Deep Learning Methods and UAV Technologies for Crop Disease Detection
The paper underscores the significant advancements in plant disease diagnostics achieved through the integration of remote sensing technologies and deep learning algorithms, particularly in aerial imagery interpretation. It focuses on evaluating deep learning techniques and unmanned aerial vehicles...
Saved in:
| Main Authors: | , |
|---|---|
| Format: | Article |
| Language: | Russian |
| Published: |
Federal Scientific Agroengineering Centre VIM
2024-12-01
|
| Series: | Сельскохозяйственные машины и технологии |
| Subjects: | |
| Online Access: | https://www.vimsmit.com/jour/article/view/617 |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1849253127800225792 |
|---|---|
| author | S. G. Mudarisov I. R. Miftakhov |
| author_facet | S. G. Mudarisov I. R. Miftakhov |
| author_sort | S. G. Mudarisov |
| collection | DOAJ |
| description | The paper underscores the significant advancements in plant disease diagnostics achieved through the integration of remote sensing technologies and deep learning algorithms, particularly in aerial imagery interpretation. It focuses on evaluating deep learning techniques and unmanned aerial vehicles for crop disease detection. (Research purpose) The study aims to review and systemize scientific literature on the application of unmanned aerial vehicles, remote sensing technologies and deep learning 24 methods for the early detection and prediction of crop diseases. (Materials and methods) The paper presents various technologies employing unmanned aerial vehicles and sensors for monitoring plant condition, with an emphasis on modern computer vision tools designed to improve the accuracy of plant pathology identification. (Results and discussion) The analysis encompasses scientific publications from 2010 to 2023, with a primary focus on comparing the effectiveness of deep learning algorithms, such as convolutional neural networks (CNN), against traditional methods, including support vector machines (SVMs) and random forest classifiers. The findings demonstrate that deep learning algorithms offer more accurate and earlier detection of diseases, highlighting their potential for application in plant growing. The paper also addresses challenges associated with the use of unmanned aerial vehicles, such as data quality limitations, the complexity of processing large volumes of images, and the need for the development of more advanced models. The paper proposes solutions to these issues, including algorithm optimization and improved data preprocessing techniques. (Conclusions) The integration of unmanned aerial vehicles and deep learning provides new prospects for enhancing the efficiency of agricultural production. These technologies enable precise early-stage diagnosis of plant diseases and facilitate the prediction of their progression, allowing for timely implementation of crop protection measures. The combination of intelligent computer vision systems with unmanned aerial vehicles presents significant opportunities for advancing monitoring methods and improving plant health management. |
| format | Article |
| id | doaj-art-ce9af025d4f8493aa5a9e9fb9f6a03de |
| institution | Kabale University |
| issn | 2073-7599 |
| language | Russian |
| publishDate | 2024-12-01 |
| publisher | Federal Scientific Agroengineering Centre VIM |
| record_format | Article |
| series | Сельскохозяйственные машины и технологии |
| spelling | doaj-art-ce9af025d4f8493aa5a9e9fb9f6a03de2025-08-20T03:56:27ZrusFederal Scientific Agroengineering Centre VIMСельскохозяйственные машины и технологии2073-75992024-12-01184243310.22314/2073-7599-2024-18-4-24-33549Deep Learning Methods and UAV Technologies for Crop Disease DetectionS. G. Mudarisov0I. R. Miftakhov1Bashkir State Agrarian UniversityBashkir State Agrarian UniversityThe paper underscores the significant advancements in plant disease diagnostics achieved through the integration of remote sensing technologies and deep learning algorithms, particularly in aerial imagery interpretation. It focuses on evaluating deep learning techniques and unmanned aerial vehicles for crop disease detection. (Research purpose) The study aims to review and systemize scientific literature on the application of unmanned aerial vehicles, remote sensing technologies and deep learning 24 methods for the early detection and prediction of crop diseases. (Materials and methods) The paper presents various technologies employing unmanned aerial vehicles and sensors for monitoring plant condition, with an emphasis on modern computer vision tools designed to improve the accuracy of plant pathology identification. (Results and discussion) The analysis encompasses scientific publications from 2010 to 2023, with a primary focus on comparing the effectiveness of deep learning algorithms, such as convolutional neural networks (CNN), against traditional methods, including support vector machines (SVMs) and random forest classifiers. The findings demonstrate that deep learning algorithms offer more accurate and earlier detection of diseases, highlighting their potential for application in plant growing. The paper also addresses challenges associated with the use of unmanned aerial vehicles, such as data quality limitations, the complexity of processing large volumes of images, and the need for the development of more advanced models. The paper proposes solutions to these issues, including algorithm optimization and improved data preprocessing techniques. (Conclusions) The integration of unmanned aerial vehicles and deep learning provides new prospects for enhancing the efficiency of agricultural production. These technologies enable precise early-stage diagnosis of plant diseases and facilitate the prediction of their progression, allowing for timely implementation of crop protection measures. The combination of intelligent computer vision systems with unmanned aerial vehicles presents significant opportunities for advancing monitoring methods and improving plant health management.https://www.vimsmit.com/jour/article/view/617plant diseasesidentificationdiagnosticsartificial intelligenceunmanned aerial vehiclecomputer visiondeep learningprecision farming system |
| spellingShingle | S. G. Mudarisov I. R. Miftakhov Deep Learning Methods and UAV Technologies for Crop Disease Detection Сельскохозяйственные машины и технологии plant diseases identification diagnostics artificial intelligence unmanned aerial vehicle computer vision deep learning precision farming system |
| title | Deep Learning Methods and UAV Technologies for Crop Disease Detection |
| title_full | Deep Learning Methods and UAV Technologies for Crop Disease Detection |
| title_fullStr | Deep Learning Methods and UAV Technologies for Crop Disease Detection |
| title_full_unstemmed | Deep Learning Methods and UAV Technologies for Crop Disease Detection |
| title_short | Deep Learning Methods and UAV Technologies for Crop Disease Detection |
| title_sort | deep learning methods and uav technologies for crop disease detection |
| topic | plant diseases identification diagnostics artificial intelligence unmanned aerial vehicle computer vision deep learning precision farming system |
| url | https://www.vimsmit.com/jour/article/view/617 |
| work_keys_str_mv | AT sgmudarisov deeplearningmethodsanduavtechnologiesforcropdiseasedetection AT irmiftakhov deeplearningmethodsanduavtechnologiesforcropdiseasedetection |