Abstract
Aiming at the problem that the correlation between multi-channel feature representation and filter structure is not considered in the objective function modeling, a object tracking algorithm with channel group regularization and time series smooth constraint using improved dynamic convolution kernels is proposed. Firstly, the elements in the filter are grouped using spatial and channel properties, the time-domain correlation of the object model is constrained by the low-rank kernel norm. A group regularization term is constructed to describe the correlation between channels with a mixed-norm structured sparsity constraint to learn lower-dimensional filters. Then, after extracting some channels in the feature map, part of the spatial information of each channel is retained to generate an efficient dynamic convolution kernel through the channel information de-redundant attention mechanism to obtain an optimized lightweight convolutional neural network. Finally, combining the advantages of hand-crafted features and deep convolutional features, the complementary localization of the object from coarse to fine is realized with the help of the constructed efficient feature model and the learned filter. The experimental results on public datasets show that the proposed algorithm can adapt to the tracking tasks of various complex traffic scenes, and enhance the tracking performance of the existing models. The proposed algorithm improves the discriminative property of the object model and the self-adaptability of the spatio-temporal information of the dynamic convolution kernel, and can be applied to neuromorphic vision system of intelligent transportation systems.
Similar content being viewed by others
References
Bertinetto L, Valmadre J, Golodetz S et al (2016) Staple: Complementary learners for real-time tracking[C]. IEEE Conference on Computer Vision and Pattern Recognition(CVPR), 1401–1409
Bhat G, Johnander J, Danelljan M et al (2018) Unveiling the power of deep tracking[C]. Proceedings of the European Conference on Computer Vision, 483–498
Chen Y, Dai X, Liu M et al (2020) Dynamic Convolution: Attention Over Convolution Kernels [C]. Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, 11030–11039
Chen SJ, Ye DY, Lin DW (2021) A Synthetic Target Tracking Algorithm Based on a New Color Distribution Model With Background Suppression[J]. Acta Automat Sin 47(3):630–640
Danelljan M, Khan FS, Felsberg M et al (2014) Adaptive color attributes for real-time visual tracking[C]. Conference on Computer Vision and Pattern Recognition(CVPR), 1090–1097
Danelljan M, Häger G, Khan FS et al (2014) Accurate Scale Estimation for Robust Visual Tracking[C]. Proceedings of the British Machine Vision Conference, BMVA
Danelljan M, Hager G, Khan FS et al (2015) Learning spatially regularized correlation filters for visual tracking[C]. Proceedings of the IEEE International Conference on Computer Vision, 4310–4318
Danelljan M, Robinson A, Khan FS et al (2016) Beyond correlation filters: Learning continuous convolution operators for visual tracking[C]. European Conference on Computer Vision, 472–488
Danelljan M, Robinson A, Khan FS et al (2016) Beyond correlation filters: Learning continuous convolution operators for visual tracking[C]. European Conference on Computer Vision:472–488
Galoogahi HK, Sim T, Lucey S (2015) Correlation filters with limited boundaries[C]. IEEE Conference on Computer Vision and Pattern Recognition(CVPR), 4630–4638
Galoogahi HK, Fagg A, Lucey S (2017) Learning Background-Aware Correlation Filters for Visual Tracking[C]. IEEE International Conference on Computer Vision(ICCV), 1369–1378
Gray RM (2006) Toeplitz and circulant matrices: A review[J]. Found Trends Commun Inf Theory 2(3):155–239
He K, Zhang X, Ren S et al (2016) Deep residual learning for image recognition[C]. Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, 770–778
Henriques JF, Rui C, Caseiror Martins P et al (2012) Exploiting the circulant structure of tracking- by-detection with kernels[C]. 12th European Conference on Computer Vision(ECCV), 702–715
Henriques JF, Carreira J, Rui C, et al (2013) Beyond Hard Negative Mining: Efficient Detector Learning via Block-Circulant Decomposition[C]. IEEE International Conference on Computer Vision(ICCV), 2760–2767
Henriques JF, Caseiro R, Martins P et al (2015) High-speed tracking with kernelized correlation filters[J]. IEEE Trans Pattern Anal Mach Intell 37(3):583–596
Howard AG, Zhu M, Chen B et al (2017) Mobilenets: Efficient convolutional neural networks for mobile vision applications[J]. ar**v preprint ar**v:04861
Howard A, Sandler M, Chu G et al (2019) Searching for mobilenetv3 [C]. Proceedings of the IEEE International Conference on Computer Vision, 1314–1324
Jun K, **g C, Min J et al (2018) Robust Visual Tracking with Combined Norm Regularized Sparse Coding and Adaptive Weighted Residual[J]. J Comput Aided Des Comput Graph 30(4):634–641
Li D, Bei LL, Bao JN et al (2021) Image contour detection based on improved level set in complex environment[J]. Wirel Netw 27(7):4389–4402
Li D, Sun JP, Wang HD et al (2022) Research on Haze Image Enhancement based on Dark Channel Prior Algorithm in Machine Vision[J]. J Environ Public Health 3887426:12. https://doi.org/10.1155/2022/3887426
Lukezic A, Vojir T, Cehovin ZL et al (2017) Discriminative correlation filter with channel and spatial reliability[C]. Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, 6309–6318
Lukezic A, Vojir T, Cehovin ZL et al (2017) Discriminative correlation filter with channel and spatial reliability[C]. EEE Conference on Computer Vision and Pattern Recognition(CVPR), 6309–6318
Meng L, Yang X (2019) A Survey of Object Tracking Algorithms[J]. Acta Automat Sin 45(7):1244–1260
Qiu LD, Liu TJ, Fu P (2017) Target Tracking Based on Deep Sparse Filtering[J]. J Comput Aided Des Comput Graph 29(3):459–468
Russakovsky O, Deng J, Su H et al (2015) Imagenet large scale visual recognition challenge[J]. Int J Comput Vis 115(3):211–252
Sandler M, Howard A, Zhu M et al (2018) Mobilenetv2: Inverted residuals and linear bottlenecks [C]. Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, 4510–4520
Simonyan K, Zisserman A (2014) Very deep convolutional networks for large-scale image recognition[J]. ar**v preprint ar**v:1409.1556
Sun JP (2021) Improved Hierarchical Convolutional Features for Robust Visual Object Tracking[J]. Complexity 2021:1–16. https://doi.org/10.1155/2021/6690237
Sun JP, Ding EJ, Sun B et al (2020) Adaptive Kernel Correlation Filter Tracking Algorithm in Complex Scenes[J]. IEEE Access 8:208179–208194
Sun JP, Ding EJ, Sun B et al (2020) Image salient object detection algorithm based on adaptive multi-feature template[J]. DYNA 95(6):646–653
Tian D, Zhang GS, **e Yi H (2019) Object tracking via low-rank and structural sparse representation with fused penalty constraint[J]. Control and Decision 34(11):2479–2484
Voigtlaender P, Luiten J, Torr PHS (2020) Siam R-CNN: visual tracking by re-detection[C]. IEEE Conference on Computer Vision and Pattern Recognition(CVPR), 6577–6587
Wu Y, Lim J, Yang MH (2013) Online object tracking: A benchmark[C]. Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, 2411–2418
Wu Y, Lim J, Yang MH (2015) Object tracking benchmark[J]. IEEE Trans Pattern Anal Mach Intell 37(9):1834–1848
Xu TY (2019) Research on correlation filter based visual object tracking[D]. Wuxi: Jiangnan University
Yuan D, Fan N, He Z (2020) Learning target-focusing convolutional regression model for visual object tracking[J]. Knowl-Based Syst 194:105526
Acknowledgments
The authors acknowledge the Basic Science Major Foundation (Natural Science) of the Jiangsu Higher Education Institutions of China (Grant: 22KJA520012), the Xuzhou Science and Technology Plan Project(Grant: KC21303) and the sixth “333 project” of Jiangsu Province.
Data sharing agreement
The datasets used and/or analyzed during the current study are available from the corresponding author on reasonable request.
Author information
Authors and Affiliations
Corresponding author
Ethics declarations
Conflict of Interest
The authors have no conflicts of interest to declare.
Additional information
Publisher’s note
Springer Nature remains neutral with regard to jurisdictional claims in published maps and institutional affiliations.
Rights and permissions
Springer Nature or its licensor (e.g. a society or other partner) holds exclusive rights to this article under a publishing agreement with the author(s) or other rightsholder(s); author self-archiving of the accepted manuscript version of this article is solely governed by the terms of such publishing agreement and applicable law.
About this article
Cite this article
Sun, J., Li, D. Object Tracking with Channel Group Regularization and Smooth Constraints Using Improved Dynamic Convolution Kernels in ITS. Multimed Tools Appl (2022). https://doi.org/10.1007/s11042-022-14294-w
Received:
Revised:
Accepted:
Published:
DOI: https://doi.org/10.1007/s11042-022-14294-w