[{"data":1,"prerenderedAt":-1},["ShallowReactive",2],{"item-3007":3,"related-3007":71},{"id":4,"title":5,"url":6,"summary":7,"summary_zh":8,"content":9,"source_name":10,"source_url":6,"published_at":11,"category":12,"cover_url":9,"hotness":13,"is_selected":14,"score":15,"score_detail":16,"sources":24,"tags":26,"search_phrases":32,"slug":35,"view_count":36,"doi":37,"paper":38,"created_at":70},3007,"Estimation of coffee leaf physiological indicators based on VAG-ViT: A lightweight framework fusing multi-view RGB images and dual-task learning","https:\u002F\u002Fdoi.org\u002F10.1016\u002Fj.compag.2026.112452","Estimation of coffee leaf physiological indicators based on VAG-ViT: A lightweight framework fusing multi-view RGB images and dual-task learning。Computers and Electronics in Agriculture","基于VAG-ViT的咖啡叶片生理指标估测：一种融合多视角RGB图像与双任务学习的轻量级框架。",null,"Computers and Electronics in Agriculture","2026-09-19T00:00:00Z","论文",10,false,77,{"impact":17,"substance":18,"depth":19,"authority":20,"freshness":21,"relevant":22,"comment":23},16,21,17,14,9,1,"提出融合多视图RGB与双任务学习的轻量化ViT框架，用于咖啡叶片生理指标估算，方法新颖且面向经济作物精准管理，具备行业参考价值。",[25],{"name":10,"url":6},[27,28,29,30,31],"智慧农业","农业人工智能","轻量化模型","咖啡种植","多视图图像",[33,34],"咖啡叶片 生理指标 多视图RGB","VAG-ViT 双任务学习","咖啡叶片生理指标多视图RGB-3007",0,"10.1016\u002Fj.compag.2026.112452",{"doi":37,"openalex_id":39,"authors":40,"venue":10,"cited_by_count":36,"oa_url":6,"card":63,"direction":67,"ingested_from":69},"W7213674051",[41,43,45,48,50,52,54,56,58,60],{"name":42,"orcid":9},"Zongyuan Lv",{"name":44,"orcid":9},"Jianping Yang",{"name":46,"orcid":47},"Li Chen","https:\u002F\u002Forcid.org\u002F0000-0002-7006-4443",{"name":49,"orcid":9},"Rongbiao Ji",{"name":51,"orcid":9},"Yadong Li",{"name":53,"orcid":9},"Mengyao Wu",{"name":55,"orcid":9},"Songling Huang",{"name":57,"orcid":9},"Jingyu Yuan",{"name":59,"orcid":9},"Zihao Jiang",{"name":61,"orcid":62},"Tong Li","https:\u002F\u002Forcid.org\u002F0000-0002-3257-213X",{"tldr":64,"method":65,"finding":66,"direction":67,"opportunity":68},"提出VAG-ViT轻量框架，融合多视角RGB图像与双任务学习，估算咖啡叶片生理指标。","多视角RGB图像融合、双任务学习、轻量级ViT框架。","VAG-ViT能有效估算咖啡叶片生理指标，兼顾精度与轻量化。","农业遥感与作物表型","可探索多视角RGB与双任务学习在更多作物生理指标估算中的泛化能力及田间部署。","openalex","2026-09-20T23:30:01.826242Z",{"total":72,"page":22,"page_size":72,"items":73},6,[74,106,134,178,207,233],{"id":75,"title":76,"url":77,"summary":78,"summary_zh":9,"content":9,"source_name":79,"source_url":9,"published_at":80,"category":12,"cover_url":9,"hotness":13,"is_selected":14,"score":81,"score_detail":82,"sources":87,"tags":89,"search_phrases":92,"slug":95,"view_count":36,"doi":9,"paper":96,"created_at":105},3048,"基于双路径注意力与多尺度融合的作物病虫害识别网络DPMFNet","https:\u002F\u002Fwww.mdpi.com\u002F1099-4300\u002F28\u002F9\u002F1032","盐城工学院Hong Zhang、Fagen Song等联合江苏开放大学提出DPMFNet轻量级双路径网络，集成空间-通道双注意力（SCDA）与多尺度深度可分离卷积（MDSC）模块，构建AttMDSCBlock残差结构。在PlantVillage与AI Challenger 2018数据集上DPMFNet仅14.24M参数和2.55G FLOPs，跨注意力机制融合局部细节与全局上下文，轻量化金字塔策略自适应整合多分辨率特征，在复杂农田场景下兼顾精度与可部署性，为嵌入式田间设备提供高性价比方案。","MDPI Entropy 28(9):1032","2026-09-20T00:00:00Z",79,{"impact":17,"substance":83,"depth":84,"authority":85,"freshness":13,"relevant":22,"comment":86},22,18,13,"轻量级双路径注意力网络在两大公开数据集上兼顾精度与可部署性，对嵌入式田间设备落地有实质参考价值。",[88],{"name":79,"url":77},[27,28,90,91,29],"病虫害识别","作物监测",[93,94],"盐城工学院 DPMFNet 病虫害识别","PlantVillage AI Challenger 作物病害","盐城工学院DPMFNet病虫害识别-3048",{"doi":9,"openalex_id":9,"authors":97,"venue":9,"cited_by_count":36,"oa_url":9,"card":98,"direction":102,"ingested_from":104},[],{"tldr":99,"method":100,"finding":101,"direction":102,"opportunity":103},"提出轻量级双路径网络DPMFNet，实现复杂农田场景下的作物病虫害高精度识别。","空间-通道双注意力与多尺度深度可分离卷积，构建AttMDSCBlock残差结构。","仅14.24M参数、2.55G FLOPs，在PlantVillage与AI Challenger ","农业人工智能与决策模型","可探索真实田间多病虫害并发与边缘设备实时推理的轻量化自适应识别研究。","agent","2026-09-21T00:04:39.305757Z",{"id":107,"title":108,"url":109,"summary":110,"summary_zh":9,"content":9,"source_name":111,"source_url":9,"published_at":112,"category":12,"cover_url":9,"hotness":13,"is_selected":14,"score":113,"score_detail":114,"sources":117,"tags":119,"search_phrases":122,"slug":125,"view_count":36,"doi":9,"paper":126,"created_at":133},3046,"基于Flor-YOLO的香石竹鲜切花分级轻量化检测方法","https:\u002F\u002Ffinance.sina.com.cn\u002Froll\u002F2026-09-20\u002Fdoc-inisnssw6528969.shtml","西南林业大学李传孟、杨洁副教授、张晓宇在《智慧农业（中英文）》2026,8(4):85-99发表Flor-YOLO模型，针对香石竹鲜切花开放度人工分级主观性强、效率低问题，以YOLO11n为基线进行骨干网络、下采样方式、检测头结构针对性改进。Flor-YOLO在自建香石竹数据集上mAP@50达到96.10%，较基准模型提升3.25个百分点；模型参数量与计算量分别为1.26M和1.1GFLOPs，同比降低51.2%和82.5%。","智慧农业(中英文)2026,8(4):85-99","2026-09-20T12:26:00Z",83,{"impact":84,"substance":115,"depth":84,"authority":20,"freshness":13,"relevant":22,"comment":116},23,"核心期刊论文，提出轻量化Flor-YOLO模型实现香石竹鲜切花自动分级，数据翔实、方法有创新，对花卉产业智能化有参考价值。",[118],{"name":111,"url":109},[27,28,120,29,121],"花卉产业","鲜切花分级",[123,124],"西南林业大学 香石竹 鲜切花分级","Flor-YOLO 香石竹 检测","西南林业大学香石竹鲜切花分级-3046",{"doi":9,"openalex_id":9,"authors":127,"venue":9,"cited_by_count":36,"oa_url":9,"card":128,"direction":102,"ingested_from":104},[],{"tldr":129,"method":130,"finding":131,"direction":102,"opportunity":132},"提出轻量化Flor-YOLO模型，实现香石竹鲜切花开放度自动分级检测。","以YOLO11n为基线，改进骨干网络、下采样方式与检测头，自建香石竹数据集。","mAP@50达96.10%，较基准提升3.25个百分点，参数量与计算量分别降低51.2%和82.5%","可迁移至其他花卉或果蔬的轻量化分级，并探索边缘设备实时部署与多任务联合检测。","2026-09-21T00:04:39.154232Z",{"id":135,"title":136,"url":137,"summary":138,"summary_zh":139,"content":9,"source_name":140,"source_url":137,"published_at":141,"category":12,"cover_url":9,"hotness":13,"is_selected":14,"score":142,"score_detail":143,"sources":145,"tags":147,"search_phrases":150,"slug":153,"view_count":36,"doi":154,"paper":155,"created_at":177},2646,"IoT-RiceMobileNet: An improved lightweight MobileNetV2 Model for real-time multi-class rice disease detection using IoT","https:\u002F\u002Fdoi.org\u002F10.1371\u002Fjournal.pone.0356383","Early and real-time detection of rice leaf diseases (RLD) poses a significant challenge for farmers, especially in rural regions with limited access to advanced technology. Conventional deep learning models often require substantial computational resources, rendering them impractical for deployment on mobile or edge devices commonly used in agricultural environments. Although models such as ResNet50, VGG16, and InceptionV3 can achieve high accuracy, they are computationally expensive and may be less suitable for real-time deployment in smart agricultural systems. Furthermore, many existing studies rely on limited datasets, which can restrict model generalizability under diverse real-world conditions. Although transfer learning can improve classification performance, developing lightweight models suitable for real-time IoT deployment remains challenging. To address these limitations, we curated a hybrid dataset of 7,092 rice leaf images by combining self-collected and Kaggle samples and proposed IoT-RiceMobileNet, a lightweight improved MobileNetV2-based model that can be effectively integrated into our developed IoT system. The proposed model outperformed transfer learning and deep learning baseline models, achieving 99.19% test accuracy and 99.20% precision while maintaining low computational complexity. We further confirmed model stability using stratified 5-fold and 10-fold cross-validation on both the constructed RLD and multi-source datasets, achieving mean accuracies of 98.04% and 98.13% on the constructed RLD dataset and 98.11% and 98.58% on the multi-source dataset, respectively. Moreover, our models compact size and 85.17 FPS inference speed support real-time deployment. Finally, the model was integrated into an IoT-enabled mobile, web, and cloud-based inference framework, demonstrating its practical potential for scalable rice disease detection in smart agriculture.","水稻叶片病害（RLD）的早期和实时检测对农民而言是一项重大挑战，尤其是在难以获取先进技术的农村地区。传统的深度学习模型通常需要大量计算资源，使其难以在实际农业环境中常用的移动或边缘设备上部署。尽管ResNet50、VGG16和InceptionV3等模型可以达到较高精度，但其计算成本高昂，可能不太适合在智慧农业系统中实时部署。此外，许多现有研究依赖有限的数据集，这可能限制模型在多样化真实条件下的泛化能力。尽管迁移学习可以提升分类性能，但开发适合实时物联网部署的轻量级模型仍具有挑战性。为解决这些局限，我们通过整合自采集样本和Kaggle样本，构建了一个包含7092张水稻叶片图像的混合数据集，并提出了IoT-RiceMobileNet，这是一种基于MobileNetV2改进的轻量级模型，可有效集成到我们开发的物联网系统中。所提出的模型优于迁移学习和深度学习基线模型，在保持低计算复杂度的同时，实现了99.19%的测试准确率和99.20%的精确率。我们进一步通过在构建的RLD数据集和多源数据集上采用分层5折和10折交叉验证确认了模型稳定性，在构建的RLD数据集上分别达到98.04%和98.13%的平均准确率，在多源数据集上分别达到98.11%和98.58%的平均准确率。此外，该模型紧凑的规模和85.17 FPS的推理速度支持实时部署。最后，该模型被集成到一个支持物联网的移动端、网页端和云端推理框架中，展示了其在智慧农业中可扩展水稻病害检测的实际潜力。","PLoS ONE","2026-09-15T00:00:00Z",80,{"impact":84,"substance":83,"depth":84,"authority":85,"freshness":21,"relevant":22,"comment":144},"提出轻量级MobileNetV2水稻病害检测模型并集成物联网推理框架，实测精度与推理速度俱佳，方法新颖、数据规模可观，对边缘端智慧农业落地有参考价值。",[146],{"name":140,"url":137},[27,28,148,149,29],"物联网","水稻病害",[151,152],"农业人工智能 轻量化模型 智慧农业 水稻病害","农业人工智能 轻量化模型","农业人工智能轻量化模型智慧农业水稻病害-2646","10.1371\u002Fjournal.pone.0356383",{"doi":154,"openalex_id":156,"authors":157,"venue":140,"cited_by_count":36,"oa_url":137,"card":171,"direction":175,"ingested_from":69},"W7213328321",[158,160,162,164,166,168],{"name":159,"orcid":9},"Khawja Imran Masud",{"name":161,"orcid":9},"Md Yasin Zihad",{"name":163,"orcid":9},"Mehedi Hasan Shuvo",{"name":165,"orcid":9},"Mst Raonik Jannat",{"name":167,"orcid":9},"Jia Uddin",{"name":169,"orcid":170},"Sahara Ali","https:\u002F\u002Forcid.org\u002F0000-0002-8578-948X",{"tldr":172,"method":173,"finding":174,"direction":175,"opportunity":176},"提出轻量级IoT-RiceMobileNet模型，实现水稻病害实时多类检测。","改进MobileNetV2，融合自采与Kaggle共7092张图像，IoT端部署","测试准确率99.19%，推理速度85.17 FPS，适合边缘设备实时检测。","智慧农业 \u002F 农业物联网","可探索多作物病害泛化、田间复杂光照下轻量模型鲁棒性及边缘联邦学习。","2026-09-16T23:30:12.197386Z",{"id":179,"title":180,"url":181,"summary":182,"summary_zh":9,"content":9,"source_name":183,"source_url":9,"published_at":184,"category":12,"cover_url":9,"hotness":13,"is_selected":14,"score":185,"score_detail":186,"sources":189,"tags":191,"search_phrases":194,"slug":197,"view_count":36,"doi":198,"paper":199,"created_at":206},2399,"Lightweight architecture optimization of YOLOv12n for improved cotton verticillium wilt detection","https:\u002F\u002Fwww.frontiersin.org\u002Farticles\u002F10.3389\u002Ffpls.2026.1822081\u002Ffull","Frontiers in Plant Science 17:1822081（2026）。Ye Zhuang等基于YOLOv12n框架提出轻量精准检测模型YOLO-SCOD。引入StarNet架构作为骨干网；颈网络C3k模块集成通道聚合块；检测头用全维动态卷积替代深度卷积。精度和召回率分别提升至0.960和0.911，mAP50-95提升6.436%；参数量、FLOPs、模型大小分别减少13.728%、20.635%、12.727%，推理速度提升4.167%。","Frontiers in Plant Science | 2026-09","2026-09-08T00:00:00Z",76,{"impact":17,"substance":18,"depth":84,"authority":85,"freshness":187,"relevant":22,"comment":188},8,"基于YOLOv12n的轻量化检测模型在棉花黄萎病识别上兼顾精度与效率，方法新颖、数据扎实，对智慧植保具参考价值。",[190],{"name":183,"url":181},[27,28,192,29,193],"棉花黄萎病","作物病害检测",[195,196],"作物病害检测 农业人工智能 棉花黄萎病 轻量化模型","作物病害检测 农业人工智能","作物病害检测农业人工智能棉花黄萎病轻量化模型-2399","10.3389\u002Ffpls.2026.1822081\u002Ffull",{"doi":198,"openalex_id":9,"authors":200,"venue":9,"cited_by_count":36,"oa_url":9,"card":201,"direction":67,"ingested_from":104},[],{"tldr":202,"method":203,"finding":204,"direction":67,"opportunity":205},"提出轻量模型YOLO-SCOD，实现棉花黄萎病精准检测。","基于YOLOv12n，引入StarNet骨干、C3k模块与全维动态卷积。","精度召回率达0.960和0.911，mAP提升6.436%，模型更轻更快。","可探索轻量模型在移动端或无人机实时病害检测中的部署与泛化。","2026-09-14T00:06:33.263987Z",{"id":208,"title":209,"url":210,"summary":211,"summary_zh":9,"content":9,"source_name":212,"source_url":9,"published_at":213,"category":12,"cover_url":9,"hotness":13,"is_selected":14,"score":15,"score_detail":214,"sources":216,"tags":218,"search_phrases":221,"slug":224,"view_count":36,"doi":9,"paper":225,"created_at":232},2274,"ArXiv 2609.10469 AgroVisNet:轻量化卷积网络及萝卜-马铃薯-葫芦病害诊断基准","https:\u002F\u002Farxiv.org\u002Fabs\u002F2609.10469","提出AgroVisNet紧凑型卷积网络及专家验证基准BD-PlantDX,包含孟加拉国Bogura和Nilphamari地区12类萝卜、土豆、葫芦共12432张田间图像。模型参数仅29万,测试精度99.52%,加权F1 99.52%,部署后量化0.46MB,CPU推理8.40ms\u002F张。","arXiv 2609.10469","2026-09-08T16:00:00Z",{"impact":84,"substance":83,"depth":84,"authority":85,"freshness":72,"relevant":22,"comment":215},"提出29万参数轻量卷积网络与万余张田间病害基准数据集，量化后仅0.46MB、CPU单张8.4ms，对低成本边缘部署的作物病害诊断有实用参考价值。",[217],{"name":212,"url":210},[27,28,219,220,29],"边缘计算","植物病害识别",[222,223],"农业人工智能 植物病害识别 轻量化模型 智慧农业","农业人工智能 植物病害识别","农业人工智能植物病害识别轻量化模型智慧农业-2274",{"doi":9,"openalex_id":9,"authors":226,"venue":9,"cited_by_count":36,"oa_url":9,"card":227,"direction":102,"ingested_from":104},[],{"tldr":228,"method":229,"finding":230,"direction":102,"opportunity":231},"提出轻量卷积网络AgroVisNet及萝卜、马铃薯、葫芦病害诊断基准BD-PlantDX。","构建12432张田间图像基准，设计29万参数紧凑CNN并量化部署。","测试精度99.52%，量化后仅0.46MB，CPU推理8.40ms\u002F张。","可探索跨地区跨作物泛化、田间复杂光照下的轻量模型鲁棒性与边缘部署。","2026-09-13T00:04:05.295687Z",{"id":234,"title":235,"url":236,"summary":237,"summary_zh":9,"content":9,"source_name":238,"source_url":9,"published_at":11,"category":12,"cover_url":9,"hotness":13,"is_selected":14,"score":239,"score_detail":240,"sources":242,"tags":244,"search_phrases":248,"slug":251,"view_count":36,"doi":9,"paper":252,"created_at":259},3047,"基于CNN\u002FLR\u002FGA-BP的辣椒叶病识别稳定性与精度多维度视觉特征比较","https:\u002F\u002Fwww.mdpi.com\u002F2311-7524\u002F12\u002F9\u002F1176","塔里木大学Xueting Ma、Yifei Li等联合东北林业大学、南京农业大学，构建1260份辣椒叶数据集（健康、细菌性斑点病、黄化卷叶病），采用Lab b-channel、RGB super-green、Otsu-ACWE三种分割算法系统评估最优预处理方案，提取32个融合视觉特征并以随机森林消除7个低贡献冗余特征保留25个判别变量。20次独立重复试验表明：CNN测试平均精度97.67%、平均AUC 0.999，稳定性最佳；LR计算成本低适合资源受限场景；GA-BP非线性拟合能力弱、预测波动严重。该研究为辣椒叶病识别提供标准化实验框架。","MDPI Horticulturae 12(9):1176",78,{"impact":17,"substance":83,"depth":84,"authority":20,"freshness":187,"relevant":22,"comment":241},"基于1260份辣椒叶数据集系统比较CNN\u002FLR\u002FGA-BP三种模型，方法规范、结论可靠，对作物病害智能识别有参考价值。",[243],{"name":238,"url":236},[27,28,245,246,247],"图像识别","辣椒叶病","病害诊断",[249,250],"塔里木大学 辣椒叶病 识别","CNN 辣椒叶病 视觉特征","塔里木大学辣椒叶病识别-3047",{"doi":9,"openalex_id":9,"authors":253,"venue":9,"cited_by_count":36,"oa_url":9,"card":254,"direction":102,"ingested_from":104},[],{"tldr":255,"method":256,"finding":257,"direction":102,"opportunity":258},"比较CNN、LR、GA-BP对辣椒叶病的识别精度与稳定性，并评估三种分割预处理方案。","1260份辣椒叶图像，Lab\u002FRGB\u002FOtsu-ACWE分割，32特征经随机森林","CNN平均精度97.67%、AUC 0.999且最稳定；LR成本低适合资源受限；GA-BP波动严重。","可探索轻量化CNN与LR融合的田间实时识别方案，并验证多作物、多病害下的泛化稳定性。","2026-09-21T00:04:39.222838Z"]