| 注册
首页|期刊导航|南京信息工程大学学报|基于智能视觉检测与语义分析的反无人机实时预警系统

基于智能视觉检测与语义分析的反无人机实时预警系统

崔勇强 周威任 毛智鹏 兰宇坤 杜飞飞 钟良

南京信息工程大学学报2026,Vol.18Issue(2):202-210,9.
南京信息工程大学学报2026,Vol.18Issue(2):202-210,9.DOI:10.13878/j.cnki.jnuist.20250402005

基于智能视觉检测与语义分析的反无人机实时预警系统

Real-time anti-UAV early warning using intelligent visual detection and semantic analysis

崔勇强 1周威任 1毛智鹏 2兰宇坤 1杜飞飞 3钟良1

作者信息

  • 1. 中南民族大学 电子信息工程学院,武汉,430074
  • 2. 国网冀北电力有限公司秦皇岛供电公司,秦皇岛,066000
  • 3. 武汉卓目科技股份有限公司,武汉,430074
  • 折叠

摘要

Abstract

To address the security threats from unauthorized and erratic UAV flights in low-altitude airspace de-fense and the technical challenge of achieving real-time and precise early warning in complex settings,this paper proposes a real-time UAV intrusion warning system that integrates the YOLOv10 object detection algorithm with the multimodal large language model of General Language Model-4V(GLM-4V).The system hardware consists of high-sensitivity electro-optical detection equipment and a central computing unit,while the software integrates a client in-teraction platform and a multimodal data processing module.At the algorithmic level,YOLOv10 is employed for rap-id UAV localization,supplemented by the SORT algorithm for dynamic trajectory tracking.An innovative framework for semantic description generation based on GLM-4V is designed,which incorporates a structured prompt template to convert detection results(target location,attributes,and environmental background)into compact textual descrip-tions in real time.This significantly alleviates the communication burden in bandwidth-limited scenarios.Experimen-tal results demonstrate that under extreme conditions—maximum detection range of 1 km and maximum flight speed of 23 m/s—the system achieves an identification accuracy of 97.6%.By forming a closed-loop process of visual de-tection-semantic analysis-dynamic transmission,the proposed system effectively tackles the challenge of real-time early warning against UAV intrusions in complex environments,thereby offering a highly robust solution for low-alti-tude airspace security.

关键词

反无人机/YOLO/GLM-4V/预警系统

Key words

anti-UAV/YOLO/GLM-4V/early warning systems

分类

航空航天

引用本文复制引用

崔勇强,周威任,毛智鹏,兰宇坤,杜飞飞,钟良..基于智能视觉检测与语义分析的反无人机实时预警系统[J].南京信息工程大学学报,2026,18(2):202-210,9.

基金项目

国家自然科学基金(62201621) (62201621)

湖北省自然科学基金指导性计划项目(2025AFC071) (2025AFC071)

湖北省自然科学基金创新群体项目(2024AFA030) (2024AFA030)

中央高校基本科研业务费项目(CZQ24001) (CZQ24001)

南京信息工程大学学报

1674-7070

访问量0
|
下载量0
段落导航相关论文