[{"data":1,"prerenderedAt":-1},["ShallowReactive",2],{"item-2270":3,"related-2270":75},{"id":4,"title":5,"url":6,"summary":7,"summary_zh":8,"content":8,"source_name":9,"source_url":8,"published_at":10,"category":11,"cover_url":8,"hotness":12,"is_selected":13,"score":14,"score_detail":15,"sources":22,"tags":24,"primary_topic":30,"secondary_topics":36,"classification":37,"search_phrases":59,"slug":62,"view_count":63,"doi":8,"paper":64,"created_at":74},2270,"华中农大实现柑橘黄龙病早期无损诊断 提LLM辅助拉曼光谱相似度融合框架","https:\u002F\u002Fwww.toutiao.com\u002Farticle\u002F7682626369448165922","华中农业大学工学院联合园艺林学学院在Agriculture Communications发表研究,提出LLM辅助的多通道光谱相似度融合框架(LAMSSF),依托少量经qPCR验证的参考样本,实现柑橘HLB早期无损诊断,降低模型对大规模标注数据的依赖。",null,"华中农业大学 Agriculture Communications","2026-09-06T16:00:00Z","论文",10,false,82,{"impact":16,"substance":16,"depth":17,"authority":18,"freshness":19,"relevant":20,"comment":21},22,18,14,6,1,"华中农大提出LLM辅助拉曼光谱融合框架，实现柑橘黄龙病早期无损诊断，方法新颖且降低标注依赖，具备行业推广价值。",[23],{"name":9,"url":6},[25,26,27,28,29],"智慧农业","农业人工智能","病害检测","柑橘","光谱遥感",{"code":31,"slug":32,"name":33,"path":34,"parent_code":35},"B2","fruit","果树","\u002Ftopic\u002Fhorticulture\u002Ffruit","B",[],{"status":38,"locked":13,"version":39,"method":40,"evidence":41},"classified","2026-10-22.2","rules",{"candidates":42,"agricultural_evidence":45},[43,49,54],{"code":31,"score":44,"supported":45,"title":46,"abstract":47,"tags":48},12,true,[28],[28],[28],{"code":50,"score":20,"supported":13,"title":51,"abstract":52,"tags":53},"I1",[],[],[25],{"code":55,"score":20,"supported":13,"title":56,"abstract":57,"tags":58},"I2",[],[],[26],[60,61],"农业人工智能 光谱遥感 智慧农业 病害检测","农业人工智能 光谱遥感","农业人工智能光谱遥感智慧农业病害检测-2270",4,{"doi":8,"openalex_id":8,"authors":65,"venue":8,"cited_by_count":66,"oa_url":8,"card":67,"direction":71,"ingested_from":73},[],0,{"tldr":68,"method":69,"finding":70,"direction":71,"opportunity":72},"提出LLM辅助多通道光谱相似度融合框架，实现柑橘黄龙病早期无损诊断。","拉曼光谱多通道相似度融合，LLM辅助，少量qPCR验证参考样本。","少量标注样本即可实现HLB早期无损诊断，降低对大规模标注数据依赖。","农业人工智能与决策模型","可探索LLM辅助光谱融合在更多作物病害早期诊断中的迁移与少样本泛化能力。","agent","2026-09-13T00:04:04.913308Z",{"total":19,"page":20,"page_size":19,"items":76},[77,130,203,264,336,377],{"id":78,"title":79,"url":80,"summary":81,"summary_zh":8,"content":8,"source_name":82,"source_url":8,"published_at":83,"category":11,"cover_url":8,"hotness":12,"is_selected":13,"score":14,"score_detail":84,"sources":88,"tags":90,"primary_topic":93,"secondary_topics":94,"classification":95,"search_phrases":116,"slug":119,"view_count":120,"doi":8,"paper":121,"created_at":129},3962,"华中农业大学柑橘类果实泛化识别与定位研究——YOLOv8n-Light轻量化部署","https:\u002F\u002Fnews.foodmate.net\u002F2026\u002F10\u002Fwap_754150.html","华中农业大学工学院马京奥、刘洁副教授团队研究YOLOv8n-Light模型在柑橘类果实识别中的应用，模型可同时识别橙、橘、柚三种果实，计算量较原始YOLOv8降低58%，工作站CPU推理速度提升45.9%（达15.35FPS），树莓派4B推理速度提升38.2%（达0.76FPS）；多轴机械臂采摘作业控制中，果实中心坐标X、Y、Z方向平均误差均控制在10mm内，半径误差小于6mm。312次果园采摘测试验证高兼容性与实用性。研究得到国家重点研发计划、国家柑橘产业技术体系资助。","食品伙伴网·2026年10月01日","2026-10-01T00:00:00Z",{"impact":17,"substance":16,"depth":85,"authority":86,"freshness":12,"relevant":20,"comment":87},19,13,"高校团队提出轻量化柑橘识别模型并完成果园实测，方法新颖、数据扎实，对智能采摘装备有参考价值。",[89],{"name":82,"url":80},[25,26,91,28,92],"采摘机器人","轻量化模型",{"code":31,"slug":32,"name":33,"path":34,"parent_code":35},[],{"status":38,"locked":13,"version":39,"method":40,"evidence":96},{"candidates":97,"agricultural_evidence":45},[98,102,107,112],{"code":31,"score":44,"supported":45,"title":99,"abstract":100,"tags":101},[28],[28],[28],{"code":55,"score":103,"supported":13,"title":104,"abstract":105,"tags":106},2,[],[],[26,92],{"code":108,"score":20,"supported":13,"title":109,"abstract":110,"tags":111},"F6",[],[],[91],{"code":50,"score":20,"supported":13,"title":113,"abstract":114,"tags":115},[],[],[25],[117,118],"华中农业大学 柑橘 采摘机器人","YOLOv8n-Light 柑橘识别","华中农业大学柑橘采摘机器人-3962",5,{"doi":8,"openalex_id":8,"authors":122,"venue":8,"cited_by_count":66,"oa_url":8,"card":123,"direction":127,"ingested_from":73},[],{"tldr":124,"method":125,"finding":126,"direction":127,"opportunity":128},"提出YOLOv8n-Light轻量化模型，实现橙橘柚三种柑橘果实泛化识别与定位，并部署于树莓派和采摘","改进YOLOv8n轻量化模型，工作站与树莓派4B部署，多轴机械臂采摘测试312次","计算量降58%，工作站CPU推理15.35FPS，果实中心坐标误差\u003C10mm，半径误差\u003C6mm。","智慧农业 \u002F 农业物联网","可探索多品种泛化模型在边缘设备上的精度-速度权衡，及跨季节、遮挡场景下的鲁棒性提升。","2026-10-02T11:53:16.558461Z",{"id":131,"title":132,"url":133,"summary":134,"summary_zh":135,"content":8,"source_name":136,"source_url":133,"published_at":137,"category":11,"cover_url":8,"hotness":12,"is_selected":13,"score":138,"score_detail":139,"sources":145,"tags":147,"primary_topic":150,"secondary_topics":151,"classification":152,"search_phrases":174,"slug":177,"view_count":103,"doi":178,"paper":179,"created_at":202},2284,"Lightweight nighttime citrus fruit detection in UAV imagery using an enhanced NightNet","https:\u002F\u002Fdoi.org\u002F10.1016\u002Fj.compag.2026.112378","Lightweight nighttime citrus fruit detection in UAV imagery using an enhanced NightNet。Computers and Electronics in Agriculture","基于增强型NightNet的无人机图像轻量化夜间柑橘果实检测。《计算机与电子农业》","Computers and Electronics in Agriculture","2026-09-11T00:00:00Z",77,{"impact":140,"substance":141,"depth":142,"authority":18,"freshness":143,"relevant":20,"comment":144},16,21,17,9,"核心期刊论文，提出轻量化夜间柑橘检测方法，方法新颖且面向无人机夜间作业场景，具备细分领域参考价值。",[146],{"name":136,"url":133},[25,148,26,149,28],"无人机","遥感",{"code":31,"slug":32,"name":33,"path":34,"parent_code":35},[],{"status":38,"locked":13,"version":39,"method":40,"evidence":153},{"candidates":154,"agricultural_evidence":45},[155,161,165,169],{"code":31,"score":156,"supported":45,"title":157,"abstract":159,"tags":160},15,[158],"citrus",[28,158],[28],{"code":50,"score":20,"supported":13,"title":162,"abstract":163,"tags":164},[],[],[25],{"code":55,"score":20,"supported":13,"title":166,"abstract":167,"tags":168},[],[],[26],{"code":170,"score":20,"supported":13,"title":171,"abstract":172,"tags":173},"I3",[],[],[149],[175,176],"农业人工智能 智慧农业 无人机 柑橘","农业人工智能 智慧农业","农业人工智能智慧农业无人机柑橘-2284","10.1016\u002Fj.compag.2026.112378",{"doi":178,"openalex_id":180,"authors":181,"venue":136,"cited_by_count":66,"oa_url":8,"card":195,"direction":199,"ingested_from":201},"W7212284586",[182,184,187,189,191,193],{"name":183,"orcid":8},"Zhixian Wu",{"name":185,"orcid":186},"Juntao Xiong","https:\u002F\u002Forcid.org\u002F0000-0002-1095-812X",{"name":188,"orcid":8},"Zhen Liu",{"name":190,"orcid":8},"Sitong Li",{"name":192,"orcid":8},"Jingru Peng",{"name":194,"orcid":8},"Sidi Chen",{"tldr":196,"method":197,"finding":198,"direction":199,"opportunity":200},"提出增强NightNet实现无人机夜间柑橘果实轻量检测。","基于NightNet改进的轻量网络，用于无人机夜间图像。","增强NightNet在夜间无人机图像中实现轻量且准确的柑橘检测。","农业遥感与作物表型","夜间无人机果实检测的轻量化与低照度增强可进一步结合多光谱或时序信息。","openalex","2026-09-13T23:30:02.020275Z",{"id":204,"title":205,"url":206,"summary":207,"summary_zh":208,"content":8,"source_name":209,"source_url":206,"published_at":210,"category":11,"cover_url":8,"hotness":12,"is_selected":13,"score":211,"score_detail":212,"sources":215,"tags":217,"primary_topic":220,"secondary_topics":221,"classification":222,"search_phrases":243,"slug":246,"view_count":247,"doi":248,"paper":249,"created_at":263},1382,"Instance Segmentation and Multi-Object Tracking for Fruit Quality Grading and Dynamic Yield Estimation in Egyptian Citrus Orchards","https:\u002F\u002Fdoi.org\u002F10.1016\u002Fj.atech.2026.102529","Egypt ranks among the world’s leading citrus producers and exporters; however, orchard operations remain constrained by subjective, labor-intensive manual quality grading and time-consuming yield estimation that require specialized expertise. This study presents an AI-driven orchard-intelligence framework for automated fruit quality grading and dynamic yield estimation under the unstructured conditions of Egyptian orange farms. To address the lack of in-field public datasets, a domain-specific instance-segmentation dataset of 618 original pixel-level annotated images, expanded to 1,545 augmented training images, and 15 videos was constructed. This dataset was used to benchmark single-stage segmentation models (YOLOv8, YOLOv11) against a two-stage (Mask R-CNN), alongside a transformer-based bounding-box detection (RT-DETR), under dense canopy occlusion, clustered fruit instances, and variable natural illumination. Each fine-tuned model was evaluated across two stages: static quality grading and dynamic yield estimation. For static grading (Good vs. Defective), YOLOv11l ranked among the top tier of evaluated segmenters, reaching mean Average Precision (mAP) of 0.932 with balanced precision-recall behavior, while maintaining real-time feasibility at 26.1 ms per image. For dynamic yield estimation, a multi-object tracking pipeline was implemented using BoT-SORT with camera-motion compensation and a virtual line-crossing counting mechanism. The evaluation reveals a three-way dissociation: the highest-mAP static segmenter (YOLOv11l), the best dynamic total counter (RT-DETR, WMAPE = 5.66%, despite the lowest box-level static accuracy), and the best quality-resolved dynamic grader (YOLOv11s, WMAPE = 6.97% at 14.2 ms per frame) are three different systems; RT-DETR did not resolve fruit quality reliably under motion. Counting accuracy and grading capability are thus separable properties requiring separate evaluation. Overall, the framework enables objective fruit quality assessment and actionable in-field fruit counting to support harvest logistics and labor planning, providing a practical foundation for smart agriculture in the Egyptian citrus sector.","埃及位居全球领先的柑橘生产国和出口国之列；然而，果园作业仍受制于主观性强、劳动密集的人工质量分级以及耗时且需专业技能的产量估算。本研究提出了一种人工智能驱动的果园智能框架，用于在埃及橙园的非结构化条件下实现自动化果实质量分级和动态产量估算。为解决田间公开数据集缺乏的问题，构建了一个领域特定的实例分割数据集，包含618张原始像素级标注图像，扩充至1545张增强训练图像，以及15段视频。该数据集用于在密集树冠遮挡、果实簇生和自然光照多变条件下，对单阶段分割模型（YOLOv8、YOLOv11）与两阶段模型（Mask R-CNN）进行基准测试，同时对比基于Transformer的边界框检测模型（RT-DETR）。每个微调模型均经过两个阶段的评估：静态质量分级和动态产量估算。在静态分级（优质与缺陷）中，YOLOv11l在评估的分割模型中位居前列，平均精度（mAP）达到0.932，精确率与召回率表现均衡，同时以每张图像26.1毫秒的处理速度保持实时可行性。在动态产量估算方面，采用基于BoT-SORT的多目标跟踪流程，结合相机运动补偿和虚拟线跨越计数机制。评估结果揭示了三重分离现象：静态分割精度最高的模型（YOLOv11l）、动态总数计数最优的模型（RT-DETR，加权平均绝对百分比误差WMAPE = 5.66%，尽管其框级静态精度最低），以及质量分辨动态分级最佳的模型（YOLOv11s，每帧14.2毫秒时WMAPE = 6.97%）是三个不同的系统；RT-DETR在运动条件下无法可靠分辨果实质量。因此，计数精度和分级能力是可分离的属性，需要分别评估。总体而言，该框架实现了客观的果实质量评估和可操作的田间果实计数，以支持采收物流和劳动力规划，为埃及柑橘产业的智慧农业提供了实用基础。","Smart Agricultural Technology","2026-09-01T00:00:00Z",79,{"impact":17,"substance":16,"depth":85,"authority":86,"freshness":213,"relevant":20,"comment":214},7,"针对埃及柑橘园提出AI驱动的品质分级与动态产量估算框架，方法新颖且数据详实，对智慧农业有参考价值。",[216],{"name":209,"url":206},[25,26,218,28,219],"目标检测","产量估算",{"code":31,"slug":32,"name":33,"path":34,"parent_code":35},[],{"status":38,"locked":13,"version":39,"method":40,"evidence":223},{"candidates":224,"agricultural_evidence":45},[225,230,235,239],{"code":31,"score":17,"supported":45,"title":226,"abstract":227,"tags":229},[158],[28,228,158],"orchard",[28],{"code":50,"score":213,"supported":45,"title":231,"abstract":232,"tags":234},[],[25,233],"smart agriculture",[25],{"code":55,"score":103,"supported":13,"title":236,"abstract":237,"tags":238},[],[],[26,218],{"code":170,"score":20,"supported":13,"title":240,"abstract":241,"tags":242},[],[],[219],[244,245],"农业人工智能 产量估算 智慧农业 目标检测","农业人工智能 产量估算","农业人工智能产量估算智慧农业目标检测-1382",3,"10.1016\u002Fj.atech.2026.102529",{"doi":248,"openalex_id":250,"authors":251,"venue":209,"cited_by_count":66,"oa_url":206,"card":258,"direction":127,"ingested_from":201},"W7204959516",[252,254,256],{"name":253,"orcid":8},"Saleh A. Farhoud",{"name":255,"orcid":8},"Yasmine A. Zaghloul",{"name":257,"orcid":8},"Omar M. Shehata",{"tldr":259,"method":260,"finding":261,"direction":127,"opportunity":262},"构建柑橘果园AI框架，实现果实质量分级与动态产量估计，并评估多种分割与跟踪模型。","构建实例分割数据集，微调YOLOv8\u002Fv11、Mask R-CNN、RT-DET","静态分级最优为YOLOv11l，动态计数最优为RT-DETR，质量动态分级最优为YOLOv11s，计","可探索多任务协同优化，如设计统一模型同时满足静态分级与动态计数，或引入时序信息提升运动场景下的质量分级鲁棒性。","2026-09-02T23:30:04.506009Z",{"id":265,"title":266,"url":267,"summary":268,"summary_zh":269,"content":8,"source_name":270,"source_url":267,"published_at":271,"category":11,"cover_url":8,"hotness":12,"is_selected":13,"score":272,"score_detail":273,"sources":276,"tags":278,"primary_topic":282,"secondary_topics":283,"classification":284,"search_phrases":310,"slug":313,"view_count":66,"doi":314,"paper":315,"created_at":335},5401,"A HIERARCHICAL DISTRIBUTED EDGE AI FRAMEWORK FOR REAL-TIME APPLE LEAF DISEASE CLASSIFICATION","https:\u002F\u002Fdoi.org\u002F10.22190\u002Ffuacr260506002g","The application of artificial intelligence (AI) in agriculture has transformed crop management, particularly in the detection of plant diseases. Apple trees, a key agricultural commodity, are vulnerable to various diseases, which can severely impact crop yields. Traditional disease detection methods, often reliant on manual inspections, are time-consuming and prone to error. In response, this study proposes a novel two-stage edge AI framework for apple leaf disease classification that integrates RGB imagery with distributed edge computing. The first stage performs binary classification to distinguish between healthy and diseased leaves, achieving an F1 score of 95.50%. This optimization is achieved by utilizing lightweight models on edge devices, thereby enhancing computational efficiency. The second stage employs a consensus-based multiclass classification approach, achieving a 96.44% F1 score in identifying specific diseases. This dual-stage system, supported by an edge AI architecture, ensures real-time disease detection while minimizing resource consumption and enhancing scalability in large-scale agricultural environments. The full system achieved a 95.50% accuracy and F1 score on the special dataset. The results demonstrate the system’s efficacy in controlled laboratory conditions, offering a promising solution for precise, real-time agricultural monitoring. This study underscores the potential of distributed edge AI systems for scalable and efficient disease detection in precision agriculture.","人工智能（AI）在农业中的应用已深刻改变了作物管理方式，尤其是在植物病害检测方面。苹果树作为重要的农业经济作物，易受多种病害侵袭，严重影响作物产量。传统的病害检测方法通常依赖人工检查，耗时且易出错。为此，本研究提出了一种新颖的两阶段边缘AI框架，用于苹果叶片病害分类，该框架将RGB图像与分布式边缘计算相结合。第一阶段执行二分类以区分健康叶片与患病叶片，F1分数达到95.50%。该优化通过在边缘设备上采用轻量级模型实现，从而提升了计算效率。第二阶段采用基于共识的多类分类方法，在识别具体病害方面F1分数达到96.44%。该双阶段系统在边缘AI架构的支持下，实现了实时病害检测，同时最大限度地降低了资源消耗，并增强了在大规模农业环境中的可扩展性。完整系统在专用数据集上达到了95.50%的准确率和F1分数。结果表明，该系统在受控实验室条件下具有有效性，为精准、实时的农业监测提供了一种有前景的解决方案。本研究凸显了分布式边缘AI系统在精准农业中实现可扩展且高效病害检测的潜力。","Facta Universitatis Series Automatic Control and Robotics","2026-10-18T00:00:00Z",76,{"impact":17,"substance":141,"depth":142,"authority":44,"freshness":274,"relevant":20,"comment":275},8,"该研究提出两级边缘AI框架，在苹果叶片病害识别上取得95%以上F1值，方法新颖、数据可靠，对精准农业实时监测有参考价值，但尚处实验室验证阶段，产业影响有限。",[277],{"name":270,"url":267},[25,26,279,280,281],"边缘计算","作物病害识别","苹果病害",{"code":31,"slug":32,"name":33,"path":34,"parent_code":35},[],{"status":38,"locked":13,"version":39,"method":40,"evidence":285},{"candidates":286,"agricultural_evidence":45},[287,293,299,305],{"code":31,"score":17,"supported":45,"title":288,"abstract":290,"tags":292},[289],"apple",[33,291,289],"苹果",[281],{"code":50,"score":213,"supported":45,"title":294,"abstract":295,"tags":298},[],[296,297],"精准农业","precision agriculture",[25],{"code":300,"score":213,"supported":45,"title":301,"abstract":302,"tags":304},"I5",[],[279,303],"edge computing",[279],{"code":55,"score":120,"supported":45,"title":306,"abstract":307,"tags":309},[],[308],"artificial intelligence",[280,26],[311,312],"苹果叶片病害 边缘AI","分布式边缘计算 病害分类","苹果叶片病害边缘AI-5401","10.22190\u002Ffuacr260506002g",{"doi":314,"openalex_id":316,"authors":317,"venue":270,"cited_by_count":66,"oa_url":267,"card":330,"direction":71,"ingested_from":201},"W7222964752",[318,321,324,327],{"name":319,"orcid":320},"Milan Grujev","https:\u002F\u002Forcid.org\u002F0009-0002-3211-6844",{"name":322,"orcid":323},"Dragan H. Stojanovic","https:\u002F\u002Forcid.org\u002F0000-0003-4893-3814",{"name":325,"orcid":326},"Miloš Ilić","https:\u002F\u002Forcid.org\u002F0000-0002-9696-2874",{"name":328,"orcid":329},"Aleksandar Milosavljević","https:\u002F\u002Forcid.org\u002F0000-0003-3057-7727",{"tldr":331,"method":332,"finding":333,"direction":127,"opportunity":334},"提出两级边缘AI框架，用RGB图像实时分类苹果叶片病害。","分布式边缘计算+轻量模型，先二分类再共识多分类。","两级系统准确率与F1均达95.50%，多分类F1为96.44%。","仅在受控实验室验证，可延伸至田间复杂光照与多作物泛化及边缘能耗优化。","2026-10-20T23:30:33.830748Z",{"id":337,"title":338,"url":339,"summary":340,"summary_zh":8,"content":8,"source_name":341,"source_url":8,"published_at":342,"category":11,"cover_url":8,"hotness":12,"is_selected":13,"score":343,"score_detail":344,"sources":346,"tags":348,"primary_topic":352,"secondary_topics":353,"classification":354,"search_phrases":365,"slug":368,"view_count":66,"doi":8,"paper":369,"created_at":376},5297,"高志永团队《基于特征优选与优化算法的干热河谷区柑橘蒸腾模拟》","https:\u002F\u002Fwww.sohu.com\u002Fa\u002F1087305323_122014422","《智慧农业(中英文)》2026年第8卷第4期刊载云南农业大学吴明清、高志永等团队论文,以10年生柑橘树为研究对象收集2020—2022年树干液流与环境因子数据;针对干热河谷加快建设智慧灌区背景下传统机理模型参数需求高、对部分参数高度敏感且误差来源复杂等难题,提出基于特征优选与优化算法的蒸腾模拟方法,可为优化灌区水分调控与配水策略提供决策支撑。","智慧农业(中英文)(2026,8(4))","2026-10-13T00:00:00Z",72,{"impact":140,"substance":141,"depth":142,"authority":86,"freshness":120,"relevant":20,"comment":345},"核心期刊论文，方法有创新且数据规模扎实，对干热河谷智慧灌区水分调控有决策参考价值，但属细分领域研究，时效性一般。",[347],{"name":341,"url":339},[25,349,28,350,351],"云南","智慧灌区","蒸腾模拟",{"code":31,"slug":32,"name":33,"path":34,"parent_code":35},[],{"status":38,"locked":13,"version":39,"method":40,"evidence":355},{"candidates":356,"agricultural_evidence":45},[357,361],{"code":31,"score":44,"supported":45,"title":358,"abstract":359,"tags":360},[28],[28],[28],{"code":50,"score":63,"supported":45,"title":362,"abstract":363,"tags":364},[],[25],[25],[366,367],"云南农业大学 柑橘 蒸腾模拟","干热河谷 智慧灌区","云南农业大学柑橘蒸腾模拟-5297",{"doi":8,"openalex_id":8,"authors":370,"venue":8,"cited_by_count":66,"oa_url":8,"card":371,"direction":127,"ingested_from":73},[],{"tldr":372,"method":373,"finding":374,"direction":127,"opportunity":375},"用特征优选与优化算法模拟干热河谷区柑橘蒸腾。","基于2020—2022年树干液流与环境因子数据构建特征优选与优化算法模型。","该方法可降低机理模型参数依赖与敏感性，提升蒸腾模拟精度。","可探索将蒸腾模拟嵌入智慧灌区实时配水决策，研究多树种迁移与边缘部署。","2026-10-19T00:07:48.135945Z",{"id":378,"title":379,"url":380,"summary":381,"summary_zh":8,"content":8,"source_name":382,"source_url":8,"published_at":383,"category":11,"cover_url":8,"hotness":12,"is_selected":13,"score":384,"score_detail":385,"sources":388,"tags":390,"primary_topic":393,"secondary_topics":394,"classification":395,"search_phrases":415,"slug":418,"view_count":66,"doi":8,"paper":419,"created_at":426},5130,"DefoliationCAM:面向葡萄藤食叶严重度实时评估的边缘AI系统 [预印本]","https:\u002F\u002Farxiv.org\u002Fabs\u002F2610.20879","Fuchen Li等提出DefoliationCAM(D-CAM),一种太阳能供电的边缘AI系统,用于估算葡萄藤树冠食叶程度并通过LoRa将结果传输至Web仪表盘。流水线使用YOLOX-Nano在4K图像中定位葡萄藤主干,并使用基于MobileNet的轻量级通道注意力分类器对320×320像素的斑块进行分类。29,674个田间采集斑块被标注为背景或四种损伤等级之一;合并中度和重度类别将类别不平衡比从约40:1降至8.8:1。合成增强使macro-F1从0.768提升至0.838。分类器以更少的参数量(1.08M vs 23.52M)在macro-F1上优于ResNet-50。利用TensorRT FP16在NVIDIA Jetson Orin Nano上每张4K图像处理时间约1.5秒,完整运行周期57-60秒。两台设备为期五周的田间部署验证了自主太阳能运行、LoRa通信和远程食叶监测的可行性。","arXiv 2610.20879 2026 年 10 月 14 日","2026-10-14T00:00:00Z",75,{"impact":140,"substance":16,"depth":17,"authority":386,"freshness":274,"relevant":20,"comment":387},11,"预印本提出太阳能边缘AI系统，实现葡萄藤食叶严重度实时评估与LoRa远程监测，方法新颖、数据规模大、田间验证充分，具智慧农业应用价值。",[389],{"name":382,"url":380},[25,26,279,391,392],"葡萄藤","病害评估",{"code":31,"slug":32,"name":33,"path":34,"parent_code":35},[],{"status":38,"locked":13,"version":39,"method":40,"evidence":396},{"candidates":397,"agricultural_evidence":45},[398,403,407,411],{"code":31,"score":386,"supported":45,"title":399,"abstract":401,"tags":402},[400],"葡萄",[400],[],{"code":50,"score":20,"supported":13,"title":404,"abstract":405,"tags":406},[],[],[25],{"code":55,"score":20,"supported":13,"title":408,"abstract":409,"tags":410},[],[],[26],{"code":300,"score":20,"supported":13,"title":412,"abstract":413,"tags":414},[],[],[279],[416,417],"DefoliationCAM 葡萄藤 食叶","Jetson Orin Nano 边缘AI 葡萄","DefoliationCAM葡萄藤食叶-5130",{"doi":8,"openalex_id":8,"authors":420,"venue":8,"cited_by_count":66,"oa_url":8,"card":421,"direction":127,"ingested_from":73},[],{"tldr":422,"method":423,"finding":424,"direction":127,"opportunity":425},"提出太阳能边缘AI系统DefoliationCAM，实时评估葡萄藤食叶严重度并远程传输。","YOLOX-Nano定位主干，MobileNet通道注意力分类，TensorRT","轻量分类器macro-F1达0.838，优于ResNet-50，田间部署验证可行。","可探索多作物迁移、损伤等级细化及边缘模型自适应更新以提升泛化性。","2026-10-17T00:13:44.932340Z"]