Fast and Robust Object Tracking Using Tracking Failure Detection in Kernelized Correlation Filter
Open accessThe DOI matches its Crossref record; 29 of the 29 references it cites were found in a registry or an index.
Abstract
Object tracking has long been an active research topic in image processing and computer vision fields with various application areas. For practical applications, the object tracking technique should be not only accurate but also fast in a real-time streaming condition. Recently, deep feature-based trackers have been proposed to achieve a higher accuracy, but those are not suitable for real-time tracking because of an extremely slow processing speed. The slow speed is a major factor to degrade tracking accuracy under a real-time streaming condition since the processing delay forces skipping frames. To increase the tracking accuracy with preserving the processing speed, this paper presents an improved kernelized correlation filter (KCF)-based tracking method that integrates three functional modules: (i) tracking failure detection, (ii) re-tracking using multiple search windows, and (iii) motion vector analysis to decide a preferred search window. Under a real-time streaming condition, the proposed method yields better results than the original KCF in the sense of tracking accuracy, and when a target has a very large movement, the proposed method outperforms a deep learning-based tracker, such as multi-domain convolutional neural network (MDNet).
Overview
Integrity signals
Registry
Cites
Statistics
Verification
Claims the paper makes
Claims other papers make about this one
Each is checked against this paper’s own text: does it say what the citing paper says it does?
In the citing paper
“Most algorithms, such as SAMF, use Maximum response value for scale searching. In turn, this degrades the performance of the overall tracking scheme when the video sequence contains one or more challenging factors, such as scale variation, occlusion, motion blur, etc. [5].”
From Multiple Cues-Based Robust Visual Object Tracking Method (2022) · cites this paper as [5]
In the citing paper
“The proposed tracking scheme outperforms the other state-of-the-art algorithms by achieving the highest mean of 0.889.”
From Multiple Cues-Based Robust Visual Object Tracking Method (2022) · cites this paper as [5]
In the citing paper
“while the remaining three trackers, i.e., STRCF [28], LCT [21], and MKCF [5], have a mean overlap success rate of 0.799, 0.717, and 0.645, respectively.”
From Multiple Cues-Based Robust Visual Object Tracking Method (2022) · cites this paper as [5]
In the citing paper
“whereas MKCF [5] lost the target in frame number 999.”
From Multiple Cues-Based Robust Visual Object Tracking Method (2022) · cites this paper as [5]
In the citing paper
“The second-best in terms of distance precision is MKCF [5], with a mean value of 0.855”
From Multiple Cues-Based Robust Visual Object Tracking Method (2022) · cites this paper as [5]
2 more claims about this paper
Create a free account to see every claim other papers make about this one.
Citations
Cites
High-Speed Tracking with Kernelized Correlation Filters
Henriques, J. F., Caseiro, R., Martins, P., & Batista, J. (2015) · IEEE Transactions on Pattern Analysis and Machine Intelligence · doi:10.1109/tpami.2014.2345390 · Cited by 5,753
Online Object Tracking: A Benchmark
Wu, Y., Lim, J., & Yang, M.-H. (2013) · 2013 IEEE Conference on Computer Vision and Pattern Recognition · doi:10.1109/cvpr.2013.312 · Cited by 4,138 · cited 3×
“After experiments using Visual Tracker Benchmark dataset [29], we found that the optimal α is 0.”
MethodInfluentialVisual object tracking using adaptive correlation filters
Bolme, D., Beveridge, J. R., Draper, B. A., & Lui, Y. M. (2010) · 2010 IEEE Computer Society Conference on Computer Vision and Pattern Recognition · doi:10.1109/cvpr.2010.5539960 · Cited by 3,406 · cited 1×
“[12] proposed an improved version of ASEF, called minimum output sum of square error (MOSSE)-based tracker.”
BackgroundLearning Multi-domain Convolutional Neural Networks for Visual Tracking
Nam, H., & Han, B. (2016) · 2016 IEEE Conference on Computer Vision and Pattern Recognition (CVPR) · doi:10.1109/cvpr.2016.465 · Cited by 2,806 · cited 1×
“[20] presented multi-domain network (MDNet) that consists of shared layers and a domain-specific fully connected layer.”
BackgroundExploiting the Circulant Structure of Tracking-by-Detection with Kernels
Henriques, J. F., Caseiro, R., Martins, P., & Batista, J. (2012) · Lecture Notes in Computer Science · doi:10.1007/978-3-642-33765-9_50 · Cited by 2,310 · cited 2×
“Henriques et al. proposed circulant structured with kernels (CSK) [1] method that exploits the correlation filter in kernel space, and kernelized correlation filter (KCF) [2] extends the kernel trick.”
BackgroundMethodStaple: Complementary Learners for Real-Time Tracking
Bertinetto, L., Valmadre, J., Golodetz, S., Miksik, O., & Torr, P. H. S. (2016) · 2016 IEEE Conference on Computer Vision and Pattern Recognition (CVPR) · doi:10.1109/cvpr.2016.156 · Cited by 1,776 · cited 1×
“[16] presented sum of template and pixel-wise learners (STAPLE) method using HOG and color histograms for target representation.”
MethodDiscriminative Scale Space Tracking
Danelljan, M., Hager, G., Khan, F. S., & Felsberg, M. (2017) · IEEE Transactions on Pattern Analysis and Machine Intelligence · doi:10.1109/tpami.2016.2609928 · Cited by 1,315
Learning to Track at 100 FPS with Deep Regression Networks
Held, D., Thrun, S., & Savarese, S. (2016) · Lecture Notes in Computer Science · doi:10.1007/978-3-319-46448-0_45 · Cited by 1,199 · cited 1×
“Held et al. [22] proposed generic object tracking using regression network (GOTURN) based on the Siamese network.”
MethodRobust object tracking via sparsity-based collaborative model
Zhong, W., Lu, H., & Yang, M.-H. (2012) · 2012 IEEE Conference on Computer Vision and Pattern Recognition · doi:10.1109/cvpr.2012.6247882 · Cited by 990
Long-term correlation tracking
Ma, C., Yang, X., Zhang, C., & Yang, M.-H. (2015) · 2015 IEEE Conference on Computer Vision and Pattern Recognition (CVPR) · doi:10.1109/cvpr.2015.7299177 · Cited by 959 · cited 1×
“[15] proposed long-term correlation tracker (LCT), which is robust against target translation and can perform re-detection if tracking failure occurs.”
Background
Cited by
Kalake, L., Wan, W., & Hou, L. (2021) · IEEE Access · doi:10.1109/access.2021.3060821 · Cited by 68
“In contrast [2], [22]–[24], [46], [54]–[61], [82], classified and assessed the matches between detection and tracklets to quickly track the targets.”
BackgroundMethodWang, X., Sun, Z., Chehri, A., Jeon, G., & Song, Y. (2024) · Information Fusion · doi:10.1016/j.inffus.2024.102247 · Cited by 78
Multiple Object Tracking in Deep Learning Approaches: A Survey
Park, Y., Dang, L. M., Lee, S., Han, D., & Moon, H. (2021) · Electronics · doi:10.3390/electronics10192406 · Cited by 69
Automatic Object Tracking and Segmentation Using Unsupervised SiamMask
Noor, S., Waqas, M., Saleem, M. I., & Minhas, H. N. (2021) · IEEE Access · doi:10.1109/access.2021.3101054 · Cited by 51
“[23] proposed a modified kernalized correlation filter (KCF) that identifies tracking failure and tries to resume tracking by searching over multiple windows.”
BackgroundObject tracking and detection techniques under GANN threats: A systemic review
Jaberi, S. M. A., Patel, A., & AL-Masri, A. N. (2023) · Applied Soft Computing · doi:10.1016/j.asoc.2023.110224 · Cited by 31
Context-Aware and Occlusion Handling Mechanism for Online Visual Object Tracking
Mehmood, K., Jalil, A., Ali, A., Khan, B., Murad, M., Khan, W. U., & He, Y. (2020) · Electronics · doi:10.3390/electronics10010043 · Cited by 28
“[40] proposed an improved KCF-based tracking algorithm.”
Mohd, M. N. H., Asaari, M. S. M., Ping, O. L., & Rosdi, B. A. (2023) · Applied Sciences · doi:10.3390/app13137433 · Cited by 17
Efficient Online Object Tracking Scheme for Challenging Scenarios
Mehmood, K., Ali, A., Jalil, A., Khan, B., Cheema, K. M., Murad, M., & Milyani, A. H. (2021) · Sensors · doi:10.3390/s21248481 · Cited by 16
A Comparison of OpenCV Algorithms for Human Tracking with a Moving Perspective Camera
Haggui, O., Tchalim, M. A., & Magnier, B. (2021) · European Workshop on Visual Information Processing · doi:10.1109/euvip50544.2021.9483957 · Cited by 14
“Indeed, initially, KCF tracks the object based on Kernel [18], it extracts characteristics from Histogram of Oriented Gradients (HOG) to improve tracking accuracy [12]; it has a high processing speed and is superior for tracking the object in real time, as reported in Fig.”
Pavlović, M., Banjac, Z., & Kovačević, B. D. (2023) · EURASIP Journal on Advances in Signal Processing · doi:10.1186/s13634-023-01030-1 · Cited by 10
“The extended object search area is implemented by replicating the search windows around the central one, [45].”
Ali, A., Ghosh, A., & Chaudhuri, S. S. (2023) · Signal Image and Video Processing · doi:10.1007/s11760-023-02758-x · Cited by 10
Yue, W., Xu, F., & Juan, Y. (2024) · Remote Sensing · doi:10.3390/rs16020323 · Cited by 12
Mehmood, K., Jalil, A., Ali, A., Khan, B., Murad, M., Cheema, K. M., & Milyani, A. H. (2021) · Sensors · doi:10.3390/s21082841 · Cited by 10
“M dified KCF p rforms sig ificantly well in sequences involving oc lusions.”
MethodInfluentialChen, X., Zhang, H., Shankar, A., Bhushan, B., & Joshi, K. (2025) · Scientific Reports · doi:10.1038/s41598-025-89929-7 · Cited by 9
Different Approaches to Background Subtraction and Object Tracking in Video Streams: A Review
Sivanantham, K., Blessington Praveen, P., & Mohan Kumar, R. (2023) · Contributions to environmental sciences & innovative business technology · doi:10.1007/978-981-99-3288-7_2 · Cited by 8
HLDNet: Abandoned Object Detection Using Hand Luggage Detection Network
Kim, D., Kim, H., Mok, Y., & Paik, J. (2021) · IEEE Consumer Electronics Magazine · doi:10.1109/mce.2021.3099288 · Cited by 7
Self-citationDeep learning-based Object Detection in Underwater Communications System
Sangari, M. S., Thangaraj, K., Vanitha, U., Srikanth, N., Sathyamoorthy, J., & Renu, K. (2023) · International Conference on Electrical, Electronics, Information and Communication Technologies (ICEEICT) · doi:10.1109/iceeict56924.2023.10157072 · Cited by 7
“Due to their superior real-time performance and quicker operation than generative algorithms, discriminant algorithms like correlation filtering are now frequently used in target tracking research [7].”
BackgroundAn adaptive kernelized correlation filters with multiple features in the tracking application
Guo, D., Zhang, G., Neri, F., Peng, S., Yang, Q., & Liu, P. (2022) · Journal of Visual Communication and Image Representation · doi:10.1016/j.jvcir.2022.103484 · Cited by 6
Multiple Cues-Based Robust Visual Object Tracking Method
Khan, B., Jalil, A., Ali, A., Alkhaledi, K., Mehmood, K., Cheema, K. M., Murad, M., Tariq, H., & El-Sherbeeny, A. M. (2022) · Electronics · doi:10.3390/electronics11030345 · Cited by 5
“[13–15], but correlation filter-based tracking is still a better choice because of its efficiency and less computation cost [5].”
BackgroundMethodInfluentialrStaple: A Robust Complementary Learning Method for Real-Time Object Tracking
He, W., Li, H., Liu, W., Li, C., & Guo, B. (2020) · Applied Sciences · doi:10.3390/app10093021 · Cited by 5
“Shin et al. [26] proposed a failure detection and re-tracking algorithm based on KCF performed in real-time.”
MethodVisual Object Tracking Based on Modified LeNet-5 and RCCF
Gullapelly, A., & Banik, B. G. (2023) · Computer Systems Science and Engineering · doi:10.32604/csse.2023.032904 · Cited by 4
“In the DCF model, several deep features are merged for the object tracking in the video [14,15].”
BackgroundRobust Long-Term Visual Object Tracking via Low-Rank Sparse Learning for Re-Detection
Luo, S., Li, B., Yuan, X., & Liu, H. (2021) · Applied Sciences · doi:10.3390/app11041963 · Cited by 4
Highly Accurate Real time human Counter with Minimum Computation Cost
Ghosh, S., Kumar, A., & Saha, S. (2021) · International Conference on Advances in Electrical, Computing, Communication and Sustainable Technologies (ICAECT) · doi:10.1109/icaect49130.2021.9392459 · Cited by 4
“After consulting many of them it’s found that the tracking accuracy is a function of tracked object [20].”
BackgroundHigh-Speed Multiple Object Tracking Based on Fusion of Intelligent and Real-Time Image Processing
Kawawaki, Y., & Yamakawa, Y. (2025) · Sensors · doi:10.3390/s25113400 · Cited by 3
“In [37–40], a tracking method has been developed that combines deep learning-based detection with template-based tracking, incorporating a retracking mechanism in case the tracking score is low.”
Target tracking based on standard hedging and feature fusion for robot
Chan, S., Tao, J., Zhou, X., Wu, B. H., Wang, H., & Chen, S. (2021) · Industrial Robot the international journal of robotics research and application · doi:10.1108/ir-09-2020-0212 · Cited by 3
Video analysis for tower crane production rate estimation
Elgendi, E. O., Shawki, K. M., & Mohy, A. A. (2023) · Journal of Information Technology in Construction · doi:10.36680/j.itcon.2023.007 · Cited by 4
“In response, a quicker on-line change (Henriques et al., 2015) was suggested, which is an abbreviation for Kernelized Correlation Filters (KCF) (Shin et al., 2020), builds on BOOSTING and MIL, but mathematically uses the natural overlapping of samples in the MIL method and the extra data that comes…”
MethodInfluentialResearch on deep correlation filter tracking based on channel importance
Yang, G., Li, C., & Chen, H. (2022) · EURASIP Journal on Advances in Signal Processing · doi:10.1186/s13634-022-00860-9 · Cited by 4
Multispectral Target Tracking with Robust Correlation and Optimal Position Prediction
Bousta, M. A., Nemra, A., & Hamami, L. (2022) · Unmanned Systems · doi:10.1142/s2301385024500043 · Cited by 2
A Survey on GPU-Based Visual Trackers
Mohamed, I., Elhenawy, I., & Salah, A. (2023) · Studies in computational intelligence · doi:10.1007/978-3-031-18735-3_4 · Cited by 2
Li, B., & Quan, H. (2022) · Journal of Sensors · doi:10.1155/2022/3190206 · Cited by 1
“Compared with generative algorithms, discriminant algorithms such as correlation filtering have better real-time performance and operation speed, so it has become the main research method in the field of target tracking [2].”
MethodRetractedMaharani, D. A., Machbub, C., & Yulianti, L. (2021) · International Journal on Electrical Engineering and Informatics · doi:10.15676/ijeei.2021.13.4.7 · Cited by 1
“Nowadays, many popular tracking methods have been developed, such as [1][2], the recursive filter that measures the state of each time step to determine the location of a moving object.”
MethodTracking heart surface features to determine myocardial contrast agent enrichment
Sprenger, J., Petersen, J., Neumann, N., Reichenspurner, H. C., Russ, D., Detter, C., & Schlaefer, A. (2021) · Current Directions in Biomedical Engineering · doi:10.1515/cdbme-2021-1012 · Cited by 1
“The Kernelized Correlation Filter (KCF) [5] and its extensions have successively been applied to different data sets [6, 7] for a robust tracking.”
MethodFeature Fusion with Deep Neural Network in Kernelized Correlation Filters Tracker
Maharani, D. A., Machbub, C., Rusmin, P. H., & Yulianti, L. (2021) · IEEE International Conference on System Engineering and Technology (ICSET) · doi:10.1109/icset53708.2021.9612567 · Cited by 1
Information Extraction and Object Tracking in Digital Video
Neves, A. J. R., & Gallegos-Funes, F. J. (2022) · Artificial intelligence · doi:10.5772/intechopen.94616
Cognitive Visual Tracking of Hand Gestures in Real-Time RGB Videos
Golash, R., & Jain, Y. K. (2022) · Artificial intelligence · doi:10.5772/intechopen.103170 · Cited by 1
A Novel TBD Method for Non-Cooperative Bistatic Radar Based on Kernel Correlation Filtering
Lu, Y., Song, J., & Xiong, W. H. (2023) · doi:10.23919/aces-china60289.2023.10249624
“To solve the problem of drift and loss of tracking frames during the tracking process, scholars have employed methods such as motion vector [7] analysis and Kalman filtering [8] .”
MethodLashari, H. M., Tahir, M., Taj, I. A., Nawaz, R., & Ahmad, R. F. (2023) · International Multi-Topic Conference · doi:10.1109/inmic60434.2023.10465924
“Among them, Jungsup Shin et al. [27] proposed an occlusion detection technique in a kernelized correlation filter.”
MethodVirtual mouse implementation with hand gesture recognition using OpenCV and VNC
Selvi, T. K., Sasirekha, S., Arun, B. S., & Manikandan, M. (2024) · AIP conference proceedings · doi:10.1063/5.0229705
Liu, X., Han, J., Peng, Y., Liang, Q., An, K., He, F., & Cheng, Y. (2024) · Sensors · doi:10.3390/s24248176
“In a subsequent development, they advanced the field of single-object tracking with the introduction of the kernel correlation filter (KCF) [5], based on the minimum mean square error principle.”
Robust Person‐Following Based on Monocular Vision for Elderly‐Care Robot
Than, T. T., Le, T., Vo, D. T., & Nguyen, M. S. (2025) · IEEJ Transactions on Electrical and Electronic Engineering · doi:10.1002/tee.70098
Liu, T., Wang, Y., Sun, H., & Yuan, S. (2026) · Applied Sciences · doi:10.3390/app16062843
Detecting Object Tracking Failure via Sequential Hypothesis Testing
Muñoz, A. M., Verma, R., & Timans, A. (2026) · IEEE/CVF Winter Conference on Applications of Computer Vision Workshops (WACVW) · doi:10.1109/wacvw68408.2026.00023
“Existing approaches rely on heuristic estimates of model confidence, such as entropy or peak values of the tracker’s internal response map [39, 48], but lack formal statistical grounding.”
Influential
Metadata
- Authors
- Shin, J., Kim, H., Kim, D., & Paik, J.
- Affiliations
- Chung-Ang University (KR)
- Corresponding author
- Paik, Joonki
- Venue
- Applied Sciences
- Publisher
- MDPI AG
- Published
- 2020-01-20
- Volume
- 10
- Issue
- 2
- Pages
- 713
- ISSN
- 2076-3417 (ISSN-L)
- OpenAlex
- W2999749273
- Cited by
- 42
- References
- 29
- Citations by year
- 2026: 2 · 2025: 3 · 2024: 4 · 2023: 11 · 2022: 7 · 2021: 13 · 2020: 2
- FWCI
- 3.20
- Type
- journal article
- Language
- en
- Open access
- gold
- dx.doi.org
- Licence
- Locations
- Applied Sciences (publishedVersion, cc-by)
- DOAJ (DOAJ: Directory of Open Access Journals) (submittedVersion)
- Funders
- Institute for Information and Communications Technology Promotion (IITP) grant funded by the Korea government (2017-0-00250)
- ICT R&D program of MSIP/IITP (2014-0-00077)
- 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 Neural Network Applications
- Physical Sciences › Computer Science › Computer Vision and Pattern Recognition › Advanced Image and Video Retrieval Techniques
- Keywords
- object tracking, kernelized correlation filter, tracking failure detection, motion vector analysis, live streaming, fast 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.