[{"data":1,"prerenderedAt":-1},["ShallowReactive",2],{"item-2620":3,"related-2620":88},{"id":4,"title":5,"url":6,"summary":7,"summary_zh":8,"content":8,"source_name":9,"source_url":6,"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":62,"slug":65,"view_count":66,"doi":67,"paper":68,"created_at":87},2620,"A deep learning-enhanced vision system for precision target spraying in chinese cabbage cultivation","https:\u002F\u002Fdoi.org\u002F10.1007\u002Fs11119-026-10444-4","A deep learning-enhanced vision system for precision target spraying in chinese cabbage cultivation。Precision Agriculture",null,"Precision Agriculture","2026-09-16T00:00:00Z","论文",10,false,70,{"impact":16,"substance":17,"depth":18,"authority":19,"freshness":12,"relevant":20,"comment":21},12,18,16,14,1,"核心期刊论文，方法新颖且时效性强，但属细分作物技术进展，产业影响范围有限。",[23],{"name":9,"url":6},[25,26,27,28,29],"智慧农业","农业人工智能","精准施药","机器视觉","大白菜",{"code":31,"slug":32,"name":33,"path":34,"parent_code":35},"I2","agricultural-ai","农业AI与大模型","\u002Ftopic\u002Fdigital-agriculture\u002Fagricultural-ai","I",[],{"status":38,"locked":13,"version":39,"method":40,"evidence":41},"classified","2026-10-22.2","rules",{"candidates":42,"agricultural_evidence":45},[43,50,57],{"code":31,"score":44,"supported":45,"title":46,"abstract":48,"tags":49},13,true,[47],"deep learning",[47],[26,28],{"code":51,"score":52,"supported":45,"title":53,"abstract":54,"tags":56},"I1",4,[],[55],"precision agriculture",[25],{"code":58,"score":20,"supported":13,"title":59,"abstract":60,"tags":61},"F4",[],[],[27],[63,64],"农业人工智能 智慧农业 机器视觉 精准施药","农业人工智能 智慧农业","农业人工智能智慧农业机器视觉精准施药-2620",2,"10.1007\u002Fs11119-026-10444-4",{"doi":67,"openalex_id":69,"authors":70,"venue":9,"cited_by_count":85,"oa_url":8,"card":8,"direction":8,"ingested_from":86},"W7213275445",[71,73,75,77,80,83],{"name":72,"orcid":8},"Changxi Liu",{"name":74,"orcid":8},"Hang Shi",{"name":76,"orcid":8},"Hao Sun",{"name":78,"orcid":79},"Hui Zhang","https:\u002F\u002Forcid.org\u002F0000-0001-8843-7298",{"name":81,"orcid":82},"Qingda Li","https:\u002F\u002Forcid.org\u002F0000-0002-9046-2094",{"name":84,"orcid":8},"Jun Hu",0,"openalex","2026-09-16T23:30:03.326664Z",{"total":89,"page":20,"page_size":89,"items":90},6,[91,146,234,304,361,448],{"id":92,"title":93,"url":94,"summary":95,"summary_zh":96,"content":8,"source_name":97,"source_url":94,"published_at":98,"category":11,"cover_url":8,"hotness":12,"is_selected":13,"score":99,"score_detail":100,"sources":105,"tags":107,"primary_topic":109,"secondary_topics":110,"classification":111,"search_phrases":129,"slug":132,"view_count":85,"doi":133,"paper":134,"created_at":145},5589,"Conformal-Risk Evaluation for Artificial Intelligence Agriculture Spray-Nozzle Fault Detection Under Label-Delay Feedback: A Computer Coverage Audit","https:\u002F\u002Fdoi.org\u002F10.5281\u002Fzenodo.23544107","Spray-nozzle fault detection in precision agriculture is a classification problem in which the label that confirms a fault arrives after the spray pass, so the detector must act on unlabelled evidence and its error rate must be certified before the label exists. Conformal prediction offers distribution-free coverage guarantees, but the guarantee is stated for exchangeable calibration and test data, an assumption that label-delayed feedback violates because the calibration set is always older than the deployment set. the present analysis formalises label-delay feedback as a distribution shift in the conformity score and derives a coverage bound for split-conformal fault detectors under that shift. The bound separates the nominal miscoverage rate into an exchangeable component and a delay-induced component that scales with the total variation distance between the calibration and deployment score distributions. A replication-based evaluation of the ['Intercept', 'exposure', 'group', 'severity'] estimator was conducted: 600 data sets of N = 500 were drawn from a declared data-generating process (intercept 12.0, exposure 0.42, group -3.1, severity 1.35, error SD 4.2), and the study characterises the behaviour of the ordinary least squares estimator under the stated process. The estimator recovered the declared coefficients with estimated bias 0.01122 for the intercept and -0.0002 for exposure, root mean squared error 0.9217 and 0.01614 respectively, and empirical coverage of the nominal 95% intervals of 1.0 for both parameters across 600 replications. The coverage audit shows that the delay-induced term, not the exchangeable term, dominates the risk of a conformal spray-nozzle detector, and that the audit procedure can certify a detector before field labels return.","在精准农业中，喷雾喷嘴故障检测是一个分类问题，其中确认故障的标签在喷雾作业结束后才到达，因此检测器必须基于未标记的证据采取行动，并且其错误率必须在标签存在之前得到认证。保形预测（conformal prediction）提供了无分布覆盖保证，但该保证是针对可交换的校准数据和测试数据而言的，而标签延迟反馈违反了这一假设，因为校准集总是比部署集更旧。本分析将标签延迟反馈形式化为一致性分数中的分布偏移，并推导了在该偏移下分裂保形故障检测器的覆盖界。该界将名义错误覆盖 rate 分解为可交换分量和延迟诱导分量，后者随校准与部署分数分布之间的全变差距离而缩放。对 ['Intercept', 'exposure', 'group', 'severity'] 估计器进行了基于重复的评估：从声明的数据生成过程（截距 12.0，暴露 0.42，分组 -3.1，严重程度 1.35，误差标准差 4.2）中抽取了 600 个 N = 500 的数据集，研究刻画了普通最小二乘估计器在所述过程下的行为。该估计器恢复了声明的系数，截距的估计偏差为 0.01122，暴露为 -0.0002，均方根误差分别为 0.9217 和 0.01614，两个参数在 600 次重复中名义 95% 区间的经验覆盖率为 1.0。覆盖审计表明，延迟诱导项而非可交换项主导了保形喷雾喷嘴检测器的风险，并且该审计程序可以在田间标签返回之前对检测器进行认证。","Zenodo (CERN European Organization for Nuclear Research)","2026-10-21T00:00:00Z",62,{"impact":101,"substance":17,"depth":102,"authority":103,"freshness":12,"relevant":20,"comment":104},8,17,9,"论文提出标签延迟下共形预测覆盖界，方法有新意但属预印本、应用面窄，可作为专业补充而非每日精选头条。",[106],{"name":97,"url":94},[25,26,27,108],"病虫害监测",{"code":31,"slug":32,"name":33,"path":34,"parent_code":35},[],{"status":38,"locked":13,"version":39,"method":40,"evidence":112},{"candidates":113,"agricultural_evidence":45},[114,119,125],{"code":31,"score":103,"supported":45,"title":115,"abstract":117,"tags":118},[116],"artificial intelligence",[],[26],{"code":51,"score":120,"supported":45,"title":121,"abstract":122,"tags":124},7,[],[123,55],"精准农业",[25],{"code":58,"score":20,"supported":13,"title":126,"abstract":127,"tags":128},[],[],[27],[130,131],"农业人工智能 病虫害监测 智慧农业 精准施药","农业人工智能 病虫害监测","农业人工智能病虫害监测智慧农业精准施药-5589","10.5281\u002Fzenodo.23544107",{"doi":133,"openalex_id":135,"authors":136,"venue":97,"cited_by_count":85,"oa_url":94,"card":139,"direction":143,"ingested_from":86},"W7223116087",[137],{"name":138,"orcid":8},"Achieng' Atim Okello",{"tldr":140,"method":141,"finding":142,"direction":143,"opportunity":144},"将标签延迟反馈建模为共形分数分布偏移，推导覆盖率界并审计喷雾喷嘴故障检测器。","分裂共形预测、总变差距离、600次重复模拟（N=500）评估OLS估计。","延迟诱导项而非可交换项主导检测器风险，审计可在田间标签返回前认证检测器。","农业人工智能与决策模型","可将该覆盖率审计框架扩展到其他标签延迟的农业传感器故障检测，并研究延迟分布估计误差对认证的影响。","2026-10-22T11:21:02.845718Z",{"id":147,"title":148,"url":149,"summary":150,"summary_zh":151,"content":8,"source_name":152,"source_url":149,"published_at":153,"category":11,"cover_url":8,"hotness":12,"is_selected":13,"score":154,"score_detail":155,"sources":158,"tags":160,"primary_topic":163,"secondary_topics":164,"classification":165,"search_phrases":188,"slug":191,"view_count":52,"doi":192,"paper":193,"created_at":233},3467,"Smart agriculture using digital holography and artificial intelligence","https:\u002F\u002Fdoi.org\u002F10.3389\u002Ffpls.2026.1871510","In viticulture, direct protection against downy and powdery mildews relies on the preventive application of fungicides, requiring growers to anticipate infection events. Decision-making is mainly supported by forecasting models driven by weather predictions. However, these decisions are inherently uncertain, as some treatments ultimately prove unnecessary, although this information only becomes available retrospectively from observed conditions. This study explores the integration of an advanced spore detection device to better target fungicide applications in vineyards, aiming to reduce the use of phytosanitary products while maintaining high grape quality. The stand-alone device uses digital holography combined with artificial intelligence (AI) for detecting and classifying airborne spores of both downy and powdery mildew. It enables the tracking of disease dynamics as well as the assessment of environmental conditions and treatment effects on spore counts. Two case studies with real-time data access in Changins, Switzerland and Château le Puy, France, are presented and revealed promising strategies for substantial reductions in fungicide use while maintaining effective disease control.","在葡萄栽培中，对霜霉病和白粉病的直接防护依赖于杀菌剂的预防性施用，这要求种植者预判侵染事件的发生。决策主要依靠由天气预报驱动的预测模型来支持。然而，这些决策本质上具有不确定性，因为有些处理最终被证明是不必要的，尽管这一信息只能通过观测条件回顾性地获得。本研究探索了集成先进孢子检测装置以更精准地指导葡萄园杀菌剂施用的方法，旨在减少植物检疫产品的使用，同时保持葡萄的高品质。该独立装置利用数字全息术结合人工智能（AI）来检测和分类空气中的霜霉病和白粉病孢子。它能够追踪病害动态，并评估环境条件和处理措施对孢子数量的影响。本文介绍了在瑞士Changins和法国Château le Puy进行的两个可实时获取数据的案例研究，并揭示了在保持有效病害控制的同时大幅减少杀菌剂用量的有前景的策略。","Frontiers in Plant Science","2026-09-24T00:00:00Z",80,{"impact":17,"substance":156,"depth":17,"authority":19,"freshness":101,"relevant":20,"comment":157},22,"数字全息结合AI检测葡萄病害孢子，为减少杀菌剂施用提供实证案例，方法新颖且具推广价值。",[159],{"name":152,"url":149},[25,26,27,161,162],"葡萄种植","病害预警",{"code":31,"slug":32,"name":33,"path":34,"parent_code":35},[],{"status":38,"locked":13,"version":39,"method":40,"evidence":166},{"candidates":167,"agricultural_evidence":45},[168,172,177,184],{"code":31,"score":16,"supported":45,"title":169,"abstract":170,"tags":171},[116],[116],[26],{"code":51,"score":103,"supported":45,"title":173,"abstract":175,"tags":176},[174],"smart agriculture",[],[25],{"code":178,"score":120,"supported":45,"title":179,"abstract":180,"tags":183},"B2",[],[181,182],"葡萄","grape",[161],{"code":58,"score":20,"supported":13,"title":185,"abstract":186,"tags":187},[],[],[27],[189,190],"数字全息 孢子检测 葡萄","霜霉病 白粉病 人工智能","数字全息孢子检测葡萄-3467","10.3389\u002Ffpls.2026.1871510",{"doi":192,"openalex_id":194,"authors":195,"venue":152,"cited_by_count":85,"oa_url":149,"card":227,"direction":231,"ingested_from":86},"W7214152870",[196,198,200,203,206,209,212,214,216,219,222,225],{"name":197,"orcid":8},"Tessa Chiara Basso",{"name":199,"orcid":8},"Sara Leoni",{"name":201,"orcid":202},"Denis Ullmann","https:\u002F\u002Forcid.org\u002F0000-0002-7179-005X",{"name":204,"orcid":205},"Adimulya Kartiyasa","https:\u002F\u002Forcid.org\u002F0009-0003-3142-1174",{"name":207,"orcid":208},"Livio Ruzzante","https:\u002F\u002Forcid.org\u002F0000-0002-8693-8678",{"name":210,"orcid":211},"Sylvain Schnée","https:\u002F\u002Forcid.org\u002F0000-0002-1014-1961",{"name":213,"orcid":8},"Anne‐Lise Fabre",{"name":215,"orcid":8},"Steven Hewison",{"name":217,"orcid":218},"Jérôme Kasparian","https:\u002F\u002Forcid.org\u002F0000-0003-2398-3882",{"name":220,"orcid":221},"Nicolas Berti","https:\u002F\u002Forcid.org\u002F0000-0003-3769-3966",{"name":223,"orcid":224},"Pierre‐Henri Dubuis","https:\u002F\u002Forcid.org\u002F0000-0002-9624-3925",{"name":226,"orcid":8},"Jean-Pierre Wolf",{"tldr":228,"method":229,"finding":230,"direction":231,"opportunity":232},"利用数字全息与AI检测葡萄园空气中霜霉和白粉病菌孢子，优化杀菌剂施用。","数字全息成像结合AI分类孢子，在瑞士和法国葡萄园实时监测。","孢子检测可追踪病害动态，在保持防效下大幅减少杀菌剂使用。","智慧农业 \u002F 农业物联网","可探索孢子自动监测与气象预报融合的精准施药决策模型，并验证多作物适用性。","2026-09-25T23:30:09.459179Z",{"id":235,"title":236,"url":237,"summary":238,"summary_zh":239,"content":8,"source_name":240,"source_url":237,"published_at":241,"category":11,"cover_url":8,"hotness":12,"is_selected":13,"score":242,"score_detail":243,"sources":246,"tags":248,"primary_topic":251,"secondary_topics":252,"classification":259,"search_phrases":284,"slug":287,"view_count":275,"doi":288,"paper":289,"created_at":303},3284,"Computer vision-based size estimation module for selective harvesting of lettuce","https:\u002F\u002Fdoi.org\u002F10.14719\u002Fpst.14546","Selective harvesting of leafy vegetables remains a major challenge in agricultural automation, particularly for lettuce that meet predefined size or maturity criteria. Vision-based perception systems play a critical role in enabling selective harvesting by identifying plants that meet predefined size or maturity criteria. This study presents the development and validation of computer vision-based size estimation software designed to support selective harvesting decisions in leafy vegetable production. A C #-based image processing application was developed to perform red, green and blue (RGB) colour segmentation, contour detection and pixel-to-metric size estimation using images acquired from a standard Universal Serial Bus (USB) webcam. The system converts pixel measurements into real-world dimensions through calibrated scaling factors that account for variations in camera-to-plant distance. Field experiments were conducted using three commercial lettuce cultivars Romaine, Iceberg and Curly. Vision-based canopy width measurements showed strong agreement with manual measurements (N = 60) and exhibited very strong correlations with plant weight (Romaine type: r = 0.9803; Iceberg type: r = 0.9935; Curly type: r = 0.9707; p \u003C 0.001). Linear regression models achieved high predictive performance (R² = 0.942–0.987), while error metrics indicated low prediction errors (Mean absolute error (MAE): 5.62–8.64 g; root mean square error (RMSE): 7.30–11.06 g). Bland-Altman analysis further confirmed strong agreement between vision-based estimates and manual measurements. This study primarily validates a lightweight vision-based measurement algorithm intended for future integration into robotic harvesting systems. The results demonstrate that simple RGB-based image processing can provide reliable size estimation for selective harvesting decisions in leafy vegetable production systems.","叶菜类蔬菜的选择性收获仍是农业自动化领域的一项重大挑战，尤其是对符合预定大小或成熟度标准的生菜而言。基于视觉的感知系统通过识别符合预定大小或成熟度标准的植株，在实现选择性收获中发挥着关键作用。本研究介绍了一款基于计算机视觉的大小估算软件的开发与验证，该软件旨在为叶菜类蔬菜生产中的选择性收获决策提供支持。研究开发了一款基于C#的图像处理应用程序，利用标准通用串行总线（USB）网络摄像头采集的图像，执行红绿蓝（RGB）颜色分割、轮廓检测以及像素到实际尺寸的估算。该系统通过经过校准的缩放因子将像素测量值转换为实际尺寸，并考虑了摄像头与植株之间距离的变化。田间试验采用三个商业化生菜品种——罗马生菜、结球生菜和皱叶生菜。基于视觉的冠幅测量结果与人工测量结果高度一致（N = 60），并与植株重量呈现极强的相关性（罗马型：r = 0.9803；结球型：r = 0.9935；皱叶型：r = 0.9707；p \u003C 0.001）。线性回归模型取得了较高的预测性能（R² = 0.942–0.987），误差指标显示预测误差较低（平均绝对误差（MAE）：5.62–8.64 g；均方根误差（RMSE）：7.30–11.06 g）。Bland-Altman分析进一步证实了基于视觉的估算值与人工测量值之间的高度一致性。本研究主要验证了一种轻量级视觉测量算法，旨在未来集成到机器人收获系统中。结果表明，简单的基于RGB的图像处理能够为叶菜类蔬菜生产系统中的选择性收获决策提供可靠的大小估算。","Plant Science Today","2026-09-22T00:00:00Z",69,{"impact":16,"substance":244,"depth":18,"authority":16,"freshness":103,"relevant":20,"comment":245},20,"该研究开发了基于RGB图像的轻量级生菜尺寸估计模块，与人工测量高度一致，为机器人选择性采收提供了可靠感知方案，具有较高的技术参考价值。",[247],{"name":240,"url":237},[25,26,249,28,250],"生菜","选择性采收",{"code":31,"slug":32,"name":33,"path":34,"parent_code":35},[253],{"code":254,"slug":255,"name":256,"path":257,"parent_code":258},"B1","vegetables","蔬菜","\u002Ftopic\u002Fhorticulture\u002Fvegetables","B",{"status":38,"locked":13,"version":39,"method":40,"evidence":260},{"candidates":261,"agricultural_evidence":45},[262,268,273,280],{"code":31,"score":18,"supported":45,"title":263,"abstract":265,"tags":267},[264],"computer vision",[266,264],"计算机视觉",[26,28],{"code":254,"score":12,"supported":45,"title":269,"abstract":270,"tags":272},[],[256,249,271],"vegetable",[249],{"code":274,"score":275,"supported":45,"title":276,"abstract":277,"tags":279},"F6",3,[],[278],"robotic harvesting",[],{"code":51,"score":20,"supported":13,"title":281,"abstract":282,"tags":283},[],[],[25],[285,286],"生菜 选择性采收 机器视觉","计算机视觉 生菜 尺寸估计","生菜选择性采收机器视觉-3284","10.14719\u002Fpst.14546",{"doi":288,"openalex_id":290,"authors":291,"venue":240,"cited_by_count":85,"oa_url":237,"card":298,"direction":143,"ingested_from":86},"W7214000589",[292,295],{"name":293,"orcid":294},"Erhan Kahya","https:\u002F\u002Forcid.org\u002F0000-0001-7768-9190",{"name":296,"orcid":297},"Fatma Funda Özdüven","https:\u002F\u002Forcid.org\u002F0000-0003-4286-8943",{"tldr":299,"method":300,"finding":301,"direction":143,"opportunity":302},"开发基于RGB图像处理的生菜尺寸估计软件，用于选择性采收决策。","C#图像处理，USB摄像头采集，RGB分割与轮廓检测，标定像素-实际尺寸转换。","视觉冠幅与重量强相关（r=0.97-0.99），回归模型R²达0.94-0.99，误差低。","可集成到机器人采收系统，并探索多品种、多光照条件下的鲁棒性及实时边缘部署。","2026-09-23T23:30:38.203393Z",{"id":305,"title":306,"url":307,"summary":308,"summary_zh":8,"content":8,"source_name":309,"source_url":8,"published_at":241,"category":11,"cover_url":8,"hotness":12,"is_selected":13,"score":310,"score_detail":311,"sources":313,"tags":315,"primary_topic":318,"secondary_topics":319,"classification":326,"search_phrases":347,"slug":350,"view_count":351,"doi":8,"paper":352,"created_at":360},3249,"设施番茄采摘机器人识别定位与采摘方法研究——江苏大学雷志龙等 基于改进YOLO v5-HSV融合算法识别准确率95.01%","http:\u002F\u002Fwww.qikanzj.com\u002Fhek\u002Fnyjxxb\u002Fmulu\u002F455758.html","智慧农业(中英文)期刊发表江苏大学雷志龙、刘畅、王权团队研究：针对设施单果番茄采摘需求，设计一款设施番茄智能采摘平台，主要由升降机构、采摘机构、识别与定位系统等部分组成。平台整体结构由低压一体化伺服滚珠丝杠副升降机构、六轴协作机械臂和力控末端执行器组成。基于改进YOLO v5-HSV融合算法来识别检测，通过对H分量进行图像阈值分割，提高对成熟目标果实识别的准确率，有效排除未成熟番茄和枝叶背景的干扰；通过眼在手外的标定方法，使用ZED双目相机进行定位。搭建的设施番茄采摘机样机平台在现场采摘试验中识别准确率达到95.01%，采摘成功率为87.96%，单果平均采摘时间为14.56s。","智慧农业(中英文)·江苏大学",82,{"impact":17,"substance":156,"depth":17,"authority":19,"freshness":12,"relevant":20,"comment":312},"核心期刊论文，方法有改进、数据完整，识别准确率与采摘成功率等指标明确，对设施农业智能装备研发有参考价值。",[314],{"name":309,"url":307},[25,26,316,28,317],"采摘机器人","设施番茄",{"code":254,"slug":255,"name":256,"path":257,"parent_code":258},[320,321],{"code":31,"slug":32,"name":33,"path":34,"parent_code":35},{"code":274,"slug":322,"name":323,"path":324,"parent_code":325},"agricultural-robots","机器人与无人农场","\u002Ftopic\u002Finputs-equipment\u002Fagricultural-robots","F",{"status":38,"locked":13,"version":39,"method":40,"evidence":327},{"candidates":328,"agricultural_evidence":45},[329,334,339,343],{"code":31,"score":44,"supported":45,"title":330,"abstract":332,"tags":333},[331],"YOLO",[331],[26,28],{"code":254,"score":16,"supported":45,"title":335,"abstract":337,"tags":338},[336],"番茄",[336],[317],{"code":274,"score":103,"supported":45,"title":340,"abstract":341,"tags":342},[316],[],[316],{"code":51,"score":52,"supported":45,"title":344,"abstract":345,"tags":346},[],[25],[25],[348,349],"江苏大学 设施番茄 采摘机器人","YOLO v5 番茄 识别定位","江苏大学设施番茄采摘机器人-3249",5,{"doi":8,"openalex_id":8,"authors":353,"venue":8,"cited_by_count":85,"oa_url":8,"card":354,"direction":143,"ingested_from":359},[],{"tldr":355,"method":356,"finding":357,"direction":143,"opportunity":358},"设计设施番茄智能采摘平台，融合改进YOLO v5与HSV实现识别定位与采摘。","改进YOLO v5-HSV融合算法、ZED双目相机眼在手外标定、六轴机械臂力控末","识别准确率95.01%，采摘成功率87.96%，单果平均采摘时间14.56秒。","可探索多果簇、遮挡与弱光环境下识别定位鲁棒性，并优化采摘效率与末端力控。","agent","2026-09-23T00:04:33.401768Z",{"id":362,"title":363,"url":364,"summary":365,"summary_zh":366,"content":8,"source_name":367,"source_url":364,"published_at":368,"category":11,"cover_url":8,"hotness":12,"is_selected":13,"score":369,"score_detail":370,"sources":372,"tags":374,"primary_topic":377,"secondary_topics":383,"classification":385,"search_phrases":413,"slug":415,"view_count":275,"doi":416,"paper":417,"created_at":447},2288,"Field-based deep learning classification of cotton and weeds for machine-vision-assisted intra-row weed management","https:\u002F\u002Fdoi.org\u002F10.1016\u002Fj.atech.2026.102567","Timely and precise weed management is essential for reducing crop-weed competition, labour requirements, and unnecessary weed-control inputs in cotton production. Reliable discrimination between cotton plants and weeds is a prerequisite for automated intra-row weed management. This study evaluated two pretrained convolutional neural network models, MobileNetV2 and DenseNet169, for binary classification of cotton and weeds using field-acquired RGB images. Images were collected from a farmer-managed cotton field in Haryana and an experimental cotton field at ICAR-Indian Agricultural Research Institute, New Delhi, during May-September 2025 under natural field conditions. The dataset comprised 2,195 weed images representing six predominant weed species and 1,211 cotton images. Images were classified into two operational classes, cotton and weed. Training images were augmented to address the original class imbalance, whereas validation and test images were retained without augmentation. Transfer learning was used to fine-tune both models, and performance was evaluated using accuracy, precision, recall, F1-score, confusion matrices, and inference time. Both models achieved high classification performance. DenseNet169 attained a test accuracy of 99.47%, compared with 98.27% for MobileNetV2. The results indicate that pretrained CNNs can provide accurate image-level discrimination between cotton and weed vegetation under the investigated field conditions. DenseNet169 therefore shows promise as a visual-perception component for machine-vision-assisted intra-row weed management. However, the present study is limited to image-level classification and does not demonstrate plant localization, continuous machine operation, actuator coordination, or field-scale weed removal. Further validation under independent locations, varying weed densities, illumination conditions, machine travel speeds, and complete perception-decision-actuation pipelines is required.","及时、精准的杂草管理对于减少棉花生产中的棉草竞争、劳动力需求和不必要的除草投入至关重要。可靠地区分棉花植株与杂草是实现行内自动化杂草管理的前提。本研究评估了两种预训练卷积神经网络模型——MobileNetV2和DenseNet169，利用田间采集的RGB图像对棉花与杂草进行二分类。图像于2025年5月至9月期间，在自然田间条件下，采集自哈里亚纳邦一处农民管理的棉田以及新德里ICAR-印度农业研究所的实验棉田。数据集包含2，195幅杂草图像，涵盖六种主要杂草种类，以及1，211幅棉花图像。图像被分为棉花和杂草两个操作类别。训练图像经过增强处理以解决原始类别不平衡问题，而验证和测试图像则保留未增强状态。采用迁移学习对两种模型进行微调，并使用准确率、精确率、召回率、F1分数、混淆矩阵和推理时间评估性能。两种模型均取得了较高的分类性能。DenseNet169的测试准确率达到99.47%，而MobileNetV2为98.27%。结果表明，预训练卷积神经网络能够在所研究的田间条件下实现棉花与杂草植被在图像层面的准确区分。因此，DenseNet169有望作为机器视觉辅助行内杂草管理的视觉感知组件。然而，本研究仅限于图像层面的分类，并未展示植株定位、机器连续作业、执行器协调或田间规模除草。仍需在独立地点、不同杂草密度、光照条件、机器行进速度以及完整的感知-决策-执行流程下进行进一步验证。","Smart Agricultural Technology","2026-09-11T00:00:00Z",67,{"impact":16,"substance":17,"depth":18,"authority":44,"freshness":101,"relevant":20,"comment":371},"基于田间RGB图像的棉花与杂草深度学习分类研究，DenseNet169测试准确率达99.47%，方法扎实但仅限图像级分类，尚缺定位与执行环节验证，属细分领域技术进展。",[373],{"name":367,"url":364},[25,26,375,376,28],"棉花","杂草识别",{"code":378,"slug":379,"name":380,"path":381,"parent_code":382},"A6","cash-crops","棉麻糖与特色经作","\u002Ftopic\u002Ffield-crops\u002Fcash-crops","A",[384],{"code":31,"slug":32,"name":33,"path":34,"parent_code":35},{"status":38,"locked":13,"version":39,"method":40,"evidence":386},{"candidates":387,"agricultural_evidence":45},[388,394,398,403,409],{"code":378,"score":389,"supported":45,"title":390,"abstract":392,"tags":393},15,[391],"cotton",[375,391],[375],{"code":31,"score":12,"supported":45,"title":395,"abstract":396,"tags":397},[47],[],[26,28],{"code":58,"score":52,"supported":45,"title":399,"abstract":400,"tags":402},[],[401],"除草",[376],{"code":404,"score":275,"supported":45,"title":405,"abstract":406,"tags":408},"A4",[],[407],"花生",[],{"code":51,"score":20,"supported":13,"title":410,"abstract":411,"tags":412},[],[],[25],[414,64],"农业人工智能 智慧农业 机器视觉 杂草识别","农业人工智能智慧农业机器视觉杂草识别-2288","10.1016\u002Fj.atech.2026.102567",{"doi":416,"openalex_id":418,"authors":419,"venue":367,"cited_by_count":85,"oa_url":364,"card":442,"direction":143,"ingested_from":86},"W7212315230",[420,422,425,428,431,433,436,438,440],{"name":421,"orcid":8},"Shaik Nasreen",{"name":423,"orcid":424},"Roaf Ahmad Parray","https:\u002F\u002Forcid.org\u002F0000-0002-8303-1990",{"name":426,"orcid":427},"Parveen Dhanger","https:\u002F\u002Forcid.org\u002F0000-0001-5250-0275",{"name":429,"orcid":430},"Rishi Raj","https:\u002F\u002Forcid.org\u002F0009-0002-7918-1141",{"name":432,"orcid":8},"Tapan Kumar Khura",{"name":434,"orcid":435},"P. Sahoo","https:\u002F\u002Forcid.org\u002F0000-0002-3888-8506",{"name":437,"orcid":8},"Tushar Dhar",{"name":439,"orcid":8},"Prajwal R",{"name":441,"orcid":8},"Sripriyanka S. Nalla",{"tldr":443,"method":444,"finding":445,"direction":143,"opportunity":446},"用MobileNetV2和DenseNet169对田间棉花与杂草图像做二分类，验证机器视觉除草可行性","迁移学习微调两种预训练CNN，使用2025年田间RGB图像共3406张。","DenseNet169测试准确率达99.47%，优于MobileNetV2的98.27%。","可延伸至植株定位、多光照与密度条件下的感知-决策-执行全流程田间验证。","2026-09-13T23:30:04.183782Z",{"id":449,"title":450,"url":451,"summary":452,"summary_zh":453,"content":8,"source_name":97,"source_url":451,"published_at":98,"category":11,"cover_url":8,"hotness":12,"is_selected":13,"score":242,"score_detail":454,"sources":457,"tags":459,"primary_topic":463,"secondary_topics":469,"classification":471,"search_phrases":487,"slug":490,"view_count":85,"doi":491,"paper":492,"created_at":506},5592,"Evaluation of Concept-Rank Collapse Audits for Computer Vision Agriculture Disease Classifiers Under Low-Label Regimes: An Interpretability Capacity Bound for Smallholder Fungicide Selectivity","https:\u002F\u002Fdoi.org\u002F10.5281\u002Fzenodo.23545193","Concept-based interpretability methods for plant-disease classifiers are typically evaluated by whether their concept activations correlate with human-annotated labels, but this criterion is silent on a prior question: whether the classifier's internal representation retains enough concept-rank structure for any audit to be informative. the present analysis formalises that prior question as an interpretability capacity bound. A classifier is modelled as a concept-rank operator whose singular values govern how much concept-level signal survives the projection from pixel space to class logits, and a collapse audit is defined as the ratio of retained concept-rank energy to total concept energy. Under a low-label regime, where concept annotations are scarce and the audit must be estimated from few labelled examples, the bound predicts that audit reliability degrades as a function of the concept-rank spectrum and the label budget. The analysis is a theoretical and methodological contribution: it derives the bound, states the conditions under which a collapse audit is identifiable, and characterises the operating characteristics of the audit as a decision procedure under a declared variance structure (between-cluster SD = 6.0, residual SD = 4.5, intraclass correlation = 0.64). Power was estimated across 2000 design cells for cluster counts of 8, 16, 24 and 32 and effect sizes of 3, 5 and 8 percentage points; 52 clusters were required for 5 percentage points at 80% power. The bound reframes concept audits as capacity tests rather than fidelity tests, with consequences for how smallholder fungicide-selectivity decisions should be supported by interpretable disease classifiers.","面向植物病害分类器的基于概念的可解释性方法，通常以其概念激活是否与人工标注标签相关作为评价标准，但该标准对一个更先前的问题保持沉默：分类器的内部表征是否保留了足够的概念秩结构，从而使任何审计具有信息量。本分析将该先前问题形式化为一个可解释性容量上界。分类器被建模为概念秩算子，其奇异值支配着从像素空间到类别logits的投影中概念级信号得以保留的程度，并将坍缩审计定义为保留的概念秩能量与总概念能量之比。在低标签情形下，概念标注稀缺且审计必须由少量标注样本估计，该上界预测审计可靠性会随概念秩谱和标签预算的函数而退化。本分析是一项理论和方法论贡献：推导出该上界，陈述坍缩审计可识别的条件，并在声明的方差结构（簇间SD = 6.0，残差SD = 4.5，组内相关系数 = 0.64）下刻画审计作为决策程序的操作特征。在2000个设计单元中，针对簇数为8、16、24和32以及效应量为3、5和8个百分点的情形估计了功效；在80%功效下达到5个百分点需要52个簇。该上界将概念审计重新框定为容量检验而非保真度检验，并对可解释病害分类器应如何支持小农杀菌剂选择性决策具有启示意义。",{"impact":101,"substance":455,"depth":17,"authority":16,"freshness":12,"relevant":20,"comment":456},21,"理论方法论文，提出可解释性容量上界并给出审计功效分析，对智慧农业病害识别可信度有参考价值，但属小众方法学研究、缺乏田间实证，暂不宜进入每日精选。",[458],{"name":97,"url":451},[25,26,460,461,462],"小农户","植物病害识别","可解释性",{"code":464,"slug":465,"name":466,"path":467,"parent_code":468},"G2","farm-services","社会化服务与规模经营","\u002Ftopic\u002Frural-services\u002Ffarm-services","G",[470],{"code":31,"slug":32,"name":33,"path":34,"parent_code":35},{"status":38,"locked":13,"version":39,"method":40,"evidence":472},{"candidates":473,"agricultural_evidence":45},[474,479,483],{"code":464,"score":16,"supported":45,"title":475,"abstract":477,"tags":478},[476],"smallholder",[476],[460],{"code":31,"score":12,"supported":45,"title":480,"abstract":481,"tags":482},[264],[],[26,461],{"code":51,"score":20,"supported":13,"title":484,"abstract":485,"tags":486},[],[],[25],[488,489],"农业人工智能 植物病害识别 可解释性 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可解释性智慧农业-5592","10.5281\u002Fzenodo.23545193",{"doi":491,"openalex_id":493,"authors":494,"venue":97,"cited_by_count":85,"oa_url":451,"card":501,"direction":143,"ingested_from":86},"W7223137323",[495,497,499],{"name":496,"orcid":8},"Akshay Ramgoolam",{"name":498,"orcid":8},"Priya Bundhoo Appadoo",{"name":500,"orcid":8},"Jean-Noël LEspérance",{"tldr":502,"method":503,"finding":504,"direction":143,"opportunity":505},"提出可解释性容量上界，评估低标签下概念秩崩溃审计的可靠性。","将分类器建模为概念秩算子，推导容量上界并做2000格功效模拟。","审计可靠性随概念秩谱与标签预算下降；5个百分点效应需52个聚类达80%功效。","可将容量上界用于小农户杀菌剂选择性决策的可解释模型审计与标签预算设计。","2026-10-22T11:21:10.425290Z"]