[{"data":1,"prerenderedAt":-1},["ShallowReactive",2],{"item-5190":3,"related-5190":73},{"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":18,"tags":20,"primary_topic":9,"secondary_topics":24,"classification":25,"search_phrases":49,"slug":52,"view_count":53,"doi":54,"paper":55,"created_at":72},5190,"Traffic surveillance video-based a unified road accident detection, classification, and vehicle tracking framework using an optimized spatio-temporal attention mechanism","https:\u002F\u002Fdoi.org\u002F10.1371\u002Fjournal.pone.0357111","In recent days, vehicular accident detection has materialized because of the unique and intriguing application potential in the evolution of Intelligent Transportation Systems (ITS). To monitor and respond to the event of a fatal accident, real-world traffic surveillance footage requires continuous analysis. In this research, the road accident from the traffic surveillance video is detected, classified, and vehicle tracked using an efficient and innovative model. The surveillance videos are gathered from the CCTV Footage dataset, which is a publicly available dataset. The gathered videos are directly applied to the Spatio-Temporal Attention-based Adaptive Yolov9 with SE-InceptionNet and Deep SORT (AYSIDSORT) model for detecting, classifying and tracking traffic accidents very effectively. The developed network allows accurate detection and tracking of vehicles in real-time, which ensures the continuous traffic flow without losing moving objects. The variables of the proposed AYSIDSORT model are tuned by the developed Generation Probability-based Equilibrium Optimizer (GP-EO) to improve the detection and classification performance. The exact location of the accident is sent to the appropriate entities using an Internet of Things (IoT) platform to provide a timely rescue for the affected individual. Here, the proposed framework acts as a computer vision-based accident detection and tracking framework with potential IoT integration to find the exact location of the accident, which helps to provide a timely rescue for the affected individual. The effectiveness of the offered approach is validated with various baseline detection models. The accuracy of the suggested AYSIDSORT reaches to 95% in the 100th epoch, whereas there is a slight variation in the accuracy values when the batch size is varied from 4 to 128. The outcomes show that the designed framework is better than existing methods.","近年来，由于在智能交通系统（ITS）演进中具有独特而引人关注的应用潜力，车辆事故检测已得以实现。为了对致命事故进行监测和响应，需要对真实世界的交通监控视频进行持续分析。本研究采用一种高效且创新的模型，对交通监控视频中的道路事故进行检测、分类和车辆跟踪。监控视频采集自CCTV Footage数据集，这是一个公开可用的数据集。采集的视频直接输入基于时空注意力的自适应Yolov9结合SE-InceptionNet与Deep SORT（AYSIDSORT）模型，以非常有效地检测、分类和跟踪交通事故。所开发的网络能够实时准确检测和跟踪车辆，从而确保交通流连续且不丢失运动目标。所提出的AYSIDSORT模型的参数由所开发的基于生成概率的平衡优化器（GP-EO）进行调优，以提高检测和分类性能。事故的精确位置通过物联网（IoT）平台发送给相关实体，以便为受影响人员提供及时救援。在此，所提出的框架作为一种基于计算机视觉的事故检测与跟踪框架，并具有潜在的物联网集成能力，以确定事故的精确位置，从而有助于为受影响人员提供及时救援。所提供方法的有效性通过多种基线检测模型进行了验证。所建议的AYSIDSORT在第100个epoch时准确率达到95%，而当批量大小在4到128之间变化时，准确率值存在轻微波动。结果表明，所设计的框架优于现有方法。",null,"PLoS ONE","2026-10-15T00:00:00Z","论文",10,false,0,{"impact":15,"substance":15,"depth":15,"authority":15,"freshness":15,"relevant":15,"comment":17},"该研究属于智能交通领域的交通事故检测与车辆跟踪，与三农、农业信息化、智慧农业无直接关联，不建议进入每日精选。",[19],{"name":10,"url":6},[21,22,23],"计算机视觉","目标检测","智能交通",[],{"status":26,"locked":14,"version":27,"method":28,"evidence":29},"needs_review","2026-10-22.2","rules",{"candidates":30,"agricultural_evidence":14,"reason":48},[31,41],{"code":32,"score":33,"supported":34,"title":35,"abstract":36,"tags":40},"I5",9,true,[],[37,38,39],"物联网","internet of things","IoT",[],{"code":42,"score":43,"supported":34,"title":44,"abstract":45,"tags":47},"I2",8,[],[21,46],"computer vision",[22,21],"农业相关性需要复核",[50,51],"交通事故检测 YOLOv9","车辆跟踪 Deep SORT","交通事故检测YOLOv9-5190",1,"10.1371\u002Fjournal.pone.0357111",{"doi":54,"openalex_id":56,"authors":57,"venue":10,"cited_by_count":15,"oa_url":63,"card":64,"direction":70,"ingested_from":71},"W7221908286",[58,61],{"name":59,"orcid":60},"Chokkakula Devi","https:\u002F\u002Forcid.org\u002F0009-0009-7296-1883",{"name":62,"orcid":9},"Gowri S.","https:\u002F\u002Fjournals.plos.org\u002Fplosone\u002Farticle\u002Ffile?id=10.1371\u002Fjournal.pone.0357111&type=printable",{"tldr":65,"method":66,"finding":67,"direction":68,"opportunity":69},"提出融合时空注意力Yolov9与DeepSORT的交通事故检测、分类与车辆跟踪框架。","CCTV监控视频数据，时空注意力Yolov9+SE-InceptionNet+D","模型第100轮准确率达95%，优于基线方法，且可IoT上报事故位置。","农业人工智能与决策模型","可将该视频事故检测框架迁移至农机作业安全监控与乡村道路风险预警场景。","数字乡村与农业信息化","openalex","2026-10-17T23:30:40.791068Z",{"total":74,"page":53,"page_size":74,"items":75},6,[76,138,200,253,302,354],{"id":77,"title":78,"url":79,"summary":80,"summary_zh":9,"content":9,"source_name":81,"source_url":9,"published_at":82,"category":12,"cover_url":9,"hotness":13,"is_selected":14,"score":83,"score_detail":84,"sources":90,"tags":92,"primary_topic":96,"secondary_topics":102,"classification":103,"search_phrases":123,"slug":126,"view_count":127,"doi":128,"paper":129,"created_at":137},4643,"多尺度异构特征协同的棉花叶片病害检测模型(Multi-Scale Heterogeneous Synergistic Model for Cotton Leaf Disease Detection)","https:\u002F\u002Fwww.smartag.net.cn\u002FCN\u002F10.12133\u002Fj.smartag.SA202601027","辽宁工程技术大学沈学利团队基于改进RT-DETR提出MHSF-DETR,通过分层上下文选择主干、可学习加权融合与边界感知重构,实现多尺度异构特征协同。相比基准模型参数量与计算量分别降低22.42%和13.29%,mAP50提升3.2个百分点,外部数据集泛化mAP分别达80.3%与86.9%。局限:模型针对特定病斑尺度设计,跨作物迁移需重新训练。","智慧农业(中英文) 2026年第4期 2026-10-08","2026-10-08T00:00:00Z",78,{"impact":85,"substance":86,"depth":87,"authority":88,"freshness":43,"relevant":53,"comment":89},16,22,18,14,"改进RT-DETR的棉花叶片病害检测模型，参数量与计算量双降且精度提升，方法新颖、数据扎实，属细分领域实质进展。",[91],{"name":81,"url":79},[93,94,21,22,95],"智慧农业","农业人工智能","棉花病害检测",{"code":97,"slug":98,"name":99,"path":100,"parent_code":101},"A6","cash-crops","棉麻糖与特色经作","\u002Ftopic\u002Ffield-crops\u002Fcash-crops","A",[],{"status":104,"locked":14,"version":27,"method":28,"evidence":105},"classified",{"candidates":106,"agricultural_evidence":34},[107,113,118],{"code":97,"score":85,"supported":34,"title":108,"abstract":111,"tags":112},[109,110],"棉花","cotton",[],[],{"code":42,"score":114,"supported":14,"title":115,"abstract":116,"tags":117},3,[],[],[94,22,21],{"code":119,"score":53,"supported":14,"title":120,"abstract":121,"tags":122},"I1",[],[],[93],[124,125],"辽宁工程技术大学 棉花叶片病害检测","MHSF-DETR 棉花病害","辽宁工程技术大学棉花叶片病害检测-4643",2,"10.12133\u002Fj.smartag.sa202601027",{"doi":128,"openalex_id":9,"authors":130,"venue":9,"cited_by_count":15,"oa_url":9,"card":131,"direction":68,"ingested_from":136},[],{"tldr":132,"method":133,"finding":134,"direction":68,"opportunity":135},"提出MHSF-DETR棉花叶片病害检测模型，提升精度并降低参数量与计算量。","改进RT-DETR，采用分层上下文选择主干、可学习加权融合与边界感知重构。","mAP50提升3.2个百分点，参数量与计算量分别降低22.42%和13.29%，外部数据集泛化良好。","可探索跨作物病害检测的轻量化迁移学习与域自适应方法，减少重新训练成本。","agent","2026-10-11T00:09:47.309161Z",{"id":139,"title":140,"url":141,"summary":142,"summary_zh":143,"content":9,"source_name":144,"source_url":141,"published_at":145,"category":12,"cover_url":9,"hotness":13,"is_selected":14,"score":146,"score_detail":147,"sources":151,"tags":153,"primary_topic":156,"secondary_topics":161,"classification":162,"search_phrases":180,"slug":183,"view_count":15,"doi":184,"paper":185,"created_at":199},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":43,"substance":87,"depth":148,"authority":149,"freshness":13,"relevant":53,"comment":150},17,12,"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。",[152],{"name":144,"url":141},[93,94,21,154,155],"产量预测","传感器校准",{"code":42,"slug":157,"name":158,"path":159,"parent_code":160},"agricultural-ai","农业AI与大模型","\u002Ftopic\u002Fdigital-agriculture\u002Fagricultural-ai","I",[],{"status":104,"locked":14,"version":27,"method":28,"evidence":163},{"candidates":164,"agricultural_evidence":34},[165,171,175],{"code":42,"score":166,"supported":34,"title":167,"abstract":169,"tags":170},24,[168,46],"artificial intelligence",[21,46],[94,21],{"code":119,"score":53,"supported":14,"title":172,"abstract":173,"tags":174},[],[],[93],{"code":176,"score":53,"supported":14,"title":177,"abstract":178,"tags":179},"I3",[],[],[154],[181,182],"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":184,"openalex_id":186,"authors":187,"venue":144,"cited_by_count":15,"oa_url":141,"card":194,"direction":68,"ingested_from":71},"W7223104380",[188,190,192],{"name":189,"orcid":9},"Tigist Alemu Gebremariam",{"name":191,"orcid":9},"Hawi Tesfaye Desta",{"name":193,"orcid":9},"Mulugeta Bekele Wolde",{"tldr":195,"method":196,"finding":197,"direction":68,"opportunity":198},"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":201,"title":202,"url":203,"summary":204,"summary_zh":205,"content":9,"source_name":144,"source_url":203,"published_at":145,"category":12,"cover_url":9,"hotness":13,"is_selected":14,"score":206,"score_detail":207,"sources":210,"tags":212,"primary_topic":215,"secondary_topics":216,"classification":217,"search_phrases":233,"slug":236,"view_count":15,"doi":237,"paper":238,"created_at":252},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":149,"substance":86,"depth":87,"authority":208,"freshness":13,"relevant":53,"comment":209},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。",[211],{"name":144,"url":203},[93,94,21,213,214],"作物病害","气候变化",{"code":42,"slug":157,"name":158,"path":159,"parent_code":160},[],{"status":104,"locked":14,"version":27,"method":28,"evidence":218},{"candidates":219,"agricultural_evidence":34},[220,224,229],{"code":42,"score":166,"supported":34,"title":221,"abstract":222,"tags":223},[168,46],[21,46],[94,21],{"code":225,"score":53,"supported":14,"title":226,"abstract":227,"tags":228},"H7",[],[],[214],{"code":119,"score":53,"supported":14,"title":230,"abstract":231,"tags":232},[],[],[93],[234,235],"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":237,"openalex_id":239,"authors":240,"venue":144,"cited_by_count":15,"oa_url":203,"card":247,"direction":68,"ingested_from":71},"W7223087892",[241,243,245],{"name":242,"orcid":9},"Kossi Afeli",{"name":244,"orcid":9},"Akouvi Amegashie",{"name":246,"orcid":9},"Komlan Sélom Dossou",{"tldr":248,"method":249,"finding":250,"direction":68,"opportunity":251},"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":254,"title":255,"url":256,"summary":257,"summary_zh":9,"content":9,"source_name":258,"source_url":9,"published_at":259,"category":12,"cover_url":9,"hotness":13,"is_selected":14,"score":206,"score_detail":260,"sources":263,"tags":265,"primary_topic":269,"secondary_topics":275,"classification":277,"search_phrases":289,"slug":292,"view_count":15,"doi":9,"paper":293,"created_at":301},5534,"DC-YOLO：应对遮挡与光照变化的湖羊行为检测模型","https:\u002F\u002Ffinance.sina.com.cn\u002Froll\u002F2026-10-19\u002Fdoc-inivumaf7730137.shtml","中国农业大学团队针对集约化养殖中多目标严重遮挡、光照多变与类别不均问题，引入自适应细节—上下文注意力机制构建模块，并采用边界框相似度软抑制防止误删遮挡目标，预训练光照编码器迁移参数应对光照变化。数据集来自湖羊养殖场全天候监控，含505张标注图像、5类行为。","智慧农业（中英文）2026-10-19","2026-10-19T00:00:00Z",{"impact":87,"substance":261,"depth":148,"authority":208,"freshness":74,"relevant":53,"comment":262},21,"论文提出面向湖羊行为检测的DC-YOLO模型，方法有新意、数据来自真实养殖场，属智慧养殖细分领域实质进展，值得精选。",[264],{"name":258,"url":256},[94,266,22,267,268],"智慧养殖","湖羊","动物行为检测",{"code":270,"slug":271,"name":272,"path":273,"parent_code":274},"C2","ruminants","草食牲畜","\u002Ftopic\u002Flivestock\u002Fruminants","C",[276],{"code":42,"slug":157,"name":158,"path":159,"parent_code":160},{"status":104,"locked":14,"version":27,"method":28,"evidence":278},{"candidates":279,"agricultural_evidence":34},[280,284],{"code":270,"score":149,"supported":34,"title":281,"abstract":282,"tags":283},[267],[267],[267],{"code":42,"score":13,"supported":34,"title":285,"abstract":287,"tags":288},[286],"YOLO",[],[94,22],[290,291],"中国农业大学 湖羊 行为检测","DC-YOLO 遮挡 光照","中国农业大学湖羊行为检测-5534",{"doi":9,"openalex_id":9,"authors":294,"venue":9,"cited_by_count":15,"oa_url":9,"card":295,"direction":299,"ingested_from":136},[],{"tldr":296,"method":297,"finding":298,"direction":299,"opportunity":300},"提出DC-YOLO模型，用于湖羊行为检测，解决遮挡与光照变化问题。","自适应细节-上下文注意力、边界框相似度软抑制、光照编码器迁移，505张标注图像。","模型在遮挡和光照变化下有效检测湖羊行为，减少误删。","智慧农业 \u002F 农业物联网","可探索多模态融合与轻量化部署，提升复杂养殖场景下的实时行为监测能力。","2026-10-22T00:07:09.998247Z",{"id":303,"title":304,"url":305,"summary":306,"summary_zh":9,"content":9,"source_name":307,"source_url":9,"published_at":308,"category":12,"cover_url":9,"hotness":13,"is_selected":14,"score":309,"score_detail":310,"sources":312,"tags":314,"primary_topic":317,"secondary_topics":318,"classification":320,"search_phrases":341,"slug":344,"view_count":15,"doi":9,"paper":345,"created_at":353},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":85,"substance":261,"depth":148,"authority":33,"freshness":74,"relevant":53,"comment":311},"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。",[313],{"name":307,"url":305},[93,94,22,315,316],"无人机遥感","棉花病害",{"code":97,"slug":98,"name":99,"path":100,"parent_code":101},[319],{"code":42,"slug":157,"name":158,"path":159,"parent_code":160},{"status":104,"locked":14,"version":27,"method":28,"evidence":321},{"candidates":322,"agricultural_evidence":34},[323,328,333,337],{"code":42,"score":87,"supported":34,"title":324,"abstract":326,"tags":327},[325,286],"深度学习",[],[94,22],{"code":97,"score":329,"supported":34,"title":330,"abstract":331,"tags":332},11,[109],[110],[],{"code":119,"score":53,"supported":14,"title":334,"abstract":335,"tags":336},[],[],[93],{"code":176,"score":53,"supported":14,"title":338,"abstract":339,"tags":340},[],[],[315],[342,343],"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":346,"venue":9,"cited_by_count":15,"oa_url":9,"card":347,"direction":351,"ingested_from":136},[],{"tldr":348,"method":349,"finding":350,"direction":351,"opportunity":352},"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":355,"title":356,"url":357,"summary":358,"summary_zh":359,"content":9,"source_name":360,"source_url":357,"published_at":259,"category":12,"cover_url":9,"hotness":13,"is_selected":14,"score":15,"score_detail":361,"sources":363,"tags":365,"primary_topic":9,"secondary_topics":367,"classification":368,"search_phrases":376,"slug":379,"view_count":15,"doi":380,"paper":381,"created_at":394},5494,"YOLO-Based Real-Time Object Detection Using Computer Vision for Robotics","https:\u002F\u002Fdoi.org\u002F10.64388\u002Firev10i4-1724117","Robots operating in dynamic environments require rapid and reliable perception to identify people, tools, obstacles, and other objects before making movement or manipulation decisions. Conventional vision pipelines may require separate stages for region proposal, classification, and localization, which can increase computational cost and latency. You Only Look Once (YOLO) formulates object detection as a single-network prediction task and has become a practical family of detectors for real-time computer-vision applications. This paper presents a research-oriented framework for integrating a lightweight YOLO detector with a robot-mounted camera. The framework covers image acquisition, preprocessing, object detection, confidence filtering, coordinate interpretation, and communication with a robot controller. It also discusses model selection, deployment constraints, evaluation metrics, safety considerations, and a reproducible testing plan. Rather than reporting unperformed experiments, the paper defines how a prototype should be evaluated using precision, recall, mean average precision, inference latency, frame rate, and end-to-end response time. The analysis indicates that compact YOLO variants are suitable starting points for resource-constrained robotic platforms, while reliable navigation requires additional depth or distance sensing and a safety controller. The proposed approach can support obstacle awareness, object following, pick-and-place assistance, and indoor mobile-robot perception.","在动态环境中运行的机器人需要快速且可靠的感知能力，以便在做出移动或操作决策之前识别人、工具、障碍物和其他物体。传统视觉流水线可能需要区域提议、分类和定位等独立阶段，这会增加计算成本和延迟。You Only Look Once（YOLO）将目标检测表述为单网络预测任务，已成为实时计算机视觉应用中实用的一类检测器。本文提出了一个面向研究的框架，用于将轻量级YOLO检测器与机器人搭载的相机集成。该框架涵盖图像采集、预处理、目标检测、置信度过滤、坐标解释以及与机器人控制器的通信。文中还讨论了模型选择、部署约束、评估指标、安全考虑以及可复现的测试方案。本文不报告未进行的实验，而是定义了应如何使用精确率、召回率、平均精度均值、推理延迟、帧率和端到端响应时间来评估原型。分析表明，紧凑型YOLO变体适合作为资源受限机器人平台的起点，而可靠导航还需要额外的深度或距离传感以及安全控制器。所提出的方法可支持障碍物感知、目标跟随、拾取与放置辅助以及室内移动机器人感知。","Iconic Research and Engineering Journals",{"impact":15,"substance":15,"depth":15,"authority":15,"freshness":15,"relevant":15,"comment":362},"该文为通用机器人视觉论文，未涉及农业场景，与三农及农业信息化无直接关联，不建议进入每日精选。",[364],{"name":360,"url":357},[94,21,366],"机器人感知",[],{"status":26,"locked":14,"version":27,"method":28,"evidence":369},{"candidates":370,"agricultural_evidence":14,"reason":48},[371],{"code":42,"score":372,"supported":34,"title":373,"abstract":374,"tags":375},27,[46,286],[22,21,286],[94,21],[377,378],"YOLO 机器人 目标检测","农业人工智能 机器人感知 计算机视觉","YOLO机器人目标检测-5494","10.64388\u002Firev10i4-1724117",{"doi":380,"openalex_id":382,"authors":383,"venue":360,"cited_by_count":15,"oa_url":388,"card":389,"direction":68,"ingested_from":71},"W7222933754",[384,386],{"name":385,"orcid":9},"Aafareen Sikandar Shaikh",{"name":387,"orcid":9},"Archana Nilesh Pawar","https:\u002F\u002Fwww.irejournals.com\u002Fformatedpaper\u002F1724117.pdf",{"tldr":390,"method":391,"finding":392,"direction":68,"opportunity":393},"提出将轻量YOLO检测器与机器人相机集成的框架，并定义原型评估方案。","轻量YOLO单阶段检测、机器人相机图像采集与预处理、置信度过滤及控制器通信。","紧凑YOLO适合资源受限机器人平台，但可靠导航仍需深度感知与安全控制器。","可将该框架迁移至农业机器人，研究田间遮挡与光照变化下的轻量检测与深度感知融合。","2026-10-21T23:30:40.721716Z"]