Infrared and visible light target tracking association method and system based on dual-mode fusion modeling
The infrared-visible light target tracking method based on dual-modal fusion modeling utilizes the fusion of multiple features from infrared and visible light images to solve the problems of mismatch and identity switching in target tracking under complex scenes, thereby improving the reliability and stability of the association.
CN122156258AActive Publication Date: 2026-06-05HUNAN UNIV
Patent Information
- Authority / Receiving Office
- CN · China
- Patent Type
- Applications(China)
- Current Assignee / Owner
- HUNAN UNIV
- Filing Date
- 2026-05-09
- Publication Date
- 2026-06-05
AI Technical Summary
Technical Problem
Existing dual-modal target tracking methods using infrared and visible light are prone to mismatches and identity switching in complex scenarios, leading to unstable associations.
Method used
A dual-modal fusion modeling method is adopted, which uses target detection from infrared and visible light images, Kalman filtering state extrapolation, gradient direction histogram descriptors, and Hungarian algorithm to calculate a comprehensive association score to achieve one-to-one matching.
Benefits of technology
It improves the reliability of target association and the stability of state updates in complex scenarios, and enhances the ability to identify identities and adapt to complex environments.
✦ Generated by Eureka AI based on patent content.
Smart Images
Figure CN122156258A_ABST
Abstract
The application discloses an infrared and visible light target tracking correlation method and system based on bimodal fusion modeling, and the method comprises the following steps: target detection networks are used to detect an infrared image and a corresponding visible light image respectively to obtain a detection frame set; Kalman filtering algorithm is used to obtain two prediction frame sets; visible light motion similarity, infrared gradient structural similarity and bimodal appearance similarity are calculated respectively between the detection frames in the detection frame set of the visible light image and the prediction frames in the prediction frame set; three indexes are fused by weighting to obtain a comprehensive correlation score, and a one-to-one matching result of infrared and visible light target tracking correlation is obtained based on the Hungarian algorithm. The application aims to solve the problems that the correlation basis is single in the existing infrared and visible light bimodal target tracking, and the identity switching and mis-matching are prone to occur in complex scenes, and improve the reliability of target correlation and the stability of subsequent state updating in complex scenes.
Need to check novelty before this filing date? Find Prior Art