Low-illumination unmanned aerial vehicle target tracking system and method
By combining the target tracking module within the edge vision camera of the UAV with a lighting-level guided dual-path interactive feature enhancement network and temporal optimization, the problem of target tracking drift and interruption in complex dynamic scenarios under low illumination is solved, achieving high-precision, real-time UAV target tracking.
Patent Information
- Authority / Receiving Office
- CN · China
- Patent Type
- Applications(China)
- Current Assignee / Owner
- TONGJI UNIV
- Filing Date
- 2026-06-24
- Publication Date
- 2026-07-21
AI Technical Summary
Existing drone target tracking algorithms are susceptible to lighting interference, day-night cross-domain feature shift, and motion blur in low-light complex dynamic scenarios, leading to tracking drift and interruption. Furthermore, they are difficult to balance high precision and real-time requirements on drone edge embedded platforms with limited computing resources.
Design a low-light UAV target tracking system, including a target tracking module deployed in the edge vision camera of an industrial-grade UAV. Through a backbone network trained with domain adaptation and a tracking result output network, combined with an illumination-level guided dual-path interactive feature enhancement network, a temporal optimization and enhancement layer, and a dynamic sparsity and semantic constraint alignment network, feature enhancement, domain adaptation, compensation calibration and lightweight deployment are achieved.
It effectively improves the accuracy and stability of target tracking in complex dynamic scenarios with low illumination, meets the real-time and lightweight requirements of UAV edge deployment, solves the problems of illumination interference, cross-domain feature offset and motion blur, and provides high-purity and robust target feature support.
Smart Images

Figure CN122434979A_ABST