[{"data":1,"prerenderedAt":-1},["ShallowReactive",2],{"item-5401":3,"related-5401":103},{"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,"primary_topic":32,"secondary_topics":38,"classification":39,"search_phrases":73,"slug":76,"view_count":77,"doi":78,"paper":79,"created_at":102},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。",null,"Facta Universitatis Series Automatic Control and Robotics","2026-10-18T00:00:00Z","论文",10,false,76,{"impact":17,"substance":18,"depth":19,"authority":20,"freshness":21,"relevant":22,"comment":23},18,21,17,12,8,1,"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。",[25],{"name":10,"url":6},[27,28,29,30,31],"智慧农业","农业人工智能","边缘计算","作物病害识别","苹果病害",{"code":33,"slug":34,"name":35,"path":36,"parent_code":37},"B2","fruit","果树","\u002Ftopic\u002Fhorticulture\u002Ffruit","B",[],{"status":40,"locked":14,"version":41,"method":42,"evidence":43},"classified","2026-10-22.2","rules",{"candidates":44,"agricultural_evidence":46},[45,52,60,66],{"code":33,"score":17,"supported":46,"title":47,"abstract":49,"tags":51},true,[48],"apple",[35,50,48],"苹果",[31],{"code":53,"score":54,"supported":46,"title":55,"abstract":56,"tags":59},"I1",7,[],[57,58],"精准农业","precision agriculture",[27],{"code":61,"score":54,"supported":46,"title":62,"abstract":63,"tags":65},"I5",[],[29,64],"edge computing",[29],{"code":67,"score":68,"supported":46,"title":69,"abstract":70,"tags":72},"I2",5,[],[71],"artificial intelligence",[30,28],[74,75],"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",0,"10.22190\u002Ffuacr260506002g",{"doi":78,"openalex_id":80,"authors":81,"venue":10,"cited_by_count":77,"oa_url":6,"card":94,"direction":100,"ingested_from":101},"W7222964752",[82,85,88,91],{"name":83,"orcid":84},"Milan Grujev","https:\u002F\u002Forcid.org\u002F0009-0002-3211-6844",{"name":86,"orcid":87},"Dragan H. Stojanovic","https:\u002F\u002Forcid.org\u002F0000-0003-4893-3814",{"name":89,"orcid":90},"Miloš Ilić","https:\u002F\u002Forcid.org\u002F0000-0002-9696-2874",{"name":92,"orcid":93},"Aleksandar Milosavljević","https:\u002F\u002Forcid.org\u002F0000-0003-3057-7727",{"tldr":95,"method":96,"finding":97,"direction":98,"opportunity":99},"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%。","智慧农业 \u002F 农业物联网","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。","农业人工智能与决策模型","openalex","2026-10-20T23:30:33.830748Z",{"total":104,"page":22,"page_size":104,"items":105},6,[106,159,221,274,332,403],{"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":119,"tags":121,"primary_topic":124,"secondary_topics":125,"classification":126,"search_phrases":146,"slug":149,"view_count":77,"doi":9,"paper":150,"created_at":158},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":115,"substance":116,"depth":17,"authority":117,"freshness":21,"relevant":22,"comment":118},16,22,11,"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。",[120],{"name":111,"url":109},[27,28,29,122,123],"葡萄藤","病害评估",{"code":33,"slug":34,"name":35,"path":36,"parent_code":37},[],{"status":40,"locked":14,"version":41,"method":42,"evidence":127},{"candidates":128,"agricultural_evidence":46},[129,134,138,142],{"code":33,"score":117,"supported":46,"title":130,"abstract":132,"tags":133},[131],"葡萄",[131],[],{"code":53,"score":22,"supported":14,"title":135,"abstract":136,"tags":137},[],[],[27],{"code":67,"score":22,"supported":14,"title":139,"abstract":140,"tags":141},[],[],[28],{"code":61,"score":22,"supported":14,"title":143,"abstract":144,"tags":145},[],[],[29],[147,148],"DefoliationCAM 葡萄藤 食叶","Jetson Orin Nano 边缘AI 葡萄","DefoliationCAM葡萄藤食叶-5130",{"doi":9,"openalex_id":9,"authors":151,"venue":9,"cited_by_count":77,"oa_url":9,"card":152,"direction":98,"ingested_from":157},[],{"tldr":153,"method":154,"finding":155,"direction":98,"opportunity":156},"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。","agent","2026-10-17T00:13:44.932340Z",{"id":160,"title":161,"url":162,"summary":163,"summary_zh":164,"content":9,"source_name":165,"source_url":162,"published_at":166,"category":12,"cover_url":9,"hotness":167,"is_selected":14,"score":168,"score_detail":169,"sources":172,"tags":176,"primary_topic":178,"secondary_topics":179,"classification":185,"search_phrases":202,"slug":205,"view_count":22,"doi":206,"paper":207,"created_at":220},4241,"Detection of Apple Plant Diseases Using Leaf Images through Convolutional Neural Network","https:\u002F\u002Fdoi.org\u002F10.5281\u002Fzenodo.23142591","Plant diseases have major social, ecological and economic impact on agriculture and frequently results in large financial losses for farmers. Therefore early and precise disease detection is crucial for efficient crop management. The severity of leaf diseases and their direct impact on yield quality have been highlighted in recent studies. Both digital cameras and flatbed scanners can be used to take leaf images but they have certain drawbacks. Although scanners offer a more secure and regulated method of acquiring images they are comparatively slow and may cause edge shadows. This study uses a hybrid deep learning approach to identify diseases in apple plant leaves. To improve classification performance; the proposed approach combines the advantages of Residual Networks (ResNet), Genetic Algorithms (GA) and Convolutional Neural Networks (CNN). CNNs are used to extract features and classify diseases whereas ResNet enhances the learning efficiency of deeper networks. The feature set is optimized using a genetic algorithm which improves accuracy and lowers computational complexity. The model also calculates the percentage of the leaf area that is impacted. According to experimental results the proposed method detects leaf diseases with high accuracy of percentage and low computational cost making it a dependable and effective precision agriculture solution. The proposed model exhibited strong classification efficiency across various leaf conditions that pertaining an accuracy of 0.97 for healthy leaves, 0.994 for apple scab, 0.89 for rust, and 0.91 for powdery mildew.","植物病害对农业产生重大的社会、生态和经济影响，并经常给农民带来巨大的经济损失。因此，早期且精确的病害检测对于高效的作物管理至关重要。近期研究强调了叶部病害的严重程度及其对产量品质的直接影响。数码相机和平板扫描仪均可用于拍摄叶片图像，但它们各有一定缺陷。尽管扫描仪提供了更安全、更可控的图像获取方式，但其速度相对较慢，且可能产生边缘阴影。本研究采用混合深度学习方法识别苹果植株叶部病害。为提高分类性能，所提方法结合了残差网络（ResNet）、遗传算法（GA）和卷积神经网络（CNN）的优势。CNN用于提取特征并分类病害，而ResNet增强了更深网络的学习效率。利用遗传算法对特征集进行优化，从而提高准确率并降低计算复杂度。该模型还计算了受影响的叶面积百分比。实验结果表明，所提方法以高准确率和低计算成本检测叶部病害，使其成为可靠且有效的精准农业解决方案。所提模型在多种叶片条件下均表现出较强的分类效率，健康叶片准确率为0.97，苹果黑星病为0.994，锈病为0.89，白粉病为0.91。","Zenodo (CERN European Organization for Nuclear Research)","2026-10-04T00:00:00Z",25,67,{"impact":20,"substance":17,"depth":115,"authority":20,"freshness":170,"relevant":22,"comment":171},9,"基于ResNet+GA+CNN的苹果叶病识别研究，准确率数据具体，方法有增量，但属实验室论文，产业影响有限。",[173,174],{"name":165,"url":162},{"name":165,"url":175},"https:\u002F\u002Fdoi.org\u002F10.5281\u002Fzenodo.23142592",[27,28,177,57,31],"深度学习",{"code":33,"slug":34,"name":35,"path":36,"parent_code":37},[180],{"code":67,"slug":181,"name":182,"path":183,"parent_code":184},"agricultural-ai","农业AI与大模型","\u002Ftopic\u002Fdigital-agriculture\u002Fagricultural-ai","I",{"status":40,"locked":14,"version":41,"method":42,"evidence":186},{"candidates":187,"agricultural_evidence":46},[188,193,197],{"code":33,"score":189,"supported":46,"title":190,"abstract":191,"tags":192},15,[48],[50,48],[31],{"code":53,"score":21,"supported":46,"title":194,"abstract":195,"tags":196},[],[57,58],[27,57],{"code":67,"score":21,"supported":46,"title":198,"abstract":199,"tags":201},[],[177,200],"deep learning",[28,177],[203,204],"苹果叶片病害 卷积神经网络","苹果锈病 白粉病 识别","苹果叶片病害卷积神经网络-4241","10.5281\u002Fzenodo.23142591",{"doi":206,"openalex_id":208,"authors":209,"venue":165,"cited_by_count":77,"oa_url":162,"card":214,"direction":219,"ingested_from":101},"W7219637192",[210,212],{"name":211,"orcid":9},"Mohd Arshad Raza",{"name":213,"orcid":9},"Kiran Pandey",{"tldr":215,"method":216,"finding":217,"direction":100,"opportunity":218},"提出ResNet+GA+CNN混合模型，用苹果叶片图像检测病害并计算病斑面积占比。","ResNet提取深层特征，遗传算法优化特征集，CNN分类，苹果叶片图像数据。","健康叶、黑星病、锈病、白粉病准确率分别达0.97、0.994、0.89、0.91，计算成本低。","可探索轻量化模型在田间移动端实时检测，并融合多病害严重度分级与产量损失预测。","数字乡村与农业信息化","2026-10-05T23:30:30.830366Z",{"id":222,"title":223,"url":224,"summary":225,"summary_zh":226,"content":9,"source_name":227,"source_url":224,"published_at":228,"category":12,"cover_url":9,"hotness":13,"is_selected":14,"score":229,"score_detail":230,"sources":233,"tags":235,"primary_topic":237,"secondary_topics":238,"classification":239,"search_phrases":255,"slug":258,"view_count":259,"doi":260,"paper":261,"created_at":273},3019,"PSPE-UNet: Projection-based Similarity Prototype Embedding UNet for Apple Leaf Disease Segmentation","https:\u002F\u002Fdoi.org\u002F10.22266\u002Fijies2026.1031.18","Apple leaf disease segmentation plays a significant role in precision agriculture by enabling the accurate identification and localization of infected regions at the pixel level.However, diverse apple leaf diseases exhibit similar symptoms, such as overlapping lesions makes it challenging to distinguish between various disease classes.In this research, a Projection-based Similarity Prototype Embedding UNet (PSPE-UNet) is proposed to segment apple leaf diseases.Employing a projection head with a similarity prototype embedding in UNet enhances feature discrimination by mapping pixel-level representations into a normalized embedding space.This ensures better separation between healthy and disease regions, even when the regions exhibit similar texture and chromatic characteristics.Three learnable prototypes corresponding to healthy, disease, and boundary regions are used.The boundary prototype act as learnable auxiliary feature prototype within the auxiliary boundary branch to compute boundary probability map during training while disease prediction is based on healthy and disease prototypes.In addition, this method enhances the boundary delineation for irregular and small lesions by refining the feature alignment.Hence, the proposed PSPE-UNet achieves a high Pixel Accuracy (PA) of 98.96%, which is compared to existing methods such as the AS-DeepLabV3+ on the Apple Tree Leaf Disease Segmentation Dataset (ATLDSD).Moreover, proposed PSPE-UNet obtains an inference time of 0.0217s per batch (8 images), corresponding to 0.0027s per image on ATLDSD dataset compared to traditional methods like UNet.","苹果叶片病害分割在精准农业中具有重要意义，能够在像素级别上准确识别和定位感染区域。然而，不同苹果叶片病害表现出相似的症状，例如病灶重叠使得区分不同病害类别具有挑战性。本研究提出了一种基于投影的相似性原型嵌入UNet（PSPE-UNet）用于苹果叶片病害分割。在UNet中采用带有相似性原型嵌入的投影头，通过将像素级表示映射到归一化嵌入空间来增强特征判别能力。这确保了健康和病害区域之间更好的分离，即使这些区域表现出相似的纹理和色彩特征。使用三个可学习原型分别对应健康、病害和边界区域。边界原型在辅助边界分支中作为可学习辅助特征原型，在训练期间计算边界概率图，而病害预测则基于健康和病害原型。此外，该方法通过细化特征对齐增强了对不规则和小病灶的边界描绘。因此，所提出的PSPE-UNet在苹果树叶病害分割数据集（ATLDSD）上达到了98.96%的高像素精度（PA），并与现有方法如AS-DeepLabV3+进行了比较。此外，所提出的PSPE-UNet在ATLDSD数据集上获得了每批次（8张图像）0.0217秒的推理时间，相当于每张图像0.0027秒，与UNet等传统方法相比具有优势。","International journal of intelligent engineering and systems","2026-09-19T00:00:00Z",70,{"impact":20,"substance":231,"depth":19,"authority":20,"freshness":170,"relevant":22,"comment":232},20,"提出基于相似度原型嵌入的UNet分割方法，在苹果叶病害数据集上取得98.96%像素精度，方法新颖、数据明确，但属细分算法研究，产业影响有限。",[234],{"name":227,"url":224},[27,28,57,236,31],"图像分割",{"code":33,"slug":34,"name":35,"path":36,"parent_code":37},[],{"status":40,"locked":14,"version":41,"method":42,"evidence":240},{"candidates":241,"agricultural_evidence":46},[242,246,250],{"code":33,"score":17,"supported":46,"title":243,"abstract":244,"tags":245},[48],[35,50,48],[31],{"code":53,"score":21,"supported":46,"title":247,"abstract":248,"tags":249},[],[57,58],[27,57],{"code":67,"score":251,"supported":14,"title":252,"abstract":253,"tags":254},2,[],[],[28,236],[256,257],"PSPE-UNet 苹果叶病害 分割","苹果叶病害 数据集 ATLDSD","PSPE-UNet苹果叶病害分割-3019",3,"10.22266\u002Fijies2026.1031.18",{"doi":260,"openalex_id":262,"authors":263,"venue":227,"cited_by_count":77,"oa_url":224,"card":268,"direction":100,"ingested_from":101},"W7213634285",[264,266],{"name":265,"orcid":9},"Vedamurthy Hadavanahalli Kumaraiah",{"name":267,"orcid":9},"Shrinivasacharya Purohit",{"tldr":269,"method":270,"finding":271,"direction":100,"opportunity":272},"提出PSPE-UNet，用投影相似原型嵌入分割苹果叶片病害区域。","UNet+投影头+可学习原型（健康\u002F病害\u002F边界），ATLDSD数据集。","像素精度98.96%，单图推理0.0027秒，优于AS-DeepLabV3+和UNet。","可探索原型嵌入在相似症状多病害区分及轻量化边缘部署中的泛化能力。","2026-09-20T23:30:34.933307Z",{"id":275,"title":276,"url":277,"summary":278,"summary_zh":279,"content":9,"source_name":280,"source_url":277,"published_at":281,"category":12,"cover_url":9,"hotness":13,"is_selected":14,"score":282,"score_detail":283,"sources":286,"tags":288,"primary_topic":290,"secondary_topics":291,"classification":293,"search_phrases":308,"slug":311,"view_count":68,"doi":312,"paper":313,"created_at":331},2910,"Precision Diagnosis of Apple Leaf Diseases Across Infection Stages via Web-Based Analysis","https:\u002F\u002Fdoi.org\u002F10.1007\u002Fs11119-026-10451-5","Abstract Purpose Throughout the growing season, leaf diseases pose a huge risk to apple fruit yield and quality. While early detection targets timely intervention, understanding disease progression across different stages is essential for effective treatment and resistance breeding. Methods This study proposes a deep learning-based detection system that identifies apple leaf diseases at various infection stages in real-world environments. Most existing methods have focused on disease detection in controlled conditions, while the developed system operates in complex field settings with variable lighting and background noise. Two YOLOv8-based variants integrated with a multi-head self-attention (MHSA) module were developed to improve detection of dense, tiny, and feature-similar lesions. In addition, a web-based interactive tool was built by combining the Segment Anything Model (SAM) with the detection model to support leaf isolation, disease localization, infection estimation, severity categorization, and automatic report generation. Results The training results on proposed PA-ALeaf dataset demonstrated that YOLOv8-MHSA_b_h varaint achieved the highest performance (Precision 60.5%, mAP50 56.3%, F1 confidence 56.0%), while maintaining real-time inference (12.38 ms per image), compared to state-of-the-art models. Conclusion By bridging practical disease monitoring and scientific research, our system offers a comprehensive, scalable solution for apple leaf disease detection in real-world orchards. This system could benefit both farmers by enabling multi-stage intervention and researchers by providing insights into disease progression.","摘要 目的 在整个生长季中，叶片病害对苹果果实产量和品质构成巨大风险。虽然早期检测有助于及时干预，但了解病害在不同阶段的进展对于有效治疗和抗性育种至关重要。方法 本研究提出了一种基于深度学习的检测系统，可在真实环境中识别不同感染阶段的苹果叶片病害。现有大多数方法侧重于受控条件下的病害检测，而所开发的系统可在光照变化和背景噪声复杂的田间环境中运行。研究开发了两种基于YOLOv8的变体，并集成了多头自注意力（MHSA）模块，以提高对密集、微小和特征相似病斑的检测能力。此外，通过将分割一切模型（SAM）与检测模型相结合，构建了一个基于网络的交互式工具，以支持叶片分离、病害定位、感染估计、严重程度分类和自动报告生成。结果 在所提出的PA-ALeaf数据集上的训练结果表明，与最先进的模型相比，YOLOv8-MHSA_b_h变体取得了最高性能（精确率60.5%，mAP50 56.3%，F1置信度56.0%），同时保持实时推理（每张图像12.38 ms）。结论 通过连接实际病害监测与科学研究，我们的系统为真实果园中的苹果叶片病害检测提供了一种全面、可扩展的解决方案。该系统既可使农民受益，实现多阶段干预，也可为研究人员提供病害进展的见解。","Precision Agriculture","2026-09-18T00:00:00Z",80,{"impact":17,"substance":116,"depth":17,"authority":284,"freshness":21,"relevant":22,"comment":285},14,"提出面向真实果园的多阶段苹果叶病检测系统并配套网页工具，方法新颖、数据与性能指标明确，对智慧植保具有参考价值。",[287],{"name":280,"url":277},[27,28,177,289,31],"病害识别",{"code":33,"slug":34,"name":35,"path":36,"parent_code":37},[292],{"code":67,"slug":181,"name":182,"path":183,"parent_code":184},{"status":40,"locked":14,"version":41,"method":42,"evidence":294},{"candidates":295,"agricultural_evidence":46},[296,300,304],{"code":33,"score":189,"supported":46,"title":297,"abstract":298,"tags":299},[48],[50,48],[31],{"code":67,"score":170,"supported":46,"title":301,"abstract":302,"tags":303},[],[177,200],[28,177,289],{"code":53,"score":22,"supported":14,"title":305,"abstract":306,"tags":307},[],[],[27],[309,310],"苹果叶部病害 深度学习 识别","YOLOv8 苹果病害 检测","苹果叶部病害深度学习识别-2910","10.1007\u002Fs11119-026-10451-5",{"doi":312,"openalex_id":314,"authors":315,"venue":280,"cited_by_count":77,"oa_url":277,"card":326,"direction":100,"ingested_from":101},"W7213537759",[316,318,321,323],{"name":317,"orcid":9},"Kangrui Han",{"name":319,"orcid":320},"Hao Cai","https:\u002F\u002Forcid.org\u002F0000-0002-9879-2960",{"name":322,"orcid":9},"Kari Peter",{"name":324,"orcid":325},"Long He","https:\u002F\u002Forcid.org\u002F0000-0001-9781-6062",{"tldr":327,"method":328,"finding":329,"direction":100,"opportunity":330},"提出基于YOLOv8-MHSA与SAM的网页系统，实现苹果叶片病害多感染阶段实时检测与分级。","YOLOv8+多头自注意力，结合SAM分割，构建PA-ALeaf数据集与网页工具","YOLOv8-MHSA_b_h变体精度60.5%、mAP50 56.3%，单图推理12.38ms，可","可探索轻量化模型在移动端的部署，并融合时序数据预测病害发展轨迹。","2026-09-19T23:30:03.474350Z",{"id":333,"title":334,"url":335,"summary":336,"summary_zh":337,"content":9,"source_name":338,"source_url":335,"published_at":339,"category":12,"cover_url":9,"hotness":13,"is_selected":14,"score":340,"score_detail":341,"sources":345,"tags":347,"primary_topic":350,"secondary_topics":351,"classification":352,"search_phrases":372,"slug":375,"view_count":376,"doi":377,"paper":378,"created_at":402},2499,"Real-time on-tree Korla pear grading with a shared ordinal–anomaly descriptor field","https:\u002F\u002Fdoi.org\u002F10.1016\u002Fj.compag.2026.112371","On-tree grading of Korla fragrant pears couples two decisions of different nature: a gradual Grade-A\u002FGrade-B appearance transition and a Grade-C surface-defect judgement, both made under illumination change, occlusion and scale variation. Detectors that treat the fruit as a single class, and graders that place the three grades on one flat classification axis, optimise a small A\u002FB deviation and an A\u002FC defect error through the same geometry and leave no explicit account of what ordinal and defect information each spatial location should preserve. We address this by adding an explicit ordinal–anomaly descriptor field to the shared feature hierarchy. A shallow module generates three channels – ordinal tendency, defect tendency and foreground confidence – that condition four downstream detector stages, and a hierarchical head converts the two kinds of evidence into normalised grade probabilities. On the orchard-disjoint KPR-3 dataset (3826 images, 12,458 instances, three commercial orchards), the model reaches 94.0% mAP@50 and 92.6% matched-instance grade accuracy, and lowers the unsafe-pick rate from 4.8% to 2.1%. On a Jetson Orin Nano at 15 W, the INT8 engine runs at 93.1% mAP@50 and sustains 42 FPS of end-to-end pipelined throughput. Monocular sensing remains a key limitation under severe front–back fruit overlap.","库尔勒香梨的树上分级耦合了两个性质不同的决策：渐变的A级\u002FB级外观过渡，以及C级表面缺陷判定，二者均在光照变化、遮挡和尺度变化下做出。将果实视为单一类别的检测器，以及将三个等级置于同一扁平分类轴上的分级器，通过相同的几何结构优化较小的A\u002FB偏差和A\u002FC缺陷误差，却未明确说明每个空间位置应保留何种序数信息和缺陷信息。我们通过在共享特征层级中增加一个显式的序数–异常描述符场来解决这一问题。一个浅层模块生成三个通道——序数倾向、缺陷倾向和前景置信度——用以调节四个下游检测器阶段，一个层级式头部将两类证据转换为归一化等级概率。在果园不相交的KPR-3数据集（3826幅图像、12458个实例、三个商业果园）上，模型达到94.0% mAP@50和92.6%的匹配实例等级准确率，并将不安全采摘率从4.8%降至2.1%。在15 W的Jetson Orin Nano上，INT8引擎以93.1% mAP@50运行，并维持42 FPS的端到端流水线吞吐量。在严重前后果实重叠情况下，单目感知仍是主要局限。","Computers and Electronics in Agriculture","2026-09-14T00:00:00Z",83,{"impact":17,"substance":342,"depth":343,"authority":284,"freshness":170,"relevant":22,"comment":344},23,19,"提出序数-异常描述子场的树上香梨实时分级方法，在自建KPR-3数据集与Jetson边缘端验证，方法新颖、数据扎实，对果园采摘机器人有直接参考价值。",[346],{"name":338,"url":335},[27,28,29,348,349],"库尔勒香梨","水果分级",{"code":33,"slug":34,"name":35,"path":36,"parent_code":37},[],{"status":40,"locked":14,"version":41,"method":42,"evidence":353},{"candidates":354,"agricultural_evidence":46},[355,360,364,368],{"code":33,"score":259,"supported":46,"title":356,"abstract":357,"tags":359},[],[358],"orchard",[],{"code":53,"score":22,"supported":14,"title":361,"abstract":362,"tags":363},[],[],[27],{"code":67,"score":22,"supported":14,"title":365,"abstract":366,"tags":367},[],[],[28],{"code":61,"score":22,"supported":14,"title":369,"abstract":370,"tags":371},[],[],[29],[373,374],"农业人工智能 库尔勒香梨 智慧农业 水果分级","农业人工智能 库尔勒香梨","农业人工智能库尔勒香梨智慧农业水果分级-2499",4,"10.1016\u002Fj.compag.2026.112371",{"doi":377,"openalex_id":379,"authors":380,"venue":338,"cited_by_count":77,"oa_url":335,"card":397,"direction":98,"ingested_from":101},"W7212908812",[381,383,386,388,390,392,394],{"name":382,"orcid":9},"Bingyu Cao",{"name":384,"orcid":385},"Peng Zhou","https:\u002F\u002Forcid.org\u002F0000-0002-6345-5307",{"name":387,"orcid":9},"Zhikai Yang",{"name":389,"orcid":9},"Wei Chen",{"name":391,"orcid":9},"Yingchao Wang",{"name":393,"orcid":9},"Mingqi Kan",{"name":395,"orcid":396},"Haiyong Chen","https:\u002F\u002Forcid.org\u002F0000-0002-5262-4208",{"tldr":398,"method":399,"finding":400,"direction":98,"opportunity":401},"提出共享序数-异常描述子场，实现树上库尔勒香梨实时分级。","在共享特征层级加入序数、缺陷、前景三通道描述子，用KPR-3数据集训练。","mAP@50达94.0%，分级准确率92.6%，不安全采摘率从4.8%降至2.1%。","可探索多模态或深度传感融合，解决严重前后遮挡下的单目感知局限。","2026-09-15T23:30:01.440708Z",{"id":404,"title":405,"url":406,"summary":407,"summary_zh":9,"content":9,"source_name":408,"source_url":9,"published_at":409,"category":12,"cover_url":9,"hotness":13,"is_selected":14,"score":282,"score_detail":410,"sources":413,"tags":415,"primary_topic":418,"secondary_topics":419,"classification":420,"search_phrases":445,"slug":448,"view_count":259,"doi":9,"paper":449,"created_at":456},2490,"Lightweight Detection of Blueberries at Different Maturity Stages in Complex Orchard Environments(YOLOv12n+SHSA2C2f+知识蒸馏)","https:\u002F\u002Fwww.mdpi.com\u002F2077-0472\u002F16\u002F18\u002F1949","云南农业大学大数据学院联合云南省农业大数据工程技术研究中心 2026 年 9 月 10 日在《Agriculture》发表。针对小果、密集、遮挡、色彩过渡细微等复杂田间条件下的蓝莓成熟期检测难题,构建 4680 图像 60573 标注框田间数据集,重新设计 YOLOv12n 的 P3\u002FP4\u002FP5 检测结构为 P2\u002FP3\u002FP4 架构,引入轻量化 SHSA2C2f 单头自注意力特征增强模块,DINOv3 (ViT-S\u002F16) 引导的非对称知识蒸馏。精度导向 M4 模型 mAP@0.5 达 92.68%±0.04%、mAP@0.5:0.95 86.38%±0.10%,参数量仅 0.79 M;经 TensorRT FP16 转换后保留 92.75% mAP@0.5,可在 Jetson Orin Nano 上以 15.9 FPS 运行。","MDPI Agriculture 2026-09-10","2026-09-09T16:00:00Z",{"impact":17,"substance":342,"depth":17,"authority":411,"freshness":21,"relevant":22,"comment":412},13,"面向复杂果园的蓝莓成熟期轻量化检测研究，方法新颖、数据规模扎实且给出边缘部署实测性能，具备较高专业参考价值。",[414],{"name":408,"url":406},[27,28,29,416,417],"目标检测","蓝莓",{"code":33,"slug":34,"name":35,"path":36,"parent_code":37},[],{"status":40,"locked":14,"version":41,"method":42,"evidence":421},{"candidates":422,"agricultural_evidence":46},[423,427,433,437,441],{"code":33,"score":170,"supported":46,"title":424,"abstract":425,"tags":426},[358],[],[417],{"code":428,"score":259,"supported":46,"title":429,"abstract":430,"tags":432},"I6",[],[431],"农业大数据",[],{"code":67,"score":251,"supported":14,"title":434,"abstract":435,"tags":436},[],[],[28,416],{"code":53,"score":22,"supported":14,"title":438,"abstract":439,"tags":440},[],[],[27],{"code":61,"score":22,"supported":14,"title":442,"abstract":443,"tags":444},[],[],[29],[446,447],"农业人工智能 智慧农业 目标检测 边缘计算","农业人工智能 智慧农业","农业人工智能智慧农业目标检测边缘计算-2490",{"doi":9,"openalex_id":9,"authors":450,"venue":9,"cited_by_count":77,"oa_url":9,"card":451,"direction":100,"ingested_from":157},[],{"tldr":452,"method":453,"finding":454,"direction":100,"opportunity":455},"提出轻量YOLOv12n改进模型，实现复杂果园中多成熟期蓝莓的实时检测。","4680张田间图像数据集，P2\u002FP3\u002FP4结构、SHSA2C2f模块与DINOv","M4模型mAP@0.5达92.68%，仅0.79M参数，Jetson Orin Nano上15.9 ","可探索多作物通用轻量检测框架，或结合成熟度计数用于产量预测与采摘决策。","2026-09-15T00:04:27.061523Z"]