一种基于高斯强跟踪自适应卡尔曼滤波的多目标跟踪方法
By using the Gaussian strong tracking adaptive Kalman filter method, the problems of trajectory drift and identity switching in multi-target tracking in industrial sites are solved, achieving stable and accurate tracking in complex environments and improving the reliability of safety monitoring.
Patent Information
- Authority / Receiving Office
- CN · China
- Patent Type
- Applications(China)
- Current Assignee / Owner
- CHANGCHUN UNIV OF TECH
- Filing Date
- 2026-06-22
- Publication Date
- 2026-07-17
AI Technical Summary
In complex industrial environments, existing multi-target tracking methods are prone to trajectory drift, identity switching, and tracking interruption due to personnel occlusion, overlap, and sudden changes in motion state, affecting the reliability of dangerous area identification.
A multi-target tracking method based on Gaussian strong tracking adaptive Kalman filtering is adopted. By continuously adjusting the filtering update strategy, calculating the strong tracking factor and adjusting the adaptive observation noise, and combining the detection confidence and observation residual, the target state update is optimized.
It effectively solves the problems of trajectory drift and identity switching, improves the stability and accuracy of tracking, and ensures the reliability of safety monitoring in complex environments.
Smart Images
Figure CN122415684A_ABST