Abstract
The realization of the 5G/6G network can ensure high-speed data transmission, which makes it possible to realize high-speed data transmission in the monitoring video system. With the technical support of 5G/6G, the peak transmission rate can reach 10G bit/s, which solves the problems of video blur and low transmission rate in the monitoring system, and provides faster and higher resolution monitoring pictures and data, and provides a good condition for surveillance video target tracking based on 5G/6G network. In this context, based on the surveillance video in the 5G/6G network, this paper implements a two-stage processing algorithm to complete the tracking task, which solves the problem of target loss and occlusion. In the first stage, we use the Yolo V5s algorithm to detect the target and transfer the detection data to the Deep SORT algorithm in the second stage as the input of Kalman Filter, Then, the deep convolution network is used to extract the features of the detection frame, and then compared with the previously saved features to determine whether it is the same target. Due to the combination of appearance information, the algorithm can continuously track the occluded objects; The algorithm can achieve the real-time effect on the processing of surveillance video and has practical value in the future 5G/6G video surveillance network.
This is a preview of subscription content, log in via an institution to check access.
Access this chapter
Tax calculation will be finalised at checkout
Purchases are for personal use only
Similar content being viewed by others
References
Wang, Z.D., Zheng, L., Liu, Y.X., et al.: Towards real-time multi-object tracking. In: 16th European Conference on Computer Vision, pp. 107–122. Springer, Heidelberg (2020)
Kuanhung, S., Chingte, C., Lin, J., et al.: Real-time object detection with reduced region proposal network via multi-feature concatenation. IEEE Trans. Neural Networks Learn. Syst. 31(6), 2164–2173 (2020)
Luo, W.H., Xing, J.L., Milan, A., et al.: Multiple object tracking: a literature review. Artif. Intell. 293, 103448 (2020)
Kalman, R.E.: A new approach to linear filtering and prediction problems. J. Basic Eng. 82(1), 35–45 (1960); Zhang, J.W.: Gradient descent based optimization algorithms for deep learning models training [EB/OL]. [2019–03–21]. https://www.researchgate.net/publication/331670579
Chen, L., Ai, H.Z., Zhuang, Z.Z., et al.: Real-time multiple people tracking with deeply learned candidate selection and person re-identification. In: IEEE International Conference on Multimedia & Expo (ICME), pp. 1–6. IEEE, New York (2018)
Redmon, J.,Farhadi, A.: Yolov3: An incremental improvement [E B/O L]. [ 2 0 1 8 - 0 4 - 0 8]
Fu, Z.Y., Naqvi, S.M., Chambers, J.A.: Collaborative detector fusion of data-driven PHD filter for online multiple human tracking. In: Proceedings of the 21st International Conference on Information Fusion, pp. 1976–1981. IEEE, New York (2018)
Ren, S.Q., He, K.M., Girshick, R., et al.: Faster R-CNN: towards real- time object detection with region proposal networks. IEEE Trans. Pattern Anal. Mach. Intell. 39(6), 1137–1149 (2017)
Bewley, A., Ge, Z.Y., Ott, L., et al.: Simple online and real time tracking. In: 2016 IEEE International Conference on Image Processing, pp. 3464–3468. IEEE, New York (2016)
Wojke, N., Bewley, A., Paulus, D.: Simple online and real time tracking with a deep association metric. In: 2017 IEEE International Conference on Image Processing, pp. 3645–3649. IEEE, New York (2017)
Cipolla, R., Gal, Y., Kendall, A.: Multi-task learning using uncertainty to weigh losses for scene geometry and semantics. In: 2018 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR), pp. 7482–7491. IEEE, New York (2018)
Acknowledgment
This work was supported by the National Natural Science Foundation of China (41861134010), the Basic scientific research project of Heilongjiang Province (KJCXZD201704), the Key Laboratory of Police Wireless Digital Communication, Ministry of Public Security (2018JYWXTX01), and partly by the Harbin research found for technological innovation (2013RFQXJ104) national education and the science program during the twelfth five-year plan (FCB150518). The authors would like to thank all the people who participated in the project.
Author information
Authors and Affiliations
Corresponding author
Editor information
Editors and Affiliations
Rights and permissions
Copyright information
© 2022 ICST Institute for Computer Sciences, Social Informatics and Telecommunications Engineering
About this paper
Cite this paper
Zhen, J., Ye, L., Li, Z. (2022). Target Detecting and Target Tracking Based on YOLO and Deep SORT Algorithm. In: Shi, S., Ma, R., Lu, W. (eds) 6GN for Future Wireless Networks. 6GN 2021. Lecture Notes of the Institute for Computer Sciences, Social Informatics and Telecommunications Engineering, vol 439. Springer, Cham. https://doi.org/10.1007/978-3-031-04245-4_32
Download citation
DOI: https://doi.org/10.1007/978-3-031-04245-4_32
Published:
Publisher Name: Springer, Cham
Print ISBN: 978-3-031-04244-7
Online ISBN: 978-3-031-04245-4
eBook Packages: Computer ScienceComputer Science (R0)