一种基于多源数据融合的反无人机智能识别与追踪系统
By improving the YOLOv8 detection network and StrongSORT tracking algorithm, and combining multi-source data from vision, sound and radar, the problems of low detection accuracy of small targets, difficulty in distinguishing similar targets, inaccurate 3D motion prediction, and difficulty in re-identification after long-term occlusion in anti-drone systems have been solved, achieving higher recognition accuracy and tracking stability.
Patent Information
- Authority / Receiving Office
- CN · China
- Patent Type
- Patents(China)
- Current Assignee / Owner
- ERDOS SHIDA TECH CO LTD
- Filing Date
- 2025-07-18
- Publication Date
- 2026-07-17
AI Technical Summary
Existing anti-drone systems suffer from technical problems such as low accuracy in detecting small targets, difficulty in distinguishing similar targets, inaccurate 3D motion prediction, and difficulty in re-identifying after prolonged occlusion. They are particularly difficult to achieve accurate identification and stable tracking in complex environments.
By improving the YOLOv8 detection network and StrongSORT tracking algorithm, combining visual, sound and radar multi-source data, performing time synchronization and coordinate transformation, adding a fine-grained morphological feature recognition branch, adopting an adaptive Kalman filter and multimodal correlation cost calculation, and combining intelligent trajectory management strategies, we achieve deep fusion and synergistic advantages of multi-source data.
It improves the accuracy of UAV target identification and tracking stability, reduces false detections and missed detections, and enhances the detection performance and robustness of the tracking system in complex environments, especially showing stronger adaptability and stability in occlusion and interference environments.
Smart Images
Figure CN120850103B_ABST