Education, Science, Technology, Innovation and Life
Open Access
Sign In

Research on video target tracking algorithm based on deep neural network

Download as PDF

DOI: 10.23977/acss.2023.070809 | Downloads: 8 | Views: 261

Author(s)

Chen Rui 1

Affiliation(s)

1 Wenzhou Business College, Wenzhou, Zhejiang, China

Corresponding Author

Chen Rui

ABSTRACT

In the field of computer vision applications, visual object tracking is a widely researched and hot-topic area, finding extensive practical applications in many key visual domains and demonstrating promising real-world performance. However, due to various factors such as lighting variations, scale changes, background clutter, low resolution, and other interferences, visual object tracking requires improvements on multiple fronts. In this paper, a video object tracking algorithm based on deep neural networks is proposed while ensuring real-time tracking. Addressing the limitation of traditional visual object tracking algorithms based on correlation filtering theory, which rely on shallow handcrafted features, this algorithm first leverages a deep neural network model to extract deep features of the target to be tracked. Given that different convolutional layers encode different information in their deep feature representations, these distinct layer features are subsequently fused to enhance representation capability. Furthermore, a kernel correlation-based approach is employed to boost the tracking speed of the visual object tracking algorithm. The experimental results demonstrate that the method proposed in this paper achieves a balance between target tracking accuracy and speed, enhancing the robustness of visual object tracking algorithms in complex and noisy backgrounds.

KEYWORDS

Visual object tracking, Real-time tracking, Deep neural network model, Robustness

CITE THIS PAPER

Chen Rui, Research on video target tracking algorithm based on deep neural network. Advances in Computer, Signals and Systems (2023) Vol. 7: 78-88. DOI: http://dx.doi.org/10.23977/acss.2023.070809.

REFERENCES

[1] Henriques J F, Caseiro R, Martins P, et al. High-speed tracking with kernelized correlation filters [J]. In Proceedings of IEEE Transactions on Pattern Analysis and Machine Intelligence, 2021, 37(3):583-596.
[2] Bhat G, Johnander J, Danelljan M, et al. Unveiling the Power of Deep Tracking [J]. In IEEE Transactions on Pattern Analysis and Machine Intelligence, 2020, 36(7):1442-1468.
[3] Wu Y, Lim J, Yang M H.Object tracking benchamark [J]. IEEE Transactions on Pattern Analysis and Machine Intelligence, 2021, 37(9): 1834-1848.
[4] Boyd S, Parikh N, Chu E, et al. Distributed optimization and statistical learning via the alternating direction method of multipliers[J]. Foundations & Trends in Machine Learning, 2019, 3(1): 1-3.
[5] Wang Q, Zhang L, Bertinetto L, et al. Fast Online Object Tracking and Segmentation: A Unifying Approach [J]. 2018, 50(8):11-13.
[6] He K M, Zhang X Y, Re S Q, et al. Deep residual learning for image recognition [J]. Proc of the IEEE Conference on Computer Vision and Pattern Recognition, 2016, 72(14):770-774.
[7] Henriques J F, Caseiro R, Martins P, et al. High-speed tracking with kernelized correlation filters [J]. IEEE Transactions on Pattern Analysis and Machine Intelligence, 2015, 37(3):583-596.
[8] Avidan S. Support vector tracking [J]. IEEE Transactions on Pattern Analysis and Machine Intelligence, 2004, 26(8): 1064-1072.
[9] Ross D A, Lim J, Lin R S, et al. Incremental learning for robust visual tracking[J]. International Journal of Computer Vision, 2019, 77(1): 125-141.
[10] Hua Y. Occlusion and motion reasoning for long-term tracking[C]// European Conference on Computer Vision. 2020: 172-187.
[11] Ma C, Yang X K, Zhang C Y, et al. Long-term correlation tracking[C]// Proceedings of IEEE Conference on Computer Vision and Pattern Recognition. 2015: 5388-5396.
[12] Li B, Wu W, Wang Q, et al. Siam RPN++: Evolution of Siamese Visual Tracking with Very Deep Networks [J]. IEEE Transactions on Pattern Analysis and Machine Intelligence, 2022, 28(8): 10-13.

Downloads: 13385
Visits: 257809

Sponsors, Associates, and Links


All published work is licensed under a Creative Commons Attribution 4.0 International License.

Copyright © 2016 - 2031 Clausius Scientific Press Inc. All Rights Reserved.