A station dense pedestrian tracking system and method based on spatial weak clues

The station dense pedestrian tracking system based on spatial weak cues utilizes a lightweight spatiotemporal attention mechanism and a modified Kalman filter module, combined with weak cues, to achieve efficient pedestrian tracking, solving the detection and tracking challenges in dense pedestrian environments and realizing high-precision and fast pedestrian analysis.

CN118037774BActive Publication Date: 2026-06-19NORTHEASTERN UNIV CHINA
View PDF 2 Cites 0 Cited by

Patent Information

Authority / Receiving Office
CN · China
Patent Type
Patents(China)
Current Assignee / Owner
NORTHEASTERN UNIV CHINA
Filing Date
2024-02-01
Publication Date
2026-06-19

AI Technical Summary

Technical Problem

Traditional methods struggle to efficiently track pedestrians in densely populated environments like subway stations, especially when occlusion and clustering occur, leading to detection and tracking failures. Existing technologies lack effective utilization of cross-frame information and spatial weak cue enhancement.

Method used

A station-based dense pedestrian tracking system based on weak spatial cues is adopted. It extracts target features through a lightweight spatiotemporal attention mechanism, and combines modified Kalman filtering and trajectory management modules. It uses weak cues such as trajectory confidence, mixed intersection-over-union ratio, and velocity direction to perform high-confidence and low-confidence correlation to achieve accurate pedestrian tracking.

Benefits of technology

It improves the accuracy and speed of pedestrian tracking, enabling real-time detection and analysis of dense crowds in complex environments, and enhances the monitoring capabilities for subway station safety.

✦ Generated by Eureka AI based on patent content.

Smart Images

  • Figure CN118037774B_ABST
    Figure CN118037774B_ABST
Patent Text Reader

Abstract

This invention designs a system and method for tracking dense pedestrians in subway stations based on weak spatial cues. First, image frames are converted into a set of predicted detection boxes. Then, these boxes are binary-classified using preset high and low thresholds to obtain high-confidence and low-confidence detection boxes. Next, the tracking boxes in the previous frame's trajectory set are predicted using Kalman filtering to obtain the tracking boxes for the current frame. The high-confidence detection boxes are then matched with the current frame's tracking boxes for the first time, and the association cost is calculated to obtain the first set of successfully matched trajectories. Detection boxes that do not match a trajectory are merged into the low-confidence detection boxes. Then, the low-confidence association module performs the same matching process on the remaining trajectory sets to obtain the second set of successfully matched trajectories, which is then merged into the first set of successfully matched trajectories. Finally, the target trajectories are created, deleted, and updated to obtain the final output trajectory, completing the tracking of dense pedestrians in subway stations. This system can detect and analyze the dense pedestrian flow in subway stations in real time.
Need to check novelty before this filing date? Find Prior Art

Citation Information

Patent Citations

  • Pedestrian multi-target tracking method and device and computer readable storage medium

    CN115240130A

  • Multi-target tracking method in dense scene

    CN116883452A