Research Article
Research on Pedestrian Tracking in Urban Rail Transit Stations Based on Adaptive Kalman Filtering
@INPROCEEDINGS{10.1007/978-3-031-50549-2_22, author={Bo Li}, title={Research on Pedestrian Tracking in Urban Rail Transit Stations Based on Adaptive Kalman Filtering}, proceedings={Advanced Hybrid Information Processing. 7th EAI International Conference, ADHIP 2023, Harbin, China, September 22-24, 2023, Proceedings, Part III}, proceedings_a={ADHIP PART 3}, year={2024}, month={3}, keywords={Adaptive Kalman filter City Track Traffic station Pedestrian tracking}, doi={10.1007/978-3-031-50549-2_22} }- Bo Li
Year: 2024
Research on Pedestrian Tracking in Urban Rail Transit Stations Based on Adaptive Kalman Filtering
ADHIP PART 3
Springer
DOI: 10.1007/978-3-031-50549-2_22
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.
