[{"data":1,"prerenderedAt":-1},["ShallowReactive",2],{"item-4039":3,"related-4039":133},{"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":68,"slug":71,"view_count":72,"doi":73,"paper":74,"created_at":132},4039,"WeedNet: a foundation model-based global-to-local AI approach for weed species identification and classification","https:\u002F\u002Fdoi.org\u002F10.1038\u002Fs41467-026-78044-4","Early weed identification is crucial for effective management and control, and researchers, agronomists, and technology developers are increasingly interested in automating this process using computer vision and artificial intelligence; however, limited expert-verified data and variable morphological features have hindered the development of AI-based weed identification models. To address these issues, we present WeedNet, a global-scale weed identification model that can recognize an extensive set of weed species. WeedNet is an end-to-end weed identification pipeline that uses self-supervised learning, fine-tuning, and enhanced trustworthiness strategies. WeedNet achieved 91.02% accuracy across 1,593 weed species, with 41% of species achieving 100% accuracy. Using a fine-tuning approach, the local Iowa WeedNet model achieved 97.38% overall accuracy for 84 Iowa weeds. Testing across intra-species dissimilarity and inter-species similarity suggests that diversity in the images collected, spanning all the growth stages and distinguishable plant characteristics, is crucial in driving model performance. The global WeedNet model serves as a foundation, and the global-to-local strategy enables targeted fine-tuning to improve performance in regional weed communities. Additional validation of drone- and ground-rover-based images highlights WeedNet’s potential for integration into robotic platforms. Furthermore, integration with artificial intelligence for conversational use provides intelligent agricultural and ecological conservation consulting tools for farmers, researchers, and government agencies across diverse landscapes. Weeds consistently threaten crop yields worldwide, making early and accurate identification essential for effective management. Trained on 14 million images representing 1,593 weed species, WeedNet achieved 91% global accuracy and, through global-to-local fine-tuning, reached 97% accuracy for Iowa weeds.","早期杂草识别对有效管理和控制至关重要，研究人员、农艺学家和技术开发者对利用计算机视觉和人工智能实现该过程自动化的兴趣日益浓厚；然而，专家验证数据有限以及形态特征多变，阻碍了基于人工智能的杂草识别模型的发展。为解决这些问题，我们提出了WeedNet，一个能够识别大量杂草物种的全球尺度杂草识别模型。WeedNet是一个端到端的杂草识别流程，采用自监督学习、微调以及增强可信度策略。WeedNet在1,593种杂草上实现了91.02%的准确率，其中41%的物种达到100%准确率。采用微调方法，爱荷华本地WeedNet模型对84种爱荷华杂草实现了97.38%的总体准确率。对种内差异性和种间相似性的测试表明，所采集图像中涵盖所有生长阶段和可区分植物特征的多样性，对驱动模型性能至关重要。全球WeedNet模型作为基础，全球到本地策略能够实现有针对性的微调，以提升区域杂草群落中的性能。对无人机和地面巡游机器人图像进行的额外验证，凸显了WeedNet集成到机器人平台中的潜力。此外，与人工智能集成用于对话式使用，可为农民、研究人员和政府机构在不同景观中提供智能农业和生态保护咨询工具。杂草持续威胁全球作物产量，因此早期准确识别对有效管理至关重要。WeedNet在代表1,593种杂草的1,400万张图像上训练，实现了91%的全球准确率，并通过全球到本地微调，对爱荷华杂草达到97%的准确率。",null,"Nature Communications","2026-09-30T00:00:00Z","论文",10,false,89,{"impact":17,"substance":18,"depth":19,"authority":20,"freshness":21,"relevant":22,"comment":23},24,23,19,15,8,1,"基于1400万图像、覆盖1593种杂草的全球基础模型，全局到局部微调思路清晰，对智慧农业与农业机器人有实质参考价值。",[25],{"name":10,"url":6},[27,28,29,30,31],"智慧农业","农业人工智能","计算机视觉","农业机器人","杂草识别",{"code":33,"slug":34,"name":35,"path":36,"parent_code":37},"I2","agricultural-ai","农业AI与大模型","\u002Ftopic\u002Fdigital-agriculture\u002Fagricultural-ai","I",[],{"status":40,"locked":14,"version":41,"method":42,"evidence":43},"classified","2026-10-22.2","rules",{"candidates":44,"agricultural_evidence":47},[45,53,58,63],{"code":33,"score":46,"supported":47,"title":48,"abstract":49,"tags":52},11,true,[],[29,50,51],"artificial intelligence","computer vision",[28,29],{"code":54,"score":22,"supported":14,"title":55,"abstract":56,"tags":57},"F4",[],[],[31],{"code":59,"score":22,"supported":14,"title":60,"abstract":61,"tags":62},"F6",[],[],[30],{"code":64,"score":22,"supported":14,"title":65,"abstract":66,"tags":67},"I1",[],[],[27],[69,70],"WeedNet 杂草识别","Nature Communications 杂草识别模型","WeedNet杂草识别-4039",3,"10.1038\u002Fs41467-026-78044-4",{"doi":73,"openalex_id":75,"authors":76,"venue":10,"cited_by_count":124,"oa_url":6,"card":125,"direction":129,"ingested_from":131},"W7214939964",[77,80,83,86,89,91,93,96,99,102,104,107,108,110,113,115,118,121,123],{"name":78,"orcid":79},"Yanben Shen","https:\u002F\u002Forcid.org\u002F0000-0002-2847-3198",{"name":81,"orcid":82},"Timilehin T. Ayanlade","https:\u002F\u002Forcid.org\u002F0000-0003-4792-5337",{"name":84,"orcid":85},"Venkata Naresh Boddepalli","https:\u002F\u002Forcid.org\u002F0009-0008-0216-9156",{"name":87,"orcid":88},"Mojdeh Saadati","https:\u002F\u002Forcid.org\u002F0000-0002-9092-8464",{"name":90,"orcid":9},"Ashlyn Rairdin",{"name":92,"orcid":9},"Zi Kang Deng",{"name":94,"orcid":95},"Muhammad Arshad","https:\u002F\u002Forcid.org\u002F0000-0003-1574-7097",{"name":97,"orcid":98},"Baskar Ganapathysubramanian","https:\u002F\u002Forcid.org\u002F0000-0003-4042-066X",{"name":100,"orcid":101},"Aditya Balu","https:\u002F\u002Forcid.org\u002F0000-0003-2005-2548",{"name":103,"orcid":9},"Daren Mueller",{"name":105,"orcid":106},"Asheesh Kumar Singh","https:\u002F\u002Forcid.org\u002F0000-0002-7522-037X",{"name":105,"orcid":106},{"name":109,"orcid":9},"Wesley Everman",{"name":111,"orcid":112},"Nirav Merchant","https:\u002F\u002Forcid.org\u002F0000-0002-1988-8180",{"name":97,"orcid":114},"https:\u002F\u002Forcid.org\u002F0000-0002-8931-4852",{"name":116,"orcid":117},"Meaghan J. B. Anderson","https:\u002F\u002Forcid.org\u002F0009-0001-5904-1574",{"name":119,"orcid":120},"Soumik Sarkar","https:\u002F\u002Forcid.org\u002F0000-0002-6775-9199",{"name":122,"orcid":9},"Arti Singh",{"name":122,"orcid":9},0,{"tldr":126,"method":127,"finding":128,"direction":129,"opportunity":130},"提出WeedNet基础模型，实现全球杂草物种识别与区域微调。","自监督学习、微调与可信策略，基于1400万张图像训练。","全球1593种杂草识别准确率91%，爱荷华84种微调后达97%。","农业人工智能与决策模型","可探索跨区域杂草基础模型微调与无人机\u002F机器人平台集成。","openalex","2026-10-02T23:30:41.979601Z",{"total":134,"page":22,"page_size":134,"items":135},6,[136,215,271,325,383,437],{"id":137,"title":138,"url":139,"summary":140,"summary_zh":141,"content":9,"source_name":142,"source_url":139,"published_at":143,"category":12,"cover_url":9,"hotness":13,"is_selected":14,"score":144,"score_detail":145,"sources":149,"tags":151,"primary_topic":153,"secondary_topics":154,"classification":155,"search_phrases":192,"slug":195,"view_count":196,"doi":197,"paper":198,"created_at":214},3660,"Designing a framework for Sustainable Smart Agriculture with Mobile Robots and CNN","https:\u002F\u002Fdoi.org\u002F10.33423\u002F25102b43","Advances in artificial intelligence, robotics, and computer vision enable intelligent gardening systems that reduce manual monitoring. This study presents a smart gardening framework integrating a mobile robot with convolutional neural network (CNN) flower recognition. The robot captures garden images, while the CNN classifies flower species and provides plant-specific information for future care decisions. Using 50 training images and 50 independent testing images, the model achieved 92.0% training accuracy and 95.0% testing accuracy. The framework connects robotic image acquisition with automated visual recognition and provides a foundation for future irrigation, fertilization, and autonomous garden-management functions.","人工智能、机器人技术和计算机视觉的进步使得智能园艺系统能够减少人工监测。本研究提出了一种智能园艺框架，将移动机器人与卷积神经网络（CNN）花卉识别相结合。机器人采集花园图像，CNN对花卉种类进行分类，并提供植物特定信息，以供未来养护决策使用。使用50张训练图像和50张独立测试图像，该模型达到了92.0%的训练准确率和95.0%的测试准确率。该框架将机器人图像采集与自动视觉识别相连接，并为未来的灌溉、施肥和自主花园管理功能奠定了基础。","Journal of Strategic Innovation and Sustainability","2026-09-28T00:00:00Z",56,{"impact":21,"substance":146,"depth":147,"authority":147,"freshness":13,"relevant":22,"comment":148},14,12,"论文提出移动机器人与CNN花卉识别结合的智能园艺框架，测试准确率95%，但样本仅50张、规模偏小，属细分领域方法探索，公共价值有限。",[150],{"name":142,"url":139},[27,28,29,30,152],"花卉识别",{"code":33,"slug":34,"name":35,"path":36,"parent_code":37},[],{"status":40,"locked":14,"version":41,"method":42,"evidence":156},{"candidates":157,"agricultural_evidence":47},[158,162,168,175,182,188],{"code":33,"score":46,"supported":47,"title":159,"abstract":160,"tags":161},[],[29,50,51],[28,29],{"code":64,"score":163,"supported":47,"title":164,"abstract":166,"tags":167},9,[165],"smart agriculture",[],[27],{"code":169,"score":134,"supported":47,"title":170,"abstract":171,"tags":174},"F3",[],[172,173],"施肥","fertilization",[],{"code":176,"score":134,"supported":47,"title":177,"abstract":178,"tags":181},"H3",[],[179,180],"灌溉","irrigation",[],{"code":183,"score":72,"supported":47,"title":184,"abstract":185,"tags":187},"B4",[],[186],"花卉",[],{"code":59,"score":22,"supported":14,"title":189,"abstract":190,"tags":191},[],[],[30],[193,194],"移动机器人 CNN 花卉识别","智能园艺 自动灌溉","移动机器人CNN花卉识别-3660",2,"10.33423\u002F25102b43",{"doi":197,"openalex_id":199,"authors":200,"venue":142,"cited_by_count":124,"oa_url":207,"card":208,"direction":212,"ingested_from":131},"W7214523094",[201,203,205],{"name":202,"orcid":9},"Ting Zhang",{"name":204,"orcid":9},"Oanh Phan",{"name":206,"orcid":9},"Jiang Lu","https:\u002F\u002Farticlegateway.com\u002Fjournals\u002Findex.php\u002FJSIS\u002Farticle\u002Fdownload\u002F8481\u002F7965",{"tldr":209,"method":210,"finding":211,"direction":212,"opportunity":213},"提出移动机器人结合CNN识别花卉的智能园艺框架，测试准确率达95%。","移动机器人采集图像，CNN用50张训练和50张测试图像分类花卉。","CNN花卉识别测试准确率95%，为自动灌溉施肥等管理奠定基础。","智慧农业 \u002F 农业物联网","可扩展至多作物识别与实时决策，并融合物联网实现闭环精准管理。","2026-09-28T23:30:08.100458Z",{"id":216,"title":217,"url":218,"summary":219,"summary_zh":220,"content":9,"source_name":221,"source_url":218,"published_at":222,"category":12,"cover_url":9,"hotness":13,"is_selected":14,"score":223,"score_detail":224,"sources":228,"tags":230,"primary_topic":233,"secondary_topics":234,"classification":235,"search_phrases":251,"slug":254,"view_count":124,"doi":255,"paper":256,"created_at":270},5587,"Calibration-Shift Inference for Computer Vision Agriculture Yield Models Under Retrofit Sensor Replacement: An Artificial Intelligence Post-Deployment Recalibration Guarantee","https:\u002F\u002Fdoi.org\u002F10.5281\u002Fzenodo.23544195","Computer vision yield models deployed in agricultural fields are routinely paired with retrofit sensor packages that replace or supplement the original imaging hardware, and the resulting calibration shift can silently invalidate the model's predictive guarantees. The analysis characterises the operating characteristics of the design under a declared variance structure with between-cluster standard deviation 6.0, residual standard deviation 4.5 and intraclass correlation 0.64, using 2000 replications per design cell across cluster counts of 8, 16, 24 and 32 and effect sizes of 3, 5 and 8 percentage points. The design attains 80% power at a 5 percentage point effect with 54 clusters. The paper states a formal guarantee: under stated assumptions on the stability of the calibration map, the before-after-control-impact estimator yields a consistent and asymptotically normal estimate of the calibration shift, and the associated confidence interval covers the true shift at the nominal rate. The contribution is a design-theoretic account of how retrofit-induced calibration shift can be detected and bounded without observational data, together with the sample-size requirements that follow.","部署在农田中的计算机视觉产量模型通常与改装传感器组件配合使用，这些组件用于替换或补充原始成像硬件，由此产生的校准偏移可能悄然使模型的预测保证失效。该分析在声明的方差结构下刻画了设计的工作特性，其中组间标准差为6.0、残差标准差为4.5、组内相关系数为0.64，每个设计单元采用2000次重复，聚类数分别为8、16、24和32，效应量为3、5和8个百分点。该设计在54个聚类、5个百分点效应下达到80%的检验力。论文给出了一项形式化保证：在关于校准映射稳定性的既定假设下，前后对照影响（before-after-control-impact）估计量给出校准偏移的一致且渐近正态的估计，且相关置信区间以名义覆盖率覆盖真实偏移。其贡献在于从设计理论角度说明了如何在没有观测数据的情况下检测并界定改装引起的校准偏移，以及随之而来的样本量要求。","Zenodo (CERN European Organization for Nuclear Research)","2026-10-21T00:00:00Z",65,{"impact":21,"substance":225,"depth":226,"authority":147,"freshness":13,"relevant":22,"comment":227},18,17,"方法学扎实、统计设计严谨的预印本论文，但偏理论设计层面，缺乏田间实证数据，产业影响有限，适合作为技术参考而非每日精选头条。",[229],{"name":221,"url":218},[27,28,29,231,232],"产量预测","传感器校准",{"code":33,"slug":34,"name":35,"path":36,"parent_code":37},[],{"status":40,"locked":14,"version":41,"method":42,"evidence":236},{"candidates":237,"agricultural_evidence":47},[238,242,246],{"code":33,"score":17,"supported":47,"title":239,"abstract":240,"tags":241},[50,51],[29,51],[28,29],{"code":64,"score":22,"supported":14,"title":243,"abstract":244,"tags":245},[],[],[27],{"code":247,"score":22,"supported":14,"title":248,"abstract":249,"tags":250},"I3",[],[],[231],[252,253],"计算机视觉 产量预测 传感器校准","农业人工智能 传感器校准 计算机视觉 产量预测","计算机视觉产量预测传感器校准-5587","10.5281\u002Fzenodo.23544195",{"doi":255,"openalex_id":257,"authors":258,"venue":221,"cited_by_count":124,"oa_url":218,"card":265,"direction":129,"ingested_from":131},"W7223104380",[259,261,263],{"name":260,"orcid":9},"Tigist Alemu Gebremariam",{"name":262,"orcid":9},"Hawi Tesfaye Desta",{"name":264,"orcid":9},"Mulugeta Bekele Wolde",{"tldr":266,"method":267,"finding":268,"direction":129,"opportunity":269},"提出改造传感器替换后视觉产量模型校准漂移的检测与置信区间保证方法。","用前后对照影响估计量，基于方差结构做2000次重复的模拟设计分析。","5个百分点效应下54个集群可达80%检验力，估计量一致且渐近正态。","可将该设计理论扩展到多传感器异构替换与在线校准监测，填补真实田间验证空白。","2026-10-22T11:21:01.554995Z",{"id":272,"title":273,"url":274,"summary":275,"summary_zh":276,"content":9,"source_name":221,"source_url":274,"published_at":222,"category":12,"cover_url":9,"hotness":13,"is_selected":14,"score":277,"score_detail":278,"sources":282,"tags":284,"primary_topic":287,"secondary_topics":288,"classification":289,"search_phrases":305,"slug":308,"view_count":124,"doi":309,"paper":310,"created_at":324},5584,"Distributionally-Robust Evaluation of Computer Vision Agriculture Disease Classifiers Under Climate-Driven Pathogen Range Shifts: An Artificial Intelligence Worst-Case Generalization Bound","https:\u002F\u002Fdoi.org\u002F10.5281\u002Fzenodo.23544150","Computer vision classifiers for crop disease are evaluated almost exclusively on held-out samples drawn from the same distribution as their training data, yet climate-driven pathogen range shifts mean that deployment environments are systematically out of distribution. The framework treats the deployment distribution as an adversarial perturbation of the training distribution within a Wasserstein ball whose radius is calibrated to observed climate displacement. Using NASA POWER monthly reanalysis for Harare, Zimbabwe (2000-2023, 312 monthly observations), the analysis estimates a mean air temperature of 18.914 C, a standard deviation of 3.107 C, and a warming trend of 0.2001 C per decade. These estimates anchor the radius of the ambiguity set and the resulting bound. The bound decomposes worst-case risk into an empirical risk term, a Wasserstein radius term scaled by the Lipschitz constant of the classifier, and a concentration term. Under plausible Lipschitz constants for convolutional backbones, the radius term dominates the empirical risk term once the climate displacement exceeds a threshold that the Harare record already approaches. The contribution is a formal evaluation criterion that replaces the i. i. d. assumption with a climate-calibrated ambiguity set, together with the analytical machinery needed to compute it.","作物病害的计算机视觉分类器几乎完全在与训练数据同分布的留出样本上进行评估，然而气候驱动的病原体分布范围变化意味着部署环境系统性地处于分布之外。该框架将部署分布视为训练分布在Wasserstein球内的对抗性扰动，球的半径根据观测到的气候位移进行校准。利用NASA POWER对津巴布韦哈拉雷的月度再分析数据（2000—2023年，312个月度观测值），分析估计平均气温为18.914°C，标准差为3.107°C，每十年升温趋势为0.2001°C。这些估计值锚定了模糊集的半径及由此得到的界。该界将最坏情况风险分解为经验风险项、由分类器Lipschitz常数缩放后的Wasserstein半径项以及集中项。在卷积骨干网络合理的Lipschitz常数下，一旦气候位移超过哈拉雷记录已接近的阈值，半径项便主导经验风险项。本文的贡献在于提出了一种形式化评估准则，以气候校准的模糊集替代独立同分布（i.i.d.）假设，并提供了计算该准则所需的分析工具。",75,{"impact":147,"substance":279,"depth":225,"authority":280,"freshness":13,"relevant":22,"comment":281},22,13,"方法新颖、数据具体，但属方法论预印论文，产业影响有限，适合作为专业精选而非头条。",[283],{"name":221,"url":274},[27,28,29,285,286],"作物病害","气候变化",{"code":33,"slug":34,"name":35,"path":36,"parent_code":37},[],{"status":40,"locked":14,"version":41,"method":42,"evidence":290},{"candidates":291,"agricultural_evidence":47},[292,296,301],{"code":33,"score":17,"supported":47,"title":293,"abstract":294,"tags":295},[50,51],[29,51],[28,29],{"code":297,"score":22,"supported":14,"title":298,"abstract":299,"tags":300},"H7",[],[],[286],{"code":64,"score":22,"supported":14,"title":302,"abstract":303,"tags":304},[],[],[27],[306,307],"NASA POWER 哈拉雷 气温","Wasserstein 分布鲁棒 病害分类","NASAPOWER哈拉雷气温-5584","10.5281\u002Fzenodo.23544150",{"doi":309,"openalex_id":311,"authors":312,"venue":221,"cited_by_count":124,"oa_url":274,"card":319,"direction":129,"ingested_from":131},"W7223087892",[313,315,317],{"name":314,"orcid":9},"Kossi Afeli",{"name":316,"orcid":9},"Akouvi Amegashie",{"name":318,"orcid":9},"Komlan Sélom Dossou",{"tldr":320,"method":321,"finding":322,"direction":129,"opportunity":323},"提出气候校准的分布鲁棒评估准则，替代i.i.d.假设评价作物病害视觉分类器。","用Wasserstein球建模部署分布偏移，以NASA POWER哈拉雷气温数据","气候位移超阈值后，半径项主导经验风险，现有评估会高估模型泛化能力。","可将气候校准的鲁棒评估扩展到多作物多区域，并研究适应分布偏移的鲁棒训练方法。","2026-10-22T11:21:00.036937Z",{"id":326,"title":327,"url":328,"summary":329,"summary_zh":330,"content":9,"source_name":331,"source_url":328,"published_at":332,"category":12,"cover_url":9,"hotness":13,"is_selected":14,"score":144,"score_detail":333,"sources":336,"tags":338,"primary_topic":341,"secondary_topics":342,"classification":343,"search_phrases":368,"slug":371,"view_count":124,"doi":372,"paper":373,"created_at":382},5385,"A Comprehensive Review of Deep Learning and Computer Vision Techniques for Fruit Quality Assessment and Classification","https:\u002F\u002Fdoi.org\u002F10.25258\u002Fijddt.16.75s.151","Fruit image analysis has become an essential research area in precision agriculture, enabling automated fruit classification, quality grading, maturity estimation, disease diagnosis, yield prediction, and intelligent harvesting through advances in computer vision and artificial intelligence (AI).Recent progress in imaging technologies, large-scale benchmark datasets, and deep learning has substantially improved the accuracy, robustness, and scalability of automated fruit analysis systems.This survey presents a comprehensive and systematic review of image processing and AI techniques for fruit image analysis.It covers the complete image analysis pipeline, including image acquisition, preprocessing, enhancement, color space transformation, segmentation, feature extraction, and handcrafted texture descriptors.Furthermore, conventional machine learning algorithms are reviewed alongside state-of-the-art deep learning architectures, including Convolutional Neural Networks (CNNs), Vision Transformers (ViTs), and Vision Mamba models, for applications such as fruit recognition, quality assessment, disease detection, ripeness estimation, and object detection.Publicly available benchmark datasets, evaluation metrics, and performance comparison strategies are also summarized to facilitate objective assessment of existing approaches.In addition, the survey discusses key research challenges, including illumination variations, occlusion, complex orchard environments, limited annotated datasets, computational complexity, and domain adaptation, while highlighting emerging research trends such as self-supervised learning, multimodal learning, explainable AI, lightweight deep networks, foundation models, and edge intelligence for real-time deployment.By providing a unified review of methodologies, datasets, evaluation protocols, challenges, and future research directions, this survey offers a comprehensive reference for researchers and practitioners developing intelligent and scalable fruit image analysis systems for precision agriculture.","水果图像分析已成为精准农业中的一个重要研究领域，借助计算机视觉和人工智能（AI）的进步，实现了果实自动分类、品质分级、成熟度估计、病害诊断、产量预测和智能采收。成像技术、大规模基准数据集和深度学习的最新进展显著提升了自动化水果分析系统的准确性、鲁棒性和可扩展性。本综述对用于水果图像分析的图像处理和AI技术进行了全面而系统的回顾。内容涵盖完整的图像分析流程，包括图像采集、预处理、增强、颜色空间变换、分割、特征提取和手工纹理描述符。此外，综述了传统机器学习算法以及最先进的深度学习架构，包括卷积神经网络（CNN）、视觉Transformer（ViT）和视觉Mamba模型，用于果实识别、品质评估、病害检测、成熟度估计和目标检测等应用。同时总结了公开可用的基准数据集、评价指标和性能比较策略，以便对现有方法进行客观评估。此外，本综述讨论了关键研究挑战，包括光照变化、遮挡、复杂果园环境、标注数据集有限、计算复杂度和域适应，并重点介绍了新兴研究趋势，如自监督学习、多模态学习、可解释AI、轻量级深度网络、基础模型和面向实时部署的边缘智能。通过提供方法、数据集、评价协议、挑战和未来研究方向的统一综述，本综述为开发面向精准农业的智能且可扩展的水果图像分析系统的研究人员和实践者提供了全面的参考。","International Journal of Drug Delivery Technology","2026-10-18T00:00:00Z",{"impact":21,"substance":225,"depth":334,"authority":134,"freshness":21,"relevant":22,"comment":335},16,"系统性综述覆盖CNN、ViT、Vision Mamba等前沿方法，信息量足，但期刊权威性一般且偏学术综述，公共价值有限，适合主题聚合而非每日精选头条。",[337],{"name":331,"url":328},[27,28,29,339,340],"深度学习","水果品质检测",{"code":33,"slug":34,"name":35,"path":36,"parent_code":37},[],{"status":40,"locked":14,"version":41,"method":42,"evidence":344},{"candidates":345,"agricultural_evidence":47},[346,355,362],{"code":33,"score":347,"supported":47,"title":348,"abstract":350,"tags":354},28,[349,51],"deep learning",[351,339,352,29,353,349,50,51],"目标检测","机器学习","machine learning",[28,339,29],{"code":64,"score":356,"supported":47,"title":357,"abstract":358,"tags":361},7,[],[359,360],"精准农业","precision agriculture",[27],{"code":363,"score":72,"supported":47,"title":364,"abstract":365,"tags":367},"B2",[],[366],"orchard",[],[369,370],"水果品质 计算机视觉 深度学习","农业人工智能 水果品质检测 计算机视觉 智慧农业","水果品质计算机视觉深度学习-5385","10.25258\u002Fijddt.16.75s.151",{"doi":372,"openalex_id":374,"authors":375,"venue":331,"cited_by_count":124,"oa_url":328,"card":376,"direction":212,"ingested_from":131},"W7222892831",[],{"tldr":377,"method":378,"finding":379,"direction":380,"opportunity":381},"系统综述深度学习与计算机视觉在水果品质评估与分级中的全流程方法。","综述图像采集到分割、特征提取及CNN、ViT、Vision Mamba等模型与公","深度学习显著提升水果分析精度与鲁棒性，但光照、遮挡和小样本仍是主要瓶颈。","农业遥感与作物表型","可探索自监督与轻量化模型在复杂果园遮挡、小样本场景下的边缘实时部署。","2026-10-20T23:30:10.066042Z",{"id":384,"title":385,"url":386,"summary":387,"summary_zh":9,"content":9,"source_name":388,"source_url":9,"published_at":389,"category":12,"cover_url":9,"hotness":13,"is_selected":14,"score":390,"score_detail":391,"sources":394,"tags":396,"primary_topic":399,"secondary_topics":405,"classification":407,"search_phrases":424,"slug":427,"view_count":124,"doi":9,"paper":428,"created_at":436},5363,"牛肉牛区域特征计算机视觉分析:基于 YOLO 与深度估计的牛体况自动评分","https:\u002F\u002Fbioengineer.org\u002Fcameras-learn-to-read-a-cows-spine-tail-head-and-body-shape-to-score-its-condition","Islam M.N., Schrick F.N., Edwards J.L., Burns R.T., Qi H., Gan H. (2026) 开发一种基于区域特定计算机视觉特征的牛肉牛体况自动评分(BCS)方法。研究通过 YOLO 检测 + 深度估计提取脊柱、尾根、体廓等区域特征,使用 SHAP 进行可解释 AI 分析,并以 XGBoost 融合。在 5 折交叉验证中两种模式均稳定。验证集仅 72 只动物且极端值样本少,深度图来自推断而非实测。框架可作为后续发展的方法学基础。DOI: 10.1016\u002Fj.atech.2026.102628。","Smart Agricultural Technology Vol.15 Article 102628 2026-10-15","2026-10-15T00:00:00Z",68,{"impact":147,"substance":392,"depth":226,"authority":280,"freshness":134,"relevant":22,"comment":393},20,"方法学上有新意，但验证样本仅72头且深度图为推断值，属细分领域论文进展，未达每日精选门槛。",[395],{"name":388,"url":386},[27,28,29,397,398],"肉牛养殖","体况评分",{"code":400,"slug":401,"name":402,"path":403,"parent_code":404},"C2","ruminants","草食牲畜","\u002Ftopic\u002Flivestock\u002Fruminants","C",[406],{"code":33,"slug":34,"name":35,"path":36,"parent_code":37},{"status":40,"locked":14,"version":41,"method":42,"evidence":408},{"candidates":409,"agricultural_evidence":47},[410,415,420],{"code":33,"score":17,"supported":47,"title":411,"abstract":413,"tags":414},[29,412],"YOLO",[29,412],[28,29],{"code":400,"score":147,"supported":47,"title":416,"abstract":418,"tags":419},[417],"肉牛",[417],[397],{"code":64,"score":22,"supported":14,"title":421,"abstract":422,"tags":423},[],[],[27],[425,426],"YOLO 深度估计 牛体况评分","牛肉牛 计算机视觉 BCS","YOLO深度估计牛体况评分-5363",{"doi":9,"openalex_id":9,"authors":429,"venue":9,"cited_by_count":124,"oa_url":9,"card":430,"direction":380,"ingested_from":435},[],{"tldr":431,"method":432,"finding":433,"direction":380,"opportunity":434},"用YOLO检测与深度估计提取牛体区域特征，实现肉牛体况自动评分。","YOLO检测、深度估计、SHAP可解释分析与XGBoost融合，5折交叉验证。","区域特征融合评分稳定，但验证集仅72头且深度图为推断值。","可引入实测深度传感器与更大样本，提升极端体况评分鲁棒性。","agent","2026-10-20T02:47:54.361149Z",{"id":438,"title":439,"url":440,"summary":441,"summary_zh":442,"content":9,"source_name":443,"source_url":440,"published_at":444,"category":12,"cover_url":9,"hotness":13,"is_selected":14,"score":445,"score_detail":446,"sources":448,"tags":450,"primary_topic":453,"secondary_topics":454,"classification":460,"search_phrases":476,"slug":479,"view_count":124,"doi":480,"paper":481,"created_at":504},5236,"A cross-domain review of artificial intelligence techniques for iot security, computer networks, image processing and smart agriculture in connected environments","https:\u002F\u002Fdoi.org\u002F10.1007\u002Fs44163-026-02500-9","The rapid digitization of modern systems has increased the demand for intelligent, adaptive, and data-driven solutions across connected systems. However, these domains face persistent challenges such as heterogeneous datasets, limited labeled data, real-time processing constraints, privacy concerns, model interpretability, and poor generalization across environments. This review examines the application of major Artificial Intelligence (AI) techniques for solving classification, prediction, optimization, anomaly detection, routing, image analysis, and decision-support problems. The empirical patterns across the literature are summarized cautiously across studies. General lessons that emerged across the reviewed domains were also presented. Overall, the review provides researchers with a concise foundation for understanding current AI methods, their practical limitations, and future research directions in the aspect of connected environments. This article has tried to clarify various aspects and overall issues related to the use of AI techniques in computer networks, image processing and computer vision, smart agriculture and related intelligent systems. The authors believe that this is a comprehensive and integrated survey of these AI techniques in a number of application domains, with an emphasis on their practical suitability, their current empirical limitations, and future research directions. Thus, the article is informative to researchers in the field and may be a guide to future research on the development of robust, interpretable, scalable, and context-aware AI-based connected systems.","现代系统的快速数字化增加了对互联系统中智能、自适应和数据驱动解决方案的需求。然而，这些领域面临诸如异构数据集、标注数据有限、实时处理约束、隐私问题、模型可解释性以及跨环境泛化能力差等持续挑战。本综述考察了主要人工智能（Artificial Intelligence, AI）技术在解决分类、预测、优化、异常检测、路由、图像分析和决策支持问题中的应用。本文谨慎地总结了文献中的实证规律。文中还提出了在所综述领域中浮现的一般性经验教训。总体而言，本综述为研究人员提供了一个简明的基础，以理解当前AI方法、其实际局限性以及互联环境方面的未来研究方向。本文试图阐明与AI技术在计算机网络、图像处理与计算机视觉、智慧农业及相关智能系统中的应用有关的各个方面和总体问题。作者认为，这是对若干应用领域中这些AI技术的全面且综合的调查，重点在于其实际适用性、当前实证局限性和未来研究方向。因此，本文对该领域的研究人员具有参考价值，并可为开发稳健、可解释、可扩展且具有情境感知能力的基于AI的互联系统的未来研究提供指导。","Discover Artificial Intelligence","2026-10-17T00:00:00Z",51,{"impact":21,"substance":147,"depth":13,"authority":147,"freshness":163,"relevant":22,"comment":447},"跨领域AI综述，涉及智慧农业但仅为其一分支，方法层面无突破性新结论，公共价值有限，不宜进入每日精选。",[449],{"name":443,"url":440},[27,28,29,451,452],"物联网安全","智能系统",{"code":33,"slug":34,"name":35,"path":36,"parent_code":37},[455],{"code":456,"slug":457,"name":458,"path":459,"parent_code":37},"I5","agricultural-iot","物联网传感与边缘计算","\u002Ftopic\u002Fdigital-agriculture\u002Fagricultural-iot",{"status":40,"locked":14,"version":41,"method":42,"evidence":461},{"candidates":462,"agricultural_evidence":47},[463,467,471],{"code":33,"score":19,"supported":47,"title":464,"abstract":465,"tags":466},[50],[29,50,51],[28,29],{"code":64,"score":20,"supported":47,"title":468,"abstract":469,"tags":470},[165],[27,165],[27],{"code":456,"score":21,"supported":47,"title":472,"abstract":474,"tags":475},[473],"IoT",[],[],[477,478],"AI 物联网安全 智慧农业","农业人工智能 物联网安全 计算机视觉 智慧农业","AI物联网安全智慧农业-5236","10.1007\u002Fs44163-026-02500-9",{"doi":480,"openalex_id":482,"authors":483,"venue":443,"cited_by_count":124,"oa_url":440,"card":499,"direction":212,"ingested_from":131},"W7222847048",[484,487,490,493,496],{"name":485,"orcid":486},"Bashir Olaniyi Sadiq","https:\u002F\u002Forcid.org\u002F0000-0001-7868-4076",{"name":488,"orcid":489},"Mohammed Dahiru Buhari","https:\u002F\u002Forcid.org\u002F0000-0002-1076-216X",{"name":491,"orcid":492},"IBRAHIM ADABARA","https:\u002F\u002Forcid.org\u002F0000-0001-8949-7540",{"name":494,"orcid":495},"Enerst Edozie","https:\u002F\u002Forcid.org\u002F0000-0002-7616-0962",{"name":497,"orcid":498},"Asaba Shabiluh","https:\u002F\u002Forcid.org\u002F0000-0001-6342-9099",{"tldr":500,"method":501,"finding":502,"direction":212,"opportunity":503},"综述AI在物联网安全、计算机网络、图像处理与智慧农业中的应用与局限。","跨领域文献综述，归纳分类、预测、优化、异常检测等方法。","各领域普遍受限于异构数据、标注少、实时性与可解释性不足。","可聚焦农业物联网中少标注、跨环境泛化的可解释实时AI模型研究。","2026-10-18T23:30:07.908595Z"]