Intelligent Weed Management Based on Object Detection Neural Networks in Tomato Crops
As the tomato (<i>Solanum lycopersicum</i> L.) is one of the most important crops worldwide, and the conventional approach for weed control compromises its potential productivity. Thus, the automatic detection of the most aggressive weed species is necessary to carry out selective contro...
| Main Authors: | , , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
MDPI AG
2022-11-01
|
| Series: | Agronomy |
| Subjects: | |
| Online Access: | https://www.mdpi.com/2073-4395/12/12/2953 |
| _version_ | 1797461909381840896 |
|---|---|
| author | Juan Manuel López-Correa Hugo Moreno Angela Ribeiro Dionisio Andújar |
| author_facet | Juan Manuel López-Correa Hugo Moreno Angela Ribeiro Dionisio Andújar |
| author_sort | Juan Manuel López-Correa |
| collection | DOAJ |
| description | As the tomato (<i>Solanum lycopersicum</i> L.) is one of the most important crops worldwide, and the conventional approach for weed control compromises its potential productivity. Thus, the automatic detection of the most aggressive weed species is necessary to carry out selective control of them. Precision agriculture associated with computer vision is a powerful tool to deal with this issue. In recent years, advances in digital cameras and neural networks have led to novel approaches and technologies in PA. Convolutional neural networks (CNNs) have significantly improved the precision and accuracy of the process of weed detection. In order to apply on-the-spot herbicide spraying, robotic weeding, or precise mechanical weed control, it is necessary to identify crop plants and weeds. This work evaluates a novel method to automatically detect and classify, in one step, the most problematic weed species of tomato crops. The procedure is based on object detection neural networks called RetinaNet. Moreover, two current mainstream object detection models, namelyYOLOv7 and Faster-RCNN, as a one and two-step NN, respectively, were also assessed in comparison to RetinaNet. CNNs model were trained on RGB images monocotyledonous (<i>Cyperus rotundus</i> L., <i>Echinochloa crus galli</i> L., <i>Setaria verticillata</i> L.) and dicotyledonous (<i>Portulaca oleracea</i> L., <i>Solanum nigrum</i> L.) weeds. The prediction model was validated with images not used during the training under the mean average precision (mAP) metric. RetinaNet performed best with an AP ranging from 0.900 to 0.977, depending on the weed species. Faster-RCNN and YOLOv7 also achieved satisfactory results, in terms of mAP, particularly through data augmentation. In contrast to Faster CNN, YOLOv7 was less precise when discriminating monocot weed species. The results provide a better insight on how weed identification methods based on CNN can be made more broadly applicable for real-time applications. |
| first_indexed | 2024-03-09T17:26:07Z |
| format | Article |
| id | doaj.art-8758e288c87741b59fc643815849bc27 |
| institution | Directory Open Access Journal |
| issn | 2073-4395 |
| language | English |
| last_indexed | 2024-03-09T17:26:07Z |
| publishDate | 2022-11-01 |
| publisher | MDPI AG |
| record_format | Article |
| series | Agronomy |
| spelling | doaj.art-8758e288c87741b59fc643815849bc272023-11-24T12:43:54ZengMDPI AGAgronomy2073-43952022-11-011212295310.3390/agronomy12122953Intelligent Weed Management Based on Object Detection Neural Networks in Tomato CropsJuan Manuel López-Correa0Hugo Moreno1Angela Ribeiro2Dionisio Andújar3Center for Automation and Robotics (CSIC-UPM), Arganda del Rey, 28500 Madrid, SpainCenter for Automation and Robotics (CSIC-UPM), Arganda del Rey, 28500 Madrid, SpainCenter for Automation and Robotics (CSIC-UPM), Arganda del Rey, 28500 Madrid, SpainCenter for Automation and Robotics (CSIC-UPM), Arganda del Rey, 28500 Madrid, SpainAs the tomato (<i>Solanum lycopersicum</i> L.) is one of the most important crops worldwide, and the conventional approach for weed control compromises its potential productivity. Thus, the automatic detection of the most aggressive weed species is necessary to carry out selective control of them. Precision agriculture associated with computer vision is a powerful tool to deal with this issue. In recent years, advances in digital cameras and neural networks have led to novel approaches and technologies in PA. Convolutional neural networks (CNNs) have significantly improved the precision and accuracy of the process of weed detection. In order to apply on-the-spot herbicide spraying, robotic weeding, or precise mechanical weed control, it is necessary to identify crop plants and weeds. This work evaluates a novel method to automatically detect and classify, in one step, the most problematic weed species of tomato crops. The procedure is based on object detection neural networks called RetinaNet. Moreover, two current mainstream object detection models, namelyYOLOv7 and Faster-RCNN, as a one and two-step NN, respectively, were also assessed in comparison to RetinaNet. CNNs model were trained on RGB images monocotyledonous (<i>Cyperus rotundus</i> L., <i>Echinochloa crus galli</i> L., <i>Setaria verticillata</i> L.) and dicotyledonous (<i>Portulaca oleracea</i> L., <i>Solanum nigrum</i> L.) weeds. The prediction model was validated with images not used during the training under the mean average precision (mAP) metric. RetinaNet performed best with an AP ranging from 0.900 to 0.977, depending on the weed species. Faster-RCNN and YOLOv7 also achieved satisfactory results, in terms of mAP, particularly through data augmentation. In contrast to Faster CNN, YOLOv7 was less precise when discriminating monocot weed species. The results provide a better insight on how weed identification methods based on CNN can be made more broadly applicable for real-time applications.https://www.mdpi.com/2073-4395/12/12/2953tomato weedssite-specific weed management (SSWM)object detection |
| spellingShingle | Juan Manuel López-Correa Hugo Moreno Angela Ribeiro Dionisio Andújar Intelligent Weed Management Based on Object Detection Neural Networks in Tomato Crops Agronomy tomato weeds site-specific weed management (SSWM) object detection |
| title | Intelligent Weed Management Based on Object Detection Neural Networks in Tomato Crops |
| title_full | Intelligent Weed Management Based on Object Detection Neural Networks in Tomato Crops |
| title_fullStr | Intelligent Weed Management Based on Object Detection Neural Networks in Tomato Crops |
| title_full_unstemmed | Intelligent Weed Management Based on Object Detection Neural Networks in Tomato Crops |
| title_short | Intelligent Weed Management Based on Object Detection Neural Networks in Tomato Crops |
| title_sort | intelligent weed management based on object detection neural networks in tomato crops |
| topic | tomato weeds site-specific weed management (SSWM) object detection |
| url | https://www.mdpi.com/2073-4395/12/12/2953 |
| work_keys_str_mv | AT juanmanuellopezcorrea intelligentweedmanagementbasedonobjectdetectionneuralnetworksintomatocrops AT hugomoreno intelligentweedmanagementbasedonobjectdetectionneuralnetworksintomatocrops AT angelaribeiro intelligentweedmanagementbasedonobjectdetectionneuralnetworksintomatocrops AT dionisioandujar intelligentweedmanagementbasedonobjectdetectionneuralnetworksintomatocrops |