Detectron2-enhanced mask R-CNN for precise instance segmentation of rice blast disease in Tanzania: Supporting timely intervention and data-driven severity assessment
Rice blast, caused by Magnaporthe oryzae, poses a significant threat to rice production in Tanzania and across Africa, affecting food security and farmers' livelihoods. Traditional inspection methods are slow and often overlook early symptoms, leading to delayed responses. Although progress has...
Saved in:
| Main Authors: | , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
Elsevier
2025-12-01
|
| Series: | Smart Agricultural Technology |
| Subjects: | |
| Online Access: | http://www.sciencedirect.com/science/article/pii/S2772375525005325 |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1849228321608433664 |
|---|---|
| author | Reuben Alfred Judith Leo Shubi F. Kaijage |
| author_facet | Reuben Alfred Judith Leo Shubi F. Kaijage |
| author_sort | Reuben Alfred |
| collection | DOAJ |
| description | Rice blast, caused by Magnaporthe oryzae, poses a significant threat to rice production in Tanzania and across Africa, affecting food security and farmers' livelihoods. Traditional inspection methods are slow and often overlook early symptoms, leading to delayed responses. Although progress has been made with deep learning diagnostics, many approaches still depend on whole-image classification or broad bounding boxes, lacking the pixel-level detail needed to assess infection severity. This study introduces a Mask R-CNN instance segmentation model developed within the Detectron2 framework to accurately detect and segment blast lesions (BL), blast-infected leaves (BIL), and healthy leaves (HL) at the pixel level. In addition to detection, the model quantifies the lesion severity by computing the proportion of infected leaf area, supporting informed evaluation and improved disease management decisions. Built on a ResNet-50 backbone with a Feature Pyramid Network (FPN), it achieved a mean average precision (mAP) of 89.4 %, with an AP50 of 94.6 % and an AP75 of 90.5 %. The model exhibited consistent performance across object scales, achieving an AP of 81.31 % for small objects and 86.06 % for large objects. Furthermore, testing on unseen images (images not used in the training process) demonstrated strong generalization, with detection confidence above 99 % and accurate masks that provide reliable severity scores. By enabling pixel-level severity assessment without expensive sensors or UAVs, this study offers a practical and affordable solution for disease monitoring in resource-constrained farming communities. It equips Tanzanian smallholder farmers with timely, accessible tools for effective blast detection and data-driven decision making. |
| format | Article |
| id | doaj-art-bc5956a0d939430db0fbf4b0730cd314 |
| institution | Kabale University |
| issn | 2772-3755 |
| language | English |
| publishDate | 2025-12-01 |
| publisher | Elsevier |
| record_format | Article |
| series | Smart Agricultural Technology |
| spelling | doaj-art-bc5956a0d939430db0fbf4b0730cd3142025-08-23T04:49:51ZengElsevierSmart Agricultural Technology2772-37552025-12-011210130110.1016/j.atech.2025.101301Detectron2-enhanced mask R-CNN for precise instance segmentation of rice blast disease in Tanzania: Supporting timely intervention and data-driven severity assessmentReuben Alfred0Judith Leo1Shubi F. Kaijage2School of Computational and Communication Science and Engineering (CoCSE), The Nelson Mandela African, Institution of Science and Technology (NM-AIST), P.O. Box 447, Arusha, Tanzania; Department of Physics, Mathematics, and Informatics (PMI), Dar es Salaam University College of Education (DUCE), P.O. Box 2329, Dar es Salaam, Tanzania; Corresponding author.School of Computational and Communication Science and Engineering (CoCSE), The Nelson Mandela African, Institution of Science and Technology (NM-AIST), P.O. Box 447, Arusha, TanzaniaSchool of Computational and Communication Science and Engineering (CoCSE), The Nelson Mandela African, Institution of Science and Technology (NM-AIST), P.O. Box 447, Arusha, TanzaniaRice blast, caused by Magnaporthe oryzae, poses a significant threat to rice production in Tanzania and across Africa, affecting food security and farmers' livelihoods. Traditional inspection methods are slow and often overlook early symptoms, leading to delayed responses. Although progress has been made with deep learning diagnostics, many approaches still depend on whole-image classification or broad bounding boxes, lacking the pixel-level detail needed to assess infection severity. This study introduces a Mask R-CNN instance segmentation model developed within the Detectron2 framework to accurately detect and segment blast lesions (BL), blast-infected leaves (BIL), and healthy leaves (HL) at the pixel level. In addition to detection, the model quantifies the lesion severity by computing the proportion of infected leaf area, supporting informed evaluation and improved disease management decisions. Built on a ResNet-50 backbone with a Feature Pyramid Network (FPN), it achieved a mean average precision (mAP) of 89.4 %, with an AP50 of 94.6 % and an AP75 of 90.5 %. The model exhibited consistent performance across object scales, achieving an AP of 81.31 % for small objects and 86.06 % for large objects. Furthermore, testing on unseen images (images not used in the training process) demonstrated strong generalization, with detection confidence above 99 % and accurate masks that provide reliable severity scores. By enabling pixel-level severity assessment without expensive sensors or UAVs, this study offers a practical and affordable solution for disease monitoring in resource-constrained farming communities. It equips Tanzanian smallholder farmers with timely, accessible tools for effective blast detection and data-driven decision making.http://www.sciencedirect.com/science/article/pii/S2772375525005325Rice blastDeep learningMask-RCNNInstance segmentationPrecision agricultureDetectron2 |
| spellingShingle | Reuben Alfred Judith Leo Shubi F. Kaijage Detectron2-enhanced mask R-CNN for precise instance segmentation of rice blast disease in Tanzania: Supporting timely intervention and data-driven severity assessment Smart Agricultural Technology Rice blast Deep learning Mask-RCNN Instance segmentation Precision agriculture Detectron2 |
| title | Detectron2-enhanced mask R-CNN for precise instance segmentation of rice blast disease in Tanzania: Supporting timely intervention and data-driven severity assessment |
| title_full | Detectron2-enhanced mask R-CNN for precise instance segmentation of rice blast disease in Tanzania: Supporting timely intervention and data-driven severity assessment |
| title_fullStr | Detectron2-enhanced mask R-CNN for precise instance segmentation of rice blast disease in Tanzania: Supporting timely intervention and data-driven severity assessment |
| title_full_unstemmed | Detectron2-enhanced mask R-CNN for precise instance segmentation of rice blast disease in Tanzania: Supporting timely intervention and data-driven severity assessment |
| title_short | Detectron2-enhanced mask R-CNN for precise instance segmentation of rice blast disease in Tanzania: Supporting timely intervention and data-driven severity assessment |
| title_sort | detectron2 enhanced mask r cnn for precise instance segmentation of rice blast disease in tanzania supporting timely intervention and data driven severity assessment |
| topic | Rice blast Deep learning Mask-RCNN Instance segmentation Precision agriculture Detectron2 |
| url | http://www.sciencedirect.com/science/article/pii/S2772375525005325 |
| work_keys_str_mv | AT reubenalfred detectron2enhancedmaskrcnnforpreciseinstancesegmentationofriceblastdiseaseintanzaniasupportingtimelyinterventionanddatadrivenseverityassessment AT judithleo detectron2enhancedmaskrcnnforpreciseinstancesegmentationofriceblastdiseaseintanzaniasupportingtimelyinterventionanddatadrivenseverityassessment AT shubifkaijage detectron2enhancedmaskrcnnforpreciseinstancesegmentationofriceblastdiseaseintanzaniasupportingtimelyinterventionanddatadrivenseverityassessment |