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 601–700 of 1,002
Visual Tracking by TridentAlign and Context Embedding
Choi, J., Kwon, J., & Lee, K. M. (2021) · Lecture notes in computer science · doi:10.1007/978-3-030-69532-3_31 · Cited by 26
Lan, K.-C., Hu, M., Chen, Y., & Zhang, J.-X. (2020) · IEEE Sensors Journal · doi:10.1109/jsen.2020.3022958 · Cited by 27
“Recently, tracking-by-detection methods [8], [40], [42], [59] have shown to provide excellent tracking performance.”
BackgroundMethodTraining-Set Distillation for Real-Time UAV Object Tracking
Li, F., Fu, C., Lin, F., Li, Y., & Lu, P. (2020) · Proceedings - IEEE International Conference on Robotics and Automation/Proceedings · doi:10.1109/icra40945.2020.9197252 · Cited by 28
“Discriminative correlation filter-based tracker was firstly introduced in the minimum output sum of squared error (MOSSE) [12] filer.”
MethodAVOT: Audio-Visual Object Tracking of Multiple Objects for Robotics
Wilson, J., & Lin, M. C. (2020) · Proceedings - IEEE International Conference on Robotics and Automation/Proceedings · doi:10.1109/icra40945.2020.9197528 · Cited by 34
“…Multiple Instance Learning (MIL) [6], Kernelized Correlation Filters (KCF) [26], Discriminative Correlation Filter with Channel and Spatial Reliability (CSRT) [40], and an adaptive correlation filter known as Minimum Output Sum of Squared Error (MOSSE) [8] are a few trackers available in OpenCV [9].”
MethodChannel Graph Regularized Correlation Filters for Visual Object Tracking
Jain, M., Tyagi, A., Subramanyam, A. V., Denman, S., Sridharan, S., & Fookes, C. (2021) · IEEE Transactions on Circuits and Systems for Video Technology · doi:10.1109/tcsvt.2021.3063144 · Cited by 27
Dual Attentional Siamese Network for Visual Tracking
Zhang, X., Ma, J., Liu, H., Hu, H., & Yang, P. (2022) · Displays · doi:10.1016/j.displa.2022.102205 · Cited by 27
An Anti-UAV Long-Term Tracking Method with Hybrid Attention Mechanism and Hierarchical Discriminator
Cheng, F., Liang, Z., Peng, G., Liu, S., Li, S., & Ji, M. (2022) · Sensors · doi:10.3390/s22103701 · Cited by 28
“[19] introduced the correlation filter into object tracking algorithms and first proposed MOSSE.”
MethodVehicle Tracking on Satellite Video Based on Historical Model
Chen, S., Wang, T., Wang, H., Wang, Y., Hong, J., Dong, T., & Li, Z. (2022) · IEEE Journal of Selected Topics in Applied Earth Observations and Remote Sensing · doi:10.1109/jstars.2022.3195522 · Cited by 26
“According to the principle followed by the algorithm, the existing object tracking algorithms can be divided into two categories: generative models [23]–[26] and discriminative models [27]–[33].”
BackgroundMethodInfluentialSaha, A., Dhara, B. C., Umer, S., Kulakov, Y., Alanazi, J. M., & AlZubi, A. A. (2022) · Sensors · doi:10.3390/s22176537 · Cited by 31
“We can see from Figure 26 that the execution times for BOOSTING, KCF, MIL, and TLD were very high compared with those of MedianFlow, MOSSE, VbOAD, and the proposed method.”
MethodInfluential3-D Objects Detection and Tracking Using Solid-State LiDAR and RGB Camera
Peng, Z., Xiong, Z., Zhao, Y., & Zhang, L. (2023) · IEEE Sensors Journal · doi:10.1109/jsen.2023.3279500 · Cited by 28
“Thus, we use minimum output sum of squared error (MOSSE [49]) filter to complete this task, which is robust enough to track two adjacent frames while having a fast computation speed.”
MethodRobust object tracking via multi-cue fusion
Hu, M., Liu, Z., Zhang, J., & Zhang, G. (2017) · Signal Processing · doi:10.1016/j.sigpro.2017.04.008 · Cited by 28
Object Tracking Using Multiple Features and Adaptive Model Updating
Hu, Q., Guo, Y., Lin, Z., An, W., & Cheng, H. (2017) · IEEE Transactions on Instrumentation and Measurement · doi:10.1109/tim.2017.2729378 · Cited by 28
“[21] trained a correlation filter on a set of gray-scale training samples.”
MethodInfluentialComparison of Tracking Techniques on 360-Degree Videos
Mi, T.-W., & Yang, M. (2019) · Applied Sciences · doi:10.3390/app9163336 · Cited by 26
“[16], is a tracker based on correlation filters.”
BackgroundDeep Learning-based Visual Tracking of UAVs using a PTZ Camera System
Unlu, H. U., Niehaus, P. S., Chirita, D., Evangeliou, N., & Tzes, A. P. (2019) · Annual Conference of the IEEE Industrial Electronics Society (IECON) · doi:10.1109/iecon.2019.8927731 · Cited by 27
“Early work in correlation filters [20], followed by schemes involving the minimization of the output sum of the squared error [21], [22] led the foundation for more sophisticated STTs [5], [23].”
MethodGPS‐level accurate camera localization with HorizonNet
Grelsson, B., Robinson, A., Felsberg, M., & Khan, F. S. (2019) · Journal of Field Robotics · doi:10.1002/rob.21929 · Cited by 30
“The introduction of the MOSSE correlation filter (Bolme et al., 2010) showed that image object tracking with adaptive correlation filters in the Fourier domain is significantly faster and also more robust to variations in target appearance than previous trackers working in the spatial domain.”
BackgroundMethodInfluentialVisDrone-SOT2020: The Vision Meets Drone Single Object Tracking Challenge Results
Fan, H., Wen, L., Du, D., Zhu, P., Hu, Q., Ling, H., Shah, M. A., Wang, B., Dong, B., Yuan, D., et al. (2020) · Lecture notes in computer science · doi:10.1007/978-3-030-66823-5_44 · Cited by 30
Face and eye detection on hard datasets
Parris, J., Wilber, M. J., Heflin, B. C., Rara, H. M., El-Barkouky, A., Farag, A. A., Movellan, J. R., Castrillón-Santana, M., Lorenzo-Navarro, J., Teli, M. N., et al. (2011) · IEEE International Joint Conference on Biometrics (IJCB) · doi:10.1109/ijcb.2011.6117593 · Cited by 26
Sparse Camera Network for Visual Surveillance -- A Comprehensive SurveyPreprint
Song, M., Tao, D., & Maybank, S. J. (2013) · BIROn (Birkbeck, University of London) · doi:10.48550/arxiv.1302.0446 · Cited by 30
“[81] presented a”
Deep People Counting with Faster R-CNN and Correlation Tracking
Li, Z., La, Z., Fang, Y., Wang, J., Xu, H., Yin, B., & Lu, H. (2016) · International Conference on Internet Multimedia Computing and Service · doi:10.1145/3007669.3007745 · Cited by 25
“Correlation tracking After the success of [2], correlation filter-based tracking framework had shown to be significantly efficient for robust tracking.”
Robust Visual Tracking via Local-Global Correlation Filter
Fan, H., & Xiang, J. (2017) · Proceedings of the AAAI Conference on Artificial Intelligence · doi:10.1609/aaai.v31i1.11207 · Cited by 25
“Bolme et al. (2010) propose a correlation filter tracker by learning a minimum output sum of squared error (MOSSE) for object appearance.”
BackgroundMethodHigh performance visual tracking with circular and structural operators
Gao, P., Ma, Y., Song, K., Li, C., Wang, F., Xiao, L., & Zhang, Y. (2018) · Knowledge-Based Systems · doi:10.1016/j.knosys.2018.08.008 · Cited by 25
“MOSSE [32] is the first tracker which exploits Fast Fourier Transform (FFT) to train single-channel correlation filters based on raw pixel samples of both the target and the background.”
BackgroundMethodA Real-time Robust Approach for Tracking UAVs in Infrared Videos
Wu, H., Li, W., Li, W., & Liu, G. (2020) · IEEE/CVF Conference on Computer Vision and Pattern Recognition Workshops (CVPRW) · doi:10.1109/cvprw50498.2020.00524 · Cited by 29
“The seminal work that put forward the correlation filter to tracking is MOSSE, which uses a set of samples random affine transformed from the single initial frame to construct a minimum output sum of squared error filter [8].”
MethodTracking-by-Trackers with a Distilled and Reinforced Model
Dunnhofer, M., Martinel, N., & Micheloni, C. (2021) · Lecture notes in computer science · doi:10.1007/978-3-030-69532-3_38 · Cited by 25
“Processing speed was pursued by algorithms like correlation filters [1,2,3,4,5] or offline methods such as siamese convolutional neural networks (CNNs) [6,7,8,9,10,11,12].”
BackgroundMethodInfluentialAntidecay LSTM for Siamese Tracking With Adversarial Learning
Zhao, F., Zhang, T., Wu, Y., Tang, M., & Wang, J. (2020) · IEEE Transactions on Neural Networks and Learning Systems · doi:10.1109/tnnls.2020.3018025 · Cited by 25
Object Tracking Using Spatio-Temporal Networks for Future Prediction Location
Liu, Y., Li, R., Cheng, Y., Tan, R. T., & Sui, X. (2020) · Lecture notes in computer science · doi:10.1007/978-3-030-58542-6_1 · Cited by 28
“By comparing the template of an arbitrary target and its 2D translations, the correlation filter [6] is employed for its speed and effective strategy for tracking-by-detection.”
MethodLearning Recurrent Memory Activation Networks for Visual Tracking
Pu, S., Song, Y., Ma, C., Zhang, H., & Yang, M. (2020) · IEEE Transactions on Image Processing · doi:10.1109/tip.2020.3038356 · Cited by 28
“Since the MOSSE tracker [6], numerous methods have”
MethodObject Tracking and Geo-Localization from Street Images
Wilson, D., Alshaabi, T., Oort, C. M. V., Zhang, X., Nelson, J. K., & Wshah, S. (2022) · Remote Sensing · doi:10.3390/rs14112575 · Cited by 30
Oops! It's Too Late. Your Autonomous Driving System Needs a Faster Middleware
Wu, T., Wu, B., Wang, S., Liu, L., Liu, S., Bao, Y., & Shi, W. (2021) · IEEE Robotics and Automation Letters · doi:10.1109/lra.2021.3097439 · Cited by 36
“For object tracking , we use Minimum Output Sum of Squared Error (MOSSE) Filter [37] which runs fast and has acceptable accuracy.”
MethodCombining complementary trackers for enhanced long-term visual object tracking
Dunnhofer, M., Simonato, K., & Micheloni, C. (2022) · Image and Vision Computing · doi:10.1016/j.imavis.2022.104448 · Cited by 25
Li, S., Liu, Y., Zhao, Q., & Feng, Z. (2021) · International Conference on 3D Vision (3DV) · doi:10.1109/3dv53792.2021.00131 · Cited by 27
“Using DCF for visual tracking starts with the minimum output sum of squared error (MOSSE) filter [6].”
MethodA UAV to UAV tracking benchmark
Wang, Y., Huang, Z., Laganière, R., Zhang, H., & Ding, L. (2022) · Knowledge-Based Systems · doi:10.1016/j.knosys.2022.110197 · Cited by 29
Learning spatial variance-key surrounding-aware tracking via multi-expert deep feature fusion
Elayaperumal, D., & Joo, Y. H. (2023) · Information Sciences · doi:10.1016/j.ins.2023.02.009 · Cited by 25
A joint local–global search mechanism for long-term tracking with dynamic memory network
Gao, Z., Zhuang, Y., Gu, J., Yang, B., & Nie, Z. (2023) · Expert Systems with Applications · doi:10.1016/j.eswa.2023.119890 · Cited by 27
SiamCAF: Complementary Attention Fusion-Based Siamese Network for RGBT Tracking
Xue, Y., Zhang, J., Lin, Z., Li, C., Huo, B., & Zhang, Y. (2023) · Remote Sensing · doi:10.3390/rs15133252 · Cited by 28
Object Tracking in Satellite Videos With Distractor–Occlusion-Aware Correlation Particle Filters
Li, Y., Wang, N., Li, W., Li, X., & Rao, M. (2024) · IEEE Transactions on Geoscience and Remote Sensing · doi:10.1109/tgrs.2024.3353298 · Cited by 34
“Visual object tracking techniques can be broadly categorized into two main classes: those based on correlation filters [1], [7], [8], [9], [10], [11], [12], [13] and those relying on end-to-end neural networks [14], [15], [16], [17], [18], [19], [20], [21].”
BackgroundEnhanced Target Tracking Algorithm for Autonomous Driving Based on Visible and Infrared Image Fusion
Yuan, Q., Shi, H., Xuan, A. T. Y., Gao, M., Xu, Q., & Wang, J. (2023) · Journal of Intelligent and Connected Vehicles · doi:10.26599/jicv.2023.9210018 · Cited by 26
StableDrag: Stable Dragging for Point-Based Image Editing
Cui, Y., Zhao, X., Zhang, G., Cao, S., Ma, K., & Wang, L. (2024) · Lecture notes in computer science · doi:10.1007/978-3-031-73636-0_20 · Cited by 40
A robust visual tracking method via local feature extraction and saliency detection
Wang, Y., Wei, X., Ding, L., Tang, X., & Zhang, H. (2019) · The Visual Computer · doi:10.1007/s00371-019-01646-1 · Cited by 25
“In [15], a minimum output sum of squared error (MOSSE) filter is proposed for visual tracking.”
BackgroundRobust Long-Term Tracking via Instance-Specific Proposals
Liu, H., Hu, Q., Li, B., & Guo, Y. (2019) · IEEE Transactions on Instrumentation and Measurement · doi:10.1109/tim.2019.2908715 · Cited by 26
City-scale vehicle tracking and traffic flow estimation using low frame-rate traffic cameras
Wei, P., Shi, H., Yang, J., Qian, J., Ji, Y., & Jiang, X. (2019) · ACM International Joint Conference on Pervasive and Ubiquitous Computing (UbiComp) · doi:10.1145/3341162.3349336 · Cited by 25
“Wecompare against three representative state-of-the-art techniques: 1) Mosse Tracking [2], a type of correlation filtering tracker; 2) Deepgaze [21], using particle filters; and 3) optical flow, which we implement using OpenCV [3].”
MethodMeMu: Metric correlation Siamese network and multi-class negative sampling for visual tracking
Xiao, Y., Li, J., Du, B., Wu, J. X., Chang, J., & Zhang, W. (2019) · Pattern Recognition · doi:10.1016/j.patcog.2019.107170 · Cited by 25
Three-step action search networks with deep Q-learning for real-time object tracking
Teng, Z., Zhang, B., & Fan, J. (2020) · Pattern Recognition · doi:10.1016/j.patcog.2019.107188 · Cited by 28
Ship Recognition and Tracking System for Intelligent Ship Based on Deep Learning Framework
Liu, B., Wang, S. Z., Xie, Z. X., Zhao, J., & Li, M. (2019) · TransNav the International Journal on Marine Navigation and Safety of Sea Transportation · doi:10.12716/1001.13.04.01 · Cited by 25
“Domel et al. applied the correlation filtering algorithm to the tracking field, and use a single gray feature to represent the target for tracking (Bolme et al. 2010).”
MethodBehavioral Signatures of a Developing Neural Code
Avitan, L., Pujic, Z., Mölter, J., McCullough, M., Zhu, S., Sun, B., Myhre, A.-E., & Goodhill, G. J. (2020) · Current Biology · doi:10.1016/j.cub.2020.06.040 · Cited by 26
Efficient object tracking using hierarchical convolutional features model and correlation filters
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/s00371-020-01833-5 · Cited by 24
“[18] proposed theminimum output sum of squared error (MOSSE) filter-based tracker in 2010.”
BackgroundCai, E., Zhang, Y., Lu, X., Ji, X., Gao, X., Hou, J., Shi, J., & Guo, W. (2024) · Mechanical Systems and Signal Processing · doi:10.1016/j.ymssp.2024.111398 · Cited by 24
Fusing Crowd Density Maps and Visual Object Trackers for People Tracking in Crowd Scenes
Ren, W., Kang, D., Tang, Y., & Chan, A. B. (2018) · 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.2018.00561 · Cited by 25
“[3] presented a Minimum Output Sum of Squared Error (MOSSE) filter for visual tracking on gray images.”
Parallel Attentive Correlation Tracking
Zhang, K., Fan, J., Liu, Q., Yang, J. J., & Lian, W. (2018) · IEEE Transactions on Image Processing · doi:10.1109/tip.2018.2868561 · Cited by 25
“Recently, CF based approaches have attracted much attention since the CFs can be efficiently calculated by FFTs [8], [12]–[14], [45]–[55].”
Learning salient features to prevent model drift for correlation tracking
Zhang, Y., Gao, X., Chen, Z., Zhong, H., Li, L., Yan, C. C., & Shen, T. (2020) · Neurocomputing · doi:10.1016/j.neucom.2019.12.006 · Cited by 24
Object Tracking Method for Videomonitoring in Intelligent Transport Systems
Makhmutova, A., Anikin, I. V., & Dagaeva, M. (2020) · International Russian Automation Conference (RusAutoCon) · doi:10.1109/rusautocon49822.2020.9208032 · Cited by 24
“Minimum Output Sum of Squared Error (MOSSE) tracker [17] uses an adaptive correlation for object tracking, which produces stable correlation filters when initialized using a single frame.”
MethodVision-Based Structural FE Model Updating Using Genetic Algorithm
Park, G., Hong, K.-N., & Yoon, H. (2021) · Applied Sciences · doi:10.3390/app11041622 · Cited by 24
“[23] achieved high efficiency by calculating the correlation in the time domain.”
BackgroundMultiple Pedestrians and Vehicles Tracking in Aerial Imagery Using a Convolutional Neural Network
Azimi, S. M., Kraus, M., Bahmanyar, R., & Reinartz, P. H. (2021) · Remote Sensing · doi:10.3390/rs13101953 · Cited by 24
“KCF works with multiple channel-like correlation filters.”
MethodInfluentialNoisyOTNet: A Robust Real-Time Vehicle Tracking Model for Traffic Surveillance
Xing, W., Yang, Y., Zhang, S., Yu, Q., & Wang, L. (2021) · IEEE Transactions on Circuits and Systems for Video Technology · doi:10.1109/tcsvt.2021.3086104 · Cited by 25
High-performance UAVs visual tracking based on siamese network
Yang, S., Chen, H., Xu, F., Li, Y., & Yuan, J. (2021) · The Visual Computer · doi:10.1007/s00371-021-02271-7 · Cited by 26
“The object tracking algorithm based on correlation filters originated from the minimum output sum of square error [5] (MOSSE) algorithm.”
MethodSiamese Cross-Domain Tracker Design for Seamless Tracking of Targets in RGB and Thermal Videos
Chandrakanth, V., Murthy, V. S. N., & Channappayya, S. S. (2022) · IEEE Transactions on Artificial Intelligence · doi:10.1109/tai.2022.3151307 · Cited by 28
“Several variations of this method are proposed in the literature [35]–[37].”
MethodSiRi: A Simple Selective Retraining Mechanism for Transformer-Based Visual Grounding
Qu, M., Wu, Y., Liu, W., Gong, Q., Liang, X., Russakovsky, O., Zhao, Y., & Wei, Y. (2022) · Lecture notes in computer science · doi:10.1007/978-3-031-19833-5_32 · Cited by 30
Target-Aware Transformer Tracking
Zheng, Y., Zhang, Y., & Xiao, B. (2023) · IEEE Transactions on Circuits and Systems for Video Technology · doi:10.1109/tcsvt.2023.3276061 · Cited by 26
“MOSSE [15] first uses correlation filters for object tracking, and its speed can reach 600FPS.”
Driver Drowsiness Detection Using Deep Learning
Jain, A. K., Sharma, V., Goel, S., Tiwari, R. G., Vajpayee, A., & Bhandari, R. (2023) · International Conference on Intelligent Technologies (CONIT) · doi:10.1109/conit59222.2023.10205537 · Cited by 24
“Recent advances in correlation filters in computer vision, have led Bolme [9] to develop a minimum output sum squared error (MOSSE) filter that can generate filters for stable linkage for tracking entities and objects.”
BackgroundIntegrating Boxes and Masks: A Multi-Object Framework for Unified Visual Tracking and Segmentation
Xu, Y., Yang, Z., & Yang, Y. (2023) · IEEE/CVF International Conference on Computer Vision (ICCV) · doi:10.1109/iccv51070.2023.00893 · Cited by 31
“Correlation filter based methods [5, 30, 16, 14, 49, 3, 15, 53] train a correlation filter on training features and perform convolution on test features to predict classification scores for the target object.”
MethodSiamDMU: Siamese Dual Mask Update Network for Visual Object Tracking
Liu, J., Wang, H., Ma, C., Su, Y., & Yang, X. (2024) · IEEE Transactions on Emerging Topics in Computational Intelligence · doi:10.1109/tetci.2024.3353674 · Cited by 28
Fast eye localization without a face model using inner product detectors
Araújo, G., Ribeiro, F. M. L., da Silva, E. A. B., & Goldenstein, S. K. (2014) · Proceedings - International Conference on Image Processing · doi:10.1109/icip.2014.7025273 · Cited by 24
“Recognizing this filter as a detector and the unknown signal as a sample to be evaluated, we can use correlation filters in pattern recognition problems such as objects [22], eyes [23] or faces detection [24, 25].”
MethodTarget tracking with dynamically adaptive correlation
Gaxiola, L. N., Diaz-Ramirez, V. H., Tapia, J. J., & García-Martínez, P. (2015) · Optics Communications · doi:10.1016/j.optcom.2015.11.077 · Cited by 25
Robust volleyball tracking system using multi-view cameras
Takahashi, M., Ikeya, K., Kano, M., Ookubo, H., & Mishina, T. (2016) · Proceedings - International Conference on Pattern Recognition/Proceedings/International Conference on Pattern Recognition · doi:10.1109/icpr.2016.7900050 · Cited by 24
“Three state-of-the-art tracking methods—TLD [10], MIL [11], KCF [12]—were used as comparison methods.”
BackgroundMethodAn Integrated Deep Learning Framework for Occluded Pedestrian Tracking
Chen, K., Song, X., Zhai, X., Zhang, B., Hou, B., & Wang, Y. (2019) · IEEE Access · doi:10.1109/access.2019.2900296 · Cited by 26
“ter [10] has attracted attention because of its speed and”
BackgroundMao, Y., He, Z., Ma, Z., Tang, X., & Wang, Z. (2019) · IEEE Access · doi:10.1109/access.2019.2932733 · Cited by 25
“The correlation filtering algorithm finds the maximum response region by comparing the signals similarity, then determines the object location, such as MOSSE [4], KCF [5], C-COT [6], ECO [7].”
MethodAn adaptive template matching-based single object tracking algorithm with parallel acceleration
Yan, B., Xiao, L., Zhang, H., Xu, D., Ruan, L., Wang, Z., & Zhang, Y. (2019) · Journal of Visual Communication and Image Representation · doi:10.1016/j.jvcir.2019.102603 · Cited by 24
Zhang, S., Li, Z., Zhang, H., & Li, J. (2020) · Remote Sensing · doi:10.3390/rs12162646 · Cited by 25
“The pioneering work of applying correlation filtering in visual object tracking is the minimum output sum of squared error (MOSSE) [1] filter method.”
MethodInfluentialIs First Person Vision Challenging for Object Tracking?
Dunnhofer, M., Furnari, A., Farinella, G. M., & Micheloni, C. (2021) · IEEE International Conference on Computer Vision Workshops · doi:10.1109/iccvw54120.2021.00304 · Cited by 32
“Specifically, we have considered short-term trackers [46] based on correlation-filters with hand-crafted features (MOSSE [11], DSST [23], KCF [37], Staple [7], BACF [42], DCFNet [79], STRCF [49], MCCTH [78]) and deep features (ECO [21], ATOM [22], DiMP [9], PrDiMP [24], KYS [10]).”
Fast Multi-Shadow Tracking for Video-SAR Using Triplet Attention Mechanism
Yang, X., Shi, J., Chen, T., Hu, Y. G., Zhou, Y., Zhang, X., Wei, S., & Wu, J. (2022) · IEEE Transactions on Geoscience and Remote Sensing · doi:10.1109/tgrs.2022.3152556 · Cited by 28
“traditional correlation filter based methods [21], [26] and deep learning based methods [6], [8], [9], [27] which can be applied for single target tracking.”
BackgroundMethodRobust Visual Tracking Using Exemplar-Based Detectors
Gao, C., Chen, F., Yu, J.-G., Huang, R., & Sang, N. (2015) · IEEE Transactions on Circuits and Systems for Video Technology · doi:10.1109/tcsvt.2015.2513700 · Cited by 25
“This view is similar to the one of [34].”
ResultWang, J., Liu, W., Xing, W., & Zhang, S. (2018) · Signal Processing Image Communication · doi:10.1016/j.image.2018.01.005 · Cited by 24
Evolving Head Tracking Routines With Brain Programming
Olague, G., Hernandez, D. E., Clemente, E., & Chan-Ley, M. (2018) · IEEE Access · doi:10.1109/access.2018.2831633 · Cited by 23
“This idea has been extended recently with the use of adaptive correlation filters and convolution through the application of the fast Fourier transform [5] with excellent results [12], [20].”
MethodZhang, L., Han, H., Zhou, M., Al‐Turki, Y. A., & Abusorrah, A. M. (2021) · IEEE Sensors Journal · doi:10.1109/jsen.2021.3079214 · Cited by 23
Javed, S., Mahmood, A., Dias, J. M. M., Werghi, N., & Rajpoot, N. (2021) · Medical Image Analysis · doi:10.1016/j.media.2021.102104 · Cited by 23
Prediction of Road Accidents Using Machine Learning Technique
Alagarsamy, S., Malathi, M., Manonmani, M., Sanathani, T., & Kumar, A. S. (2021) · International Conference on Electronics, Communication and Aerospace Technology (ICECA) · doi:10.1109/iceca52323.2021.9675852 · Cited by 23
“Early information provided can save the life of many people riding along in the risk side [2].”
BackgroundWATB: Wild Animal Tracking Benchmark
Wang, F., Ping, C., Li, F., Wang, X., He, B., & Sun, F. (2022) · International Journal of Computer Vision · doi:10.1007/s11263-022-01732-3 · Cited by 26
“Correlation filter based tracking methods : MOSSE Bolme et al. (2010) is the first CF-based tracking method which brings researchers to a new direction.”
MethodA ball-shaped target development and pose estimation strategy for a tracking-based scanning system
Jiang, T., Cui, H., Cheng, X., Li, P., & Tian, W. (2022) · IEEE Transactions on Instrumentation and Measurement · doi:10.1109/tim.2022.3205675 · Cited by 23
“11(a), the confidence value of MOSSE-based tracking is 0.54, indicating that the prediction box deviates from the target.”
MethodInfluentialAdaptive temporal feature modeling for visual tracking via cross-channel learning
Wang, Y., Zhang, W., Lai, C., & Wang, J. (2023) · Knowledge-Based Systems · doi:10.1016/j.knosys.2023.110380 · Cited by 24
MobileSAM-Track: Lightweight One-Shot Tracking and Segmentation of Small Objects on Edge Devices
Liu, Y., Zhao, Y., Zhang, X., Wang, X., Lian, C., Li, J., Shan, P., Fu, C., Lyu, X., Li, L., et al. (2023) · Remote Sensing · doi:10.3390/rs15245665 · Cited by 28
Robust weld seam tracking method based on detection and tracking of laser stripe
Wang, N., Yang, J., Zhang, X., Gong, T., & Zhong, K. (2024) · The International Journal of Advanced Manufacturing Technology · doi:10.1007/s00170-023-12667-5 · Cited by 24
Yu, Y., Zhang, Y., Chen, L., Ge, P., & Chen, C. L. P. (2024) · IEEE Transactions on Intelligent Vehicles · doi:10.1109/tiv.2024.3355171 · Cited by 23
Learning Siamese networks for laser vision seam tracking
Zou, Y., Li, J., Chen, X., & Lan, R. (2018) · Journal of the Optical Society of America A · doi:10.1364/josaa.35.001805 · Cited by 24
Channel Pruning for Visual Tracking
Che, M., Wang, R., Lu, Y., Li, Y., Zhi, H., & Xiong, C. (2019) · Lecture notes in computer science · doi:10.1007/978-3-030-11009-3_3 · Cited by 23
Part-based visual tracking with spatially regularized correlation filters
Zhang, D., Zhang, Z., Zou, L., Xie, Z., He, F., Wu, Y., & Tu, Z. (2019) · The Visual Computer · doi:10.1007/s00371-019-01634-5 · Cited by 23
“Recently, Discriminative Correlation Filter (DCF)-based approaches [2,3,6,13,14,18,22,27,45] have been shown to achieve a fairly rapid and robust tracking performance, and thus, they have attracted considerable attention.”
InfluentialA multi-agent dynamic system for robust multi-face tracking
Maleš, L., Marčetić, D., & Ribarič, S. (2019) · Expert Systems with Applications · doi:10.1016/j.eswa.2019.02.008 · Cited by 23
EnKCF: Ensemble of Kernelized Correlation Filters for High-Speed Object Tracking
Uzkent, B., & Seo, Y. (2018) · IEEE Winter Conference on Applications of Computer Vision · doi:10.1109/wacv.2018.00129 · Cited by 24
Adaptive Compressive Tracking via Online Vector Boosting Feature Selection
Liu, Q., Yang, J., Zhang, K., & Wu, Y. (2016) · IEEE Transactions on Cybernetics · doi:10.1109/tcyb.2016.2606512 · Cited by 25
“mum output sum of squared errors tracker [41] with robust scale estimation.”
A Hybrid Method for Tracking of Objects by UAVs
Sarıbaş, H., Uzun, B., Benlıgıray, B., Eker, O., & Çevıkalp, H. (2019) · IEEE/CVF Conference on Computer Vision and Pattern Recognition Workshops (CVPRW) · doi:10.1109/cvprw.2019.00082 · Cited by 23
“The correlation filter-based tracking methods on the other hand solve a ridge regression problem in the frequency space to locate the object to be tracked [4, 16, 9].”
MethodJoint Channel Reliability and Correlation Filters Learning for Visual Tracking
Du, F., Liu, P., Zhao, W., & Tang, X. (2019) · IEEE Transactions on Circuits and Systems for Video Technology · doi:10.1109/tcsvt.2019.2909654 · Cited by 24
“Many machine learning techniques have been used in the tracking community, such as support vector machine (SVM) [31], [32], multiple instance learning [33], [34], random forests [35], boosting [36], and correlation filtering [2], [3].”
MethodInfluentialLocation-Aware and Regularization-Adaptive Correlation Filters for Robust Visual Tracking
Liu, R., Chen, Q., Yao, Y., Fan, X., & Luo, Z. (2020) · IEEE Transactions on Neural Networks and Learning Systems · doi:10.1109/tnnls.2020.3005447 · Cited by 25
“[9] first applied CF for visual tracking.”
Multi-Task Deep Dual Correlation Filters for Visual Tracking
Zheng, Y., Liu, X., Cheng, X., Zhang, K., Wu, Y., & Chen, S. (2020) · IEEE Transactions on Image Processing · doi:10.1109/tip.2020.3029897 · Cited by 24
“[9] first introduced CF into object tracking in 2010, where the CF was trained through the mean square error minimization between the actual output and expected output in the Fourier domain.”
BackgroundMethodInfluentialVisual Object Tracking in Drone Images with Deep Reinforcement Learning
Gozen, D., & Özer, S. (2021) · Proceedings - International Conference on Pattern Recognition/Proceedings/International Conference on Pattern Recognition · doi:10.1109/icpr48806.2021.9413316 · Cited by 27
“Recently, correlation filter based techniques are also widely used in object tracking because of their efficient and robust results [3], [5].”
BackgroundMutual-Complementing Framework for Nuclei Detection and Segmentation in Pathology Image
Feng, Z., Wang, Z., Wang, X., Mao, Y., Li, T., Lei, J., Wang, Y., & Song, M. (2021) · IEEE/CVF International Conference on Computer Vision (ICCV) · doi:10.1109/iccv48922.2021.00400 · Cited by 26
“The correlation filter has been successfully applied in the object tracking task [5], where the correlation between the correlation filter and the corresponding input image patch will have the highest response.”
Contextual Bag-of-Words for Robust Visual Tracking
Zeng, F., Ji, Y., & Levine, M. D. (2017) · IEEE Transactions on Image Processing · doi:10.1109/tip.2017.2778561 · Cited by 23
Adaptive feature representation for visual tracking
Han, Y., Deng, C., Zhang, Z., Li, J., & Zhao, B. (2017) · Proceedings - International Conference on Image Processing · doi:10.1109/icip.2017.8296605 · Cited by 22
“[7] introduce correlation filter into tracking as classifiers.”
MethodDynamically Spatiotemporal Regularized Correlation Tracking
Zheng, Y., Song, H., Zhang, K., Fan, J., & Liu, X. (2019) · IEEE Transactions on Neural Networks and Learning Systems · doi:10.1109/tnnls.2019.2929407 · Cited by 22
“Since the minimum output sum of squared error (MOSSE) [25] tracker has a great success in”
BackgroundRobust adaptive learning with Siamese network architecture for visual tracking
Zhang, W., Du, Y., Chen, Z., Deng, J., & Liu, P. (2020) · The Visual Computer · doi:10.1007/s00371-020-01839-z · Cited by 22
“In order to improve the accuracy and robustness of the correlation filter-based tracking algorithm, researchers introduce color attribute features (CN) [28], histogram of oriented gradients features (HOG) [8, 9], fusedHOGandCNfeatures [12, 13], fused HOG and color histogram feature [14], etc.”
MethodBoundary‐aware vehicle tracking upon UAV
Han, Y., Wang, H., Zhang, Z., & Wang, W. (2020) · Electronics Letters · doi:10.1049/el.2020.1170 · Cited by 22
Intelligent droplet tracking with correlation filters for digital microfluidics
Li, L., Gu, Z., Zhou, J., Yan, B., Kong, C., Wang, H., & Wang, H. (2021) · Chinese Chemical Letters · doi:10.1016/j.cclet.2021.05.002 · Cited by 22
CapsuleRRT: Relationships-aware Regression Tracking via Capsules
Ma, D., & Wu, X. (2021) · IEEE Computer Society Conference on Computer Vision and Pattern Recognition/Proceedings - IEEE Computer Society Conference on Computer Vision and Pattern Recognition/Proceedings · doi:10.1109/cvpr46437.2021.01080 · Cited by 25
“By computing the ridge regression in the Fourier domain, DCFs trackers showing attractive efficiency [4, 35, 16].”
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.