Abstract
The conventional tracking-learning-detection (TLD) algorithm is sensitive to illumination changes, clutter, significant changes of target shape between consecutive frames. In addition, low frame rate scenarios result in drift in object position or even missing the object. To solve these problems and enhance the tracking robustness, in this paper, TLD algorithm was extended in two folds. First, Kalman filter and Mean-shift algorithms were combined for the tracking part and second, co-training semi-supervised learning algorithm was used for the learning part of the conventional TLD structure. The Kalman filter estimates the position of the target in the next frame based on the previous positions of the target. This reduces tracking failure. On the other hands, the Mean-shift tracking algorithm is robust to rotation, partial occlusion and scale changing. In the learning part of TLD structure, two training tracking algorithms with two independent classifiers were run on the current frame simultaneously. Its structure makes data of both pools (color features and target templates) update by the results of other algorithm, in addition to the results of the corresponding algorithm in each of the tracking and detection algorithms. Therefore, classifiers can learn faster changing features of the target during the consecutive frames in online tracking process. Finally, the extended structure can solve the problem of lost object in LFR videos tracking and other similar challenges simultaneously. In terms of overlap ratio metric, comparing with conventional TLD and extended kernelized correlation filters (EKCF) algorithms, the success rate of our algorithm under various scenarios has increased by 161.03% and 255.82% respectively and under other scenarios, in terms of precision metric, it has increased by 18.46% and 1479.47%, respectively. Accordingly, comparative evaluations of the proposed method to other top state-of-the-art tracking algorithms under various scenarios present in TB-100 dataset, the superior performance of the proposed algorithm was demonstrated compared to other tracking algorithms in terms of tracking robustness, stability and real-time performance.
Similar content being viewed by others
Data availability
The data that support the finding of this study are publicly available from “http://cvlab.hanyang.ac.kr/tracker_benchmark/datasets.html”.
References
Ahmad S, Mehfuz S, Mebarek-Oudina F, Beg J, (2022) RSM analysis based cloud access security broker: a systematic literature review. Cluster Comput, pp 1–31
Bao C, Wu Y, Ling H, Ji H (2012) Real time robust l1 tracker using accelerated proximal gradient approach. In: 2012 IEEE conference on computer vision and pattern recognition, pp 1830–1837
Bhatti UA, Huang M, Wu D, Zhang Y, Mehmood A, Han H (2019) Recommendation system using feature extraction and pattern recognition in clinical care systems. Enterprise Inf Syst 13(3):329–351
Bhatti UA, Yu Z, Chanussot J, Zeeshan Z, Yuan L, Luo W, Nawaz SA, Bhatti MA, Ain QU, Mehmood A (2021) Local similarity-based spatial–spectral fusion hyperspectral image classification with deep CNN and Gabor filtering. IEEE Trans Geosci Remote Sens 60:1–15
Boroujeni HS, Charkari NM, Behrouzifar M, Makhsoos PT (2011) Tracking multiple variable-sizes moving objects in LFR videos using a novel genetic algorithm approach. In: Knowledge technology week, pp 143–153
Carneiro G, Nascimento JC (2011) Incremental on-line semi-supervised learning for segmenting the left ventricle of the heart from ultrasound data. In: IEEE international conference on computer vision, pp 1700–1707
Chowdhary CL, Patel PV, Kathrotia KJ, Attique M, Perumal K, Ijaz MF (2020) Analytical study of hybrid techniques for image encryption and decryption. Sensors 20(18):5162
Chuang MC, Hwang JN, Kuo FF, Shan MK, Williams K (2014) Recognizing live fish species by hierarchical partial classification based on the exponential benefit. In: IEEE international conference on image processing (ICIP), pp 5232–5236
Dai W, Chang T, Su K, Wang Q (2016) Improved TLD target algorithm based on feature fusion. In: 2nd workshop on advanced research and Technology in Industry Applications (WARTIA-16), pp 398–403
Dong E, Deng M, Tong J, Jia C, Du S (2019) Moving vehicle tracking based on improved tracking–learning–detection algorithm. IET Comput Vis 13(8):730–741
Duan H, Zhang Y, Sheng W, Chen X, Ren J (2020) An improved TLD target tracking algorithm combined with kernel correlation filtering. IOP Conf Ser: Earth Environ Sci 440(3):032015
Everingham M, Van Gool L, Williams CK, Winn J, Zisserman A (2010) The pascal visual object classes (voc) challenge. Int J Comput Vis 88(2):303–338
Fang Y, Liu J, Li J, Cheng J, Hu J, Yi D, Xiao X, Bhatti UA (2022) Robust zero-watermarking algorithm for medical images based on SIFT and Bandelet-DCT. Multimed Tools Appl 81(12):16863–16879
Gaxiola LN, Diaz-Ramirez VH, Tapia JJ, García-Martínez P (2016) Target tracking with dynamically adaptive correlation. Opt Commun 365:140–149
Godec M, Roth PM, Bischof H (2013) Hough-based tracking of non-rigid objects. Comput Vis Image Underst 117(10):1245–1256
Henriques JF, Caseiro R, Martins P, Batista J (2014) High-speed tracking with kernelized correlation filters. IEEE Trans Pattern Anal Mach Intell 37(3):583–596
Hu J, Cai M, Li J (2017) An improved TLD method based on color feature. In: 2017 29th Chinese control and decision conference (CCDC), pp 6096–6101
Hussain R, Karbhari Y, Ijaz MF, Woźniak M, Singh PK, Sarkar R (2021) Revise-net: exploiting reverse attention mechanism for salient object detection. Remote Sens 13(23):4941
Jalali V, Kaur D (2020) A study of classification and feature extraction techniques for brain tumor detection. Int J Multimed Inf Retriev 9:271–290
Jeong J, Yoon TS, Park JB (2017) Mean shift tracker combined with online learning-based detector and Kalman filtering for real-time tracking. Expert Syst Appl 79:194–206
Kalal Z, Mikolajczyk K, Matas J (2011) Tracking-learning-detection. IEEE Trans Pattern Anal Mach Intell 34(7):1409–1422
Lee G, Mallipeddi R, Lee M (2017) Trajectory-based vehicle tracking at low frame rates. Expert Syst Appl 80:46–57
Li Y, Ai H, Yamashita T, Lao S, Kawade M (2008) Tracking in low frame rate video: a cascade particle filter with discriminative observers of different life spans. IEEE Trans Pattern Anal Mach Intell 30(10):1728–1740
Li Z, Chen J, Schraudolph NN (2008) An improved mean-shift tracker with kernel prediction and scale optimisation targeting for low-frame-rate video tracking. In: 2008 19th international conference on pattern recognition, pp 1051–1055
Li T, Zhao WJ, Yang S, Li C (2016) An improved TLD object tracking algorithm. In eighth international conference on digital image processing (ICDIP 2016), pp 100330–100334
Li T, Li J, Liu J, Huang M, Chen YW, Bhatti UA (2022) Robust watermarking algorithm for medical images based on log-polar transform. EURASIP J Wirel Commun Netw 24:1–11
Miao F, Cang-ju X (2017) Improved TLD target tracking method based on frame difference. Electron Design Eng 7
Moridvaisi H, Razzazi F, Pourmina MA, Dousti M (2020) An extended KCF tracking algorithm based on TLD structure in low frame rate videos. Multimed Tools Appl 79(29):20995–21012
Nawaz SA, Li J, Bhatti UA, Bazai SU, Zafar A, Bhatti MA, Mehmood A, Ain QU, Shoukat MU (2021) A hybrid approach to forecast the COVID-19 epidemic trend. Plos One 16(10):e0256971
Nummiaro K, Koller-Meier E, Van Gool L (2003) An adaptive color-based particle filter. Image Vis Comput 21(1):99–110
Nyo MT, Mebarek-Oudina F, Hlaing SS, Khan NA (2022) Otsu’s thresholding technique for MRI image brain tumor segmentation. Multimed Tools Appl:1–13
Oron S, Bar-Hillel A, Levi D, Avidan S (2015) Locally orderless tracking. Int J Comput Vis 111(2):213–228
Otoom M, Al-Louzi M (2021) Enhanced TLD-based video object-tracking implementation tested on embedded platforms. J Real-Time Image Process 18:937–952
Palaniappan K, Bunyak F, Kumar P, Ersoy I, Jaeger S, Ganguli K, Haridas A, Fraser J, Rao RM, Seetharaman G (2010) Efficient feature extraction and likelihood fusion for vehicle tracking in low frame rate airborne video. In: 2010 13th international conference on information fusion, pp 1–8
Pan Z, Liu S, Fu W (2017) A review of visual moving target tracking. Multimed Tools Appl 76(16):16989–17018
Pang Y, Shen D, Chen G, Liang P, Pham K, Blasch E, Wang Z, Ling H (2013) Low frame rate video target localization and tracking testbed. In ground/air multisensor interoperability, integration, and networking for persistent ISR IV 8742(1):87420T
Park E, Ju H, Jeong YM, Min SY (2015) Tracking-learning-detection adopted unsupervised learning algorithm. In: 2015 seventh international conference on knowledge and systems engineering (KSE), pp 234–237
Piao S, Berns K (2014) Multi-object tracking based on tracking-learning-detection framework. Field Assist Robot-Adv Syst Algorithms: 74–87
Porikli F, Yilmaz A (2012) Object detection and tracking. In: Video analytics for business intelligence, pp 3–41
Sathish PK, Balaji S (2018) A complete person re-identification model using kernel-PCA-based Gabor-filtered hybrid descriptors. Int J Multimed Inf Retriev 7(4):221–229
Siqueira DL, MacHado AMC (2016) People detection and tracking in low frame-rate dynamic scenes. IEEE Lat Am Trans 14(4):1966–1971
Song Z, Cong Z, Yanan Z, Yuren D (2017) An improved TLD target tracking algorithm based on mean shift. In: 2017 13th IEEE international conference on Electronic Measurement & Instruments (ICEMI), pp 387–391
Taman J, Nkapkop JDD, Ijaz MF, Prasad PK, Tsafack N, Saha A, Kengne J, Son Y (2021) Dynamical properties of ion-acoustic waves in space plasma and its application to image encryption. IEEE Access 9:18762–18782
Wang F, Liu E, Yang J, Liu R (2007) Target tracking based on a hybrid tracker with two hierarchical appearance models. Measure Sci Technol 18(8):2546
Wang T, Qin R, Chen Y, Snoussi H, Choi C (2019) A reinforcement learning approach for UAV target searching and tracking. Multimed Tools Appl 78(4):4347–4364
Weiwei K, Daibing Z, Shulong Z, Dianle Z, Boxin Z, Zhiwei Z, Zhaowei M, Dengqing T, Jianwei Z (2015) Autonomous track and land a MAV using a modified tracking-learning-detection framework. In: 2015 34th Chinese control conference (CCC), pp 5359–5366
Wu Y, Shen B, Ling H (2012) Online robust image alignment via iterative convex optimization. In: 2012 IEEE conference on computer vision and pattern recognition, pp 1808–1814
Xu T, Huang C, He Q, Guan G, Zhang Y (2016) An improved TLD target tracking algorithm. In: 2016 IEEE international conference on information and automation (ICIA), pp 2051–2055
Yang, X, Zhu, S, Xia, S, Zhou, D, (2019) A new TLD target tracking method based on improved correlation filter and adaptive scale. Vis Comput, pp.1-13
Yu L, Zheng T, Shi Q (2016) Image tracking algorithm improvement based on TLD frame. J Sign Process Image Process Pattern Recogn 9(5):431–440
Yue C, Yu W, Hou, Z, Ma S (2020) Visual tracking algorithm based on color name histogram. IOP Conf Ser: Mater Sci Eng 790(1):012063
Zanina MA, Pavlov VA, Zavjalov SV, Volvenko SV (2018) TLD object tracking algorithm improved with particle filter. In: 2018 41st international conference on telecommunications and signal processing (TSP), pp 1–4
Zhang T, Fei S, Lu H, Li X (2009) Modified particle filter for object tracking in low frame rate video. In: Proceedings of the 48h IEEE conference on decision and control (CDC) held jointly with 2009 28th Chinese control conference, pp 2552–2557
Zhang X, Hu W, Xie N, Bao H, Maybank S (2015) A robust tracking system for low frame rate video. Int J Comput Vis 115(3):279–304
Zhang J, Wang A, Wang M, Iwahori Y (2017) A novel target algorithm based on TLD combining with SLBP. Int J Performability Eng 13(4):458–468
Zhang L, Hou J, Chen M, Li H (2020) The improved TLD algorithm that combines CAMShift and orientation prediction to realize face tracking in low illumination. In: 2020 Chinese automation congress (CAC), pp 3193–3200
Zhang J, Lv X, Cheng C, Long Z (2021) TLD tracking algorithm based on feature fusion. In: 2021 China automation congress (CAC), pp 310–315
Zhao L, Chen Y, Ye Q (2017) An improved TLD algorithm based on Kalman filter and SURF feature matching. AIP Conf Proc 1839(1):020214
Zhen X, Fei S, Wang Y, Du W (2020) A visual object tracking algorithm based on improved TLD. Algorithms 13(1):15
Zhong W, Lu H, Yang MH (2012) Robust object tracking via sparsity-based collaborative model. In: 2012 IEEE conference on computer vision and pattern recognition, pp 1838–1845
Zhou J, Liu S, Qiu G, Zhang F, Sun J (2013) Tensor missing value recovery with tucker thresholding method. In: 2013 5th international conference on intelligent networking and collaborative systems, pp 716–720
Zhu XJ (2005) Semi-supervised learning literature survey. http://digital.library.wisc.edu/1793/60444
Author information
Authors and Affiliations
Corresponding author
Ethics declarations
Conflict of interests/competing interests
The authors certify that the work is original. There is no conflict of interest by anyone or any organization, no funding has been received for the conduct of this study and/or preparation of this manuscript.
Additional information
Publisher’s note
Springer Nature remains neutral with regard to jurisdictional claims in published maps and institutional affiliations.
Rights and permissions
Springer Nature or its licensor (e.g. a society or other partner) holds exclusive rights to this article under a publishing agreement with the author(s) or other rightsholder(s); author self-archiving of the accepted manuscript version of this article is solely governed by the terms of such publishing agreement and applicable law.
About this article
Cite this article
Moridvaisi, H., Razzazi, F., Pourmina, M. et al. An extended TLD tracking algorithm using co-training learning for low frame rate videos. Multimed Tools Appl 82, 24743–24769 (2023). https://doi.org/10.1007/s11042-022-14106-1
Received:
Revised:
Accepted:
Published:
Issue Date:
DOI: https://doi.org/10.1007/s11042-022-14106-1