Application of UAV-Based Imaging and Deep Learning in Assessment of Rice Blast Resistance

IF 5.6 2区 农林科学 Q1 AGRONOMY Rice Science Pub Date : 2023-11-01 DOI:10.1016/j.rsci.2023.06.005
Lin Shaodan , Yao Yue , Li Jiayi , Li Xiaobin , Ma Jie , Weng Haiyong , Cheng Zuxin , Ye Dapeng
{"title":"Application of UAV-Based Imaging and Deep Learning in Assessment of Rice Blast Resistance","authors":"Lin Shaodan ,&nbsp;Yao Yue ,&nbsp;Li Jiayi ,&nbsp;Li Xiaobin ,&nbsp;Ma Jie ,&nbsp;Weng Haiyong ,&nbsp;Cheng Zuxin ,&nbsp;Ye Dapeng","doi":"10.1016/j.rsci.2023.06.005","DOIUrl":null,"url":null,"abstract":"<div><p>Rice blast is regarded as one of the major diseases of rice. Screening rice genotypes with high resistance to rice blast is a key strategy for ensuring global food security. Unmanned aerial vehicles (UAV)-based imaging, coupled with deep learning, can acquire high-throughput imagery related to rice blast infection. In this study, we developed a segmented detection model (called RiceblastSegMask) for rice blast detection and resistance evaluation. The feasibility of different backbones and target detection models was further investigated. RiceblastSegMask is a two-stage instance segmentation model, comprising an image-denoising backbone network, a feature pyramid, a trinomial tree fine-grained feature extraction combination network, and an image pixel codec module. The results showed that the model combining the image-denoising and fine-grained feature extraction based on the Swin Transformer and the feature pixel matching feature labels with the trinomial tree recursive algorithm performed the best. The overall accuracy for instance segmentation of RiceblastSegMask reached 97.56%, and it demonstrated a satisfactory accuracy of 90.29% for grading unique resistance to rice blast. These results indicated that low-altitude remote sensing using UAV, in conjunction with the proposed RiceblastSegMask model, can efficiently calculate the extent of rice blast infection, offering a new phenotypic tool for evaluating rice blast resistance on a field scale in rice breeding programs.</p></div>","PeriodicalId":56069,"journal":{"name":"Rice Science","volume":"30 6","pages":"Pages 652-660"},"PeriodicalIF":5.6000,"publicationDate":"2023-11-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://www.sciencedirect.com/science/article/pii/S1672630823000896/pdfft?md5=73f0978cd379874e860c3f749056918e&pid=1-s2.0-S1672630823000896-main.pdf","citationCount":"0","resultStr":null,"platform":"Semanticscholar","paperid":null,"PeriodicalName":"Rice Science","FirstCategoryId":"97","ListUrlMain":"https://www.sciencedirect.com/science/article/pii/S1672630823000896","RegionNum":2,"RegionCategory":"农林科学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":null,"EPubDate":"","PubModel":"","JCR":"Q1","JCRName":"AGRONOMY","Score":null,"Total":0}
引用次数: 0

Abstract

Rice blast is regarded as one of the major diseases of rice. Screening rice genotypes with high resistance to rice blast is a key strategy for ensuring global food security. Unmanned aerial vehicles (UAV)-based imaging, coupled with deep learning, can acquire high-throughput imagery related to rice blast infection. In this study, we developed a segmented detection model (called RiceblastSegMask) for rice blast detection and resistance evaluation. The feasibility of different backbones and target detection models was further investigated. RiceblastSegMask is a two-stage instance segmentation model, comprising an image-denoising backbone network, a feature pyramid, a trinomial tree fine-grained feature extraction combination network, and an image pixel codec module. The results showed that the model combining the image-denoising and fine-grained feature extraction based on the Swin Transformer and the feature pixel matching feature labels with the trinomial tree recursive algorithm performed the best. The overall accuracy for instance segmentation of RiceblastSegMask reached 97.56%, and it demonstrated a satisfactory accuracy of 90.29% for grading unique resistance to rice blast. These results indicated that low-altitude remote sensing using UAV, in conjunction with the proposed RiceblastSegMask model, can efficiently calculate the extent of rice blast infection, offering a new phenotypic tool for evaluating rice blast resistance on a field scale in rice breeding programs.

查看原文
分享 分享
微信好友 朋友圈 QQ好友 复制链接
本刊更多论文
基于无人机成像和深度学习技术在水稻稻瘟病抗性评估中的应用
稻瘟病被认为是水稻的主要病害之一。筛选稻瘟病高抗水稻基因型是保障全球粮食安全的一项关键战略。基于无人机(UAV)的成像技术,结合深度学习,可以获得水稻稻瘟病相关的高通量图像。在这项研究中,我们开发了一个分段检测模型(称为稻瘟病分段检测模型)用于稻瘟病检测和抗性评估。进一步研究了不同主干网和目标检测模型的可行性。riceblastsegask是一种两阶段的实例分割模型,由图像去噪骨干网络、特征金字塔、三叉树细粒度特征提取组合网络和图像像素编解码模块组成。结果表明,基于Swin Transformer的图像去噪和细粒度特征提取与基于三叉树递归算法的特征像素匹配特征标签相结合的模型效果最好。稻瘟病基因片段分割总体准确率达97.56%,稻瘟病独特抗性分级准确率达90.29%。这些结果表明,利用无人机低空遥感技术,结合所提出的稻瘟病基因片段模型,可以有效地计算水稻稻瘟病感染程度,为水稻育种项目中田间水稻稻瘟病抗性评估提供了一种新的表型工具。
本文章由计算机程序翻译,如有差异,请以英文原文为准。
求助全文
约1分钟内获得全文 去求助
来源期刊
Rice Science
Rice Science Agricultural and Biological Sciences-Agronomy and Crop Science
CiteScore
8.90
自引率
6.20%
发文量
55
审稿时长
40 weeks
期刊介绍: Rice Science is an international research journal sponsored by China National Rice Research Institute. It publishes original research papers, review articles, as well as short communications on all aspects of rice sciences in English language. Some of the topics that may be included in each issue are: breeding and genetics, biotechnology, germplasm resources, crop management, pest management, physiology, soil and fertilizer management, ecology, cereal chemistry and post-harvest processing.
期刊最新文献
Appropriate Supply of Ammonium Nitrogen and Ammonium Nitrate Reduces Cadmium Content in Rice Seedlings by Inhibiting Cadmium Uptake and Transport Development of Machine Vision-Based Algorithm for Counting and Discriminating Filled and Unfilled Paddy Rice in Overlapping Mode Biochar Decreases Soil Cadmium (Cd) Availability and Regulates Expression Levels of Cd Uptake/Transport-Related Genes to Reduce Cd Translocation in Rice Next Generation Nutrition: Genomic and Molecular Breeding Innovations for Iron and Zinc Biofortification in Rice Ameliorative Effects of Paclobutrazol via Physio-Biochemical and Molecular Manifestation in Rice under Water Deficit Stress
×
引用
GB/T 7714-2015
复制
MLA
复制
APA
复制
导出至
BibTeX EndNote RefMan NoteFirst NoteExpress
×
×
提示
您的信息不完整,为了账户安全,请先补充。
现在去补充
×
提示
您因"违规操作"
具体请查看互助需知
我知道了
×
提示
现在去查看 取消
×
提示
确定
0
微信
客服QQ
Book学术公众号 扫码关注我们
反馈
×
意见反馈
请填写您的意见或建议
请填写您的手机或邮箱
已复制链接
已复制链接
快去分享给好友吧!
我知道了
×
扫码分享
扫码分享
Book学术官方微信
Book学术文献互助
Book学术文献互助群
群 号:481959085
Book学术
文献互助 智能选刊 最新文献 互助须知 联系我们:info@booksci.cn
Book学术提供免费学术资源搜索服务,方便国内外学者检索中英文文献。致力于提供最便捷和优质的服务体验。
Copyright © 2023 Book学术 All rights reserved.
ghs 京公网安备 11010802042870号 京ICP备2023020795号-1