Drone-Aided Plants Health Monitoring Using Enhanced Vision Transformer
<p dir="ltr">Precision agriculture demands robust yet efficient models capable of operating on resource-constrained edge devices for real-time plant health monitoring. Existing Vision Transformer (ViT) models often underperform in data-scarce agricultural settings due to their relian...
Saved in:
| Main Author: | |
|---|---|
| Other Authors: | , |
| Published: |
2025
|
| Subjects: | |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1864513521710006272 |
|---|---|
| author | Junaid Ahmad Khan (23739870) |
| author2 | Muhammad Asif Khan (7367468) Imen Filali (23739873) |
| author2_role | author author |
| author_facet | Junaid Ahmad Khan (23739870) Muhammad Asif Khan (7367468) Imen Filali (23739873) |
| author_role | author |
| dc.creator.none.fl_str_mv | Junaid Ahmad Khan (23739870) Muhammad Asif Khan (7367468) Imen Filali (23739873) |
| dc.date.none.fl_str_mv | 2025-12-04T09:00:00Z |
| dc.identifier.none.fl_str_mv | 10.1109/access.2025.3632545 |
| dc.relation.none.fl_str_mv | https://figshare.com/articles/journal_contribution/Drone-Aided_Plants_Health_Monitoring_Using_Enhanced_Vision_Transformer/32033856 |
| dc.rights.none.fl_str_mv | CC BY 4.0 info:eu-repo/semantics/openAccess |
| dc.subject.none.fl_str_mv | Information and computing sciences Artificial intelligence Computer vision and multimedia computation CNN disease classification drones plants ViT Computer architecture Transformers Standards Computational modeling Accuracy Biological system modeling Training Real-time systems Feature extraction |
| dc.title.none.fl_str_mv | Drone-Aided Plants Health Monitoring Using Enhanced Vision Transformer |
| dc.type.none.fl_str_mv | Text Journal contribution info:eu-repo/semantics/publishedVersion text contribution to journal |
| description | <p dir="ltr">Precision agriculture demands robust yet efficient models capable of operating on resource-constrained edge devices for real-time plant health monitoring. Existing Vision Transformer (ViT) models often underperform in data-scarce agricultural settings due to their reliance on large-scale pretraining and limited local feature extraction capabilities. In this study, we propose a enhanced lightweight ViT architecture (EViT) for edge devices used in plants disease classification. The core of our approach is a domain-optimized convolutional stem (ConvStem) architecture that replaces the standard patch embedding with a convolutional stem to enhance local feature extraction, particularly effective in data-scarce scenarios. Unlike ViT architectures, which rely on large-scale pretraining, the proposed ConvStem-ViT (i.e., EViT) achieves a notable improvement in accuracy and generalization on two benchmark datasets - PlantVillage (a widely used dataset of leaf disease images) and CCMT (a more challenging, real-world crop disease dataset). Comprehensive experiments, including ablation studies using model variant analysis, supported with attention map visualizations, confirm the superiority of the proposed model over standard ViTs and contemporary CNN-based baselines. Our EViT achieves over 94.8% accuracy on PlantVillage and 78.0% on CCMT, outperforming conventional ViTs by up to 13.6%. Computational analysis shows the model achieves these gains with minimal overhead (5.55 ms/image latency, 1.30 GFLOPs); these efficiency metrics enable real-time inference on UAVs or low-power edge devices, making the model suitable for practical drone-based scouting in agricultural fields. This work offers a viable framework for scalable, accurate, and efficient plant disease classification, making it an effective choice for resource-constrained edge devices such as drones for plant disease classification.</p><h2 dir="ltr">Other Information</h2><p dir="ltr">Published in: IEEE Access<br>License: <a href="https://creativecommons.org/licenses/by/4.0/deed.en" target="_blank">https://creativecommons.org/licenses/by/4.0/</a><br>See article on publisher's website: <a href="https://dx.doi.org/10.1109/access.2025.3632545" target="_blank">https://dx.doi.org/10.1109/access.2025.3632545</a></p> |
| eu_rights_str_mv | openAccess |
| id | Manara2_a76caebefc3b588cb8107f7970fc4a7f |
| identifier_str_mv | 10.1109/access.2025.3632545 |
| network_acronym_str | Manara2 |
| network_name_str | Manara2 |
| oai_identifier_str | oai:figshare.com:article/32033856 |
| publishDate | 2025 |
| repository.mail.fl_str_mv | |
| repository.name.fl_str_mv | |
| repository_id_str | |
| rights_invalid_str_mv | CC BY 4.0 |
| spelling | Drone-Aided Plants Health Monitoring Using Enhanced Vision TransformerJunaid Ahmad Khan (23739870)Muhammad Asif Khan (7367468)Imen Filali (23739873)Information and computing sciencesArtificial intelligenceComputer vision and multimedia computationCNNdisease classificationdronesplantsViTComputer architectureTransformersStandardsComputational modelingAccuracyBiological system modelingTrainingReal-time systemsFeature extraction<p dir="ltr">Precision agriculture demands robust yet efficient models capable of operating on resource-constrained edge devices for real-time plant health monitoring. Existing Vision Transformer (ViT) models often underperform in data-scarce agricultural settings due to their reliance on large-scale pretraining and limited local feature extraction capabilities. In this study, we propose a enhanced lightweight ViT architecture (EViT) for edge devices used in plants disease classification. The core of our approach is a domain-optimized convolutional stem (ConvStem) architecture that replaces the standard patch embedding with a convolutional stem to enhance local feature extraction, particularly effective in data-scarce scenarios. Unlike ViT architectures, which rely on large-scale pretraining, the proposed ConvStem-ViT (i.e., EViT) achieves a notable improvement in accuracy and generalization on two benchmark datasets - PlantVillage (a widely used dataset of leaf disease images) and CCMT (a more challenging, real-world crop disease dataset). Comprehensive experiments, including ablation studies using model variant analysis, supported with attention map visualizations, confirm the superiority of the proposed model over standard ViTs and contemporary CNN-based baselines. Our EViT achieves over 94.8% accuracy on PlantVillage and 78.0% on CCMT, outperforming conventional ViTs by up to 13.6%. Computational analysis shows the model achieves these gains with minimal overhead (5.55 ms/image latency, 1.30 GFLOPs); these efficiency metrics enable real-time inference on UAVs or low-power edge devices, making the model suitable for practical drone-based scouting in agricultural fields. This work offers a viable framework for scalable, accurate, and efficient plant disease classification, making it an effective choice for resource-constrained edge devices such as drones for plant disease classification.</p><h2 dir="ltr">Other Information</h2><p dir="ltr">Published in: IEEE Access<br>License: <a href="https://creativecommons.org/licenses/by/4.0/deed.en" target="_blank">https://creativecommons.org/licenses/by/4.0/</a><br>See article on publisher's website: <a href="https://dx.doi.org/10.1109/access.2025.3632545" target="_blank">https://dx.doi.org/10.1109/access.2025.3632545</a></p>2025-12-04T09:00:00ZTextJournal contributioninfo:eu-repo/semantics/publishedVersiontextcontribution to journal10.1109/access.2025.3632545https://figshare.com/articles/journal_contribution/Drone-Aided_Plants_Health_Monitoring_Using_Enhanced_Vision_Transformer/32033856CC BY 4.0info:eu-repo/semantics/openAccessoai:figshare.com:article/320338562025-12-04T09:00:00Z |
| spellingShingle | Drone-Aided Plants Health Monitoring Using Enhanced Vision Transformer Junaid Ahmad Khan (23739870) Information and computing sciences Artificial intelligence Computer vision and multimedia computation CNN disease classification drones plants ViT Computer architecture Transformers Standards Computational modeling Accuracy Biological system modeling Training Real-time systems Feature extraction |
| status_str | publishedVersion |
| title | Drone-Aided Plants Health Monitoring Using Enhanced Vision Transformer |
| title_full | Drone-Aided Plants Health Monitoring Using Enhanced Vision Transformer |
| title_fullStr | Drone-Aided Plants Health Monitoring Using Enhanced Vision Transformer |
| title_full_unstemmed | Drone-Aided Plants Health Monitoring Using Enhanced Vision Transformer |
| title_short | Drone-Aided Plants Health Monitoring Using Enhanced Vision Transformer |
| title_sort | Drone-Aided Plants Health Monitoring Using Enhanced Vision Transformer |
| topic | Information and computing sciences Artificial intelligence Computer vision and multimedia computation CNN disease classification drones plants ViT Computer architecture Transformers Standards Computational modeling Accuracy Biological system modeling Training Real-time systems Feature extraction |