Skip to main navigation Skip to search Skip to main content

Detection and Tracking of Intruding Unmanned Aerial Vehicles Based on Dual-modality

  • Southeast University, Nanjing
  • Civil Aviation Flight University of China

Research output: Chapter in Book/Report/Conference proceedingConference contributionpeer-review

Abstract

The unmanned aerial vehicles detection and tracking system is of vital significance in the current military and civil aviation fields. The research on this system is inseparable from object detection and object tracking algorithms. This paper first introduces the self-collected dual-modal dataset and briefly explains the data annotation tool. Subsequently, six mainstreams deep learning based object detection algorithms are tested on this dataset, and the basic detection results of these detectors are obtained. To further enhance the detection performance, we improved the YOLOv8 algorithm with the best performance by integrating two types of feature pyramids into it. After the improvement, it can be clearly seen that the detection effect has been enhanced. Finally, this paper elaborates on how to combine the object detector and the object tracker to construct a complete system.

Original languageEnglish
Title of host publicationProceedings - 5th International Conference on Big Data Engineering and Education, BDEE 2025
PublisherInstitute of Electrical and Electronics Engineers Inc.
Pages107-111
Number of pages5
ISBN (Electronic)9798331598853
DOIs
Publication statusPublished - 2025
Externally publishedYes
Event5th International Conference on Big Data Engineering and Education, BDEE 2025 - Luoyang, China
Duration: 11 Apr 202513 Apr 2025

Publication series

NameProceedings - 5th International Conference on Big Data Engineering and Education, BDEE 2025

Conference

Conference5th International Conference on Big Data Engineering and Education, BDEE 2025
Country/TerritoryChina
CityLuoyang
Period11/04/2513/04/25

Keywords

  • Dual-modality
  • Object Detection
  • Unmanned Aerial Vehicles
  • Visual Tracking

Fingerprint

Dive into the research topics of 'Detection and Tracking of Intruding Unmanned Aerial Vehicles Based on Dual-modality'. Together they form a unique fingerprint.

Cite this