Abstract
Recently, Siamese network (Siam)-based visual tracking describes the tracking problems as the cross-correlation between convolutional features of the target template and searching regions and solves them by similarity learning, which has achieved great success in performance. However, most of the existing Siam-based tracking methods neglect to explore the feature correlations, which is very important to learn more representative features. Moreover, the first frame is used as the fixed template without updating the template, which leads to a reduction in accuracy. To address these issues, in this paper, we propose an Adaptive Updating Siamese Network (AU-Siam) for more powerful feature correlations and adaptive template updating. Specifically, a siamese feature extraction subnetwork is proposed to introduce the attention mechanism for more discriminative representations. Furthermore, an object template updating subnetwork is developed to dynamically learn object appearance changes for robust tracking. It’s interesting to show that the proposed AU-Siam can effectively reduce the probability of tracking drift in the case of fast motions and heavy occlusion and improve the tracking accuracy. Experimental results on public tracking benchmarks with challenging sequences demonstrate that our AU-Siam performs favorably against other state-of-the-art methods.
Similar content being viewed by others
References
Bertinetto L, Valmadre J, Henriques JF, Vedaldi A, Torr PH (2016) Fully-convolutional siamese networks for object tracking. In European Conference on Computer Vision Workshop, pages 850-865. Springer. 1, 2, 3, 4, 5, 7, 8
Bertinetto L, Valmadre J, Golodetz S, Miksik O, Torr PHS (2016) Staple: Complementary learners for real-time tracking. In The IEEE Conference on Computer Vision and Pattern Recognition, CVPR, June
Bhat G, Johnander J, Danelljan M, Khan FS, Felsberg M (2018) Unveiling the power of deep tracking. In: ECCV, pp 493–509
Choi J, Chang HJ, Yun S, Fischer T, Demiris Y (2017) Attentional correlation filter network for adaptive visual tracking. In: IEEE Conference on Computer Vision and Pattern Recognition, pages 4807-4816. 2 7
Danelljan M., Ager G. H., Khan F. S., Felsberg M. (2016) Adaptive decontamination of the training set: a unified formulation for discriminative visual tracking. In: IEEE Conference on Computer Vision and Pattern Recognition, pages 1430-1438. 4 7
Danelljan M, Bhat G, Khan FS et al (2017) ECO: Efficient convolution operators for tracking. Proc IEEE Conf Comput Vis Pattern Recognit, page 6
Danelljan M, Häger G et al (2015) Convolutional Features for Correlation Filter Based Visual Tracking. ICCV workshop
Danelljan M, Robinson A, Khan FS, Felsberg M (2016) Beyond correlation filters: Learning continuous convolution operators for visual tracking. In: ECCV, pages 472-488. 1 2 5
Dong X, Shen J (2018) Triplet loss in siamese network for object tracking[C]. Proceedings of the European Conference on Computer Vision (ECCV). 459-474
Dong X, Shen J, Wang W et al (2018) Hyperparameter optimization for tracking with continuous deep q-learning[C].Proceedings of the IEEE conference on computer vision and pattern recognition. 518-527
Dong X, Shen J, Wang W et al (2019) Dynamical Hyperparameter Optimization via Deep Reinforcement Learning in Tracking[J]. IEEE Transactions on Pattern Analysis and Machine Intelligence PP(99):1–1
Dong X, Shen J, Wu D et al (2019) Quadruplet network with One-Shot learning for fast visual object Tracking[J]. IEEE Trans Image Process 28 (7):3516–3527
Dong X, Shen J, Yu D et al (2017) Occlusion-aware real-time object tracking[J], vol 19
Fan DP, Cheng MM, Liu JJ et al (2018) Salient objects in clutter: Bringing salient object detection to the foreground[C]. Proceedings of the European conference on computer vision (ECCV). 186-202
Fu K, Fan D P, Ji G P et al (2020) Siamese network for rgb-d salient object detection and beyond[J]. arXiv preprint arXiv:2008.12134
Fu K, Fan DP, Ji GP et al (2020) Jl-dcf: Joint learning and densely-cooperative fusion framework for rgb-d salient object detection[C].Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition. 3052-3062
Fu K, Zhao Q, Gu IYH et al (2019) Deepside: A general deep framework for salient object detection[J]. Neurocomputing 356:69–82
Gong C, Tao D, Liu W et al (2015) Saliency propagation from simple to difficult[C].Proceedings of the IEEE conference on computer vision and pattern recognition. 2531-2539
Guo Q, Feng W, Zhou C, Huang R, Wan L, Wang S (2017) Learning dynamic siamese network for visual object tracking. In: ICCV. 1
He A, Luo C et al (2018) A twofold siamese network for real-time object tracking[C]. Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition. 4834–4843
Henriques J, Caseiro R, Martins P, Batista J (2015) Highspeed tracking with kernelized correlation filters. IEEE Transactions on Pattern Analysis and Machine Intelligence 37(3):583–596. 1 3 7
Hu H, Ma B, Shen J et al (2018) Robust object tracking using manifold regularized convolutional neural networks[J]. IEEE Transactions on Multimedia 21(2):510–521
Hu J, Shen L, Sun G (2018) Squeeze-and-excitation networks[C].Proceedings of the IEEE conference on computer vision and pattern recognition. 7132-7141
Jianbing S, Xin et al (2019) Visual Object Tracking by Hierarchical Attention Siamese Network.[J] IEEE transactions on cybernetics
Kristan M, Leonardis A et al (2016) The visual object tracking vot2016 challenge results. In: ECCV, pp 777–823
Kristan M, Leonardis A et al (2018) The sixth visual object tracking VOT2018 challenge results. In: ECCV, pp 3–53
Krizhevsky A, Sutskever I et al (2012) Imagenet Classification with Deep Convolutional Neural Networks[C]. NIPS Curran Associates Inc
Li B, Wu W et al (2019) Siamrpn++:, Evolution of siamese visual tracking with very deep networks[C].Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition. 4282–4291
Li B, Yan J, Wu W, Zhu Z, Hu X (2018) High performance visual tracking with siamese region proposal network. In: CVPR. 1, 2, 3, 4, 5, 8
Liang Z, Shen J (2019) Local semantic siamese networks for fast tracking[J]. IEEE Trans Image Process 29:3351–3364
Liu F, Gong C, Huang X et al (2018) Robust visual tracking revisited: From correlation filter to template matching[J]. IEEE Trans Image Process 27 (6):2777–2790
Liu F, Gong C, Huang X et al (2018) Robust visual tracking revisited: From correlation filter to template matching[J]. IEEE Trans Image Process 27 (6):2777–2790
Liu P, Yu H, Cang S (2019) Adaptive neural network tracking control for underactuated systems with matched and mismatched disturbances[J]. Nonlinear Dynamics 98(2):1447–1464
Lu X, Ni B, Ma C et al (2019) Learning transform-aware attentive network for object tracking[J]. Neurocomputing 349:133–144
Lu X, Wang W, Ma C et al (2019) See more, know more: Unsupervised video object segmentation with co-attention siamese networks[C].Proceedings of the IEEE conference on computer vision and pattern recognition. 3623-3632
Lukezic A, Vojir T, Cehovin Zajc L, Matas J, Kristan M (2017) Discriminative correlation filter with channel and spatial reliability
Ren S, Girshick R et al (2017) Faster r-CNN: towards Real-Time object detection with region proposal Networks[J]. IEEE Transactions on Pattern Analysis Machine Intelligence 39(6):1137–1149
Sun L, Zhao C, Yan Z et al (2018) A novel weakly-supervised approach for RGB-D-based nuclear waste object detection[J]. IEEE Sensors J 19 (9):3487–3500
Tang Z, Li C, Wu J et al (2019) Classification of EEG-based single-trial motor imagery tasks using a B-CSP method for BCI[J]. Frontiers of Information Technology & Electronic Engineering 20(8):1087–1098
Tang Z, Yu H, Lu C et al (2019) Single-Trial Classification of Different Movements on One Arm Based on ERD/ERS and Corticomuscular Coherence[J]. IEEE Access 7:128185–128197
Tao R, Gavves E, Smeulders AWM (2016) Siamese instance search for tracking. In IEEE Conference on Computer Vision and Pattern Recognition. 1, 2, 3, 7
Valmadre J, Bertinetto L, Henriques JF, Vedaldi A, Torr PH (2017) End-to-end representation learning for correlation filter based tracking. In: CVPR. 1, 2, 3, 4, 8
Wang W, Lu X, Shen J et al (2019) Zero-shot video object segmentation via attentive graph neural networks[C].Proceedings of the IEEE international conference on computer vision. 9236–9245
Wang W, Shen J, Ling H (2018) A deep network solution for attention and aesthetics aware photo cropping[J]. IEEE transactions on pattern analysis and machine intelligence 41(7):1531–1544
Wang Q, Teng Z, Xing J, Gao J, Hu WS (2018) Maybank.Learning attentions: Residual attentional siamese network for high performance online visual tracking. In: CVPR. 1 2
Woo S, Park J, Lee JY et al (2018) CBAM : Convolutional Block Attention Module[J]
Wu Y, Lim J, Yang M-H (2013) Online object tracking: a benchmark. In: CVPR. 2
Wu Y, Lim J, Yang M-H (2015) Object tracking benchmark.TPAMI, 1, 2, 5, 6, 7
Xiao Y, Li J, Du B, Wu J, Chang J, Zhang W (2020) Memu: Metric Correlation Siamese Network and Multi-class Negative Sampling for Visual Tracking. Pattern Recognition, Volume 100. https://doi.org/10.1016/j.patcog.2019.107170
Yilmaz A., Javed O., Shah M. (2006) Object tracking: a survey. ACM Comput Surv 38(4):1–45
Z T, Ghanem B, Liu S, Ahuja N (2012) Robust visual tracking via multi-task sparse learning. In: IEEE Conference on Computer Vision and Pattern Recognition CVPR
Zhang Z, Lai Z, Huang Z et al (2019) Scalable supervised asymmetric hashing with semantic and latent factor Embedding[J] IEEE transactions on image processing
Zhang Z, Peng H (2019) Deeper and wider siamese networks for real-time visual tracking[C]. Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition. 4591-4600
Zhang Y, Wang L et al (2018) Structured siamese network for real-time visual tracking[C].Proceedings of the European conference on computer vision (ECCV). 351-366
Zhou Y, Li J, Du B, Chang J, Xiao Y (2020) A Target Response Adaptive Correlation Filter Tracker with Spatial Attention. Multimedia Tools and Applications. https://doi.org/10.1007/s11042-020-08839-0
Zhu Z, Wang Q, Li B, Wu W, Yan J, Hu W (2018) Distractor-aware siamese networks for visual object tracking. In: ECCV. 1, 2, 3, 6, 7, 8
Author information
Authors and Affiliations
Corresponding author
Additional information
Publisher’s note
Springer Nature remains neutral with regard to jurisdictional claims in published maps and institutional affiliations.
This work was supported in part by the Science and Technology Major Project of Hubei Province (Next-Generation AI Technologies) under Grant 2019AEA170.
Rights and permissions
About this article
Cite this article
Zhou, Y., Li, J., Du, B. et al. Learning adaptive updating siamese network for visual tracking. Multimed Tools Appl 80, 29849–29873 (2021). https://doi.org/10.1007/s11042-021-11154-x
Received:
Revised:
Accepted:
Published:
Issue Date:
DOI: https://doi.org/10.1007/s11042-021-11154-x