Abstract
In recent years, visual tracking methods that are based on discriminative correlation filters (DCFs) have been very promising. However, most of these methods suffer from a lack of robust scale estimation skills. Although a wide range of recent DCF-based methods exploit the features that are extracted from deep convolutional neural networks (CNNs) in their translation model, the scale of the visual target is still estimated by hand-crafted features. Whereas the exploitation of CNNs imposes a high computational burden, this paper exploits pre-trained lightweight CNNs models to propose two efficient scale estimation methods, which not only improve the visual tracking performance but also provide acceptable tracking speeds. The proposed methods are formulated based on either holistic or region representation of convolutional feature maps to efficiently integrate into DCF formulations to learn a robust scale model in the frequency domain. Moreover, against the conventional scale estimation methods with iterative feature extraction of different target regions, the proposed methods exploit proposed one-pass feature extraction processes that significantly improve the computational efficiency. Comprehensive experimental results on the OTB-50, OTB-100, TC-128 and VOT-2018 visual tracking datasets demonstrate that the proposed visual tracking methods outperform the state-of-the-art methods, effectively.
Similar content being viewed by others
References
Bertinetto L, Valmadre J, Golodetz S, Miksik O, Torr PHS (2016) Staple: complementary learners for real-time tracking. In: Proceedings of the IEEE CVPR, pp 1401–1409
Bertinetto L, Jack V, Henriques JF, Vedaldi A, Torr PHS (2016) Fully-convolutional Siamese networks for object tracking. In: Proceedings of the ECCV, pp 850–865
Bolme DS, Beveridge JR, Draper BA, Lui YM (2010) Visual object tracking using adaptive correlation filters. In: Proceedings of the IEEE CVPR, pp 2544–2550
Čehovin L (2017) TraX: the visual tracking exchange protocol and library. Neurocomputing 260:5–8
Chatfield K, Simonyan K, Vedaldi A, Zisserman A (2014) Return of the devil in the details: delving deep into convolutional nets. In: Proceedings of the BMVC, pp 1–11
Chen C, Li S, Qin H, Hao A (2015) Real-time and robust object tracking in video via low-rank coherency analysis in feature space. Pattern Recogn 48(9):2885–2905
Chen X, Yao L, Zhang Y (2020) Residual attention U-Net for automated multi-class segmentation of COVID-19 chest CT images. arXiv.org/abs/2004.05645v1
Choi J, Chang HJ, Fischer T, Yun S, Lee K, Jeong J, Demiris Y, Choi JY (2018) Context-aware deep feature compression for high-speed visual tracking. In: Proceedings of the IEEE CVPR, pp 479–488
Danelljan M, Hager G, Khan FS, Felsberg M (2015) Learning spatially regularized correlation filters for visual tracking. In: Proceedings of the IEEE ICCV, pp 4310–4318
Danelljan M, Hager G, Khan FS, Felsberg M (2016) Convolutional features for correlation filter based visual tracking. In: Proceedings of the IEEE ICCVW, pp 621–629
Danelljan M, Robinson A, Khan FS, Felsberg M (2016) Beyond correlation filters: learning continuous convolution operators for visual tracking. In: Proceedings of the ECCV, pp 472–488
Danelljan M, Bhat G, Khan FS, Felsberg M (2017) ECO: efficient convolution operators for tracking. In: Proceedings of the IEEE CVPR, pp 6931–6939
Danelljan M, Häger G, Khan FS, Felsberg M (2017) Discriminative scale space tracking. IEEE Trans Pattern Anal Mach Intell 39(8):1561–1575
Fan H, Ling H (2019) Siamese cascaded region proposal networks for real-time visual tracking. In: Proceedings of the IEEE CVPR
Galoogahi HK, Sim T, Lucey S (2015) Correlation filters with limited boundaries. In: Proceedings of the IEEE CVPR, pp 4630–4638
Galoogahi HK, Fagg A, Lucey S (2017) Learning background-aware correlation filters for visual tracking. In: Proceedings of the IEEE ICCV, pp 1144–1152
Gao J, Zhang T, Xu C (2019) Graph convolutional tracking. In: Proceedings of the CVPR, pp 4649–4659
Gong D, Yang J, Liu L, Zhang Y, Reid I, Shen C, Van Den Hengel A, Shi Q (2017) From motion blur to motion flow: a deep learning solution for removing heterogeneous motion blur. In: Proceedings of the IEEE CVPR
Guo Q, Feng W, Zhou C, Huang R, Wan Li, Wang S (2017) Learning dynamic Siamese network for visual object tracking. In: Proceedings of the IEEE ICCV, pp 1781–1789
Hao J, Zhou Y, Zhang G, Qin L, Wu Q (2019) A review of target tracking algorithm based on UAV. In: Proceedings of the IEEE CBS, pp 328–333
Hare S, Golodetz S, Saffari A, Vineet V, Cheng MM, Hicks SL, Torr PHS (2016) Struck: structured output tracking with kernels. IEEE Trans Pattern Anal Mach Intell 38(10):2096–2109
He A, Luo C, Tian X, Zeng W (2018) A twofold Siamese network for real-time object tracking. In: Proceedings of the IEEE CVPR, pp 4834–4843
Henriques JF, Caseiro R, Martins P, Batista J (2012) Exploiting the circulant structure of tracking-by-detection with kernels. In: Proceedings of the ECCV, pp 702–715
Henriques JF, Caseiro R, Martins P, Batista J (2015) High-speed tracking with kernelized correlation filters. IEEE Trans Pattern Anal Mach Intell 37(3):583–596
Hong Z, Chen WC, Mei X, Prokhorov D, Tao D (2015) MUlti-Store Tracker (MUSTer): a cognitive psychology inspired approach to object tracking. In: Proceedings of the IEEE CVPR, pp 749–758
Howard AG, Zhu M, Chen B, Kalenichenko D, Wang W, Weyand T, Andreetto M, Adam H (2015) MobileNets: efficient convolutional neural networks for mobile vision applicationss. arXiv.org/abs/1704.04861
Kristan M, Leonardis A, Matas J, Felsberg M, Pflugfelder R et al (2019) The sixth visual object tracking VOT2018 challenge results. In: Proceedings of the ECCVW, pp 3–53
Kwon J, Lee KM (2014) Tracking by sampling and integrating multiple trackers. IEEE Trans Pattern Anal Mach Intell 36(7):1428–1441
Li B, Yan J, Wu W, Zhu Z, Hu X (2018) High performance visual tracking with Siamese region proposal network. In: Proceedings of the IEEE CVPR, pp 8971–8980
Li F, Tian C, Zuo W, Zhang L, Yang MH (2018) Learning spatial-temporal regularized correlation filters for visual tracking. In: Proceedings of the IEEE CVPR, pp 4904–4913
Li P, Wang D, Wang L, Lu H (2018) Deep visual tracking: review and experimental comparison. Pattern Recognit 76:323–338
Li Y, Zhu J (2015) A scale adaptive kernel correlation filter tracker with feature integration. In: Proceedings of the ECCVW, pp 254–265
Liang P, Blasch E, Ling H (2015) Encoding color information for visual tracking: algorithms and benchmark. IEEE Trans Image Process 24(12):5630–5644
Liu T, Kong J, Jiang M, Liu C, Xiaofeng G, Wang X (2019) Collaborative model with adaptive selection scheme for visual tracking. Int J Mach Learn Cyb 10(2):215–228
Lugmayr A, Danelljan M, Timofte R (2020) NTIRE 2020 challenge on real-world image super-resolution: methods and results. In: Proceedings of the IEEE CVPRW
Lukežič A, Vojíř T, Zajc L, Matas J, Kristan M (2018) Discriminative correlation filter tracker with channel and spatial reliability. IJCV 126(7):671–688
Ma C, Huang JB, Yang X, Yang MH (2015) Hierarchical convolutional features for visual tracking. In: Proceedings of the IEEE ICCV, pp 3074–3082
Ma C, Huang JB, Yang X, Yang MH (2019) Robust visual tracking via hierarchical convolutional features. IEEE Trans Pattern Anal Mach Intell 41(11):2709–2723. https://doi.org/10.1109/TPAMI.2018.2865311
Ma C, Huang JB, Yang X, Yang MH (2018) Adaptive correlation filters with long-term and short-term memory for object tracking. IJCV 126(8):771–796
Marvasti-Zadeh SM, Ghanei-Yakhdan H, Kasaei S (2018) Adaptive spatio-temporal context learning for visual target tracking. In: Proceedings of the Iranian conference on machine vision and image processing (MVIP)
Marvasti-Zadeh SM, Cheng L, Ghanei-Yakhdan H, Kasaei S (2019) Deep learning for visual tracking: a comprehensive survey. In: Computer vision and pattern recognition. arXiv:1912.00535v1
Marvasti-Zadeh SM, Ghanei-Yakhdan H, Kasaei S (2019) Rotation-aware discriminative scale space tracking. In: Proceedings of the Iranian conference on electrical engineering (ICEE), pp 1272–1276
Marvasti-Zadeh SM, Khaghani J, Ghanei-Yakhdan H, Kasaei S, Cheng L (2020) COMET: context-aware IoU-guided network for small object tracking. In: Proceedings of the ACCV
Nah S, Son S, Timofte R, Lee KM (2020) NTIRE challenge on image and video deblurring. In: Proceedings of the IEEE CVPRW
Possegger H, Mauthner T, Bischof. H (2015) In defense of color-based model-free tracking. In: Proceedings of the IEEE CVPR, pp 2113–2120
Russakovsky O, Deng J, Hao S, Krause J, Satheesh S, Ma S, Huang Z, Karpathy A, Khosla A, Bernstein M, Berg AC, Fei-Fei L (2015) ImageNet large scale visual recognition challenge. IJCV 115(3):211–252
Sandler M, Howard A, Zhu M, Zhmoginov A, Chen LC (2018) MobileNetV2: inverted residuals and linear bottlenecks. In: Proceedings of the IEEE CVPR, pp 4510–4520
Sun C, Wang D, Lu H, Yang MH (2018) Learning spatial-aware regressions for visual tracking. In: Proceedings of the IEEE CVPR, pp 8962–8970
Sun C, Wang D, Lu H, Yang MH (2018) Correlation tracking via joint discrimination and reliability learning. In: Proceedings of the IEEE CVPR, pp 489–497
Sun S, An Z, Jian X, Zhang B, Zhang J (2019) Robust object tracking with the inverse relocation strategy. Neural Comput Appl 31:123–132
Tong K, Wu Y, Fei Z (2020) Recent advances in small object detection based on deep learning: a review. Image Vis Comput 97
Valmadre J, Bertinetto L, Henriques J, Vedaldi A, Torr PHS (2017) End-to-end representation learning for correlation filter based tracking. In: Proceedings of the IEEE CVPR, pp 5000–5008
Wang D, Lu H, Bo C (2015) Visual tracking via weighted local cosine similarity. IEEE Trans Cybernetics 45(9):1838–1850
Wang P, Sun M, Wang H, Li X, Yang Y (2020) Convolution operators for visual tracking based on spatial-temporal regularization. Neural Comput Appl 45:50. https://doi.org/10.1007/s00521-020-04704-1
Wang Q, Gao J, Xing J, Zhang M, Hu W (2017) DCFNet: discriminant correlation filters network for visual tracking. arXiv.org/abs/1704.04057
Wu Y, Lim J, Yang MH (2013) Online object tracking: a benchmark. In: Proceedings of the IEEE CVPR, pp 2411–2418
Yi W, Lim J, Yang MH (2015) Object tracking benchmark. IEEE Trans Pattern Anal Mach Intell 37(9):1834–1848
Zhang J, Ma S, Sclaroff S (2014) MEEM: robust tracking via multiple experts using entropy minimization. In: Proceedings of the ECCV, pp 188–203
Zhang T, Xu C, Yang MH (2017) Multi-task correlation particle filter for robust object tracking. In: Proceedings of the IEEE CVPR, pp 4819–4827
Zhang X, Yao L, Wang X, Monaghan J, Mcalpine D, Zhang Y (2019) A survey on deep learning based brain computer interface: recent advances and new frontiers. arXiv:1905.04149v4
Zhang Z, Peng H (2019) Deeper and wider Siamese networks for real-time visual tracking. In: Proceedings of the IEEE CVPR
Zhou T, Lu Y, Di H (2017) Locality-constrained collaborative model for robust visual tracking. IEEE Trans Circuits Syst Video Technol 27(2):313–325
Zhu Z, Huang G, Zou W, Du D, Huang C (2018) UCT: learning unified convolutional networks for real-time visual tracking. In: Proceedings of the ICCVW, pp 1973–1982
Acknowledgements
This work was partly supported by a Grant (No. 96013046) from Iran National Science Foundation (INSF).
Author information
Authors and Affiliations
Corresponding author
Ethics declarations
Conflict of interest
All authors declare that they have no conflict of interest.
Additional information
Publisher's Note
Springer Nature remains neutral with regard to jurisdictional claims in published maps and institutional affiliations.
Rights and permissions
About this article
Cite this article
Marvasti-Zadeh, S.M., Ghanei-Yakhdan, H. & Kasaei, S. Efficient scale estimation methods using lightweight deep convolutional neural networks for visual tracking. Neural Comput & Applic 33, 8319–8334 (2021). https://doi.org/10.1007/s00521-020-05586-z
Received:
Accepted:
Published:
Issue Date:
DOI: https://doi.org/10.1007/s00521-020-05586-z