[{"data":1,"prerenderedAt":-1},["ShallowReactive",2],{"item-2283":3,"related-2283":83},{"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":9,"secondary_topics":32,"classification":33,"search_phrases":57,"slug":60,"view_count":61,"doi":62,"paper":63,"created_at":82},2283,"Fruit-OIC: An anti-occlusion flower and fruit detection algorithm for dragon fruit using dynamic case mining and global feature enhancement","https:\u002F\u002Fdoi.org\u002F10.1016\u002Fj.compag.2026.112414","Fruit-OIC: An anti-occlusion flower and fruit detection algorithm for dragon fruit using dynamic case mining and global feature enhancement。Computers and Electronics in Agriculture","Fruit-OIC：一种基于动态案例挖掘与全局特征增强的火龙果抗遮挡花果检测算法。",null,"Computers and Electronics in Agriculture","2026-09-11T00:00:00Z","论文",10,false,75,{"impact":17,"substance":18,"depth":19,"authority":20,"freshness":21,"relevant":22,"comment":23},16,20,17,14,8,1,"核心期刊论文，提出动态案例挖掘与全局特征增强的抗遮挡花果检测算法，方法新颖、结论可靠，对果园智能采摘与产量监测有实用价值。",[25],{"name":10,"url":6},[27,28,29,30,31],"智慧农业","农业人工智能","目标检测","果园管理","火龙果",[],{"status":34,"locked":14,"version":35,"method":36,"evidence":37},"unclassified","2026-10-22.2","rules",{"candidates":38,"agricultural_evidence":55,"reason":56},[39,45,50],{"code":40,"score":41,"supported":14,"title":42,"abstract":43,"tags":44},"I2",2,[],[],[28,29],{"code":46,"score":22,"supported":14,"title":47,"abstract":48,"tags":49},"B2",[],[],[31],{"code":51,"score":22,"supported":14,"title":52,"abstract":53,"tags":54},"I1",[],[],[27],true,"缺少足够的主题证据",[58,59],"农业人工智能 智慧农业 果园管理 目标检测","农业人工智能 智慧农业","农业人工智能智慧农业果园管理目标检测-2283",4,"10.1016\u002Fj.compag.2026.112414",{"doi":62,"openalex_id":64,"authors":65,"venue":10,"cited_by_count":74,"oa_url":9,"card":75,"direction":79,"ingested_from":81},"W7212275801",[66,68,70,72],{"name":67,"orcid":9},"Wentao Huang",{"name":69,"orcid":9},"Peilin Yao",{"name":71,"orcid":9},"Bin Han",{"name":73,"orcid":9},"Xiaoshuan Zhang",0,{"tldr":76,"method":77,"finding":78,"direction":79,"opportunity":80},"提出抗遮挡的火龙果花果检测算法Fruit-OIC，结合动态案例挖掘与全局特征增强。","动态案例挖掘与全局特征增强，用于火龙果花果检测。","Fruit-OIC能有效提升遮挡场景下火龙果花果的检测性能。","农业人工智能与决策模型","可探索动态案例挖掘与全局特征增强在其他果园遮挡场景的泛化应用。","openalex","2026-09-13T23:30:01.950106Z",{"total":84,"page":22,"page_size":84,"items":85},6,[86,139,202,266,333,370],{"id":87,"title":88,"url":89,"summary":90,"summary_zh":9,"content":9,"source_name":91,"source_url":9,"published_at":92,"category":12,"cover_url":9,"hotness":13,"is_selected":14,"score":93,"score_detail":94,"sources":98,"tags":100,"primary_topic":9,"secondary_topics":102,"classification":103,"search_phrases":126,"slug":129,"view_count":84,"doi":9,"paper":130,"created_at":138},4158,"基于改进YOLOv8的火龙果采摘机器人系统设计与研究","https:\u002F\u002Fm.chinaaet.com\u002Farticle\u002F3000180728","刘爱华、支铁山（电子技术应用\u002F集成电路应用2026-09-28；广西物流职业技术学院、广西自然资源职业技术学院）。提出针对火龙果采摘的改进YOLOv8算法：1）在主干网络中引入可变形卷积增强对不规则形状果实的特征提取；2）设计高效多尺度注意力模块强化遮挡果物的上下文建模；3）优化检测头结构提升边界框回归精度。同时设计轻量化采摘机械臂与柔性末端执行器，构建完整的机器人系统并开展田间验证（深度信息计算采摘点三维坐标、电液比例升降平台调整高度、六自由度机械臂移动）。","电子技术应用·2026-09-28","2026-09-28T00:00:00Z",68,{"impact":95,"substance":18,"depth":19,"authority":96,"freshness":84,"relevant":22,"comment":97},12,13,"论文提出改进YOLOv8检测算法并构建火龙果采摘机器人系统，方法有创新且经田间验证，但属细分作物技术进展，公共影响有限。",[99],{"name":91,"url":89},[27,28,29,101,31],"采摘机器人",[],{"status":104,"locked":14,"version":35,"method":36,"evidence":105},"needs_review",{"candidates":106,"agricultural_evidence":14,"reason":125},[107,113,117,121],{"code":108,"score":109,"supported":55,"title":110,"abstract":111,"tags":112},"F6",9,[101],[],[101],{"code":40,"score":41,"supported":14,"title":114,"abstract":115,"tags":116},[],[],[28,29],{"code":46,"score":22,"supported":14,"title":118,"abstract":119,"tags":120},[],[],[31],{"code":51,"score":22,"supported":14,"title":122,"abstract":123,"tags":124},[],[],[27],"农业相关性需要复核",[127,128],"火龙果采摘机器人 YOLOv8","广西物流职业技术学院 火龙果","火龙果采摘机器人YOLOv8-4158",{"doi":9,"openalex_id":9,"authors":131,"venue":9,"cited_by_count":74,"oa_url":9,"card":132,"direction":79,"ingested_from":137},[],{"tldr":133,"method":134,"finding":135,"direction":79,"opportunity":136},"提出改进YOLOv8火龙果检测算法并集成六自由度采摘机器人系统，完成田间验证。","可变形卷积、多尺度注意力、优化检测头，结合深度相机与柔性末端执行器。","改进算法提升不规则与遮挡果实检测精度，机器人系统实现采摘点定位与自动采摘。","可探索多果实遮挡下的实时检测与采摘路径规划协同优化，并拓展至其他藤本作物。","agent","2026-10-04T00:09:10.086989Z",{"id":140,"title":141,"url":142,"summary":143,"summary_zh":9,"content":9,"source_name":144,"source_url":142,"published_at":145,"category":12,"cover_url":9,"hotness":13,"is_selected":14,"score":146,"score_detail":147,"sources":151,"tags":153,"primary_topic":155,"secondary_topics":160,"classification":161,"search_phrases":179,"slug":182,"view_count":183,"doi":184,"paper":185,"created_at":201},3808,"Orchard worker detection using spatial-context attention on 2D LiDAR data","https:\u002F\u002Fdoi.org\u002F10.1016\u002Fj.biosystemseng.2026.104604","Orchard worker detection using spatial-context attention on 2D LiDAR data。Biosystems Engineering","Biosystems Engineering","2026-09-30T00:00:00Z",79,{"impact":17,"substance":148,"depth":149,"authority":20,"freshness":13,"relevant":22,"comment":150},21,18,"提出基于二维激光雷达与空间上下文注意力的果园工人检测方法，属农业人工智能与智能农机细分领域的方法创新，具备一定专业参考价值。",[152],{"name":144,"url":142},[27,28,29,30,154],"激光雷达",{"code":46,"slug":156,"name":157,"path":158,"parent_code":159},"fruit","果树","\u002Ftopic\u002Fhorticulture\u002Ffruit","B",[],{"status":162,"locked":14,"version":35,"method":36,"evidence":163},"classified",{"candidates":164,"agricultural_evidence":55},[165,171,175],{"code":46,"score":166,"supported":55,"title":167,"abstract":169,"tags":170},11,[168],"orchard",[168],[],{"code":40,"score":41,"supported":14,"title":172,"abstract":173,"tags":174},[],[],[28,29],{"code":51,"score":22,"supported":14,"title":176,"abstract":177,"tags":178},[],[],[27],[180,181],"2D LiDAR 果园 工人检测","农业人工智能 智慧农业 果园管理 激光雷达","2DLiDAR果园工人检测-3808",3,"10.1016\u002Fj.biosystemseng.2026.104604",{"doi":184,"openalex_id":186,"authors":187,"venue":144,"cited_by_count":74,"oa_url":142,"card":9,"direction":9,"ingested_from":81},"W7214801786",[188,190,192,195,198],{"name":189,"orcid":9},"Jintack Jeon",{"name":191,"orcid":9},"Huijong Chung",{"name":193,"orcid":194},"Gookhwan Kim","https:\u002F\u002Forcid.org\u002F0000-0002-7278-3476",{"name":196,"orcid":197},"Yong–Joo Kim","https:\u002F\u002Forcid.org\u002F0000-0002-1212-9018",{"name":199,"orcid":200},"Dae-Hyun Lee","https:\u002F\u002Forcid.org\u002F0000-0001-9544-5974","2026-09-30T23:30:05.310491Z",{"id":203,"title":204,"url":205,"summary":206,"summary_zh":9,"content":9,"source_name":207,"source_url":9,"published_at":208,"category":12,"cover_url":9,"hotness":13,"is_selected":14,"score":209,"score_detail":210,"sources":212,"tags":214,"primary_topic":217,"secondary_topics":223,"classification":229,"search_phrases":253,"slug":256,"view_count":74,"doi":9,"paper":257,"created_at":265},5532,"精准棉花病害管理：融合无人机影像与定制YOLO深度学习框架","https:\u002F\u002Farxiv.org\u002Fabs\u002F2610.24182","研究提出单阶段全卷积检测器Cotton-Vision，融合幽灵瓶颈通道注意力与跨阶段部分融合三项轻量化设计，参数减少20%。在巴基斯坦旁遮普省7个棉田采集的2700余幅高分辨率无人机影像上测试，精确率97.7%、召回率77.7%、mAP@50为85.6%，较主流基线提升10至20个百分点。预印本，仅在巴基斯坦单一区域验证。","arXiv 预印本 2026-10-16","2026-10-16T00:00:00Z",69,{"impact":17,"substance":148,"depth":19,"authority":109,"freshness":84,"relevant":22,"comment":211},"方法轻量化与实测数据有增量，但仅单区域预印本验证，属细分技术进展，可入精选备选。",[213],{"name":207,"url":205},[27,28,29,215,216],"无人机遥感","棉花病害",{"code":218,"slug":219,"name":220,"path":221,"parent_code":222},"A6","cash-crops","棉麻糖与特色经作","\u002Ftopic\u002Ffield-crops\u002Fcash-crops","A",[224],{"code":40,"slug":225,"name":226,"path":227,"parent_code":228},"agricultural-ai","农业AI与大模型","\u002Ftopic\u002Fdigital-agriculture\u002Fagricultural-ai","I",{"status":162,"locked":14,"version":35,"method":36,"evidence":230},{"candidates":231,"agricultural_evidence":55},[232,238,244,248],{"code":40,"score":149,"supported":55,"title":233,"abstract":236,"tags":237},[234,235],"深度学习","YOLO",[],[28,29],{"code":218,"score":166,"supported":55,"title":239,"abstract":241,"tags":243},[240],"棉花",[242],"cotton",[],{"code":51,"score":22,"supported":14,"title":245,"abstract":246,"tags":247},[],[],[27],{"code":249,"score":22,"supported":14,"title":250,"abstract":251,"tags":252},"I3",[],[],[215],[254,255],"Cotton-Vision 棉花病害","无人机影像 棉花 检测","Cotton-Vision棉花病害-5532",{"doi":9,"openalex_id":9,"authors":258,"venue":9,"cited_by_count":74,"oa_url":9,"card":259,"direction":263,"ingested_from":137},[],{"tldr":260,"method":261,"finding":262,"direction":263,"opportunity":264},"提出轻量化检测器Cotton-Vision，用无人机影像精准识别棉花病害。","基于YOLO改进，融合幽灵瓶颈通道注意力与跨阶段部分融合，用2700余幅无人机影","精确率97.7%、mAP@50达85.6%，较主流基线提升10至20个百分点。","农业遥感与作物表型","仅在巴基斯坦单一区域验证，可扩展至多区域多品种，并探索边缘设备实时部署。","2026-10-22T00:07:09.816790Z",{"id":267,"title":268,"url":269,"summary":270,"summary_zh":271,"content":9,"source_name":272,"source_url":269,"published_at":273,"category":12,"cover_url":9,"hotness":13,"is_selected":14,"score":274,"score_detail":275,"sources":278,"tags":280,"primary_topic":282,"secondary_topics":283,"classification":284,"search_phrases":304,"slug":307,"view_count":74,"doi":308,"paper":309,"created_at":332},5393,"IMPLEMENTATION OF META-HEURISTIC OPTIMIZATION ALGORITHMS IN CONVOLUTIONAL NEURAL NETWORKS FOR OBJECT DETECTION AND CLASSIFICATION","https:\u002F\u002Fdoi.org\u002F10.22190\u002Ffuacr251214006i","CNNs have grown to form the backbone of modern computer vision systems, producing outstanding object detection and classification performance within diverse application domains. However, the manual development of suitable CNN architectures and, correspondingly, the selection of optimal hyperparameter sets are still inconvenient and time-consuming processes. The aim of this survey is to contribute a comprehensive review regarding how meta-heuristic optimization algorithms such as Genetic Algorithms, Particle Swarm Optimization, and other swarm intelligence-based methods are embedded in the CNN-based pipelines with the intent to achieve better detection and classification results. We gather recent progress regarding automated architecture search, hyperparameter tuning, model compression, and ensemble learning. We identify how hybrid optimization approaches consistently yield superior accuracy with computational efficiency by systematically reviewing applications in medical imaging, agriculture, vehicular recognition, and remote sensing. Optimized CNN models outperform their baseline versions many times, especially in health diagnostics, where several fine-tuned architectures reach accuracies greater than 99%. This survey provides a structured and updated overview of methodological developments, implementation practices, and emerging research directions for those practitioners and researchers who will apply meta-heuristic optimization within deep learning-based computer vision systems.","卷积神经网络（CNNs）已发展成为现代计算机视觉系统的核心骨干，在多个应用领域中展现出卓越的目标检测与分类性能。然而，人工设计合适的CNN架构并相应地选择最优超参数集仍然是繁琐且耗时的过程。本综述旨在全面回顾遗传算法、粒子群优化及其他群体智能方法等元启发式优化算法如何嵌入基于CNN的流程中以获得更优的检测与分类结果。我们汇集了自动化架构搜索、超参数调优、模型压缩和集成学习方面的最新进展。通过系统梳理在医学影像、农业、车辆识别和遥感领域的应用，我们揭示了混合优化方法如何以计算效率持续实现更优的精度。优化后的CNN模型在多数情况下远超其基线版本，尤其在健康诊断领域，若干精细调优的架构达到了超过99%的准确率。本综述为将在基于深度学习的计算机视觉系统中应用元启发式优化的从业者和研究者，提供了关于方法学进展、实施实践和新兴研究方向的结构化且更新的概述。","Facta Universitatis Series Automatic Control and Robotics","2026-10-18T00:00:00Z",61,{"impact":21,"substance":149,"depth":276,"authority":95,"freshness":21,"relevant":22,"comment":277},15,"综述系统梳理元启发式优化在CNN视觉任务中的嵌入方法，含农业应用，但属通用方法综述，非农业专属突破。",[279],{"name":272,"url":269},[27,28,29,281],"遥感",{"code":40,"slug":225,"name":226,"path":227,"parent_code":228},[],{"status":162,"locked":14,"version":35,"method":36,"evidence":285},{"candidates":286,"agricultural_evidence":55},[287,294,300],{"code":40,"score":166,"supported":55,"title":288,"abstract":289,"tags":293},[],[29,234,290,291,292],"计算机视觉","deep learning","computer vision",[28,29],{"code":249,"score":295,"supported":55,"title":296,"abstract":297,"tags":299},7,[],[281,298],"remote sensing",[281],{"code":51,"score":22,"supported":14,"title":301,"abstract":302,"tags":303},[],[],[27],[305,306],"元启发式优化 卷积神经网络","CNN 目标检测","元启发式优化卷积神经网络-5393","10.22190\u002Ffuacr251214006i",{"doi":308,"openalex_id":310,"authors":311,"venue":272,"cited_by_count":74,"oa_url":269,"card":327,"direction":263,"ingested_from":81},"W7222920697",[312,315,318,321,324],{"name":313,"orcid":314},"Nikola Ivačko","https:\u002F\u002Forcid.org\u002F0000-0003-4367-119X",{"name":316,"orcid":317},"Ivan S Ciric","https:\u002F\u002Forcid.org\u002F0000-0003-0430-8937",{"name":319,"orcid":320},"Milica Tasić","https:\u002F\u002Forcid.org\u002F0009-0001-9160-6379",{"name":322,"orcid":323},"Ljiljana Radović","https:\u002F\u002Forcid.org\u002F0000-0002-4099-1289",{"name":325,"orcid":326},"Žarko Ćojbašić","https:\u002F\u002Forcid.org\u002F0000-0002-4581-1048",{"tldr":328,"method":329,"finding":330,"direction":79,"opportunity":331},"综述元启发式算法嵌入CNN流程以优化目标检测与分类的研究进展。","系统综述遗传算法、粒子群等群智能方法用于CNN架构搜索与超参调优。","混合优化方法在医学影像、农业等领域兼顾精度与效率，部分模型准确率超99%。","农业场景下元启发式优化CNN的架构搜索与轻量化部署仍缺乏系统基准与田间验证。","2026-10-20T23:30:19.233167Z",{"id":334,"title":335,"url":336,"summary":337,"summary_zh":9,"content":9,"source_name":338,"source_url":9,"published_at":208,"category":12,"cover_url":9,"hotness":13,"is_selected":14,"score":339,"score_detail":340,"sources":342,"tags":344,"primary_topic":9,"secondary_topics":346,"classification":347,"search_phrases":358,"slug":361,"view_count":41,"doi":9,"paper":362,"created_at":369},5302,"Peach-YOLO:基于改进YOLOv8与多注意力融合的复杂环境桃实时检测方法","https:\u002F\u002Fm2.mtmt.hu\u002Fapi\u002Fpublication\u002F37332430","Frontiers in Plant Science 2026年第17期刊载You, Shuanghong等的Peach-YOLO论文,基于改进YOLOv8n框架,引入RFAConv模块强化特征表示、融合CAFM模块提取关键果实特征、采用CA-HSFPN金字塔网络、引入Shape-IoU损失函数;在自建桃数据集上模型仅5.0 MB,推理速度115.7 FPS,mAP@0.5达82.2%、精度78.9%、召回率76.4%,较YOLOv8n基线mAP、精度、召回率分别提升3.0、3.6、4.8个百分点。","Frontiers in Plant Science(2026, 17)",72,{"impact":95,"substance":148,"depth":19,"authority":96,"freshness":109,"relevant":22,"comment":341},"方法改进扎实、指标明确，但属细分作物检测算法研究，产业影响有限，适合作为技术类精选。",[343],{"name":338,"url":336},[27,28,29,345],"果实识别",[],{"status":104,"locked":14,"version":35,"method":36,"evidence":348},{"candidates":349,"agricultural_evidence":14,"reason":125},[350,354],{"code":40,"score":96,"supported":55,"title":351,"abstract":352,"tags":353},[235],[235],[28,29],{"code":51,"score":22,"supported":14,"title":355,"abstract":356,"tags":357},[],[],[27],[359,360],"Peach-YOLO 桃检测","YOLOv8 果实检测","Peach-YOLO桃检测-5302",{"doi":9,"openalex_id":9,"authors":363,"venue":9,"cited_by_count":74,"oa_url":9,"card":364,"direction":263,"ingested_from":137},[],{"tldr":365,"method":366,"finding":367,"direction":263,"opportunity":368},"提出Peach-YOLO改进YOLOv8n模型，实现复杂环境下桃果实实时检测。","改进YOLOv8n，引入RFAConv、CAFM、CA-HSFPN与Shape-","模型仅5.0MB、115.7FPS，mAP@0.5达82.2%，较基线提升3.0个百分点。","可探索轻量检测模型在采摘机器人边缘端部署及多果园场景泛化能力。","2026-10-19T00:07:48.648980Z",{"id":371,"title":372,"url":373,"summary":374,"summary_zh":375,"content":9,"source_name":376,"source_url":373,"published_at":377,"category":12,"cover_url":9,"hotness":13,"is_selected":14,"score":378,"score_detail":379,"sources":381,"tags":383,"primary_topic":9,"secondary_topics":386,"classification":387,"search_phrases":398,"slug":401,"view_count":22,"doi":402,"paper":403,"created_at":434},5136,"Enhanced YOLOv8n for adhered leaf cluster detection in RGB-based fresh green tea leaf sorting","https:\u002F\u002Fdoi.org\u002F10.1016\u002Fj.atech.2026.102640","High-precision detection of adhered leaf clusters (ALCs) based on RGB imaging has long posed a critical challenge in the post-harvest sorting of fresh green tea leaves. To address this issue, this study designed an enhanced YOLOv8n model, named SDSI-YOLO, by integrating the StarNet backbone, DySample upsampling method, and Shape-Inner-IoU loss function to improve ALC detection performance. Experimental results demonstrated that SDSI-YOLO achieved an optimal balance between accuracy and efficiency, with a mean average precision of 92.6% and an F 1 -score of 89.2. It also maintained lightweight characteristics, with a model size of only 3.89 MB and efficient inference speed of 3.1 ms per frame. Ablation experiments confirmed the effectiveness of each module in constructing SDSI-YOLO. The results of visualization tests indicated that the model exhibited a stronger capability in capturing critical details and structural features of ALCs. This research provides a feasible solution for the industrial sorting of fresh green tea leaves, demonstrating considerable application potential.","基于RGB成像的高精度粘连叶簇（adhered leaf clusters，ALCs）检测一直是新鲜绿茶鲜叶采后分选中的关键难题。为解决该问题，本研究通过融合StarNet主干网络、DySample上采样方法和Shape-Inner-IoU损失函数，设计了一种增强型YOLOv8n模型，命名为SDSI-YOLO，以提升ALCs检测性能。实验结果表明，SDSI-YOLO在精度与效率之间实现了最优平衡，平均精度均值达到92.6%，F1分数为89.2。同时，该模型保持了轻量化特性，模型大小仅为3.89 MB，推理速度高达每帧3.1 ms。消融实验验证了各模块在构建SDSI-YOLO中的有效性。可视化测试结果表明，该模型在捕捉ALCs关键细节和结构特征方面表现出更强的能力。本研究为新鲜绿茶鲜叶的工业化分选提供了一种可行方案，具有相当大的应用潜力。","Smart Agricultural Technology","2026-10-14T00:00:00Z",76,{"impact":17,"substance":148,"depth":19,"authority":96,"freshness":109,"relevant":22,"comment":380},"提出轻量化改进YOLOv8n模型用于鲜茶叶粘连叶簇检测，指标与推理速度均有实测数据，方法新颖且面向产业分选场景，具备精选价值。",[382],{"name":376,"url":373},[27,28,29,384,385],"YOLOv8","茶叶分选",[],{"status":104,"locked":14,"version":35,"method":36,"evidence":388},{"candidates":389,"agricultural_evidence":14,"reason":125},[390,394],{"code":40,"score":84,"supported":55,"title":391,"abstract":392,"tags":393},[],[235],[384,28,29],{"code":51,"score":22,"supported":14,"title":395,"abstract":396,"tags":397},[],[],[27],[399,400],"SDSI-YOLO 茶叶分选","鲜叶 粘连叶簇 检测","SDSI-YOLO茶叶分选-5136","10.1016\u002Fj.atech.2026.102640",{"doi":402,"openalex_id":404,"authors":405,"venue":376,"cited_by_count":74,"oa_url":373,"card":429,"direction":79,"ingested_from":81},"W7221817030",[406,408,410,412,414,417,419,422,424,426],{"name":407,"orcid":9},"Jian Wang",{"name":409,"orcid":9},"Yi-jian Liu",{"name":411,"orcid":9},"Yin-yin Lin",{"name":413,"orcid":9},"Cheng-chen Zhang",{"name":415,"orcid":416},"Shengnan Liu","https:\u002F\u002Forcid.org\u002F0000-0001-9886-068X",{"name":418,"orcid":9},"Bin Ji",{"name":420,"orcid":421},"Qiu Wang","https:\u002F\u002Forcid.org\u002F0000-0002-5861-4115",{"name":423,"orcid":9},"Li-hong Du",{"name":425,"orcid":9},"Lei Zheng",{"name":427,"orcid":428},"Fei Ma","https:\u002F\u002Forcid.org\u002F0000-0002-7313-1787",{"tldr":430,"method":431,"finding":432,"direction":79,"opportunity":433},"提出改进YOLOv8n模型SDSI-YOLO，实现鲜茶叶粘连叶簇的高精度检测。","融合StarNet主干、DySample上采样与Shape-Inner-IoU损","mAP达92.6%、F1为89.2，模型仅3.89MB、单帧3.1ms，精度与效率兼顾。","可探索轻量检测模型在茶叶分选产线的嵌入式部署与多品类叶簇泛化能力。","2026-10-17T23:30:03.404999Z"]