Review of Deep Learning Applications in Unmanned Aerial Vehicle Remote Sensing Images of Grass Plants
Year: 2025
Type: article
Abstract: The invasion of grass species competes for resources necessary for the growth of crops, significantly affecting crop yield and quality. Grasses such as the Artemisia genus release allergenic pollen, causing allergic reactions and impacting human health. The integration of deep learning and unmanned aerial vehicle (UAV) remote sensing technologies for the efficient identification and detection of grass species is of considerable practical significance in the prevention of plant invasion, allergen monitoring, and agricultural production management. Currently, remote sensing images face challenges such as low resolution, complex background information, and indistinct detail information. The combination of deep learning with UAV remote sensing RGB images and multispectral images addresses various application challenges, including high grass density, numerous species, wide coverage, and identification difficulties. This paper provides a comprehensive and in-depth review of the research progress on the application of deep learning technology in UAV remote sensing images of grass species. Initially, this paper elaborates on various UAV remote sensing image technologies widely used in grass species research, with a particular emphasis on the application of visible light RGB and multispectral remote sensing technologies. Subsequently, it provides a detailed summary of UAV-acquired grass species datasets, and focuses on the main network architectures and methods where deep learning is applied to grass species remote sensing images. Finally, it summarizes the current major issues when using deep learning in UAV remote sensing images of grass plants, and anticipates future development trends.
Author: LI Shaobo, WANG Xiaoqiang, GUO Libiao, HONG Ying, WANG Zhiguo
Institution: Inner Mongolia University of Technology
Language: English
Subfield: Media Technology
Field: Engineering
Domain: Physical Sciences
Open Access status: green
OpenAlex ID: W6928771309
FWCI:
Cites:
Cited by:
Related to: