Design, Analysis, and Implementation of a New Online Object Tracking Method Based on Sketch Kernel Correlation Filter (SHKCF)

Yousefzadeh, M.; Golmakani, A.; Sarbishaei, G.

doi:10.22061/jecei.2023.10126.680

نشریات مستقل دانشگاه در سامانه ارزیابی نشریات علمی وزارت علوم

نشریه معماری وشهرسازی پایدار موفق به اخذ رتبه علمی-پژوهشی شد

تعداد نشریات	13
تعداد شماره‌ها	200
تعداد مقالات	2,008
تعداد مشاهده مقاله	2,680,168
تعداد دریافت فایل اصل مقاله	1,937,362

	Design, Analysis, and Implementation of a New Online Object Tracking Method Based on Sketch Kernel Correlation Filter (SHKCF)
Journal of Electrical and Computer Engineering Innovations (JECEI)
مقاله 8، دوره 12، شماره 1، فروردین 2024، صفحه 115-132 اصل مقاله (3.08 M)
نوع مقاله: Review paper
شناسه دیجیتال (DOI): 10.22061/jecei.2023.10126.680
نویسندگان
M. Yousefzadeh؛ A. Golmakani^* ؛ G. Sarbishaei
Department of Electrical Engineering, Sadjad University of Technology, Mashhad, Iran.
تاریخ دریافت: 17 تیر 1402، تاریخ بازنگری: 20 شهریور 1402، تاریخ پذیرش: 19 مهر 1402
چکیده
Background and Objectives: To design an efficient tracker in a crowded environment based on artificial intelligence and image processing, there are several challenges such as the occlusion, fast motion, in-plane rotation, variations in target illumination and Other challenges of online tracking are the time complexity of the algorithm, increasing memory space, and tracker dependence on the target model. In this paper, for the first time, sketch matrix theory in ridge regression for video sequences has been proposed. Methods: A new tracking object method based on the element-wise matrix with an online training method is proposed including the kernel correlation Filter (KCF), circular, and sketch matrix. The proposed algorithm is not only the free model but also increases the robustness of the tracker related to the scale variation, occlusion, fast motion, and reduces KCF drift. Results: The simulation results demonstrate that the proposed sketch kernel correlation filter (SHKCF) can increase the computational speed of the algorithm and reduces both the time complexity and the memory space. Finally, the proposed tracker is implemented and experimentally evaluated based on video sequences of OTB50, OTB100 and VOT2016 benchmarks. Conclusion: The experimental results show that the SHKCF method obtains not only OPE partial evaluation of Out of view, Occlusion and Motion Blur in object accuracy but also achieved the partial evaluation of Illumination Variation, Out of Plane Rotation, Scale Variation, Out of View, Occlusion, In of Plane Rotation, Background Clutter, Fast Motion and Deformation in object overlap which are the first rank compared to the state-the-art works. The result of accuracy, robustness and time complexity are obtained 0.929, 0.93 and 35.4, respectively.
کلیدواژه‌ها
Artificial intelligence؛ Video analysis؛ Object tracking؛ SHKCF؛ KCF and online tracker

مراجع
[1] J. F. Henriques, R. Caseiro, P. Martins, J. Batista, “Highspeed tracking with kernelized correlation filters,” IEEE Trans. Pattern Anal. Mach. Intell., 37(3): 583–596, 2014. [2] P. Zhang, S. Yu, J. Xu, Xinge You, X. Jiang, X. Y. Jing, D. Tao, “Robust visual tracking using multi-frame multi-feature joint modeling,” IEEE Trans. Circuits Syst. Video Technol., 29(12): 3673–3686, 2018. [3] B. Chen, P. Li, C. Sun, D. Wang, G. Yang, H. Lu, “Multi attention module for visual tracking,” Pattern Recognit., 87: 80–93, 2019. [4] P. Li, D. Wang, L. Wang, H. Lu, “Deep visual tracking: Review and experimental comparison,” Pattern Recognit., 76: 323–338, 2018. [5] T. Xu, Z. H. Feng, X. J. Wu, J. Kittler, “Learning low-rank and sparse discriminative correlation filters for coarse-to-fine visual object tracking,” IEEE Trans, Circuits Syst. Video Technol., 30(10): 3727–3739, 2019. [6] B. Zhang, Z. Li, X. Cao, Q. Ye, C. Chen, L. Shen, A. Perina, R. Jill, “Output constraint transfer for kernelized correlation filter in tracking,” IEEE Trans. Syst. Man Cybern. Syst., 47(4): 693–703, 2016. [7] H. Wang, H. Xu, Y. Yuan, “High-dimensional expensive multi-objective optimization via additive structure,” Intell. Syst. Appl., 14: 200062, 2022. [8] C. Du, M. Lan, M. Gao, Zh. Dong, H. Yu, Zh. He, “Real-time object tracking via adaptive correlation filters,” Sensors, 20(15): 4124, 2020. [9] M. Y. Abbass, K. C. Kwon, N. Kim, S. A Abdelwahab, F. E. A. El-Samie, A. A. Khalaf, “A survey on online learning for visual tracking,” Visual Comput., 37: 993–1014, 2021. [10] X. Zhang, G. S. Xia, Q. Lu, W. Shen, L. Zhang, “Visual object tracking by correlation filters and online learning,” ISPRS J. Photogramm. Remote Sens., 140: 77–89, 2018. [11] R. Yin, Y. Liu, W. Wang, D. Meng, “Sketch kernel ridge regression using circulant matrix: Algorithm and theory,” IEEE Trans. Neural Networks Learn. Syst., 31(9): 3512–3524, 2019. [12] B. Yan, H. Zhao, D. Wang, H. Lu, X. Yang, “Skimming-perusal tracking: A framework for real-time and robust longterm tracking,” in Proc. the IEEE/CVF International Conference on Computer Vision: 2385–2393, 2019. [13] S. Avidan, “Ensemble tracking,” IEEE transactions on pattern analysis and machine intelligence, 29(2):261–271, 2007. [14] J. Zheng, Bo. Li, P. Tian, G. Luo, “Robust object tracking using valid fragments selection,” in Proc. Multi Media Modeling: 22nd International Conference, Part I 22: 738–751, 2016. [15] H. Yang, S. Qu, “Online hierarchical sparse representation of multifeature for robust object tracking,” Comput. Intell. Neurosci., 330-341, 2016. [16] D. T Nguyen, C. D Nguyen, R. Hargraves, L. A Kurgan, K. J. Cios, “mi-ds: Multiple-instance learning algorithm,” IEEE Trans. Cybern., 43(1): 143–154, 2012. [17] D. Comaniciu, V. Ramesh, P. Meer, “Kernel-based object tracking,” IEEE Trans. Pattern Anal. Mach. Intell., 25(5): 564–577, 2003. [18] M. Danelljan, G. Hager, F. Shahbaz Khan, M. Felsberg, “Learning spatially regularized correlation filters for visual tracking,” in Proc. the IEEE International Conference on Computer Vision: 4310–4318, 2015. [19] H. K. Galoogahi, A. Fagg, S. Lucey, “Learning background-aware correlation filters for visual tracking,” in Proc. the IEEE International Conference on Computer Vision: 1135– 1143, 2017. [20] Q. Guo, R. Han, W. Feng, Zh. Chen, L. Wan, “Selective spatial regularization by reinforcement learned decision making for object tracking,” IEEE Trans. Image Proc., 29: 2999–3013, 2019. [21] S. Hadfield, R. Bowden, K. Lebeda, “The visual object tracking vot2016 challenge results,” Lect. Notes Comput. Sci., 9914: 777– 823, 2016. [22] M. Danelljan, G. Hager, F. Shahbaz Khan, M. Felsberg, “Adaptive decontamination of the training set: A unified formulation for discriminative visual tracking,” in Proc. the IEEE conference on Computer Vision and Pattern Recognition: 1430–1438, 2016. [23] M. Danelljan, G. Bhat, F. Shahbaz Khan, M. Felsberg, “Eco: Efficient convolution operators for tracking,” in Proc. the IEEE conference On Computer Vision and Pattern Recognition: 6638–6646, 2017. [24] A. Yilmaz, O. Javed, M. Shah, “Object tracking: A survey,” Acm Comput. Surv. (CSUR), 38(4): 13–es, 2006. [25] X. Mei, H. Ling, Y. Wu, E. Blasch, L. Bai, “Minimum error bounded efficient l1 tracker with occlusion detection,” in Proc. CVPR: 1257–1264, 2011. [26] Sh. Shekhar, N. Hoque, D. K. Bhattacharyya, “Pknnmifs: A parallel knn classifier over an optimal subset of features,” Intell. Syst. Appl., 14: 200073, 2022. [27] D.A Ross, J. Lim, et al., “Incremental learning for robust visual tracking,” Int. J. Comput. Vision, 77(1r3): 125r141, 2008. [28] Y. Li, J. Zhu, et al., “A scale adaptive kernel correlation filter tracker with feature integration,” in Proc. ECCV workshops (2), 8926: 254–265, 2014. [29] M. Danelljan, G. Häger, F. Khan, M. Felsberg, “Accurate scale estimation for robust visual tracking,” in Proc. British Machine Vision Conference, Bmva Press, 2014. [30] M. Kristan, J. Matas, A. Leonardis, M. Felsberg, L. Cehovin, G. Fernandez, T. Vojir, G. Hager, G. Nebehay, R. Pflugfelder, “The visual object tracking vot2015 challenge results,” in Proc. the IEEE International Conference on Computer Vision Workshops: 1–23, 2015. [31] H. Lian, F. Zhang, W. Lu, “Randomized sketches for kernel cca,” Neural Networks, 127: 29–37, 2020. [32] A. Mahalanobis, B. V. Kumar, D. Casasent, “Minimum average correlation energy filters,” Appl. Opt., 26(17): 3633– 3640, 1987. [33] B. V. Kumar, “Minimum-variance synthetic discriminant functions,” JOSA A, 3(10): 1579–1584, 1986. [34] D. S. Bolme, J. R. Beveridge, B. A. Draper, Y. M. Lui, “Visual object tracking using adaptive correlation filters,” in Proc. 2010 IEEE Computer Society Conference on Computer Vision and Pattern Recognition: 2544–2550, 2010. [35] S. Liu, D. Liu, G. Srivastava, D. Połap, M. Woźniak, “Overview of correlation filter based algorithms in object tracking,” Complex Intell. Syst., 7: 1895–1917, 2020. [36] M. Danelljan, A. Robinson, F. Sh. Khan, M. Felsberg, “Beyond correlation filters: Learning continuous convolution operators for visual tracking,” in Proc. Computer Vision–ECCV 2016: 14th European Conference: 472–488, 2016. [37] T. Liu, G. Wang, Q. Yang, “Real-time part-based visual tracking via adaptive correlation filters,” in Proc. the IEEE Conference on Computer Vision and Pattern Recognition: 4902– 4912, 2015. [38] C. Ma, X. Yang, Ch. Zhang, M. H. Yang, “Long-term correlation tracking,” in Proc. the IEEE Conference on Computer Vision and Pattern Recognition: 5388–5396, 2015. [39] D. S. Bolme, J. R. Beveridge, B. A. Draper, Y. M. Lui, “Visual object tracking using adaptive correlation filters,” in Proc. 2010 IEEE Computer Society Conference on Computer Vision and Pattern Recognition: 2544–2550, 2010. [40] G. Turin, “An introduction to matched filters,” IRE Trans. Inf. Theory, 6(3): 311–329, 1960. [41] E. Gundogdu, A. A. Alatan, “Good features to correlate for visual tracking,” IEEE Trans. Image Process., 27(5): 2526– 2540, 2018. [42] J. F. Henriques, R. Caseiro, P. Martins, J. Batista, “Exploiting the circulant structure of tracking-by-detection with kernels,” in Proc. Computer Vision–ECCV 2012: 12th European Conference on Computer Vision, Florence, Part IV 12: 702–715, 2012. [43] Y. Yang, M. Pilanci, M. J. Wainwright, “Randomized sketches for kernels: Fast and optimal nonparametric regression,” arXiv preprint arXiv:1501.06195, 2017. [44] L. Čehovin, A. Leonardis, M. Kristan, “Visual object tracking performance measures revisited,” IEEE Trans. Image Process., 25(3): 1261–1274, 2016. [45] P. F. Felzenszwalb, R. B. Girshick, D. McAllester, D. Ramanan, “Object detection with discriminatively trained part-based models,” IEEE Trans. Pattern Anal. Mach. Intell., 32(9): 1627–1645, 2009. [46] Q. He, X. Shao, W. Chen, X. Li, X. Yang, T. Sun, “Adaptive multi-scale tracking target algorithm through drone,” IEICE Trans. Commun., 102(10): 1998–2005, 2019. [47] K. Zhang, J. T Kwok, “Clustered nyström method for large scale manifold learning and dimension reduction,” IEEE Trans. Neural Networks, 21(10): 1576–1587, 2010. [48] S. Xuan, Sh. Li, M. Han, X. Wan, G. S. Xia, “Object tracking in satellite videos by improved correlation filters with motion estimations,” IEEE Trans. Geosci. Remote Sens., 58(2): 1074–1086, 2019. [49] M. Ding, W. H. Chen, L. Wei, Y. F. Cao, Z. Y. Zhang, “Visual tracking with online assessment and improved sampling strategy,” IEEE Access, 8: 36948–36962, 2020. [50] J. P. Sun, E. J. Ding, B. Sun, Zh. Y. Liu, K. L. Zhang, “Adaptive kernel correlation filter tracking algorithm in complex scenes,” IEEE Access, 8: 208179–208194, 2020. [51] G. Zhu, J. Wang, Y. Wu, X. Zhang, H. Lu, “Mchog correlation tracking with saliency proposal,” in Proc. the AAAI Conference on Artificial Intelligence, 30, 2016. [52] M. Danelljan, A. Robinson, F. S. Khan, M. Felsberg, “Beyond correlation filters: Learning continuous convolution operators for visual tracking,” in Proc. Computer Vision–ECCV 2016: 14th European Conference, Part V 14: 472–488, 2016. [53] X. Li, Q. Liu, Zh. He, H. Wang, Ch. Zhang, W. S. Chen, “A multi-view model for visual tracking via correlation filters,” Knowledge-Based Systems, 113: 88–99, 2016. [54] Y. Zhang, L. Wang, J. Qi, D. Wang, M.Feng, H. Lu, “Structured siamese network for real-time visual tracking,” in Proc. the European Conference on Computer Vision (ECCV): 351–366, 2018. [55] X. Hao, J. Huang, F. Qin, X. Zheng, “Multi-label learning with missing features and labels and its application to text categorization,” Intell. Syst. Appl., 14: 200086, 2022. [56] M. Tang, B. Yu, F. Zhang, J. Wang, “High-speed tracking with multi-kernel correlation filters,” in Proc. the IEEE Conference on Computer Vision and Pattern Recognition: 4874–4883, 2018. [57] P. Dollár, R. Appel, S. Belongie, P. Perona, “Fast feature pyramids for object detection,” IEEE Trans. Pattern Anal. Mach. Intell., 36(8): 1532–1545, 2014. [58] B. Li, W. Wu, Q. Wang, F. Zhang, J. Xing, J. Yan, “Siamrpn++: Evolution of siamese visual tracking with very deep networks,” in Proc. the IEEE/CVF conference on Computer Vision and Pattern Recognition: 4282–4291, 2019. [59] K. Dai, D. Wang, H. Lu, C. Sun, J. Li, “Visual tracking via adaptive spatially-regularized correlation filters,” in Proc. the IEEE/CVF Conference on Computer Vision and Pattern Recognition: 4670–4679, 2019.
آمار تعداد مشاهده مقاله: 170 تعداد دریافت فایل اصل مقاله: 141

سامانه مدیریت نشریات علمی. قدرت گرفته از سیناوب

پیوندهای مفید

پیوندهای مفید

اخبار و اعلانات

آمار

Design, Analysis, and Implementation of a New Online Object Tracking Method Based on Sketch Kernel Correlation Filter (SHKCF)