[{"data":1,"prerenderedAt":-1},["ShallowReactive",2],{"item-3544":3,"related-3544":53},{"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,"search_phrases":25,"slug":28,"view_count":15,"doi":29,"paper":30,"created_at":52},3544,"ATTENDANCE TRACKING USING COMPUTER VISION","https:\u002F\u002Fdoi.org\u002F10.62643\u002Fijerst.2026.v22.n3.4653","The Attendance Tracking Using Computer Vision system is an automated attendance-management solution that uses computer vision and face-recognition technologies to record attendance efficiently. Traditional attendance systems often require manual registers, identity cards, or biometric devices, which can consume time and require additional effort. The proposed system aims to automate the attendance process by identifying authorized individuals through captured images or video. The system uses a camera to capture images or video frames of people entering a classroom, office, laboratory, or other authorized area. A computer vision module detects faces from the captured frames and prepares them for recognition. The facerecognition module compares detected faces with previously enrolled and authorized face templates to identify the corresponding individuals. After successful identification, the system records attendance along with relevant information such as person ID, date, time, and attendance status. Duplicate entries can be prevented by applying session-based attendance rules. The system can also provide dashboards and reports showing attendance records, daily attendance counts, and historical attendance information. The proposed solution reduces the need for manual attendance marking and can improve the speed of attendance recording in suitable environments. It can be used in educational institutions, offices, training centers, and other controlled environments where authorized use and appropriate consent are available. Overall, the Attendance Tracking Using Computer Vision system provides a convenient approach to automated attendance management. Future enhancements can include liveness detection, improved recognition under different lighting conditions, mobile notifications, real-time dashboards, multilingual interfaces, and stronger privacy-preserving biometric storage.","使用计算机视觉的考勤跟踪系统是一种自动化考勤管理解决方案，利用计算机视觉和人脸识别技术高效地记录考勤。传统考勤系统通常需要人工登记、身份证件或生物识别设备，这些方式耗时且需要额外投入。所提出的系统旨在通过捕获的图像或视频识别授权人员，从而实现考勤流程的自动化。该系统使用摄像头捕获进入教室、办公室、实验室或其他授权区域的人员图像或视频帧。计算机视觉模块从捕获的帧中检测人脸，并为其识别做好准备。人脸识别模块将检测到的人脸与先前注册并授权的面部模板进行比对，以识别对应的人员。成功识别后，系统记录考勤及相关信息，如人员ID、日期、时间和出勤状态。通过应用基于会话的考勤规则，可以防止重复记录。该系统还可以提供仪表板和报告，展示考勤记录、每日出勤人数和历史考勤信息。所提出的解决方案减少了人工标记考勤的需求，并可在合适环境中提高考勤记录的速度。它可用于教育机构、办公室、培训中心以及其他受控环境，前提是存在授权使用和适当同意。总体而言，使用计算机视觉的考勤跟踪系统为自动化考勤管理提供了一种便捷方法。未来的增强功能可以包括活体检测、改进不同光照条件下的识别效果、移动通知、实时仪表板、多语言界面以及更强的隐私保护生物特征存储。",null,"International Journal of Engineering Research and Science & Technology","2026-09-24T00:00:00Z","论文",10,false,0,{"impact":15,"substance":15,"depth":15,"authority":15,"freshness":15,"relevant":15,"comment":17},"通用计算机视觉考勤系统论文，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},[21,22,23,24],"计算机视觉","人脸识别","智慧校园","考勤管理",[26,27],"计算机视觉 人脸识别 考勤系统","计算机视觉 人脸识别 智慧校园 考勤管理","计算机视觉人脸识别考勤系统-3544","10.62643\u002Fijerst.2026.v22.n3.4653",{"doi":29,"openalex_id":31,"authors":32,"venue":10,"cited_by_count":15,"oa_url":43,"card":44,"direction":50,"ingested_from":51},"W7214200153",[33,35,37,39,41],{"name":34,"orcid":9},"M Mohan rao",{"name":36,"orcid":9},"P Srividya",{"name":38,"orcid":9},"G Bala Ankith Reddy",{"name":40,"orcid":9},"P Abhishek Jayanth Goud",{"name":42,"orcid":9},"T Dattu Sai","https:\u002F\u002Fijerst.org\u002Findex.php\u002Fijerst\u002Farticle\u002Fdownload\u002F4653\u002F4295",{"tldr":45,"method":46,"finding":47,"direction":48,"opportunity":49},"用摄像头和计算机视觉人脸识别自动记录考勤，替代人工点名与刷卡。","摄像头采集图像，人脸检测与识别比对已注册模板，按会话规则记录考勤。","系统可自动识别授权人员并生成考勤记录与报表，减少人工操作、提升记录速度。","农业人工智能与决策模型","可将该考勤\u002F识别框架迁移到农业场景，如农户培训签到、田间作业人员到岗与用工管理。","智慧农业 \u002F 农业物联网","openalex","2026-09-26T23:30:11.568035Z",{"total":54,"page":55,"page_size":54,"items":56},6,1,[57,90,142,182,241,279],{"id":58,"title":59,"url":60,"summary":61,"summary_zh":9,"content":9,"source_name":62,"source_url":9,"published_at":63,"category":12,"cover_url":9,"hotness":13,"is_selected":14,"score":64,"score_detail":65,"sources":70,"tags":72,"search_phrases":77,"slug":80,"view_count":15,"doi":9,"paper":81,"created_at":89},3602,"Advancing pig lameness detection with a multi-task framework: Leveraging multi-view 3D pose estimation and wavelet convolution（多任务框架推进生猪跛行检测：利用多视角3D姿态估计与小波卷积）","https:\u002F\u002Fm2.mtmt.hu\u002Fapi\u002Fpublication\u002F36981064?&labelLang=hun","Xiang Li、Wang Haidong、Hu Zixuan、Norton Tomas、Jiang Tian、Xue Yueju等在Biosystems Engineering 1537-5110 Vol. 263 Paper: 104393（2026）发表。研究针对生猪跛行检测提出PoseGait-MT多任务分类框架，可同时检测跛行严重程度与受影响肢体。框架从多视角2D视频重建3D骨骼以缓解遮挡与视角依赖问题；提取3D步态时空特征（空间跟踪距离sTRK、头部上下振幅HBA、关节屈曲角JFA），并结合小波卷积（WTConv）增强低频特征提取、抑制高频噪声。实验结果显示：PoseGait-MT在5折交叉验证下对跛行严重程度分类平均准确率94.7%、受影响肢体识别95.7%；独立测试集上分别89%、91.4%。","Biosystems Engineering Vol. 263 2026-09-20","2026-09-20T00:00:00Z",78,{"impact":66,"substance":67,"depth":66,"authority":68,"freshness":54,"relevant":55,"comment":69},18,22,14,"核心期刊论文，方法新颖且实验数据扎实，对智慧养殖中的动物健康监测有实质参考价值，值得进入每日精选。",[71],{"name":62,"url":60},[73,21,74,75,76],"智慧农业","生猪养殖","3D姿态估计","动物健康监测",[78,79],"PoseGait-MT 生猪跛行检测","多视角3D姿态估计 生猪","PoseGait-MT生猪跛行检测-3602",{"doi":9,"openalex_id":9,"authors":82,"venue":9,"cited_by_count":15,"oa_url":9,"card":83,"direction":48,"ingested_from":88},[],{"tldr":84,"method":85,"finding":86,"direction":48,"opportunity":87},"提出PoseGait-MT多任务框架，用多视角3D姿态与小波卷积同时检测生猪跛行程度和患肢。","多视角2D视频重建3D骨骼，提取步态时空特征，结合小波卷积WTConv。","5折交叉验证跛行程度准确率94.7%、患肢识别95.7%，独立测试集为89%和91.4%。","可探索轻量化实时部署与跨农场泛化，并融合多模态数据提升早期跛行预警能力。","agent","2026-09-27T00:05:18.483996Z",{"id":91,"title":92,"url":93,"summary":94,"summary_zh":95,"content":9,"source_name":96,"source_url":93,"published_at":97,"category":12,"cover_url":9,"hotness":13,"is_selected":14,"score":98,"score_detail":99,"sources":102,"tags":104,"search_phrases":108,"slug":111,"view_count":15,"doi":112,"paper":113,"created_at":141},3513,"Accelerated development and deployment of computer vision models for invasive aquatic pests","https:\u002F\u002Fdoi.org\u002F10.1038\u002Fs41598-026-72212-8","Abstract Aquatic non-indigenous species (NIS) incur significant cultural, environmental and economic costs worldwide, and human surveillance is expensive and impractical at large scales. Computer vision models (CVMs) deployed on remote and autonomous vehicles can reduce the burden on trained human observers, but aquatic environments present unique challenges and lack frameworks for biosecurity-focused development and deployment. We present a practical framework for developing and deploying new species-specific CVMs for real-time use across surface vessel and remote vehicle platforms. We demonstrate the utility of our framework through its application to several taxonomically and ecologically diverse NIS in New Zealand: Mediterranean fanworm Sabella spallanzanii , South African oxygen weed Lagarosiphon major, and exotic Caulerpa ( Caulerpa brachypus and C. parvifolia ). For S. spallanzanii , we demonstrate efficient training from small datasets and deployment for real-time detection. Using exotic Caulerpa , we show how CVMs can be rapidly improved during an early incursion response. For L. major , standardised field validation methods enable the comparison of CVM and human detection rates across diverse locations and operating conditions. Collectively, these case studies demonstrate that our framework enables accurate detection and the robust assessment of model effectiveness under realistic field conditions and can be effectively applied to imagery from multiple platforms.","摘要 水生外来非本土物种（NIS）在全球范围内造成显著的文化、环境和经济损失，而人工监测成本高昂且难以大规模实施。部署在远程和自主载具上的计算机视觉模型（CVM）可减轻对训练有素的人类观察者的依赖，但水生环境面临独特挑战，且缺乏以生物安全为重点的开发和部署框架。我们提出了一个实用框架，用于开发和部署新的物种特异性CVM，以在水面船只和远程载具平台上实时使用。我们通过将该框架应用于新西兰多个在分类学和生态学上具有多样性的NIS来展示其效用：地中海缨鳃虫 Sabella spallanzanii、南非氧草 Lagarosiphon major 以及外来Caulerpa（Caulerpa brachypus 和 C. parvifolia）。对于 S. spallanzanii，我们展示了从小型数据集进行高效训练并部署用于实时检测。利用外来Caulerpa，我们展示了CVM如何在入侵早期响应期间快速改进。对于 L. major，标准化野外验证方法使得能够在不同地点和操作条件下比较CVM与人类检测率。总体而言，这些案例研究表明，我们的框架能够在现实野外条件下实现准确检测和对模型有效性的稳健评估，并可有效应用于来自多个平台的图像。","Scientific Reports","2026-09-23T00:00:00Z",80,{"impact":66,"substance":67,"depth":66,"authority":68,"freshness":100,"relevant":55,"comment":101},8,"提出面向水生入侵物种的计算机视觉模型开发与部署框架，含多物种实地验证，方法新颖且具生物安全应用价值，但属新西兰案例，对国内农业信息化影响有限。",[103],{"name":96,"url":93},[73,105,21,106,107],"农业人工智能","入侵物种监测","水生生物安全",[109,110],"新西兰 入侵水生物种 计算机视觉","Caulerpa 实时检测 模型","新西兰入侵水生物种计算机视觉-3513","10.1038\u002Fs41598-026-72212-8",{"doi":112,"openalex_id":114,"authors":115,"venue":96,"cited_by_count":15,"oa_url":134,"card":135,"direction":140,"ingested_from":51},"W7214089404",[116,119,121,123,125,128,131],{"name":117,"orcid":118},"Rose A. Pearson","https:\u002F\u002Forcid.org\u002F0000-0002-4700-2113",{"name":120,"orcid":9},"Gareth Preston",{"name":122,"orcid":9},"Jeremy Bulleid",{"name":124,"orcid":9},"Svenja David",{"name":126,"orcid":127},"Felix Vaux","https:\u002F\u002Forcid.org\u002F0000-0002-2882-7996",{"name":129,"orcid":130},"Daniel Clements","https:\u002F\u002Forcid.org\u002F0000-0001-9319-5588",{"name":132,"orcid":133},"Leigh W. Tait","https:\u002F\u002Forcid.org\u002F0000-0001-9153-139X","https:\u002F\u002Fwww.nature.com\u002Farticles\u002Fs41598-026-72212-8_reference.pdf",{"tldr":136,"method":137,"finding":138,"direction":48,"opportunity":139},"提出一套开发与部署水生入侵物种计算机视觉模型的实用框架，并在新西兰三种入侵物种上验证。","基于水面船与遥控平台图像，小数据集训练、实时检测与标准化野外验证。","框架能实现实时准确检测，并在真实野外条件下稳健评估模型效果。","可迁移至农业入侵生物监测，探索小样本跨平台模型与野外标准化评估体系。","数字乡村与农业信息化","2026-09-25T23:30:42.003495Z",{"id":143,"title":144,"url":145,"summary":146,"summary_zh":147,"content":9,"source_name":148,"source_url":145,"published_at":149,"category":12,"cover_url":9,"hotness":13,"is_selected":14,"score":150,"score_detail":151,"sources":155,"tags":157,"search_phrases":160,"slug":163,"view_count":15,"doi":9,"paper":164,"created_at":181},3489,"RootQuantV2: Adapting a Vision Foundation Model for Root-Trait Regression from Minirhizotron Imagery","https:\u002F\u002Farxiv.org\u002Fabs\u002F2609.25567","A lack of high-throughput phenotyping solutions for root traits in field-grown crops has severely constrained understanding and improvement of below-ground traits and processes. Minirhizotrons are the standard non-destructive root-phenotyping method in field environments. Computer vision solutions are needed to allow automated trait estimation at scale, but training data is scarce and human annotations are often inaccessible because they reside in proprietary software that only exports per-image scalar totals of root length and surface area. Nevertheless, large numeric archives of these root traits already exist. RootQuant showed that the traits can be predicted directly from the whole image by regression, thus removing manually traced masks from the pipeline; RootQuantV2 takes that idea further by replacing RootQuant's CNN backbone with a self-supervised ViT. We adapt a frozen DINOv3 ViT-L\u002F16 with a hybrid parameter-efficient scheme. Training only 11.9M parameters (3.78% of the model), RootQuantV2 achieves length and area $R^2$ of 0.950 and 0.930, respectively, while lowering length\u002Farea RMSE by 24.3%\u002F20.7% over RootQuant. RootQuantV2 thus repurposes legacy numeric archives for high-throughput, automated root trait estimation.","田间作物根系性状缺乏高通量表型分析解决方案，严重制约了对地下性状与过程的理解和改良。微根管（minirhizotron）是田间环境下标准的非破坏性根系表型分析方法。实现规模化自动化性状估计需要计算机视觉解决方案，但训练数据稀缺，且人工标注往往难以获取，因为这些标注存于专有软件中，而该软件仅能导出每幅图像根系长度和表面积的标量汇总值。尽管如此，这些根系性状的大型数值档案已经存在。RootQuant表明，可通过回归直接从整幅图像预测这些性状，从而将人工勾画的分割掩膜从流程中移除；RootQuantV2进一步推进了这一思路，将RootQuant的CNN骨干网络替换为自监督ViT。我们采用混合参数高效方案对冻结的DINOv3 ViT-L\u002F16进行适配。仅训练11.9M参数（占模型的3.78%），RootQuantV2在长度和面积上的$R^2$分别达到0.950和0.930，同时相较RootQuant将长度\u002F面积RMSE降低了24.3%\u002F20.7%。因此，RootQuantV2将遗留数值档案重新用于高通量、自动化的根系性状估计。","arXiv (Cornell University)","2026-09-22T00:00:00Z",77,{"impact":152,"substance":67,"depth":66,"authority":153,"freshness":100,"relevant":55,"comment":154},16,13,"将自监督视觉基础模型用于微根管图像根系性状回归，仅训练3.78%参数即显著提升精度，为田间根系高通量表型提供可复用方案。",[156],{"name":148,"url":145},[73,105,21,158,159],"根系表型","高通量育种",[161,162],"RootQuantV2 根系表型","DINOv3 微根管 根系","RootQuantV2根系表型-3489",{"doi":9,"openalex_id":165,"authors":166,"venue":148,"cited_by_count":15,"oa_url":174,"card":175,"direction":179,"ingested_from":51},"W7214246102",[167,169,171],{"name":168,"orcid":9},"Kinjalk Parth",{"name":170,"orcid":9},"Sebastian Varela",{"name":172,"orcid":173},"Andrew D. B. Leakey","https:\u002F\u002Forcid.org\u002F0000-0001-6251-024X","https:\u002F\u002Farxiv.org\u002Fpdf\u002F2609.25567",{"tldr":176,"method":177,"finding":178,"direction":179,"opportunity":180},"用冻结DINOv3 ViT微调回归，从微根管图像直接预测根系长度和面积。","冻结DINOv3 ViT-L\u002F16，混合参数高效微调，仅训11.9M参数。","长度和面积R²达0.950和0.930，RMSE比RootQuant降低24.3%\u002F20.7%。","农业遥感与作物表型","可探索将此类基础模型回归范式迁移到其他稀缺标注的田间表型性状，并融合多模态数据。","2026-09-25T23:30:24.097147Z",{"id":183,"title":184,"url":185,"summary":186,"summary_zh":187,"content":9,"source_name":188,"source_url":185,"published_at":97,"category":12,"cover_url":9,"hotness":13,"is_selected":14,"score":98,"score_detail":189,"sources":191,"tags":193,"search_phrases":196,"slug":199,"view_count":15,"doi":200,"paper":201,"created_at":240},3366,"Brazilian Insect Survey: A Platform for Pest Management","https:\u002F\u002Fdoi.org\u002F10.1007\u002Fs13744-026-01426-2","Abstract Modern agriculture faces significant challenges in integrated pest management, where collecting, connecting, and processing monitoring data in real time are essential. This study presents the Brazilian Insect Survey (BIS), a web-based platform designed to centralize and streamline phytosanitary data management, enabling the integration of computer vision, field experimentation, and population modeling within a unified digital ecosystem. The platform is organized into functional modules that support experimental data management (TrapSystem and AgroExperiment), automated insect detection and counting from digital images (InsectCV and AphidCV), and simulation of aphid population dynamics (ABISM). These components operate in synergy, supported by distributed processing infrastructure, to ensure scalable data handling and efficient analytical workflows. Multi-year field applications demonstrate that integrating field data acquisition and automated image analysis with mechanistic population modeling enables timely, model-driven interventions that reduce aphid infestation levels and protect crop yield potential under variable environmental conditions, providing empirical evidence for queryPlease check if the captured keywords are correct.the effectiveness of combining AI-based insect detection with population dynamics modeling in operational integrated pest management. The case studies presented here demonstrate that the BIS platform successfully integrates computer vision, field experimentation, and population modeling within a modular digital ecosystem, highlighting its potential to enhance decision-making and advance data-driven integrated pest management.","摘要 现代农业在有害生物综合治理方面面临重大挑战，其中实时采集、连接和处理监测数据至关重要。本研究提出了巴西昆虫调查平台（Brazilian Insect Survey，BIS），这是一个基于网络的平台，旨在集中化和简化植物检疫数据管理，使计算机视觉、田间试验和种群建模能够整合在一个统一的数字生态系统中。该平台按功能模块组织，支持实验数据管理（TrapSystem和AgroExperiment）、基于数字图像的昆虫自动检测与计数（InsectCV和AphidCV），以及蚜虫种群动态模拟（ABISM）。这些组件在分布式处理基础设施的支持下协同运行，以确保可扩展的数据处理和高效的分析工作流。多年田间应用表明，将田间数据采集和自动图像分析与机制性种群建模相结合，能够实现及时的、模型驱动的干预，从而在多变的环境条件下降低蚜虫侵染水平并保护作物产量潜力，为将基于人工智能的昆虫检测与种群动态建模相结合在实际有害生物综合治理中的有效性提供了经验证据。本文所呈现的案例研究表明，BIS平台成功地将计算机视觉、田间试验和种群建模整合在一个模块化数字生态系统中，凸显了其在增强决策能力和推进数据驱动有害生物综合治理方面的潜力。","Neotropical Entomology",{"impact":66,"substance":67,"depth":66,"authority":68,"freshness":100,"relevant":55,"comment":190},"巴西昆虫调查平台将计算机视觉与种群动态模型整合进IPM实践，方法新颖、多年田间验证，对智慧农业病虫害监测有参考价值。",[192],{"name":188,"url":185},[73,105,21,194,195],"病虫害监测","种群模型",[197,198],"Brazil 蚜虫 监测平台","农业人工智能 病虫害监测 计算机视觉 智慧农业","Brazil蚜虫监测平台-3366","10.1007\u002Fs13744-026-01426-2",{"doi":200,"openalex_id":202,"authors":203,"venue":188,"cited_by_count":15,"oa_url":185,"card":235,"direction":140,"ingested_from":51},"W7214074071",[204,207,209,212,215,217,220,223,226,229,232],{"name":205,"orcid":206},"Telmo De Cesaro Júnior","https:\u002F\u002Forcid.org\u002F0000-0002-2886-229X",{"name":208,"orcid":9},"Bárbara Stella Wehrmann",{"name":210,"orcid":211},"Alexandre Tagliari Lazzaretti","https:\u002F\u002Forcid.org\u002F0009-0004-8345-8216",{"name":213,"orcid":214},"Roberto Wiest","https:\u002F\u002Forcid.org\u002F0000-0001-7982-6603",{"name":216,"orcid":9},"Jorge Luis Boeira Bavaresco",{"name":218,"orcid":219},"Brenda Slongo Taca","https:\u002F\u002Forcid.org\u002F0009-0000-6408-5523",{"name":221,"orcid":222},"Nicolas Welfer Kirinus","https:\u002F\u002Forcid.org\u002F0009-0003-5260-3161",{"name":224,"orcid":225},"Crislaine Sartori Suzana Milan","https:\u002F\u002Forcid.org\u002F0000-0003-0562-7286",{"name":227,"orcid":228},"Jayme Garcia Arnal Barbedo","https:\u002F\u002Forcid.org\u002F0000-0002-1156-8270",{"name":230,"orcid":231},"Douglas Lau","https:\u002F\u002Forcid.org\u002F0000-0001-8648-0102",{"name":233,"orcid":234},"Rafael Rieder","https:\u002F\u002Forcid.org\u002F0000-0002-7435-9054",{"tldr":236,"method":237,"finding":238,"direction":50,"opportunity":239},"巴西昆虫调查平台整合计算机视觉、田间试验与种群建模，实现害虫实时监测与治理。","构建BIS网络平台，集成InsectCV\u002FAphidCV图像识别、TrapSys","AI昆虫检测与种群动态建模结合可降低蚜虫侵害并保护作物产量。","可探索多害虫跨区域监测数据标准化与模型迁移，构建开放植保决策生态。","2026-09-24T23:30:25.977846Z",{"id":242,"title":243,"url":244,"summary":245,"summary_zh":246,"content":9,"source_name":247,"source_url":244,"published_at":248,"category":12,"cover_url":9,"hotness":13,"is_selected":14,"score":15,"score_detail":249,"sources":251,"tags":253,"search_phrases":255,"slug":258,"view_count":15,"doi":259,"paper":260,"created_at":278},3064,"Computer vision and artificial intelligence system for real-time detection of the use of personal protective equipment in industrial environments","https:\u002F\u002Fdoi.org\u002F10.11591\u002Fijece.v16i5.pp2731-2749","Workplace safety in high-risk industrial sectors, such as heavy machinery maintenance, remains a critical challenge due to the improper use or omission of personal protective equipment (PPE). This study proposes an intelligent system based on computer vision and artificial intelligence, complemented by electronic devices for real-time detection and monitoring of helmet, vest, glove, and boot use. The research follows a quantitative approach with a quasi-experimental design, validated through controlled tests using a mannequin equipped with protective elements to simulate real working conditions. The system uses a camera connected to a Raspberry Pi running the YOLOv8 detection model, achieving 96.5% accuracy and 91.8% recall on a test set of 300 images. The model was trained on 2,250 images and validated with an additional 300. Detection results are transmitted to an ESP32 microcontroller, which controls local alerts through LEDs, an LCD screen, and a buzzer, as well as automatic notifications via Telegram over Wi-Fi. A sliding window filtering technique is applied to reduce false positives, improving monitoring reliability and reinforcing a preventative safety culture. It is concluded that integrating artificial intelligence into automated PPE detection offers an efficient, practical, and replicable solution for improving workplace safety in industrial environments.","在高风险工业部门（如重型机械维护）中，由于个人防护装备（PPE）的不当使用或缺失，工作场所安全仍然是一项关键挑战。本研究提出了一种基于计算机视觉和人工智能的智能系统，并辅以电子设备，用于实时检测和监测安全帽、背心、手套和靴子的使用情况。研究采用定量方法，结合准实验设计，并通过使用配备防护元素的假人模型进行受控测试来验证，以模拟真实工作条件。该系统使用连接至运行YOLOv8检测模型的Raspberry Pi的摄像头，在300张图像的测试集上实现了96.5%的准确率和91.8%的召回率。该模型在2,250张图像上进行了训练，并使用额外的300张图像进行了验证。检测结果传输至ESP32微控制器，由其通过LED、LCD屏幕和蜂鸣器控制本地警报，并通过Wi-Fi经Telegram实现自动通知。应用滑动窗口滤波技术以减少误报，提高监测可靠性，并强化预防性安全文化。研究结论认为，将人工智能集成到自动化PPE检测中，为改善工业环境中的工作场所安全提供了一种高效、实用且可复制的解决方案。","International Journal of Power Electronics and Drive Systems\u002FInternational Journal of Electrical and Computer Engineering","2026-09-18T00:00:00Z",{"impact":15,"substance":15,"depth":15,"authority":15,"freshness":15,"relevant":15,"comment":250},"该论文聚焦工业场景下个人防护装备的计算机视觉检测，与三农、农业信息化、智慧农业等主题无直接关联，不建议进入每日精选。",[252],{"name":247,"url":244},[105,21,254],"智能安防",[256,257],"农业人工智能 计算机视觉 智能安防","农业人工智能 计算机视觉","农业人工智能计算机视觉智能安防-3064","10.11591\u002Fijece.v16i5.pp2731-2749",{"doi":259,"openalex_id":261,"authors":262,"venue":247,"cited_by_count":15,"oa_url":272,"card":273,"direction":50,"ingested_from":51},"W7213550675",[263,266,269],{"name":264,"orcid":265},"Sebastian Jeremy Alegre Mendoza","https:\u002F\u002Forcid.org\u002F0009-0002-4509-2212",{"name":267,"orcid":268},"Luis Elias Mendoza Hueyta","https:\u002F\u002Forcid.org\u002F0009-0000-3410-130X",{"name":270,"orcid":271},"Félix Pucuhuayla-Revatta","https:\u002F\u002Forcid.org\u002F0000-0002-4603-6557","https:\u002F\u002Fijece.iaescore.com\u002Findex.php\u002FIJECE\u002Farticle\u002Fdownload\u002F41631\u002F18912",{"tldr":274,"method":275,"finding":276,"direction":48,"opportunity":277},"提出基于YOLOv8和树莓派的实时个人防护装备检测系统，准确率96.5%。","YOLOv8模型、树莓派、ESP32、滑动窗口滤波，2250张训练图像。","系统能实时检测头盔、背心、手套和靴子，准确率96.5%，召回率91.8%。","可迁移至农业场景，检测农机操作员或温室工人的防护装备使用，提升农业作业安全。","2026-09-21T23:30:10.777297Z",{"id":280,"title":281,"url":282,"summary":283,"summary_zh":284,"content":9,"source_name":285,"source_url":282,"published_at":248,"category":12,"cover_url":9,"hotness":13,"is_selected":14,"score":286,"score_detail":287,"sources":291,"tags":293,"search_phrases":296,"slug":299,"view_count":55,"doi":300,"paper":301,"created_at":316},3008,"AshGdNutDefAM: Machine-learning-based multi-feature framework for nutrient deficiency detection and classification in Ash gourd Plant","https:\u002F\u002Fdoi.org\u002F10.1016\u002Fj.atech.2026.102577","The sustainability of agricultural production is increasingly threatened by nutrient deficiencies that compromise crop health, quality, and yield. Optimal crop management requires early detection and classification of these nutrient deficiencies. Traditional methods employ laboratory testing to predict nutrient deficiency in plant samples. Computer vision models provide an alternative to visual inspection by analysing and predicting the presence of nutrient deficiencies. A hybrid feature-based learning framework, AshGdNutDefAM, is proposed for the automated detection of nutrient deficiencies in the Ash gourd ( Benincasa hispida ) plant variety as part of the study. A rule-based and vein-based feature extraction approach is proposed, encompassing domain-specific botanical knowledge along with conventional features such as colour, texture, and spatial descriptors to provide an exhaustive representation of nutrient deficiency symptoms. Key physiological characteristics, such as the green-to-yellow pixel ratio, extent of interveinal chlorosis, and the dimensions of necrotic margins, that are associated with macronutrient and micronutrient deficiencies, especially magnesium (Mg) and iron (Fe), are captured by rule-based features. The proposed framework extracts 55 discriminative features across five groups: colour, spatial, texture, vein, and rule-based features. These features are evaluated using three machine learning classifiers: Support Vector Machine (SVM), Random Forest, and Gradient Boosting. The dataset collected includes healthy, magnesium and iron deficiency of the Ash gourd plant variety captured from agricultural farms in Mysuru, India. The performance of the proposed feature set is further compared with conventional handcrafted feature extraction techniques, including Gray-Level Co-occurrence Matrix (GLCM), Histogram of Oriented Gradients (HOG), and Local Binary Patterns (LBP). The experimental results show that the SVM classifier trained with the proposed feature set achieves an accuracy of 82% and outperforms the conventional handcrafted feature extraction approaches. The dataset used includes only the Ash gourd plant variety and exhibits geographic and temporal biases, as it primarily covers data from specific regions and periods potentially limiting the model’s effectiveness. The proposed design paves the way for intelligent decision-support systems for precision agriculture and sustainable crop management while providing a scalable, comprehensible approach to nutrient deficiency identification.","农业生产的可持续性日益受到养分缺乏的威胁，养分缺乏会损害作物健康、品质和产量。优化的作物管理需要对这些养分缺乏进行早期检测和分类。传统方法采用实验室检测来预测植物样本中的养分缺乏。计算机视觉模型通过分析和预测养分缺乏的存在，为视觉检查提供了一种替代方案。本研究提出了一种基于混合特征的学习框架AshGdNutDefAM，用于自动检测冬瓜（Benincasa hispida）品种中的养分缺乏。研究提出了一种基于规则和叶脉的特征提取方法，结合领域特定的植物学知识以及颜色、纹理和空间描述符等常规特征，以提供养分缺乏症状的详尽表征。基于规则的特征捕获了与大量元素和微量元素缺乏（尤其是镁（Mg）和铁（Fe）缺乏）相关的关键生理特征，如绿黄像素比、脉间失绿程度和坏死边缘尺寸。所提出的框架提取了五组共55个判别性特征：颜色、空间、纹理、叶脉和基于规则的特征。这些特征使用三种机器学习分类器进行评估：支持向量机（SVM）、随机森林和梯度提升。所收集的数据集包括从印度迈苏鲁农业农场采集的冬瓜品种健康、镁缺乏和铁缺乏样本。所提出特征集的性能进一步与常规手工特征提取技术进行了比较，包括灰度共生矩阵（GLCM）、方向梯度直方图（HOG）和局部二值模式（LBP）。实验结果表明，使用所提出特征集训练的SVM分类器达到了82%的准确率，优于常规手工特征提取方法。所使用的数据集仅包含冬瓜品种，且存在地理和时间偏差，因为它主要涵盖特定区域和时间段的数据，可能限制模型的有效性。所提出的设计为精准农业和可持续作物管理的智能决策支持系统开辟了道路，同时提供了一种可扩展的、全面的","Smart Agricultural Technology",66,{"impact":100,"substance":288,"depth":152,"authority":153,"freshness":289,"relevant":55,"comment":290},20,9,"提出融合叶脉与规则特征的多特征机器学习框架，用于冬瓜缺镁缺铁识别，方法有创新但数据集地域局限、精度一般，属细分领域技术进展。",[292],{"name":285,"url":282},[73,105,21,294,295],"作物营养诊断","冬瓜种植",[297,298],"Ash gourd 营养缺乏 检测","Benincasa hispida 机器学习","Ashgourd营养缺乏检测-3008","10.1016\u002Fj.atech.2026.102577",{"doi":300,"openalex_id":302,"authors":303,"venue":285,"cited_by_count":15,"oa_url":282,"card":311,"direction":48,"ingested_from":51},"W7213551922",[304,306,309],{"name":305,"orcid":9},"Keerthi Prasad",{"name":307,"orcid":308},"B R Pushpa","https:\u002F\u002Forcid.org\u002F0000-0002-2585-0613",{"name":310,"orcid":9},"Ardashir Mohammadzadeh",{"tldr":312,"method":313,"finding":314,"direction":48,"opportunity":315},"提出AshGdNutDefAM多特征机器学习框架，自动检测和分类冬瓜缺镁缺铁症状。","融合颜色、纹理、空间、叶脉及规则特征共55维，用SVM、随机森林、梯度提升分类。","SVM结合所提特征集准确率达82%，优于GLCM、HOG、LBP等传统手工特征方法。","可扩展至多作物多营养元素，结合深度学习与田间实时图像提升泛化能力。","2026-09-20T23:30:03.844236Z"]