathematical-sound way.”
BackgroundA Review of Target Tracking Algorithm Based on UAV
Hao, J., Zhou, Y., Zhang, G., Lv, Q., & Wu, Q. (2018) · IEEE International Conference on Cyborg and Bionic Systems (CBS) · doi:10.1109/cbs.2018.8612263 · Cited by 46
Research on a real-time pose estimation method for a seam tracking system
Zou, Y., Chen, J., & Wei, X. (2019) · Optics and Lasers in Engineering · doi:10.1016/j.optlaseng.2019.105947 · Cited by 45
Augmented Memory for Correlation Filters in Real-Time UAV Tracking
Li, Y., Fu, C., Ding, F., Huang, Z., & Pan, J. (2020) · IEEE/RSJ International Conference on Intelligent Robots and Systems (IROS) · doi:10.1109/iros45743.2020.9341595 · Cited by 43
“Unfortunately, the pioneering works [5]–[7], despite their incredible speed, have inferior tracking performances.”
BackgroundSiamCAN: Real-Time Visual Tracking Based on Siamese Center-Aware Network
Zhou, W., Wen, L., Zhang, L., Du, D., Luo, T., & Wu, Y. (2021) · IEEE Transactions on Image Processing · doi:10.1109/tip.2021.3060905 · Cited by 48
“MOSSE [27] and CSK [28] attempt to exploit discriminative correlation filters learned dynamically to adapt to appearance variations of targets.”
BackgroundDrowsiness Detection System Using Deep Learning
Sinha, A., Aneesh, R. P., & Gopal, S. K. (2021) · International Conference on Bio Signals, Images, and Instrumentation (ICBSII) · doi:10.1109/icbsii51839.2021.9445132 · Cited by 43
“Lui, investigated a simpler tracking strategy [5].”
Zhao, J. K., Hu, F., Xu, Y., Zuo, W., Zhong, J., & Li, H. (2021) · Computer-Aided Civil and Infrastructure Engineering · doi:10.1111/mice.12761 · Cited by 43
Fast and Robust Object Tracking Using Tracking Failure Detection in Kernelized Correlation Filter
Shin, J., Kim, H., Kim, D., & Paik, J. (2020) · Applied Sciences · doi:10.3390/app10020713 · Cited by 42
“[12] proposed an improved version of ASEF, called minimum output sum of square error (MOSSE)-based tracker.”
BackgroundPromptVT: Prompting for Efficient and Accurate Visual Tracking
Zhang, M., Zhang, Q., Song, W., Huang, D., & He, Q. (2024) · IEEE Transactions on Circuits and Systems for Video Technology · doi:10.1109/tcsvt.2024.3376582 · Cited by 49
“Early tracking algorithms [26], [27] mainly used correlation filtering methods, where a filtering template is designed and used to perform correlation operations with candidate regions of the target.”
MethodRGBT tracking: A comprehensive review
Feng, M., & Su, J. (2024) · Information Fusion · doi:10.1016/j.inffus.2024.102492 · Cited by 50
Semantics-Aware Visual Object Tracking
Yao, R., Lin, G., Shen, C., Zhang, Y., & Shi, Q. (2018) · IEEE Transactions on Circuits and Systems for Video Technology · doi:10.1109/tcsvt.2018.2848358 · Cited by 46
“Examples of such approaches include the support vector tracker [13], online adaptive boosting (OAB) [14], multiple instance learning (MIL) [15], random forest [5], structural output tracking (Struck) [4] and correlation filter tracker [3], [16].”
BackgroundObject Tracking for a Smart City Using IoT and Edge Computing
Zhang, H., Zhang, Z., Zhang, L., Yang, Y. F., Kang, Q., & Sun, D. W. (2019) · Sensors · doi:10.3390/s19091987 · Cited by 43
“However, no feature extraction is implemented in [1], thus, the tracking ability is limited by the feature discrimination.”
BackgroundMethodInfluentialDeep GoogLeNet Features for Visual Object Tracking
Aswathy, P. B., Siddhartha, & Mishra, D. (2018) · IEEE International Conference on Industrial and Information Systems (ICIIS) · doi:10.1109/iciinfs.2018.8721317 · Cited by 44
“Most tracking approaches initially relied on image intensity or simple color names for feature representation [12], [15].”
BackgroundA vehicle tracking algorithm combining detector and tracker
Yang, B., Tang, M., Chen, S., Wang, G., Tan, Y. Q., & Li, B. (2020) · EURASIP Journal on Image and Video Processing · doi:10.1186/s13640-020-00505-7 · Cited by 42
“(11) [33]. where g max is the peak value of the CF response map, and μ s 1 and σ s 1 are the average value and variance, respectively, within an N × N window, with the peak value of the response map as its center, respectively.”
BackgroundSiamese Local and Global Networks for Robust Face Tracking
Qi, Y., Zhang, S., Jiang, F., Zhou, H., Tao, D., & Li, X. (2020) · IEEE Transactions on Image Processing · doi:10.1109/tip.2020.3023621 · Cited by 42
“[49] propose to learn robust filters by minimizing the sum of squared errors over image”
BackgroundGround Moving Target Tracking and Refocusing Using Shadow in Video-SAR
Yang, X., Shi, J., Zhou, Y., Wang, C., Hu, Y. G., Zhang, X., & Wei, S. (2020) · Remote Sensing · doi:10.3390/rs12183083 · Cited by 45
“There are many algorithms for tracking task, including traditional correlation filter based methods [48,49] and deep learning based methods [50–52].”
InfluentialRobust visual object tracking using context-based spatial variation via multi-feature fusion
Elayaperumal, D., & Joo, Y. H. (2021) · Information Sciences · doi:10.1016/j.ins.2021.06.084 · Cited by 42
Single Object Tracking in Satellite Videos: A Correlation Filter-Based Dual-Flow Tracker
Chen, Y., Tang, Y., Yin, Z., Han, T., Zou, B., & Feng, H. (2022) · IEEE Journal of Selected Topics in Applied Earth Observations and Remote Sensing · doi:10.1109/jstars.2022.3185328 · Cited by 46
“Although these methods [39]–[44] have performed good performance in natural videos, it remains unknown whether they would work well in SVs. CF-based trackers have emerged as a highlight since the MOSSE [45] was first proposed.”
BackgroundZhao, D., Cao, J., Zhu, X., Zhang, Z., Arun, P. V., Guo, Y., Qian, K., Zhang, L., Zhou, H., & Hu, J. (2022) · Remote Sensing · doi:10.3390/rs14246219 · Cited by 42
“In stage I, the deep features are equally divided into 32 groups, each group having a size of 28 × 28 × 16, and are denoted as Ei, i ∈ [1, 32].”
BackgroundMethodTang, Y., Liu, Y., & Huang, H. B. (2022) · Computer Vision and Image Understanding · doi:10.1016/j.cviu.2022.103535 · Cited by 41
Wang, Z., Guan, X., Liu, C., Yang, S., Xiang, X., & Chen, H. (2023) · Control Engineering Practice · doi:10.1016/j.conengprac.2023.105529 · Cited by 41
MC-HOG Correlation Tracking with Saliency Proposal
Zhu, G., Wang, J., Wu, Y., Zhang, X., & Lu, H. (2016) · Proceedings of the AAAI Conference on Artificial Intelligence · doi:10.1609/aaai.v30i1.10450 · Cited by 42
“Bolme et al. (Bolme et al. 2010) proposed an adaptive correlation filter with minimizing the output sum of squared error (MOSSE) for the target appearance in visual tracking.”
BackgroundMethodInfluentialLiu, Y., Meng, Z., Zou, Y., & Cao, M. (2020) · IEEE/CAA Journal of Automatica Sinica · doi:10.1109/jas.2020.1003530 · Cited by 44
“Moreover, discriminative approaches [11], [17], [18] have been proposed, and both the foreground and background information is considered from sequential images.”
BackgroundMemory-Efficient CNN Accelerator Based on Interlayer Feature Map Compression
Shao, Z., Chen, X., Du, L., Chen, L., Du, Y., Zhuang, W., Wei, H., Xie, C., & Wang, Z. (2021) · IEEE Transactions on Circuits and Systems I Regular Papers · doi:10.1109/tcsi.2021.3120312 · Cited by 45
Detecting Rails and Obstacles Using a Train-Mounted Thermal Camera
Berg, A., Öfjäll, K., Ahlberg, J., & Felsberg, M. (2015) · Lecture notes in computer science · doi:10.1007/978-3-319-19665-7_42 · Cited by 41
“The derivation of (6) is given in [2].”
BackgroundMethodLearning spatio-temporal discriminative model for affine subspace based visual object tracking
Xu, T., Zhu, X., & Wu, X. (2023) · Visual Intelligence · doi:10.1007/s44267-023-00002-1 · Cited by 46
“The seminal work of the DCF framework is minimum output sum of squared error (MOSSE) [42], which formulates the tracking task as discriminative filter learning [43] rather than template matching [44], achieving improved tracking efficiency.”
MethodRobust occlusion-aware part-based visual tracking with object scale adaptation
Wang, X., Hou, Z., Yu, W., Pu, L., Jin, Z., & Qin, X. (2018) · Pattern Recognition · doi:10.1016/j.patcog.2018.04.011 · Cited by 42
Robust Event-Based Object Tracking Combining Correlation Filter and CNN Representation
Li, H., & Shi, L. (2019) · Frontiers in Neurorobotics · doi:10.3389/fnbot.2019.00082 · Cited by 40
Yuan, D., Shu, X., & He, Z. (2020) · Journal of Visual Communication and Image Representation · doi:10.1016/j.jvcir.2020.102882 · Cited by 42
Zhu, K., Zhang, X., Chen, G., Tan, X., Liao, P., Wu, H., Cui, X., Zuo, Y., & Lv, Z. (2021) · Remote Sensing · doi:10.3390/rs13071298 · Cited by 40
“Since Minimum Output Sum of Squared Error filter (MOSSE) [10] introduced correlation filters in object tracking, many outstanding natural scene video tracking algorithms (e.g., Discriminative Scale Space Tracking (DSST) [11], Kernelized Correlation Filter (KCF) [12], Color Names (CN) [13]) were proposed.”
BackgroundYıldız, S., Aydemir, O., Memiş, A., & Varlı, S. (2022) · Engineering Applications of Artificial Intelligence · doi:10.1016/j.engappai.2022.105032 · Cited by 44
SITUP: Scale Invariant Tracking Using Average Peak-to-Correlation Energy
Ma, H., Acton, S. T., & Lin, Z. (2020) · IEEE Transactions on Image Processing · doi:10.1109/tip.2019.2962694 · Cited by 39
Semantic-Aware Real-Time Correlation Tracking Framework for UAV Videos
Xue, X., Li, Y., Yin, X., Shang, C., Peng, T., & Shen, Q. (2020) · IEEE Transactions on Cybernetics · doi:10.1109/tcyb.2020.3005453 · Cited by 39
“Although the handcrafted features [15]–[19] are widely utilized, the application of deep features [20], [21] is also investigated for more accurate and comprehensive appearance representation.”
BackgroundWang, J., Jia, Z., Hui-cheng, L., Yang, J., & Kasabov, N. K. (2022) · IEEE photonics journal · doi:10.1109/jphot.2022.3227118 · Cited by 39
“In 2010, a filtering algorithm for the minimum output sum of squared error filter (MOSSE) was proposed [9], which was the first time the CF was introduced into visual tracking.”
MethodUnderwater object tracker: UOSTrack for marine organism grasping of underwater vehicles
Li, Y., Wang, B., Li, Y., Liu, Z., Huo, W., Li, Y., & Cao, J. (2023) · Ocean Engineering · doi:10.1016/j.oceaneng.2023.115449 · Cited by 42
“Using MOSSE[7] as a starting point, most trackers are developed by adding a Hanning window to the response map to suppress interference from similar distractors in the non-central regions of the search area.”
MethodMartin, B., Tarraf, D. C., Whitmore, T. C., DeWeese, J., Kenney, C., Schmid, J., & DeLuca, P. (2019) · RAND Corporation eBooks · doi:10.7249/rr2751 · Cited by 55
Distilling Channels for Efficient Deep Tracking
Ge, S., Luo, Z., Zhang, C., Hua, Y., & Tao, D. (2019) · IEEE Transactions on Image Processing · doi:10.1109/tip.2019.2950508 · Cited by 47
Gaussian-response correlation filter for robust visual object tracking
Moorthy, S., Choi, J. Y., & Joo, Y. H. (2020) · Neurocomputing · doi:10.1016/j.neucom.2020.06.016 · Cited by 40
Spatial Reliability Enhanced Correlation Filter: An Efficient Approach for Real-Time UAV Tracking
Fu, C., Jin, J., Ding, F., Li, Y., & Lu, G. (2021) · IEEE Transactions on Multimedia · doi:10.1109/tmm.2021.3118891 · Cited by 44
Chen, L., Li, G., Xie, W., Tan, J., Li, Y., Pu, J., Chen, L., Gan, D., & Shi, W. (2024) · Energies · doi:10.3390/en17205177 · Cited by 47
Learning Linear Regression via Single-Convolutional Layer for Visual Object Tracking
Chen, K., & Tao, W. (2018) · IEEE Transactions on Multimedia · doi:10.1109/tmm.2018.2846405 · Cited by 39
“In [9], correlation filter is learned by minimizing the output sum of squared error (MOSSE).”
Joint Server Assignment and Resource Management for Edge-Based MAR System
Wang, C., Zhang, S., Qian, Z., Xiao, M., Wu, J., Ye, B., & Lu, S. (2020) · IEEE/ACM Transactions on Networking · doi:10.1109/tnet.2020.3012410 · Cited by 39
“object tracking [36] and image rendering [37]), the algorithm complexity is also closely relevant to the amount of pixels in the image [38].”
BackgroundSiamATL: Online Update of Siamese Tracking Network via Attentional Transfer Learning
Huang, B., Xu, T., Shen, Z., Jiang, S., Zhao, B., & Bian, Z. (2021) · IEEE Transactions on Cybernetics · doi:10.1109/tcyb.2020.3043520 · Cited by 39
Zhou, Y., Su, H., Tian, S., Liu, X., & Suo, J. (2022) · IEEE Transactions on Aerospace and Electronic Systems · doi:10.1109/taes.2022.3150262 · Cited by 41
Tracking Holistic Object RepresentationsPreprint
Sauer, A., Aljalbout, E., & Haddadin, S. (2019) · arXiv (Cornell University) · doi:10.48550/arxiv.1907.12920 · Cited by 44
“Following [3], we multiply the feature vector fi with a tapered cosine window before calculating the similarities between templates.”
MethodHierarchical Attention Siamese Network for Thermal Infrared Target Tracking
Yuan, D., Liao, D., Huang, F., Qiu, Z., Shu, X., Tian, C., & Liu, Q. (2024) · IEEE Transactions on Instrumentation and Measurement · doi:10.1109/tim.2024.3462973 · Cited by 42
“For example, Bolme et al. [23] used the method of time domain convolution conversion to frequency domain multiplication to build the minimum output square sum MOSSE filter to achieve some good target tracking performance.”
MethodRobust visual tracking using joint scale-spatial correlation filters
Zhang, M., Xing, J., Gao, J., & Hu, W. (2015) · 2015 IEEE International Conference on Image Processing (ICIP) · doi:10.1109/icip.2015.7351044 · Cited by 38
“Based on these innovations, our new Joint Scale-Spatial Correlation (JSSC) tracker significantly outperforms previous Spatial Correlation trackers [13, 14] in the robustness and adaptability respects, and advances the best performance on the benchmark [10] with a very large margin.”
MethodDeformable Object Tracking With Gated Fusion
Liu, W., Song, Y., Chen, D., He, S., Yu, Y., Yan, T., Hancke, G. P., & Lau, R. W. H. (2019) · IEEE Transactions on Image Processing · doi:10.1109/tip.2019.2902784 · Cited by 40
“based trackers [12], [13] are widely studied.”
Online Multi-Expert Learning for Visual Tracking
Li, Z., Wei, W., Zhang, T., Wang, M., Hou, S., & Xin, P. (2019) · IEEE Transactions on Image Processing · doi:10.1109/tip.2019.2931082 · Cited by 37
“The use of DCF for visual tracking starts with MOSSE [16], which learns the filter with few samples in the frequency domain.”
SSET: a dataset for shot segmentation, event detection, player tracking in soccer videos
Feng, N., Song, Z., Yu, J., Chen, Y. P., Zhao, Y., He, Y., & Guan, T. (2020) · Multimedia Tools and Applications · doi:10.1007/s11042-020-09414-3 · Cited by 39
“[6] proposes the Minimum Output Sum of Squared Error (MOSSE), which defines the loss as the minimum mean Table 12 (continued)”
BackgroundMethodInfluential500-Fps Omnidirectional Visual Tracking Using Three-Axis Active Vision System
Jiang, M., Sogabe, R., Shimasaki, K., Hu, S., Senoo, T., & Ishii, I. (2021) · IEEE Transactions on Instrumentation and Measurement · doi:10.1109/tim.2021.3053971 · Cited by 37
Zhu, H., Peng, H., Xu, G., Deng, L., Cheng, Y., & Song, A. (2021) · IEEE Transactions on Multimedia · doi:10.1109/tmm.2021.3075876 · Cited by 39
Perceiving Temporal Environment for Correlation Filters in Real-Time UAV Tracking
Zhang, F., Ma, S., Zhang, Y., & Qiu, Z. (2021) · IEEE Signal Processing Letters · doi:10.1109/lsp.2021.3120943 · Cited by 37
Transparent Object Tracking Benchmark
Fan, H., Miththanthaya, H. A., Harshit, H., Rajan, S. R., Liu, X., Zou, Z., Lin, Y., & Ling, H. (2021) · IEEE/CVF International Conference on Computer Vision (ICCV) · doi:10.1109/iccv48922.2021.01056 · Cited by 44
“Correlation filter trackers like [5, 24] demonstrate impressive running speeds of several hundreds frames per second and attract great attention in the tracking community with many inspired extensions for improvements.”
BackgroundCirculant Temporal Encoding for Video Retrieval and Temporal Alignment
Douze, M., Revaud, J., Verbeek, J. J., Jeǵou, H., & Schmid, C. (2015) · International Journal of Computer Vision · doi:10.1007/s11263-015-0875-0 · Cited by 43
“To tackle this issue, (Bolme et al. 2010) average the filters obtained from independent samples (dimensions in our case).”
BackgroundA review of object tracking methods: From general field to autonomous vehicles
Cao, J., Zhang, H., Jin, L., Lv, J., Hou, G., & Zhang, C. (2024) · Neurocomputing · doi:10.1016/j.neucom.2024.127635 · Cited by 42
Vision Technologies with Applications in Traffic Surveillance Systems: A Holistic Survey
Zhou, W., Yang, L., Zhao, L., Zhang, R., Cui, Y., Huang, H., Qie, K., & Wang, C. (2025) · ACM Computing Surveys · doi:10.1145/3760525 · Cited by 52
“…performance in challenging cross-camera scenarios with extreme viewpoint and lighting variations, their real-world applicability is constrained by the availability of additional annotations during training and potential domain gaps when deployed across different traffic surveillance networks.”
On-line fusion of trackers for single-object tracking
Leang, I., Herbin, S., Girard, B., & Droulez, J. (2017) · Pattern Recognition · doi:10.1016/j.patcog.2017.09.026 · Cited by 38
Large Margin Structured Convolution Operator for Thermal Infrared Object Tracking
Gao, P., Ma, Y., Song, K., Li, C., Wang, F., & Xiao, L. (2018) · Proceedings - International Conference on Pattern Recognition/Proceedings/International Conference on Pattern Recognition · doi:10.1109/icpr.2018.8545716 · Cited by 42
Nam, D. V., & Kim, G.-W. (2020) · Sensors · doi:10.3390/s20102922 · Cited by 37
“Next, the optical flow with the KLT tracking algorithm with RANSAC [33,34] is employed to determine the feature corresponding in the boundary of it.”
MethodInfluentialFast Learning of Spatially Regularized and Content Aware Correlation Filter for Visual Tracking
Han, R., Feng, W., & Wang, S. (2020) · IEEE Transactions on Image Processing · doi:10.1109/tip.2020.2998978 · Cited by 38
“proposed the tracker MOSSE [11], which”
BackgroundMethodInfluentialTRAT: Tracking by attention using spatio-temporal features
Sarıbaş, H., Çevıkalp, H., Köpüklü, O., & Uzun, B. (2022) · Neurocomputing · doi:10.1016/j.neucom.2022.04.043 · Cited by 36
“[5] introduced a very fast CF based method using the minimum output of squared error (MOSSE) for visual tracking.”
MethodReal-Time Multiple Object Visual Tracking for Embedded GPU Systems
Fernández-Sanjurjo, M., Mucientes, M., & Brea, V. M. (2021) · IEEE Internet of Things Journal · doi:10.1109/jiot.2021.3056239 · Cited by 41
“One of the solutions of this type of tracking that has had more presence in the field since 2010 [9] has been trackers based on DCFs.”
BackgroundYu, Q., Wang, B., & Su, Y. (2021) · IEEE Access · doi:10.1109/access.2021.3072897 · Cited by 41
“Typical tracking algorithms based on correlation filtering include the minimum output sum of squared error (MOSSE) [12], circulant structure tracking with kernels (CSK) [13], kernel correlation filter (KCF) [14], background-aware correlation filter (BACF) [15] and scale-adaptive multiple-feature (SAMF) [16] approaches.”
MethodLearning background-aware and spatial-temporal regularized correlation filters for visual tracking
Zhang, J., He, Y., Feng, W., Wang, J., & Xiong, N. N. (2022) · Applied Intelligence · doi:10.1007/s10489-022-03868-8 · Cited by 36
“CF-based tracking In 2010, the least square error sum of output (MOSSE) algorithm [30] introduced correlation filters to object tracking for the first time and was trained only on gray samples.”
MethodReal-Time Locomotion Mode Recognition Employing Correlation Feature Analysis Using EMG Pattern
Kim, D., Cho, C.-Y., & Ryu, J. (2014) · ETRI Journal · doi:10.4218/etrij.14.0113.0064 · Cited by 36
Yao, R., Xia, S., Zhang, Z., & Zhang, Y. (2016) · IEEE Transactions on Multimedia · doi:10.1109/tmm.2016.2631727 · Cited by 38
“Recently, correlation-filter-based approaches [9], [10] achieve real-time tracking performance with dense sampling by utilizing the fast computational operation in frequency domain.”
BackgroundMethodVisual object tracking by correlation filters and online learning
Zhang, X., Xia, G.-S., Lu, Q., Shen, W., & Zhang, L. (2017) · ISPRS Journal of Photogrammetry and Remote Sensing · doi:10.1016/j.isprsjprs.2017.07.009 · Cited by 35
Parallel Tracking and Verifying
Fan, H., & Ling, H. (2019) · IEEE Transactions on Image Processing · doi:10.1109/tip.2019.2904789 · Cited by 37
“[19] propose to use correlation filter for tracking through learning the minimum output sum of squared error (MOSSE).”
MethodData Driven Feature Selection for Machine Learning Algorithms in Computer Vision
Zhang, F., Li, W., Zhang, Y., & Feng, Z. (2018) · IEEE Internet of Things Journal · doi:10.1109/jiot.2018.2845412 · Cited by 44
“[6] first introduced correlation filters to visual tracking, and proposed minimum output sum of squared error filter.”
MethodUnderwater Object Tracking Benchmark and Dataset
Kezebou, L., Oludare, V., Panetta, K. A., & Agaian, S. С. (2019) · IEEE Conference on Technologies for Homeland Security (HST) · doi:10.1109/hst47167.2019.9032954 · Cited by 46
“Some of the popular object tracking algorithms include Kernelized correlation Filter (KCF) [8], TLD tracker [12], Boosting [13], CSRT [14], MIL [15], GOTURN [16], MOSSE [17], MEDIANFLOW [18], and LKT tracker [11]; most of which are all available in OpenCV library.”
MethodLong-term visual tracking algorithm for UAVs based on kernel correlation filtering and SURF features
Fan, J., Yang, X., Lu, R., Li, W., & Huang, Y. (2022) · The Visual Computer · doi:10.1007/s00371-021-02331-y · Cited by 40
“This paper obtains the PSR of the response map to judge the occlusion or loss of the tracking target [61]:”
BackgroundWhen Correlation Filters Meet Siamese Networks for Real-Time Complementary Tracking
Li, D., Porikli, F., Wen, G., & Kuai, Y. (2019) · IEEE Transactions on Circuits and Systems for Video Technology · doi:10.1109/tcsvt.2019.2892759 · Cited by 35
“[20] conducts spatial correlation in the frequency domain and achieves a runtime of over 600 frames per second (fps).”
BackgroundLearning to Update for Object Tracking With Recurrent Meta-Learner
Li, B., Xie, W., Zeng, W., & Liu, W. (2019) · IEEE Transactions on Image Processing · doi:10.1109/tip.2019.2900577 · Cited by 36
“aspects since the seminal work of [14].”
BackgroundInfluentialDetection based visual tracking with convolutional neural network
Wang, Y., Luo, X., Ding, L., Fu, S., & Wei, X. (2019) · Knowledge-Based Systems · doi:10.1016/j.knosys.2019.03.012 · Cited by 35
Vision Tracking: A Survey of the State-of-the-Art
Dutta, A., Mondal, A., Dey, N., Sen, S., Moraru, L., & Hassanien, A. E. (2020) · SN Computer Science · doi:10.1007/s42979-019-0059-z · Cited by 37
“In [165], a discriminative correlation filter-based (DCF) approach is proposed which is used to evaluate the object in the next frame.”
MethodExtracting Accurate Long-term Behavior Changes from a Large Pig Dataset
Bergamini, L., Pini, S., Simoni, A., Vezzani, R., Calderara, S., D’Eath, R. B., & Fisher, R. B. (2021) · International Joint Conference on Computer Vision, Imaging and Computer Graphics Theory and Applications (VISIGRAPP) · doi:10.5220/0010288405240533 · Cited by 38
“As tracker, we employ the MOSSE (Bolme et al., 2010) algorithm.”
MethodAdaptive Fusion CNN Features for RGBT Object Tracking
Wang, Y., Wei, X., Tang, X., Shen, H., & Zhang, H. (2021) · IEEE Transactions on Intelligent Transportation Systems · doi:10.1109/tits.2021.3073046 · Cited by 40
Visual Tracking via Hierarchical Deep Reinforcement Learning
Zhang, D., Zheng, Z., Jia, R., & Li, M. (2021) · Proceedings of the AAAI Conference on Artificial Intelligence · doi:10.1609/aaai.v35i4.16443 · Cited by 38
“A pioneering work is Minimum Output Sum of Squared Error (MOSSE) filter (Bolme et al. 2010), achieving a very fast tracking speed.”
MethodWang, C., Shi, Z., Meng, L., Wang, J., Wang, T., Gao, Q., & Wang, E. (2022) · Drones · doi:10.3390/drones6060149 · Cited by 36
A Siamese network-based tracking framework for hyperspectral video
Tang, Y., Huang, H. B., Liu, Y., & Li, Y. (2022) · Neural Computing and Applications · doi:10.1007/s00521-022-07712-5 · Cited by 35
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.