Ultra-High-Resolution UAV-Based Detection of <i>Alternaria solani</i> Infections in Potato Fields
Automatic detection of foliar diseases in potato fields, such as early blight caused by <i>Alternaria solani</i>, could allow farmers to reduce the application of plant protection products while minimizing production losses. UAV-based, high resolution, NIR-sensitive cameras offer the adv...
| Main Authors: | , , , , , , , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
MDPI AG
2022-12-01
|
| Series: | Remote Sensing |
| Subjects: | |
| Online Access: | https://www.mdpi.com/2072-4292/14/24/6232 |
| _version_ | 1827637079598694400 |
|---|---|
| author | Ruben Van De Vijver Koen Mertens Kurt Heungens David Nuyttens Jana Wieme Wouter H. Maes Jonathan Van Beek Ben Somers Wouter Saeys |
| author_facet | Ruben Van De Vijver Koen Mertens Kurt Heungens David Nuyttens Jana Wieme Wouter H. Maes Jonathan Van Beek Ben Somers Wouter Saeys |
| author_sort | Ruben Van De Vijver |
| collection | DOAJ |
| description | Automatic detection of foliar diseases in potato fields, such as early blight caused by <i>Alternaria solani</i>, could allow farmers to reduce the application of plant protection products while minimizing production losses. UAV-based, high resolution, NIR-sensitive cameras offer the advantage of a detailed top-down perspective, with high-contrast images ideally suited for detecting <i>Alternaria solani</i> lesions. A field experiment was conducted with 8 plots housing 256 infected plants which were monitored 6 times over a 16-day period with a UAV. A modified RGB camera, sensitive to NIR, was combined with a superzoom lens to obtain ultra-high-resolution images with a spatial resolution of 0.3 mm/px. More than 15,000 lesions were annotated with points in two full size images corresponding to 1250 cropped tiles of 256 by 256 pixels. A deep learning U-Net model was trained to predict the density of <i>Alternaria solani</i> lesions for every pixel. In this way, density maps were calculated to indicate disease hotspots as a guide for the farmer. |
| first_indexed | 2024-03-09T15:54:19Z |
| format | Article |
| id | doaj.art-41f64dc9160845578a76aa0bd05321c6 |
| institution | Directory Open Access Journal |
| issn | 2072-4292 |
| language | English |
| last_indexed | 2024-03-09T15:54:19Z |
| publishDate | 2022-12-01 |
| publisher | MDPI AG |
| record_format | Article |
| series | Remote Sensing |
| spelling | doaj.art-41f64dc9160845578a76aa0bd05321c62023-11-24T17:46:18ZengMDPI AGRemote Sensing2072-42922022-12-011424623210.3390/rs14246232Ultra-High-Resolution UAV-Based Detection of <i>Alternaria solani</i> Infections in Potato FieldsRuben Van De Vijver0Koen Mertens1Kurt Heungens2David Nuyttens3Jana Wieme4Wouter H. Maes5Jonathan Van Beek6Ben Somers7Wouter Saeys8Flanders Research Institute for Agriculture, Fisheries and Food (ILVO), 9820 Merelbeke, BelgiumFlanders Research Institute for Agriculture, Fisheries and Food (ILVO), 9820 Merelbeke, BelgiumFlanders Research Institute for Agriculture, Fisheries and Food (ILVO), 9820 Merelbeke, BelgiumFlanders Research Institute for Agriculture, Fisheries and Food (ILVO), 9820 Merelbeke, BelgiumFlanders Research Institute for Agriculture, Fisheries and Food (ILVO), 9820 Merelbeke, BelgiumFlanders Research Institute for Agriculture, Fisheries and Food (ILVO), 9820 Merelbeke, BelgiumFlanders Research Institute for Agriculture, Fisheries and Food (ILVO), 9820 Merelbeke, BelgiumKU Leuven, Department of Earth and Environmental Sciences, 3001 Leuven, BelgiumKU Leuven, Department of Biosystems, MeBioS, 3001 Leuven, BelgiumAutomatic detection of foliar diseases in potato fields, such as early blight caused by <i>Alternaria solani</i>, could allow farmers to reduce the application of plant protection products while minimizing production losses. UAV-based, high resolution, NIR-sensitive cameras offer the advantage of a detailed top-down perspective, with high-contrast images ideally suited for detecting <i>Alternaria solani</i> lesions. A field experiment was conducted with 8 plots housing 256 infected plants which were monitored 6 times over a 16-day period with a UAV. A modified RGB camera, sensitive to NIR, was combined with a superzoom lens to obtain ultra-high-resolution images with a spatial resolution of 0.3 mm/px. More than 15,000 lesions were annotated with points in two full size images corresponding to 1250 cropped tiles of 256 by 256 pixels. A deep learning U-Net model was trained to predict the density of <i>Alternaria solani</i> lesions for every pixel. In this way, density maps were calculated to indicate disease hotspots as a guide for the farmer.https://www.mdpi.com/2072-4292/14/24/6232deep learningdronespotato cropsprecision farmingsupervisedU-Net |
| spellingShingle | Ruben Van De Vijver Koen Mertens Kurt Heungens David Nuyttens Jana Wieme Wouter H. Maes Jonathan Van Beek Ben Somers Wouter Saeys Ultra-High-Resolution UAV-Based Detection of <i>Alternaria solani</i> Infections in Potato Fields Remote Sensing deep learning drones potato crops precision farming supervised U-Net |
| title | Ultra-High-Resolution UAV-Based Detection of <i>Alternaria solani</i> Infections in Potato Fields |
| title_full | Ultra-High-Resolution UAV-Based Detection of <i>Alternaria solani</i> Infections in Potato Fields |
| title_fullStr | Ultra-High-Resolution UAV-Based Detection of <i>Alternaria solani</i> Infections in Potato Fields |
| title_full_unstemmed | Ultra-High-Resolution UAV-Based Detection of <i>Alternaria solani</i> Infections in Potato Fields |
| title_short | Ultra-High-Resolution UAV-Based Detection of <i>Alternaria solani</i> Infections in Potato Fields |
| title_sort | ultra high resolution uav based detection of i alternaria solani i infections in potato fields |
| topic | deep learning drones potato crops precision farming supervised U-Net |
| url | https://www.mdpi.com/2072-4292/14/24/6232 |
| work_keys_str_mv | AT rubenvandevijver ultrahighresolutionuavbaseddetectionofialternariasolaniiinfectionsinpotatofields AT koenmertens ultrahighresolutionuavbaseddetectionofialternariasolaniiinfectionsinpotatofields AT kurtheungens ultrahighresolutionuavbaseddetectionofialternariasolaniiinfectionsinpotatofields AT davidnuyttens ultrahighresolutionuavbaseddetectionofialternariasolaniiinfectionsinpotatofields AT janawieme ultrahighresolutionuavbaseddetectionofialternariasolaniiinfectionsinpotatofields AT wouterhmaes ultrahighresolutionuavbaseddetectionofialternariasolaniiinfectionsinpotatofields AT jonathanvanbeek ultrahighresolutionuavbaseddetectionofialternariasolaniiinfectionsinpotatofields AT bensomers ultrahighresolutionuavbaseddetectionofialternariasolaniiinfectionsinpotatofields AT woutersaeys ultrahighresolutionuavbaseddetectionofialternariasolaniiinfectionsinpotatofields |