Abstract
According to the lack of spatio-temporal information of convolution neural network abstraction, an online visual tracking algorithm based on convolution neural network is proposed, combining the spatio-temporal context model to the order filter of convolution neural network. Firstly, the initial target is preprocessed and the target spatial model is extracted, the spatio-temporal context model is obtained by the spatio-temporal information. The first layer adopts the spatio-temporal context model to convolve the input to obtain the simple layer feature. The second layer starts with skip the spatio-temporal context model to get a set of convolution filters, convolving with the simple features of the first layer to extract the target abstract features, and then the deep expression of the target can be obtained by superimposing the convolution results of the simple layer. Finally, the target tracking is realized by sparse updating method combining with particle filter tracking framework. Experiments show that deep abstract feature extracted by online convolution network structure combining with spatio-temporal context model, can preserve spatio-temporal information and improve the background clutters, illumination variation, low resolution, occlusion and scale variation and the tracking efficiency under complex background.
Similar content being viewed by others
References
Babenko B, Yang MH, Belongie S (2009) Visual tracking with online multiple instance learning. In CVPR
Bao C, Wu Y, Ling H, Ji H (2012) Real time robust L1 tracker using accelerated proximal gradient approach. In CVPR
Bolme DS, Beveridge JR, Draper B, Lui YM (2010) Visual object tracking using adaptive correlation filters. In ICCV
Chi ZZ, Li HY, Lu HC, Yang MH (2017) Dual deep network for visual tracking. In TIP
Danelljan M, Khan FS, Felsberg M, van de Weijer J (2014) Adaptive color attributes for real-time visual tracking. In CVPR
Danelljan M, Häger G, Khan FS, Felsberg M (2014) Accurate scale estimation for robust visual tracking. In BMVC
Danelljan M, Khan FS, Häger G, Felsberg M (2015) Learning spatially regularized correlation filters for visual tracking. In ICCV
Danelljan M, Häger G, Khan FS, Felsberg M (2015) Convolutional features for correlation filter based visual tracking. In ICCV workshop
Danelljan M, Robinson A, Khan F, Felsberg M (2016) Beyond correlation filters: learning continuous convolution operators for visual tracking. In ECCV
Hare S, Golodetz S, Saffari A, Vineet V, Cheng MM (2016) Struck: structured output tracking with Kernels. In TPAMI
Held D, Thrun S, Savarese S (2016) Learning to track at 100 FPS with deep regression networks. In ECCV
Henriques JF, Caseiro R, Martins P, Batista J (2012) Exploiting the circulant structure of tracking-by-detection with Kernels. In ECCV
Henriques JF, Caseiro R, Martins P, Batista J (2015) High-speed tracking with kernelized correlation filters. In TPAMI
Kalal Z, Mikolajczyk K, Matas J (2012) Tracking-learning-detection, In TPAMI
Ma C, Huang JB, Yang XK, Yang MH (2015) Hierarchical convolutional features for visual tracking. In ICCV
Nam H, Han B (2016) Learning multi-domain convolutional neural networks for visual tracking. In CVPR
Nam H, Baek M, Han B (2016) Modeling and propagating CNNs in a tree structure for visual tracking. In arXiv
Qi YK, Zhang SP, Qin L, Yao HX, Huang QM, Lim JW, Yang MH (2016) Hedged deep tracking. In CVPR
Wang NY, Yeung DY (2013) Learning a deep compact image representation for visual tracking. In NIPS
Wang NY, Shi JP, Yeung DY, Jia JY (2015) Understanding and diagnosing visual tracking systems. In ICCV
Wang LJ, Ouyang WL, Wang XG, Lu HC (2016) STCT: sequentially training convolutional networks for visual tracking. In CVPR
Wu Y, Lim J, Yang MH (2013) online object tracking: a benchmark. In CVPR
Wu Y, Lim J, Yang MH (2015) Object tracking benchmark. In TPAMI
Zhang KH, Zhang L, Yang MH (2012) Real-time compressive tracking. In ECCV
Zhang KH, Zhang L, Yang MH, Zhang D (2014) Fast tracking via spatio-temporal context learning. In ECCV
Zhang KH, Liu QS, Wu Y, Yang MH (2016) Robust visual tracking via convolutional networks without training. In TIP
Zhong W, Lu H, Yang MH (2012) Robust object tracking via sparsity-based collaborative model. In CVPR
Acknowledgements
This work is supported by the Nature Science Foundation of China (Grant No. 61605048), and the Fujian Provincial Natural Science Foundation Projects Grant (No. 2016 J01300).The authors would like to thank the reviewers for their valuable suggestions and comments.
Author information
Authors and Affiliations
Corresponding author
Rights and permissions
About this article
Cite this article
Wang, H., Liu, P., Du, Y. et al. Online convolution network tracking via spatio-temporal context. Multimed Tools Appl 78, 257–270 (2019). https://doi.org/10.1007/s11042-017-5533-9
Received:
Revised:
Accepted:
Published:
Issue Date:
DOI: https://doi.org/10.1007/s11042-017-5533-9