Přístupnostní navigace
E-přihláška
Vyhledávání Vyhledat Zavřít
Detail publikačního výsledku
BARTONĚK, J.; JANOUŠEK, J.
Originální název
Vision-Based Autonomous UAV Tracking and Control
Anglický název
Druh
Stať ve sborníku v databázi WoS či Scopus
Originální abstrakt
This paper presents a vision-based control approach for unmanned aerial vehicles (UAVs), focusing on the detection and tracking of airborne objects. The proposed system integrates deep-learning-based object detection using YOLO models with computationally efficient tracking algorithms to ensure realtime performance. The control methodology involves extracting positional information from visual data and generating attitude commands to regulate UAV movement via MAVLink communication. The implementation is optimized for deployment on a Raspberry Pi 5, leveraging OpenCV and NCNN frameworks. Experimental results demonstrate the system’s capability to detect and track small UAVs while maintaining high frame rates, enabling reliable feedback-based flight adjustments.
Anglický abstrakt
Klíčová slova
detection | drone | tracking | UAV
Klíčová slova v angličtině
Autoři
Rok RIV
2026
Vydáno
01.01.2025
Nakladatel
Brno University of Technology
ISBN
9788021463202
Kniha
Proceedings II of the Conference Student Eeict
Strany od
128
Strany do
131
Strany počet
4
BibTex
@inproceedings{BUT201502, author="{} and Josef {Bartoněk} and {} and Jiří {Janoušek}", title="Vision-Based Autonomous UAV Tracking and Control", booktitle="Proceedings II of the Conference Student Eeict", year="2025", pages="128--131", publisher="Brno University of Technology", doi="10.13164/eeict.2025.128", isbn="9788021463202" }