用于田间马铃薯病害识别的有效无监督领域适应技术

IF 4.4 1区 农林科学 Q1 AGRICULTURAL ENGINEERING Biosystems Engineering Pub Date : 2024-10-23 DOI:10.1016/j.biosystemseng.2024.10.005
Xueze Gao , Quan Feng , Shuzhi Wang , Jianhua Zhang , Sen Yang
{"title":"用于田间马铃薯病害识别的有效无监督领域适应技术","authors":"Xueze Gao ,&nbsp;Quan Feng ,&nbsp;Shuzhi Wang ,&nbsp;Jianhua Zhang ,&nbsp;Sen Yang","doi":"10.1016/j.biosystemseng.2024.10.005","DOIUrl":null,"url":null,"abstract":"<div><div>Accurate disease recognition through computer vision is crucial for the intelligent management of potato production. Popular data-driven classification methods face challenges including limited labelled data and poor model portability. Unsupervised Domain Adaptation (UDA) addresses these challenges with a novel learning strategy. However, the complex field environment introduces a significant domain shift problem due to varying conditions. Existing UDA methods usually concentrate on aligning global data distribution and employ a single structure for disease feature extraction, thereby limiting their efficacy in true field environment. To tackle this challenge of potato disease recognition, the Multi-Representation Adaptive Network (MRSAN) based on subdomain alignment is presented. MRSAN effectively aligns feature distributions across diverse data by minimising distribution differences among relevant subdomains. Simultaneously, the multi-representation extraction method captures finer details from various perspectives in the disease images. The combination of these two approaches efficiently mitigates the adverse effects caused by various interference factors in field environment. Based on the acquisition conditions of light variation and disease progression, two field potato disease image datasets are created, containing five and six kinds of potato leaf disease, respectively. Extensive transfer experiments are conducted on the two datasets. MRSAN achieves average classification accuracies of 87.03% and 80.06% on the datasets for the corresponding transfer tasks, outperforming the other compared methods. This not only validates the effectiveness of MRSAN but also demonstrates its robust ability to generalise across changes in regard to light variation and disease progression.</div></div>","PeriodicalId":9173,"journal":{"name":"Biosystems Engineering","volume":"247 ","pages":"Pages 267-282"},"PeriodicalIF":4.4000,"publicationDate":"2024-10-23","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":"0","resultStr":"{\"title\":\"An effective unsupervised domain adaptation for in-field potato disease recognition\",\"authors\":\"Xueze Gao ,&nbsp;Quan Feng ,&nbsp;Shuzhi Wang ,&nbsp;Jianhua Zhang ,&nbsp;Sen Yang\",\"doi\":\"10.1016/j.biosystemseng.2024.10.005\",\"DOIUrl\":null,\"url\":null,\"abstract\":\"<div><div>Accurate disease recognition through computer vision is crucial for the intelligent management of potato production. Popular data-driven classification methods face challenges including limited labelled data and poor model portability. Unsupervised Domain Adaptation (UDA) addresses these challenges with a novel learning strategy. However, the complex field environment introduces a significant domain shift problem due to varying conditions. Existing UDA methods usually concentrate on aligning global data distribution and employ a single structure for disease feature extraction, thereby limiting their efficacy in true field environment. To tackle this challenge of potato disease recognition, the Multi-Representation Adaptive Network (MRSAN) based on subdomain alignment is presented. MRSAN effectively aligns feature distributions across diverse data by minimising distribution differences among relevant subdomains. Simultaneously, the multi-representation extraction method captures finer details from various perspectives in the disease images. The combination of these two approaches efficiently mitigates the adverse effects caused by various interference factors in field environment. Based on the acquisition conditions of light variation and disease progression, two field potato disease image datasets are created, containing five and six kinds of potato leaf disease, respectively. Extensive transfer experiments are conducted on the two datasets. MRSAN achieves average classification accuracies of 87.03% and 80.06% on the datasets for the corresponding transfer tasks, outperforming the other compared methods. This not only validates the effectiveness of MRSAN but also demonstrates its robust ability to generalise across changes in regard to light variation and disease progression.</div></div>\",\"PeriodicalId\":9173,\"journal\":{\"name\":\"Biosystems Engineering\",\"volume\":\"247 \",\"pages\":\"Pages 267-282\"},\"PeriodicalIF\":4.4000,\"publicationDate\":\"2024-10-23\",\"publicationTypes\":\"Journal Article\",\"fieldsOfStudy\":null,\"isOpenAccess\":false,\"openAccessPdf\":\"\",\"citationCount\":\"0\",\"resultStr\":null,\"platform\":\"Semanticscholar\",\"paperid\":null,\"PeriodicalName\":\"Biosystems Engineering\",\"FirstCategoryId\":\"97\",\"ListUrlMain\":\"https://www.sciencedirect.com/science/article/pii/S1537511024002307\",\"RegionNum\":1,\"RegionCategory\":\"农林科学\",\"ArticlePicture\":[],\"TitleCN\":null,\"AbstractTextCN\":null,\"PMCID\":null,\"EPubDate\":\"\",\"PubModel\":\"\",\"JCR\":\"Q1\",\"JCRName\":\"AGRICULTURAL ENGINEERING\",\"Score\":null,\"Total\":0}","platform":"Semanticscholar","paperid":null,"PeriodicalName":"Biosystems Engineering","FirstCategoryId":"97","ListUrlMain":"https://www.sciencedirect.com/science/article/pii/S1537511024002307","RegionNum":1,"RegionCategory":"农林科学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":null,"EPubDate":"","PubModel":"","JCR":"Q1","JCRName":"AGRICULTURAL ENGINEERING","Score":null,"Total":0}
引用次数: 0

摘要

通过计算机视觉准确识别病害对于马铃薯生产的智能化管理至关重要。流行的数据驱动分类方法面临着标签数据有限和模型可移植性差等挑战。无监督领域适应(UDA)通过一种新颖的学习策略解决了这些难题。然而,由于条件不同,复杂的田间环境带来了严重的领域转移问题。现有的无监督领域适应方法通常集中于调整全局数据分布,并采用单一结构进行病害特征提取,因此限制了其在真实田间环境中的功效。为了应对马铃薯病害识别的这一挑战,提出了基于子域对齐的多呈现自适应网络(MRSAN)。MRSAN 通过最大限度地减少相关子域之间的分布差异,有效地调整了不同数据的特征分布。同时,多重呈现提取方法还能从疾病图像的不同角度捕捉更精细的细节。这两种方法的结合可有效缓解现场环境中各种干扰因素造成的不利影响。根据光照变化和病害发展的采集条件,创建了两个田间马铃薯病害图像数据集,分别包含五种和六种马铃薯叶片病害。在这两个数据集上进行了广泛的转移实验。在相应的转移任务中,MRSAN 在数据集上取得了 87.03% 和 80.06% 的平均分类准确率,优于其他比较方法。这不仅验证了 MRSAN 的有效性,还证明了它在不同光照变化和疾病进展情况下的强大泛化能力。
本文章由计算机程序翻译,如有差异,请以英文原文为准。
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
An effective unsupervised domain adaptation for in-field potato disease recognition
Accurate disease recognition through computer vision is crucial for the intelligent management of potato production. Popular data-driven classification methods face challenges including limited labelled data and poor model portability. Unsupervised Domain Adaptation (UDA) addresses these challenges with a novel learning strategy. However, the complex field environment introduces a significant domain shift problem due to varying conditions. Existing UDA methods usually concentrate on aligning global data distribution and employ a single structure for disease feature extraction, thereby limiting their efficacy in true field environment. To tackle this challenge of potato disease recognition, the Multi-Representation Adaptive Network (MRSAN) based on subdomain alignment is presented. MRSAN effectively aligns feature distributions across diverse data by minimising distribution differences among relevant subdomains. Simultaneously, the multi-representation extraction method captures finer details from various perspectives in the disease images. The combination of these two approaches efficiently mitigates the adverse effects caused by various interference factors in field environment. Based on the acquisition conditions of light variation and disease progression, two field potato disease image datasets are created, containing five and six kinds of potato leaf disease, respectively. Extensive transfer experiments are conducted on the two datasets. MRSAN achieves average classification accuracies of 87.03% and 80.06% on the datasets for the corresponding transfer tasks, outperforming the other compared methods. This not only validates the effectiveness of MRSAN but also demonstrates its robust ability to generalise across changes in regard to light variation and disease progression.
求助全文
通过发布文献求助,成功后即可免费获取论文全文。 去求助
来源期刊
Biosystems Engineering
Biosystems Engineering 农林科学-农业工程
CiteScore
10.60
自引率
7.80%
发文量
239
审稿时长
53 days
期刊介绍: Biosystems Engineering publishes research in engineering and the physical sciences that represent advances in understanding or modelling of the performance of biological systems for sustainable developments in land use and the environment, agriculture and amenity, bioproduction processes and the food chain. The subject matter of the journal reflects the wide range and interdisciplinary nature of research in engineering for biological systems.
期刊最新文献
Optimisation design and experimental analysis of rotary blade reinforcing ribs using DEM-FEM techniques Guidelines for mechanical weeding: Developing weed control lines through point extraction at maize root zones Evaluation of water distribution and uniformity of sprinkler irrigation based on harmonic analysis and finite element method A vibration-based machine learning approach for roller gap detection in biomass pellet production Relative contributions of respiration and transpiration to the weight loss of russet-type potatoes
×
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