Abstract
Traditional methods mainly use kernel-weighted feature histograms as tracking models, which are easily influenced by the similarity of tracking distributions, resulting in lower mean average precision (mAP) for tracking. In order to effectively address the issues of traditional methods, a new pedestrian tracking method based on adaptive Kalman filtering for urban rail transit stations is proposed. By combining pedestrian micro-walking state analysis with urban rail transit station pedestrian tracking features, a pedestrian tracking model is constructed. The urban rail transit station pedestrian tracking algorithm is designed using adaptive Kalman filtering, and pedestrian tracking is achieved based on the tracking model. Experimental results show that the designed pedestrian tracking method based on adaptive Kalman filtering for urban rail transit stations has a higher mAP for tracking and has certain practical value.
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
References
Yang, S., Chen, Z., Ma, X., et al.: Real-time high-precision pedestrian tracking: a detection-tracking-correction strategy based on improved SSD and Cascade R-CNN. J. Real-Time Image Proc. 2, 19 (2022)
Xu, Y., Chan, H.Y., Chen, A., et al.: Walk this way: Visualizing accessibility and mobility in metro station areas on a 3D pedestrian network. Environ. Plan. B Urban Anal. City Sci. 49(4), 1331–1335 (2022)
Xu, X., Li, X., Zhao, H., et al.: A real-time, continuous pedestrian tracking and positioning method with multiple coordinated overhead-view cameras. Measurement 178, 109386 (2021)
Xu, Y., Shmaliy, Y.S., Hua, L., et al.: Decision tree-extended finite impulse response filtering for pedestrian tracking over tightly integrated inertial navigation system/ultra wide band data. Meas. Sci. Technol. 3, 32 (2021)
Zhou, Y., Yang, W., Shen, Y.: Scale-adaptive KCF mixed with deep feature for pedestrian tracking. Electronics 10(5), 536 (2021)
Zhang, X., Wang, X., Gu, C.: Online multi-object tracking with pedestrian re-identification and occlusion processing. Vis. Comput. 5, 37 (2021)
Wong, K.Y., Luo, H., Wang, M., et al.: Recognition of pedestrian trajectories and attributes with computer vision and deep learning techniques. Adv. Eng. Inform. 49, 101356 (2021)
Huang, Y., Li, D., Cheng, J.: Simulation of pedestrian-vehicle interference in railway station drop-off area based on cellular automata. Phys. A 579(4), 126142 (2021)
Mo, D.L., Yang, R.H., Wu, W., et al.: Pedestrian target detection in surveillance video based on improved three-frame difference method. Sci. Technol. Innov. Guide 18(6), 138–142 (2021)
Shao, W., Zhao, F., Luo, H., et al.: Particle filter reinforcement via context-sensing for smartphone-based pedestrian dead reckoning. IEEE Commun. Let. PP(99), 1–1 (2021)
Author information
Authors and Affiliations
Corresponding author
Editor information
Editors and Affiliations
Rights and permissions
Copyright information
© 2024 ICST Institute for Computer Sciences, Social Informatics and Telecommunications Engineering
About this paper
Cite this paper
Li, B. (2024). Research on Pedestrian Tracking in Urban Rail Transit Stations Based on Adaptive Kalman Filtering. In: Yun, L., Han, J., Han, Y. (eds) Advanced Hybrid Information Processing. ADHIP 2023. Lecture Notes of the Institute for Computer Sciences, Social Informatics and Telecommunications Engineering, vol 549. Springer, Cham. https://doi.org/10.1007/978-3-031-50549-2_22
Download citation
DOI: https://doi.org/10.1007/978-3-031-50549-2_22
Published:
Publisher Name: Springer, Cham
Print ISBN: 978-3-031-50548-5
Online ISBN: 978-3-031-50549-2
eBook Packages: Computer ScienceComputer Science (R0)