[{"data":1,"prerenderedAt":-1},["ShallowReactive",2],{"item-3489":3,"related-3489":56},{"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,"search_phrases":32,"slug":35,"view_count":36,"doi":9,"paper":37,"created_at":55},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。",null,"arXiv (Cornell University)","2026-09-22T00:00:00Z","论文",10,false,77,{"impact":17,"substance":18,"depth":19,"authority":20,"freshness":21,"relevant":22,"comment":23},16,22,18,13,8,1,"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。",[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","根系表型","高通量育种",[33,34],"RootQuantV2 根系表型","DINOv3 微根管 根系","RootQuantV2根系表型-3489",0,{"doi":9,"openalex_id":38,"authors":39,"venue":10,"cited_by_count":36,"oa_url":47,"card":48,"direction":52,"ingested_from":54},"W7214246102",[40,42,44],{"name":41,"orcid":9},"Kinjalk Parth",{"name":43,"orcid":9},"Sebastian Varela",{"name":45,"orcid":46},"Andrew D. B. Leakey","https:\u002F\u002Forcid.org\u002F0000-0001-6251-024X","https:\u002F\u002Farxiv.org\u002Fpdf\u002F2609.25567",{"tldr":49,"method":50,"finding":51,"direction":52,"opportunity":53},"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。","openalex","2026-09-25T23:30:24.097147Z",{"total":57,"page":22,"page_size":57,"items":58},6,[59,111,171,210,253,288],{"id":60,"title":61,"url":62,"summary":63,"summary_zh":64,"content":9,"source_name":65,"source_url":62,"published_at":66,"category":12,"cover_url":9,"hotness":13,"is_selected":14,"score":67,"score_detail":68,"sources":71,"tags":73,"search_phrases":76,"slug":79,"view_count":36,"doi":80,"paper":81,"created_at":110},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":19,"substance":18,"depth":19,"authority":69,"freshness":21,"relevant":22,"comment":70},14,"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。",[72],{"name":65,"url":62},[27,28,29,74,75],"入侵物种监测","水生生物安全",[77,78],"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":80,"openalex_id":82,"authors":83,"venue":65,"cited_by_count":36,"oa_url":102,"card":103,"direction":109,"ingested_from":54},"W7214089404",[84,87,89,91,93,96,99],{"name":85,"orcid":86},"Rose A. Pearson","https:\u002F\u002Forcid.org\u002F0000-0002-4700-2113",{"name":88,"orcid":9},"Gareth Preston",{"name":90,"orcid":9},"Jeremy Bulleid",{"name":92,"orcid":9},"Svenja David",{"name":94,"orcid":95},"Felix Vaux","https:\u002F\u002Forcid.org\u002F0000-0002-2882-7996",{"name":97,"orcid":98},"Daniel Clements","https:\u002F\u002Forcid.org\u002F0000-0001-9319-5588",{"name":100,"orcid":101},"Leigh W. Tait","https:\u002F\u002Forcid.org\u002F0000-0001-9153-139X","https:\u002F\u002Fwww.nature.com\u002Farticles\u002Fs41598-026-72212-8_reference.pdf",{"tldr":104,"method":105,"finding":106,"direction":107,"opportunity":108},"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。","农业人工智能与决策模型","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":112,"title":113,"url":114,"summary":115,"summary_zh":116,"content":9,"source_name":117,"source_url":114,"published_at":66,"category":12,"cover_url":9,"hotness":13,"is_selected":14,"score":67,"score_detail":118,"sources":120,"tags":122,"search_phrases":125,"slug":128,"view_count":36,"doi":129,"paper":130,"created_at":170},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":19,"substance":18,"depth":19,"authority":69,"freshness":21,"relevant":22,"comment":119},"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。",[121],{"name":117,"url":114},[27,28,29,123,124],"病虫害监测","种群模型",[126,127],"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":129,"openalex_id":131,"authors":132,"venue":117,"cited_by_count":36,"oa_url":114,"card":164,"direction":109,"ingested_from":54},"W7214074071",[133,136,138,141,144,146,149,152,155,158,161],{"name":134,"orcid":135},"Telmo De Cesaro Júnior","https:\u002F\u002Forcid.org\u002F0000-0002-2886-229X",{"name":137,"orcid":9},"Bárbara Stella Wehrmann",{"name":139,"orcid":140},"Alexandre Tagliari Lazzaretti","https:\u002F\u002Forcid.org\u002F0009-0004-8345-8216",{"name":142,"orcid":143},"Roberto Wiest","https:\u002F\u002Forcid.org\u002F0000-0001-7982-6603",{"name":145,"orcid":9},"Jorge Luis Boeira Bavaresco",{"name":147,"orcid":148},"Brenda Slongo Taca","https:\u002F\u002Forcid.org\u002F0009-0000-6408-5523",{"name":150,"orcid":151},"Nicolas Welfer Kirinus","https:\u002F\u002Forcid.org\u002F0009-0003-5260-3161",{"name":153,"orcid":154},"Crislaine Sartori Suzana Milan","https:\u002F\u002Forcid.org\u002F0000-0003-0562-7286",{"name":156,"orcid":157},"Jayme Garcia Arnal Barbedo","https:\u002F\u002Forcid.org\u002F0000-0002-1156-8270",{"name":159,"orcid":160},"Douglas Lau","https:\u002F\u002Forcid.org\u002F0000-0001-8648-0102",{"name":162,"orcid":163},"Rafael Rieder","https:\u002F\u002Forcid.org\u002F0000-0002-7435-9054",{"tldr":165,"method":166,"finding":167,"direction":168,"opportunity":169},"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。","智慧农业 \u002F 农业物联网","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":172,"title":173,"url":174,"summary":175,"summary_zh":176,"content":9,"source_name":177,"source_url":174,"published_at":178,"category":12,"cover_url":9,"hotness":13,"is_selected":14,"score":179,"score_detail":180,"sources":184,"tags":186,"search_phrases":189,"slug":192,"view_count":36,"doi":193,"paper":194,"created_at":209},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","2026-09-18T00:00:00Z",66,{"impact":21,"substance":181,"depth":17,"authority":20,"freshness":182,"relevant":22,"comment":183},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。",[185],{"name":177,"url":174},[27,28,29,187,188],"作物营养诊断","冬瓜种植",[190,191],"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":193,"openalex_id":195,"authors":196,"venue":177,"cited_by_count":36,"oa_url":174,"card":204,"direction":107,"ingested_from":54},"W7213551922",[197,199,202],{"name":198,"orcid":9},"Keerthi Prasad",{"name":200,"orcid":201},"B R Pushpa","https:\u002F\u002Forcid.org\u002F0000-0002-2585-0613",{"name":203,"orcid":9},"Ardashir Mohammadzadeh",{"tldr":205,"method":206,"finding":207,"direction":107,"opportunity":208},"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",{"id":211,"title":212,"url":213,"summary":214,"summary_zh":9,"content":9,"source_name":215,"source_url":213,"published_at":216,"category":12,"cover_url":9,"hotness":13,"is_selected":14,"score":217,"score_detail":218,"sources":222,"tags":224,"search_phrases":227,"slug":230,"view_count":36,"doi":231,"paper":232,"created_at":252},2864,"Multi-Species Egg Morphometry and Weight Prediction Using Computer Vision","https:\u002F\u002Fdoi.org\u002F10.21203\u002Frs.3.rs-10538483\u002Fv1","Multi-Species Egg Morphometry and Weight Prediction Using Computer Vision。Research Square","Research Square","2026-09-17T00:00:00Z",64,{"impact":219,"substance":19,"depth":220,"authority":13,"freshness":182,"relevant":22,"comment":221},12,15,"计算机视觉用于多物种禽蛋形态测量与重量预测，方法有创新但属预印本、应用面偏窄，可作为智慧养殖技术动态收录。",[223],{"name":215,"url":213},[27,28,29,225,226],"家禽养殖","蛋品检测",[228,229],"蛋重预测 计算机视觉","禽蛋 形态测量","蛋重预测计算机视觉-2864","10.21203\u002Frs.3.rs-10538483\u002Fv1",{"doi":231,"openalex_id":233,"authors":234,"venue":215,"cited_by_count":36,"oa_url":251,"card":9,"direction":168,"ingested_from":54},"W7213451539",[235,238,241,243,245,247,249],{"name":236,"orcid":237},"Henna Hamadani","https:\u002F\u002Forcid.org\u002F0000-0002-0316-7418",{"name":239,"orcid":240},"Ambreen Hamadani","https:\u002F\u002Forcid.org\u002F0000-0002-5455-0468",{"name":242,"orcid":9},"Pakcha Hannah Boje",{"name":244,"orcid":9},"Amelia Moyon",{"name":246,"orcid":9},"Maliha Gulzar",{"name":248,"orcid":9},"A A Khan",{"name":250,"orcid":9},"R Kumar","https:\u002F\u002Fwww.researchsquare.com\u002Farticle\u002Frs-10538483\u002Flatest.pdf","2026-09-18T23:30:08.789024Z",{"id":254,"title":255,"url":256,"summary":257,"summary_zh":258,"content":9,"source_name":259,"source_url":256,"published_at":260,"category":12,"cover_url":9,"hotness":13,"is_selected":14,"score":15,"score_detail":261,"sources":265,"tags":267,"search_phrases":271,"slug":274,"view_count":36,"doi":275,"paper":276,"created_at":287},2650,"Automated Cocoa Bean Classification and Defect Detection Based on ASEAN Standard Using Image Processing and Feature-Based Analysis","https:\u002F\u002Fdoi.org\u002F10.64823\u002Fijeee.2601005","This study presents an automated cocoa bean classification and defect detection system developed in accordance with the ASEAN Standard for Cocoa Bean (ASEAN Stan 34:2014). Implemented in MATLAB, the system utilizes digital image processing and computer vision techniques to segment individual cocoa beans, extract geometric, color, and texture features, and classify them into quality categories: Extra Class, Class I, Class II, and Non-Compliant. The image processing workflow integrates color space transformations (RGB to HSV), adaptive thresholding, and morphological filtering to ensure accurate segmentation. Feature extraction targets parameters such as area, length, aspect ratio, texture entropy, and color uniformity to identify specific defects including moldy, slaty, insect-damaged, and germinated beans. Validation against independent expert grading achieved an overall reliability rate of 96.2%, with high precision (0.93) and recall (0.91), and an average processing speed of 1.3 seconds per image. The developed analyzer provides an objective, rapid, and repeatable tool to support standardization and postharvest cocoa quality control across the ASEAN region. Keywords: Defect Detection; MATLAB; cocoa bean grading; ASEAN Standard; digital image processing; computer vision","本研究提出了一套依据《东盟可可豆标准》（ASEAN Stan 34:2014）开发的自动化可可豆分类与缺陷检测系统。该系统在MATLAB中实现，利用数字图像处理与计算机视觉技术对单颗可可豆进行分割，提取几何、颜色和纹理特征，并将其分为优质级（Extra Class）、一级（Class I）、二级（Class II）和不合格（Non-Compliant）四个质量类别。图像处理流程整合了颜色空间变换（RGB转HSV）、自适应阈值分割和形态学滤波，以确保分割的准确性。特征提取针对面积、长度、长宽比、纹理熵和颜色均匀性等参数，以识别霉变、僵化、虫害和发芽等特定缺陷。经与独立专家评级进行验证，系统总体可靠率达到96.2%，精确率为0.93，召回率为0.91，平均处理速度为每张图像1.3秒。所开发的分析仪为支持东盟地区可可采后质量控制的标准化提供了一种客观、快速且可重复的工具。关键词：缺陷检测；MATLAB；可可豆分级；东盟标准；数字图像处理；计算机视觉","International Journal of Electrical and Electronics Engineering","2026-09-14T00:00:00Z",{"impact":19,"substance":262,"depth":263,"authority":20,"freshness":21,"relevant":22,"comment":264},21,17,"基于东盟标准的可可豆自动分级与缺陷检测研究，方法成熟、验证可靠（96.2%），对热带经济作物产后质控有实用价值，但属细分领域技术进展，影响力有限。",[266],{"name":259,"url":256},[27,28,29,268,269,270],"行业标准","农产品分级","可可产业",[272,273],"农业人工智能 农产品分级 计算机视觉 可可产业","农业人工智能 农产品分级","农业人工智能农产品分级计算机视觉可可产业-2650","10.64823\u002Fijeee.2601005",{"doi":275,"openalex_id":277,"authors":278,"venue":259,"cited_by_count":36,"oa_url":281,"card":282,"direction":168,"ingested_from":54},"W7212670192",[279],{"name":280,"orcid":9},"Jennifer Natnat","https:\u002F\u002Fioro.org\u002Farticle\u002F529160740839\u002Fpdf",{"tldr":283,"method":284,"finding":285,"direction":107,"opportunity":286},"基于图像处理与特征分析，按东盟标准自动分类可可豆并检测缺陷。","MATLAB图像处理，RGB转HSV、自适应阈值、形态学滤波，提取几何颜色纹理特","系统分类准确率96.2%，精度0.93，召回0.91，单图处理1.3秒。","可扩展至多作物、多标准实时分级，结合深度学习提升复杂缺陷识别鲁棒性。","2026-09-16T23:30:13.899726Z",{"id":289,"title":290,"url":291,"summary":292,"summary_zh":293,"content":9,"source_name":294,"source_url":291,"published_at":260,"category":12,"cover_url":9,"hotness":13,"is_selected":14,"score":295,"score_detail":296,"sources":298,"tags":300,"search_phrases":303,"slug":306,"view_count":22,"doi":307,"paper":308,"created_at":337},2511,"Evaluation of hybrid models based on image segmentation and inference for pig weight estimation","https:\u002F\u002Fdoi.org\u002F10.3389\u002Ffrai.2026.1876396","Introduction Accurate weight estimation in pig production is essential for optimizing management, feeding, and commercialization decisions; however, traditional weighing methods are invasive, time-consuming, and prone to operational errors. This study proposes a non-invasive computer vision–based approach to estimate pig weight under real farm conditions in San Martín, Peru. Methods A dataset of 3,800 lateral images paired with their corresponding ground-truth weights was collected. A computational pipeline was implemented, including geometric standardization, instance segmentation using YOLOv8n-seg, and feature extraction through EfficientNet-B0. The resulting embeddings were used as input for supervised regression models (SVR, XGBoost, and CatBoost), evaluated using repeated stratified cross-validation and an independent test set, with MAE, RMSE, and R² as performance metrics. Statistical comparisons were conducted using the Friedman test followed by Wilcoxon post hoc analysis with Holm correction. Results The results demonstrated strong predictive performance, with the SVR model achieving the best results (RMSE = 2.68 kg, MAE = 1.81 kg, R 2 = 0.85), showing statistically significant differences compared to the other models. Discussion These findings indicate that combining computer vision techniques with models capable of capturing non-linear relationships effectively models the relationship between animal morphology and body weight, providing a low-cost, non-invasive solution applicable to real-world production systems and supporting the advancement of precision livestock farming.","引言 在生猪生产中，准确的体重估测对于优化管理、饲喂和商业化决策至关重要；然而，传统称重方法具有侵入性、耗时且易产生操作误差。本研究提出了一种基于非侵入式计算机视觉的方法，用于在秘鲁圣马丁的实际农场条件下估测生猪体重。方法 收集了3，800张侧向图像及其对应的真实体重数据集。实施了计算流程，包括几何标准化、使用YOLOv8n-seg进行实例分割，以及通过EfficientNet-B0进行特征提取。所得嵌入向量被用作监督回归模型（SVR、XGBoost和CatBoost）的输入，采用重复分层交叉验证和独立测试集进行评估，以MAE、RMSE和R²作为性能指标。统计比较采用Friedman检验，随后进行Wilcoxon事后分析并应用Holm校正。结果 结果表明预测性能良好，SVR模型取得了最佳结果（RMSE = 2.68 kg，MAE = 1.81 kg，R² = 0.85），与其他模型相比显示出统计学显著差异。讨论 这些发现表明，将计算机视觉技术与能够捕捉非线性关系的模型相结合，可以有效建模动物形态与体重之间的关系，提供一种适用于实际生产系统的低成本、非侵入式解决方案，并支持精准畜牧养殖的发展。","Frontiers in Artificial Intelligence",73,{"impact":220,"substance":181,"depth":263,"authority":20,"freshness":21,"relevant":22,"comment":297},"基于YOLOv8分割与EfficientNet特征提取的生猪无接触称重研究，3800张图像、RMSE 2.68kg，方法组合与统计验证扎实，对精准畜牧有实用价值，但属细分技术进展，影响面有限。",[299],{"name":294,"url":291},[27,28,29,301,302],"生猪养殖","精准畜牧",[304,305],"农业人工智能 计算机视觉 智慧农业 生猪养殖","农业人工智能 计算机视觉","农业人工智能计算机视觉智慧农业生猪养殖-2511","10.3389\u002Ffrai.2026.1876396",{"doi":307,"openalex_id":309,"authors":310,"venue":294,"cited_by_count":36,"oa_url":331,"card":332,"direction":168,"ingested_from":54},"W7212747795",[311,314,317,319,322,324,326,329],{"name":312,"orcid":313},"Miguel Angel Valles-Coral","https:\u002F\u002Forcid.org\u002F0000-0002-8806-2892",{"name":315,"orcid":316},"Kelvin Lleins Rojas-Córdova","https:\u002F\u002Forcid.org\u002F0009-0001-4097-3961",{"name":318,"orcid":9},"Lloy Pinedo",{"name":320,"orcid":321},"Richard Injante","https:\u002F\u002Forcid.org\u002F0000-0002-2449-8937",{"name":323,"orcid":9},"Pierre Vidaurre-Rojas",{"name":325,"orcid":9},"Jorge Saavedra-Ramírez",{"name":327,"orcid":328},"Fernando Ruiz-Saavedra","https:\u002F\u002Forcid.org\u002F0000-0003-4664-4867",{"name":330,"orcid":9},"Williams Ramirez","https:\u002F\u002Fwww.frontiersin.org\u002Fjournals\u002Fartificial-intelligence\u002Farticles\u002F10.3389\u002Ffrai.2026.1876396\u002Fpdf",{"tldr":333,"method":334,"finding":335,"direction":107,"opportunity":336},"用YOLOv8n-seg分割猪体并提取EfficientNet特征，结合回归模型实现非侵入式猪体重估","3800张侧视图像，YOLOv8n-seg实例分割+EfficientNet-B","SVR表现最佳（RMSE=2.68kg，MAE=1.81kg，R²=0.85），显著优于其他模型。","可探索多视角、多品种及轻量化边缘部署，提升复杂农场环境下的泛化能力。","2026-09-15T23:30:08.535413Z"]