Research on Crop Pest and Disease Detection Technology Based on Unmanned Aerial Vehicles
Industry Science and Engineering · 2026-02 · 3 (2) · 23-28
DOI: 10.62381/i265204 ↗Kurz gefasst
Fachartikel in der Zeitschrift Industry Science and Engineering, 2026-02. Verfasst von Baoyi Liao. Die Arbeit nennt 9 Literaturangaben.
Abstract (Originalsprache)
To enhance the automation and precision of crop pest and disease monitoring, this study systematically investigates a detection technology framework based on unmanned aerial vehicle (UAV) platforms. The research comprehensively utilizes multispectral and hyperspectral sensors for field data acquisition, constructs an analytical framework integrating traditional machine learning and deep learning models, and quantitatively evaluates algorithm performance through field experiments. The results indicate that deep learning models significantly outperform traditional methods in recognition accuracy, particularly excelling in the detection of typical diseases. However, the study also reveals limitations of these models when facing early-stage symptoms, complex backgrounds, and generalization across different crop types. The conclusion states that this technology system provides an effective tool for precision agriculture. Future work requires continuous optimization in areas such as algorithm lightweighting, edge deployment, and multi-source data fusion to promote its large-scale application in actual production.
Zitieren
APA
Liao, B. (2026). Research on Crop Pest and Disease Detection Technology Based on Unmanned Aerial Vehicles. Industry Science and Engineering, 3(2), 23-28. https://doi.org/10.62381/i265204
Vancouver
Liao B. Research on Crop Pest and Disease Detection Technology Based on Unmanned Aerial Vehicles. Industry Science and Engineering. 2026;3(2):23-28. doi:10.62381/i265204
BibTeX
@article{Liao2026,
author = {Liao, Baoyi},
title = {Research on Crop Pest and Disease Detection Technology Based on Unmanned Aerial Vehicles},
journal = {Industry Science and Engineering},
year = {2026},
volume = {3},
number = {2},
pages = {23--28},
doi = {10.62381/i265204}
}
EUVIMED