Enhancing unmanned aerial vehicle capabilities: integrating YOLO algorithms for diverse industrial applications

Описание

Тип публикации: доклад, тезисы доклада, статья из сборника материалов конференций

Конференция: Hybrid Methods of Modeling and Optimization in Complex Systems (HMMOCS-II-2023); Krasnoyarsk; Krasnoyarsk

Год издания: 2024

Идентификатор DOI: 10.1051/itmconf/20245903012

Аннотация: The integration of UAVs with advanced deep learning algorithms, particularly the You Only Look Once models, has opened new horizons in various industries. This paper explores the transformative impact of YOLO-based systems across diverse sectors, including agriculture, forest fire detection, ecology, marine science, target detectioПоказать полностьюn, and UAV navigation. We delve into the specific applications of different YOLO models, ranging from YOLOv3 to the lightweight YOLOv8, highlighting their unique contributions to enhancing UAV functionalities. In agriculture, UAVs equipped with YOLO algorithms have revolutionized disease detection, crop monitoring, and weed management, contributing to sustainable farming practices. The application in forest fire management showcases the capability of these systems in real-time fire localization and analysis. In ecological and marine sciences, the use of YOLO models has significantly improved wildlife monitoring, environmental surveillance, and resource management. Target detection studies reveal the efficacy of YOLO models in processing complex UAV imagery for accurate and efficient object recognition. Moreover, advancements in UAV navigation, through YOLO-based visual landing recognition and operation in challenging environments, underscore the versatility and efficiency of these integrated systems. This comprehensive analysis demonstrates the profound impact of YOLO-based UAV technologies in various fields, underscoring their potential for future innovations and applications.

Ссылки на полный текст

Издание

Журнал: Hybrid Methods of Modeling and Optimization in Complex Systems (HMMOCS-II-2023)

Выпуск журнала: 59

Номера страниц: 3012

Место издания: Krasnoyarsk

Персоны

  • Guliutin Nikolai (Siberian Federal University, Artificial Intelligence Systems Department)
  • Antamoshkin Oleslav (Reshetnev Siberian State University of Science and Technology)

Вхождение в базы данных