Evaluation of Weed Infestations in Row Crops Using Aerial RGB Imaging and Deep Learning
One of the important factors negatively affecting the yield of row crops is weed infestations. Using non-contact detection methods allows for a rapid assessment of weed infestations’ extent and management decisions for practical weed control. This study aims to develop and demonstrate a methodology...
Saved in:
| Main Authors: | , , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
MDPI AG
2025-02-01
|
| Series: | Agriculture |
| Subjects: | |
| Online Access: | https://www.mdpi.com/2077-0472/15/4/418 |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1850080885151367168 |
|---|---|
| author | Plamena D. Nikolova Boris I. Evstatiev Atanas Z. Atanasov Asparuh I. Atanasov |
| author_facet | Plamena D. Nikolova Boris I. Evstatiev Atanas Z. Atanasov Asparuh I. Atanasov |
| author_sort | Plamena D. Nikolova |
| collection | DOAJ |
| description | One of the important factors negatively affecting the yield of row crops is weed infestations. Using non-contact detection methods allows for a rapid assessment of weed infestations’ extent and management decisions for practical weed control. This study aims to develop and demonstrate a methodology for early detection and evaluation of weed infestations in maize using UAV-based RGB imaging and pixel-based deep learning classification. An experimental study was conducted to determine the extent of weed infestations on two tillage technologies, plowing and subsoiling, tailored to the specific soil and climatic conditions of Southern Dobrudja. Based on an experimental study with the DeepLabV3 classification algorithm, it was found that the ResNet-34-backed model ensures the highest performance compared to different versions of ResNet, DenseNet, and VGG backbones. The achieved performance reached precision, recall, F1 score, and Kappa, respectively, 0.986, 0.986, 0.986, and 0.957. After applying the model in the field with the investigated tillage technologies, it was found that a higher level of weed infestation is observed in subsoil deepening areas, where 4.6% of the area is infested, compared to 0.97% with the plowing treatment. This work contributes novel insights into weed management during the critical early growth stages of maize, providing a robust framework for optimizing weed control strategies in this region. |
| format | Article |
| id | doaj-art-8a0606e68d834f7cbe1de139b7cffe72 |
| institution | DOAJ |
| issn | 2077-0472 |
| language | English |
| publishDate | 2025-02-01 |
| publisher | MDPI AG |
| record_format | Article |
| series | Agriculture |
| spelling | doaj-art-8a0606e68d834f7cbe1de139b7cffe722025-08-20T02:44:51ZengMDPI AGAgriculture2077-04722025-02-0115441810.3390/agriculture15040418Evaluation of Weed Infestations in Row Crops Using Aerial RGB Imaging and Deep LearningPlamena D. Nikolova0Boris I. Evstatiev1Atanas Z. Atanasov2Asparuh I. Atanasov3Department of Agricultural Machinery, Agrarian and Industrial Faculty, University of Ruse “Angel Kanchev”, 7017 Ruse, BulgariaDepartment of Automatics and Electronics, Faculty of Electrical Engineering, Electronics, and Automation, University of Ruse “Angel Kanchev”, 7004 Ruse, BulgariaDepartment of Agricultural Machinery, Agrarian and Industrial Faculty, University of Ruse “Angel Kanchev”, 7017 Ruse, BulgariaDepartment of Mechanics and Elements of Machines, Technical University of Varna, 9010 Varna, BulgariaOne of the important factors negatively affecting the yield of row crops is weed infestations. Using non-contact detection methods allows for a rapid assessment of weed infestations’ extent and management decisions for practical weed control. This study aims to develop and demonstrate a methodology for early detection and evaluation of weed infestations in maize using UAV-based RGB imaging and pixel-based deep learning classification. An experimental study was conducted to determine the extent of weed infestations on two tillage technologies, plowing and subsoiling, tailored to the specific soil and climatic conditions of Southern Dobrudja. Based on an experimental study with the DeepLabV3 classification algorithm, it was found that the ResNet-34-backed model ensures the highest performance compared to different versions of ResNet, DenseNet, and VGG backbones. The achieved performance reached precision, recall, F1 score, and Kappa, respectively, 0.986, 0.986, 0.986, and 0.957. After applying the model in the field with the investigated tillage technologies, it was found that a higher level of weed infestation is observed in subsoil deepening areas, where 4.6% of the area is infested, compared to 0.97% with the plowing treatment. This work contributes novel insights into weed management during the critical early growth stages of maize, providing a robust framework for optimizing weed control strategies in this region.https://www.mdpi.com/2077-0472/15/4/418weed detectionnon-contact methodsmaizeneural networksclassification |
| spellingShingle | Plamena D. Nikolova Boris I. Evstatiev Atanas Z. Atanasov Asparuh I. Atanasov Evaluation of Weed Infestations in Row Crops Using Aerial RGB Imaging and Deep Learning Agriculture weed detection non-contact methods maize neural networks classification |
| title | Evaluation of Weed Infestations in Row Crops Using Aerial RGB Imaging and Deep Learning |
| title_full | Evaluation of Weed Infestations in Row Crops Using Aerial RGB Imaging and Deep Learning |
| title_fullStr | Evaluation of Weed Infestations in Row Crops Using Aerial RGB Imaging and Deep Learning |
| title_full_unstemmed | Evaluation of Weed Infestations in Row Crops Using Aerial RGB Imaging and Deep Learning |
| title_short | Evaluation of Weed Infestations in Row Crops Using Aerial RGB Imaging and Deep Learning |
| title_sort | evaluation of weed infestations in row crops using aerial rgb imaging and deep learning |
| topic | weed detection non-contact methods maize neural networks classification |
| url | https://www.mdpi.com/2077-0472/15/4/418 |
| work_keys_str_mv | AT plamenadnikolova evaluationofweedinfestationsinrowcropsusingaerialrgbimaginganddeeplearning AT borisievstatiev evaluationofweedinfestationsinrowcropsusingaerialrgbimaginganddeeplearning AT atanaszatanasov evaluationofweedinfestationsinrowcropsusingaerialrgbimaginganddeeplearning AT asparuhiatanasov evaluationofweedinfestationsinrowcropsusingaerialrgbimaginganddeeplearning |