Pixel-Precise Explainable Stress Indexing: A Semantic Segmentation Framework for Disease Severity Quantification in Field Crops(像素级可解释压力指数:田间作物病害严重程度量化的语义分割框架)
论文提出基于语义分割的作物病害严重度量化框架，方法新颖且性能优异，对智慧农业有参考价值，但时效性较低。
植物病害每年造成全球农业产量损失20%-40%、经济损失超2200亿美元。文章提出统一深度学习流水线,集成语义分割、基于回归的严重程度估计和病害分类,根据感染叶片面积比例将胁迫严重程度分为四档。在包含1641样本、六个类别的苹果树叶病害分割数据集上,采用MobileNetV2的U-Net表现最佳,像素准确率98.20%、mIoU 0.70、检测准确率99.41%、单张图像处理时间仅14.7毫秒,适合实时田间应用。计算出的严重程度指数与专家标注高度相关(r=0.968, R²=0.937),为自动化作物监测和决策支持提供可靠方案。[预印本]
arXiv is now an independent nonprofit×
Search arXiv
Press Enter to search · Advanced search
Computer Science > Computer Vision and Pattern Recognition
arXiv:2607.06585 (cs)
[Submitted on 5 Jul 2026]
Title:Pixel-Precise Explainable Stress Indexing: A Semantic Segmentation Framework for Disease Severity Quantification in Field Crops
Authors:Raunak Kumar, Soumyashree Kar
View a PDF of the paper titled Pixel-Precise Explainable Stress Indexing: A Semantic Segmentation Framework for Disease Severity Quantification in Field Crops, by Raunak Kumar and Soumyashree Kar
Abstract:Plant diseases, resulting from both biotic and abiotic stresses, cause an estimated 20-40% loss in global agricultural yield annually, resulting in economic damages exceeding USD 220 billion. Accurate and scalable stress quantification is essential for precision agriculture, yet traditional manual assessments are labour-intensive and subjective. This paper proposes a unified deep learning pipeline integrating semantic segmentation, regression-based severity estimation, and disease classification. Stress severity is categorised into four levels (Low to Very High) based on the proportion of infected leaf area. Experiments on the Apple Tree Leaf Disease Segmentation dataset (1,641 samples, six classes) evaluate four models: U-Net (MobileNetV2), SegFormer, FCN, and PSPNet. U-Net with MobileNetV2 achieves the best performance with 98.20% pixel accuracy, 0.70 mIoU, and 99.41% detection accuracy at 14.7 ms per image, making it suitable for real-time use. SegFormer performs competitively (mIoU 0.66), while FCN and PSPNet show lower spatial accuracy (approximately 0.49 mIoU). The computed severity index strongly correlates with expert annotations (r = 0.968, R^2 = 0.937), demonstrating the system's reliability for automated crop monitoring and decision support.
Comments:26 pages, 15 figures, 5 tables
Subjects:Computer Vision and Pattern Recognition (cs.CV); Machine Learning (cs.LG)
Cite as:arXiv:2607.06585 [cs.CV]
(or arXiv:2607.06585v1 [cs.CV] for this version)
https://doi.org/10.48550/arXiv.2607.06585
Focus to learn more
arXiv-issued DOI via DataCite
Submission history
From: Raunak Kumar [view email]
[v1] Sun, 5 Jul 2026 06:04:20 UTC (2,899 KB)
Access Paper:
View a PDF of the paper titled Pixel-Precise Explainable Stress Indexing: A Semantic Segmentation Framework for Disease Severity Quantification in Field Crops, by Raunak Kumar and Soumyashree Kar
Current browse context:
Change to browse by:
References & Citations
export BibTeX citation Loading...
BibTeX formatted citation
×
Bookmark
Bibliographic Tools
Bibliographic and Citation Tools
- [x] Bibliographic Explorer Toggle
Bibliographic Explorer (What is the Explorer?)
- [x] Connected Papers Toggle
Connected Papers (What is Connected Papers?)
- [x] Litmaps Toggle
Litmaps (What is Litmaps?)
- [x] scite.ai Toggle
scite Smart Citations (What are Smart Citations?)
Code, Data, Media
Code, Data and Media Associated with this Article
- [x] alphaXiv Toggle
alphaXiv (What is alphaXiv?)
- [x] Links to Code Toggle
CatalyzeX Code Finder for Papers (What is CatalyzeX?)
- [x] DagsHub Toggle
DagsHub (What is DagsHub?)
- [x] GotitPub Toggle
Gotit.pub (What is GotitPub?)
- [x] Huggingface Toggle
Hugging Face (What is Huggingface?)
- [x] ScienceCast Toggle
ScienceCast (What is ScienceCast?)
Demos
Demos
- [x] Replicate Toggle
Replicate (What is Replicate?)
- [x] Spaces Toggle
Hugging Face Spaces (What is Spaces?)
- [x] Spaces Toggle
Related Papers
Recommenders and Search Tools
- [x] Link to Influence Flower
Influence Flower (What are Influence Flowers?)
- [x] Core recommender toggle
CORE Recommender (What is CORE?)
About arXivLabs
arXivLabs: experimental projects with community collaborators
arXivLabs is a framework that allows collaborators to develop and share new arXiv features directly on our website.
Both individuals and organizations that work with arXivLabs have embraced and accepted our values of openness, community, excellence, and user data privacy. arXiv is committed to these values and only works with partners that adhere to them.
Have an idea for a project that will add value for arXiv's community? Learn more about arXivLabs.
Which authors of this paper are endorsers? | [Disable MathJax](javascript:setMathjaxCookie()) (What is MathJax?)
We gratefully acknowledge support from our major funders, member institutions, , and all contributors.
About·Help·Contact·Subscribe·Copyright·Privacy·Accessibility·Operational Status (opens in new tab)
Major funding support from
