Abstract
In most existing hierarchical convolution feature-based trackers, the extracted target features are redundant or insufficient to achieve accurate and robust tracking. To cope with this issue, we propose an adaptive target tracking based on channel attention and hierarchical convolutional features. First, we extract multi-layer features using VGG-M network to represent the different semantic information of the target. Channel attention module is introduced to obtain the weights of each channel for ensuring adaptation of our method to the target deformation. Then, we train the correlation filters of each layer online and compute the response map independently. To better overcome feature excessiveness, we fuse the corresponding responses by an adaptive fusion scheme. Finally, the exhaustive experimental analysis on public datasets OTB2015 and VOT2017 shows that the proposed algorithm outperforms several state-of-the-art algorithms and can track the target stably even in the case of disturbance.
Similar content being viewed by others
References
Li X, Zha YF, Zhang TZ, Cui Z, Zuo WM, Hou ZQ, Lu HC, Wang HZ (2019) Survey of visual object tracking algorithms based on deep learning. J Image Graph 24(12):2057–2080
Wu Y, Lim J, Yang M-H (2013) Online object tracking: a benchmark. In: IEEE conference on computer vision and pattern recognition. IEEE, pp 2411–2418
Bolme D, Beveridge J, Draper B, Lui Y (2010) Visual object tracking using adaptive correlation filters. In: IEEE conference on computer vision and pattern recognition. IEEE, pp 2544–2550
Henriques J, Caseiro R, Martins P, Batista J (2015) High speed tracking with kernelized correlation filters. IEEE Trans Pattern Anal Mach Intell 37:583–596
Van De Weijer J, Schmid C, Verbeek J, Larlus D (2009) Learning color names for real-world applications. IEEE Trans Image Process 18:1512–1523
Bertinetto L, Valmadre J, Golodetz S, Miksik O, Torr PH (2016) Staple: Complementary learners for real-time tracking. In: Proceedings of the IEEE conference on computer vision and pattern recognition. IEEE, pp 1401–1409
Wu Y, Lim J, Yang M-H (2015) Object tracking benchmark. IEEE Trans Pattern Anal Mach Intell 37:1834–1848
Kristan M, Leonardis A, Matas J, Felsberg M, Pflugfelder R, Cehovin Zajc L, Vojir T, Hager G, Lukezic A, Eldesokey A, Fernandez G (2017) The visual object tracking vot2017 challenge results. In: IEEE international conference on computer vision (ICCV). IEEE, Oct 2017. 1, 7, 8
Kristan M, Leonardis A, Matas J, Felsberg M, Pflugfelder R, Zajc LC, Vojir T, Bhat G, Lukezic A, Eldesokey A, Fernandez G et al (2018) The sixth visual object tracking vot2018 challenge results
Danelljan M, Hager G, Khan FS, Felsberg M (2015) Convolutional features for correlation filter based visual tracking. In: Proceedings of the IEEE international conference on computer vision workshops, pp 58–66
Danelljan M, Hger G, Khan FS, Felsberg M (2015) Learning spatially regularized correlation filters for visual tracking. In: Proceedings of the IEEE International Conference on Computer Vision 4310–4318
Danelljan M, Robinson A, Khan FS, Felsberg M (2016) Beyond correlation filters: learning continuous convolution operators for visual tracking. In: ECCV
Danelljan M, Bhat G, Khan FS, Felsberg M (2017) Eco: efficient convolution operators for tracking. In: Proceedings of the 2017 IEEE conference on computer vision and pattern recognition (CVPR), Honolulu, HI, USA, pp. 21–26
Henriques JF, Rui C, Martins P, Batista J (2012) Exploiting the circulant structure of tracking-by-detection with kernels. Springer, Berlin
Simonyan K, Zisserman A (2014) Very deep convolutional networks for large-scale image recognition. arXiv preprint http://arxiv.org/abs/1409.1556
Bertinetto L, Valmadre J, Henriques JF, Vedaldi A, Torr PH (2016) Fully-convolutional siamese networks for object tracking. Springer, In European conference on computer vision, pp 850–865
Valmadre J, Bertinetto L, Henriques JF, Vedaldi A, Torr PH (2017) End-to-end representation learning for correlation filter based tracking. In: IEEE conference on computer vision and pattern recognition. IEEE
Wang Q, Teng Z, Xing J et al (2018) Learning attentions: residual attentional siamese network for high performance online visual tracking. In: IEEE/CVF conference on computer vision and pattern recognition, Salt Lake City, USA. IEEE, pp 4854–4863
Ma C, Huang J-B, Yang X, Yang M-H (2015) Hierarchical convolutional features for visual tracking. In: IEEE international conference on computer vision, pp 3074–3082
Qi YK, Zhang SP, Qin L et al (2016) Hedged deep tracking. In: Proceedings of 2016 IEEE conference on computer vision and pattern recognition, Las Vegas, Nevada, USA. IEEE, pp 4303–4311
He ZQ, Fan YR, Zhuang JF et al (2017) Correlation filters with weighted convolution responses. In: Proceedings of 2017 IEEE international conference on computer vision, Venice, Italy. IEEE, pp 1992–2000
Vedaldi A, Lenc K (2015) Matconvnet: convolutional neural networks for matlab. In: ACM international conference on multimedia. ACM, pp 689–692
Danelljan M, Hger G, Khan FS, Felsberg M (2016) Adaptive decontamination of the training set: a unified formulation for discriminative visual tracking. In: Proceedings of 2016 IEEE conference on computer vision and pattern recognition. IEEE, pp 1430–1438
Lukezic A, Vojir T, Cehovin Zajc L, Matas J, Kristan M (2017) Discriminative correlation filter with channel and spatial reliability. In: IEEE conference on computer vision and pattern recognition. IEEE
Sun C, Lu H, Yang M-H (2017) Learning spatial aware regressions for visual tracking. arXiv preprint http://arxiv.org/abs/1706.07457
Wang Q, Gao J, Xing J, Zhang M, Hu W (2017) Dcfnet: discriminant correlation filters network for visual tracking. arXiv preprint http://arxiv.org/abs/1704.040571704.04057
Gundogdu E, Alatan AA (2018) Good features to correlate for visual tracking. IEEE Trans Image Process 27:2526–2540
He Z, Fan Y, Zhuang J, Dong Y, Bai H (2017) Correlation filters with weighted convolution responses. In: IEEE international conference on computer vision
Li B, Yan J, Wu W, Zhu Z, Hu X (2018) High performance visual tracking with Siamese region proposal network. In: Proceedings of 2018 IEEE international conference on computer vision
Wang Q, Zhang L, Bertinetto L, Hu W, Torr PHS (2019) Fast online object tracking and segmentation: a unifying approach. In: Proceedings of the IEEE conference on computer vision and pattern recognition
Voigtlaender P, Luiten J, Torr PHS, Leibe B (2020) Siam r-cnn: visual tracking by re-detection. In: Proceedings of the IEEE conference on computer vision and pattern recognition
Acknowledgements
This work is supported by the National Key Research and Development Project of China (2018YFB1601200).
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.
Rights and permissions
About this article
Cite this article
Wang, H., Zhang, H. Adaptive target tracking based on channel attention and multi-hierarchical convolutional features. Pattern Anal Applic 25, 305–313 (2022). https://doi.org/10.1007/s10044-021-01043-2
Received:
Accepted:
Published:
Issue Date:
DOI: https://doi.org/10.1007/s10044-021-01043-2