[{"data":1,"prerenderedAt":-1},["ShallowReactive",2],{"item-2511":3,"related-2511":115},{"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":76,"slug":79,"view_count":61,"doi":80,"paper":81,"created_at":114},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。",null,"Frontiers in Artificial Intelligence","2026-09-14T00:00:00Z","论文",10,false,73,{"impact":17,"substance":18,"depth":19,"authority":20,"freshness":21,"relevant":22,"comment":23},15,20,17,13,8,1,"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。",[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","生猪养殖","精准畜牧",{"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":46},[45,51,59,66,71],{"code":33,"score":21,"supported":46,"title":47,"abstract":48,"tags":50},true,[],[29,49],"computer vision",[28,29],{"code":52,"score":53,"supported":46,"title":54,"abstract":55,"tags":58},"C",6,[],[56,57],"畜牧","livestock",[],{"code":60,"score":61,"supported":46,"title":62,"abstract":63,"tags":65},"C1",4,[],[64],"生猪",[30],{"code":67,"score":61,"supported":46,"title":68,"abstract":69,"tags":70},"C6",[],[31],[31],{"code":72,"score":22,"supported":14,"title":73,"abstract":74,"tags":75},"I1",[],[],[27],[77,78],"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":80,"openalex_id":82,"authors":83,"venue":10,"cited_by_count":104,"oa_url":105,"card":106,"direction":112,"ingested_from":113},"W7212747795",[84,87,90,92,95,97,99,102],{"name":85,"orcid":86},"Miguel Angel Valles-Coral","https:\u002F\u002Forcid.org\u002F0000-0002-8806-2892",{"name":88,"orcid":89},"Kelvin Lleins Rojas-Córdova","https:\u002F\u002Forcid.org\u002F0009-0001-4097-3961",{"name":91,"orcid":9},"Lloy Pinedo",{"name":93,"orcid":94},"Richard Injante","https:\u002F\u002Forcid.org\u002F0000-0002-2449-8937",{"name":96,"orcid":9},"Pierre Vidaurre-Rojas",{"name":98,"orcid":9},"Jorge Saavedra-Ramírez",{"name":100,"orcid":101},"Fernando Ruiz-Saavedra","https:\u002F\u002Forcid.org\u002F0000-0003-4664-4867",{"name":103,"orcid":9},"Williams Ramirez",0,"https:\u002F\u002Fwww.frontiersin.org\u002Fjournals\u002Fartificial-intelligence\u002Farticles\u002F10.3389\u002Ffrai.2026.1876396\u002Fpdf",{"tldr":107,"method":108,"finding":109,"direction":110,"opportunity":111},"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。","农业人工智能与决策模型","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。","智慧农业 \u002F 农业物联网","openalex","2026-09-15T23:30:08.535413Z",{"total":53,"page":22,"page_size":53,"items":116},[117,184,274,333,388,440],{"id":118,"title":119,"url":120,"summary":121,"summary_zh":122,"content":9,"source_name":123,"source_url":120,"published_at":124,"category":12,"cover_url":9,"hotness":13,"is_selected":14,"score":125,"score_detail":126,"sources":131,"tags":133,"primary_topic":135,"secondary_topics":139,"classification":141,"search_phrases":163,"slug":166,"view_count":22,"doi":167,"paper":168,"created_at":183},4426,"Animal welfare in the world of digitalization: Computer Vision in the context of foundational structures","https:\u002F\u002Fdoi.org\u002F10.1007\u002Fs43681-026-01417-4","Abstract Computer Vision is an emerging technology within Precision Livestock Farming (PLF), combining camera systems with artificial intelligence to monitor animal welfare. While animal ethicists recognize its potential benefits, they also raise concerns about possible negative implications for animal welfare. This paper argues that addressing ethical concerns cannot rely on solutions targeting isolated ethical risks; rather, potential solutions must account for the technology’s embeddedness within society-wide structures. The focus in this paper will be on foundational structures, these structures concern how the world is experienced and understood, what is taken as self-evident. Over centuries, humans have increasingly delegated tasks to machines and standardized the world in doing so. This process has fostered growing trust in the outcomes of (digital) technologies. These developments have changed human experience and understanding of the world in various ways. Farmers, as members of society, are unlikely to be exempt from this trend. Therefore, reflection on Computer Vision must go beyond the farming practice and take into account these foundational structures that are currently reshaping society at large. Computer Vision examined as embedded within foundational structures demonstrates that ethical issues are also embedded within these structures, consequently, potential solutions must take account of them to increase their effectiveness.","摘要 计算机视觉是精准畜牧业（PLF）中的一项新兴技术，它将摄像系统与人工智能相结合，以监测动物福利。尽管动物伦理学家认可其潜在益处，但也对其可能给动物福利带来的负面影响表示担忧。本文认为，解决伦理关切不能依赖于针对孤立伦理风险的方案；相反，潜在的解决方案必须考虑到该技术嵌入于全社会结构之中的事实。本文的关注重点将是基础性结构，这些结构关乎世界如何被体验和理解，以及什么被视为不言自明。几个世纪以来，人类越来越多地将任务委托给机器，并在此过程中使世界标准化。这一进程培育了人们对（数字）技术产物的日益信任。这些发展以多种方式改变了人类对世界的体验和理解。农民作为社会成员，不太可能置身于这一趋势之外。因此，对计算机视觉的反思必须超越养殖实践，并考虑到这些当前正在重塑整个社会的基础性结构。将计算机视觉置于基础性结构中加以审视表明，伦理问题同样嵌入于这些结构之中，因此，潜在的解决方案必须将其纳入考量，以提高其有效性。","AI and Ethics","2026-10-06T00:00:00Z",72,{"impact":127,"substance":18,"depth":128,"authority":129,"freshness":21,"relevant":22,"comment":130},12,18,14,"从社会基础结构层面反思计算机视觉在精准畜牧中的伦理嵌入，视角新颖、论证扎实，对智慧农业伦理治理有参考价值。",[132],{"name":123,"url":120},[27,28,29,134,31],"动物福利",{"code":67,"slug":136,"name":137,"path":138,"parent_code":52},"smart-livestock","养殖环境与智慧畜牧","\u002Ftopic\u002Flivestock\u002Fsmart-livestock",[140],{"code":33,"slug":34,"name":35,"path":36,"parent_code":37},{"status":40,"locked":14,"version":41,"method":42,"evidence":142},{"candidates":143,"agricultural_evidence":46},[144,150,155,159],{"code":67,"score":145,"supported":46,"title":146,"abstract":148,"tags":149},19,[147],"animal welfare",[31,134,147],[134,31],{"code":33,"score":145,"supported":46,"title":151,"abstract":152,"tags":154},[49],[29,153,49],"artificial intelligence",[28,29],{"code":52,"score":53,"supported":46,"title":156,"abstract":157,"tags":158},[],[56,57],[],{"code":72,"score":22,"supported":14,"title":160,"abstract":161,"tags":162},[],[],[27],[164,165],"计算机视觉 精准畜牧 动物福利","农业人工智能 计算机视觉 动物福利 智慧农业","计算机视觉精准畜牧动物福利-4426","10.1007\u002Fs43681-026-01417-4",{"doi":167,"openalex_id":169,"authors":170,"venue":123,"cited_by_count":104,"oa_url":177,"card":178,"direction":112,"ingested_from":113},"W7220695950",[171,174],{"name":172,"orcid":173},"Mariska Thalitha Bosschaert","https:\u002F\u002Forcid.org\u002F0000-0002-9160-7638",{"name":175,"orcid":176},"Bart Gremmen","https:\u002F\u002Forcid.org\u002F0000-0002-9652-6407","https:\u002F\u002Flink.springer.com\u002Fcontent\u002Fpdf\u002F10.1007\u002Fs43681-026-01417-4.pdf",{"tldr":179,"method":180,"finding":181,"direction":112,"opportunity":182},"论文论证计算机视觉用于动物福利时，伦理问题须置于社会基础结构中理解。","概念分析与伦理反思，结合精准畜牧中计算机视觉技术。","伦理问题嵌入社会基础结构，孤立风险方案无效，需整体考量。","可实证研究农民对计算机视觉的信任如何受社会基础结构影响，并设计嵌入伦理的监测系统。","2026-10-08T23:30:12.350082Z",{"id":185,"title":186,"url":187,"summary":188,"summary_zh":189,"content":9,"source_name":190,"source_url":187,"published_at":191,"category":12,"cover_url":9,"hotness":13,"is_selected":46,"score":192,"score_detail":193,"sources":198,"tags":200,"primary_topic":202,"secondary_topics":207,"classification":214,"search_phrases":251,"slug":253,"view_count":242,"doi":254,"paper":255,"created_at":273},2017,"Two Decades of Computer Vision in Precision Livestock Farming: an Umbrella Review of Applications, Benchmarking Evidence, and the Performance-to-Deployment Gap Across Cattle, Pig, and Poultry Systems","https:\u002F\u002Fdoi.org\u002F10.1016\u002Fj.compag.2026.112419","Computer vision is becoming a core technology in PLF, enabling non-contact monitoring, phenotyping, and decision support at both animal and group levels. This umbrella review synthesised review-level evidence from 112 reviews on cattle, pig, and poultry systems, covering visual applications for identification, phenotyping, health, behaviour, locomotion, body condition, growth, reproduction, mortality, and resource use. To preserve the review as the bibliographic unit while capturing multi-topic evidence, multi-label coding generated 328 review-domain assignments across six PLF computer vision domains. Health\u002Fstress and posture\u002Factivity were the most frequently reviewed areas; however, these patterns reflect review coverage rather than evidence strength. Benchmarking reporting averaged 11.09 out of 14 criteria, corresponding to 79.2%, but validation-critical items, including class balance, annotation protocols, validation splits, and farm or site reporting, remained less complete. Methodological confidence was limited: AMSTAR 2 classified 95 reviews as critically low and 17 as moderate, while ROBIS classified 78 as high, 17 as unclear, and 17 as low risk of bias. The corpus-level candidate-reference overlap estimate was 0.122% and is retained only as a sensitivity estimate, not as formal primary-study CCA or evidence of independence. Review-derived performance and readiness tiers identified a mean descriptive performance-to-deployment gap of 0.63 across 328 assignments. Overall, reported model performance continues to exceed documented farm-deployment evidence, highlighting the need for stronger external validation, transparent benchmarking, workflow integration, economic assessment, and user-readiness evidence before routine deployment claims can be supported.","计算机视觉正成为精准畜牧养殖（PLF）中的核心技术，能够在个体和群体层面实现非接触式监测、表型分析和决策支持。本伞状综述综合了112篇综述的综述级证据，涵盖牛、猪和家禽养殖系统，涉及识别、表型分析、健康、行为、运动、体况、生长、繁殖、死亡率和资源利用等视觉应用。为在保留综述作为文献计量单元的同时捕捉多主题证据，采用多标签编码在六个PLF计算机视觉领域中生成了328个综述-领域分配。健康\u002F应激和姿态\u002F活动是综述覆盖最多的领域；然而，这些模式反映的是综述覆盖情况而非证据强度。基准报告平均得分为14项标准中的11.09项，对应79.2%，但验证关键条目，包括类别平衡、标注方案、验证集划分以及农场或场地报告，仍不够完整。方法学可信度有限：AMSTAR 2将95篇综述评为极低质量，17篇评为中等质量；ROBIS将78篇评为高偏倚风险，17篇评为不明确，17篇评为低偏倚风险。语料库层面的候选参考文献重叠估计值为0.122%，仅作为敏感性估计保留，而非正式的一手研究CCA或独立性证据。基于综述推导的性能与就绪度分级在328个分配中识别出平均描述性性能-部署差距为0.63。总体而言，所报告的性能持续超过已记录的农场部署证据，凸显了在支持常规部署声明之前，需要更强的外部验证、透明的基准测试、工作流程整合、经济评估和用户就绪度证据。","Computers and Electronics in Agriculture","2026-09-09T00:00:00Z",87,{"impact":194,"substance":195,"depth":145,"authority":129,"freshness":196,"relevant":22,"comment":197},22,23,9,"基于112篇综述的伞式综述，系统揭示计算机视觉在牛猪禽精准养殖中性能与落地之间的差距，方法学与证据分级扎实，对智慧畜牧研发与部署具有较高参考价值。",[199],{"name":190,"url":187},[27,28,29,31,201],"智能养殖",{"code":203,"slug":204,"name":205,"path":206,"parent_code":52},"C3","poultry","家禽","\u002Ftopic\u002Flivestock\u002Fpoultry",[208,209],{"code":33,"slug":34,"name":35,"path":36,"parent_code":37},{"code":210,"slug":211,"name":212,"path":213,"parent_code":52},"C2","ruminants","草食牲畜","\u002Ftopic\u002Flivestock\u002Fruminants",{"status":40,"locked":14,"version":41,"method":42,"evidence":215},{"candidates":216,"agricultural_evidence":46},[217,222,226,231,236,240,247],{"code":33,"score":145,"supported":46,"title":218,"abstract":219,"tags":221},[49],[29,49,220],"decision support",[28,29],{"code":203,"score":129,"supported":46,"title":223,"abstract":224,"tags":225},[204],[205,204],[],{"code":52,"score":227,"supported":46,"title":228,"abstract":229,"tags":230},11,[57],[56],[],{"code":210,"score":227,"supported":46,"title":232,"abstract":234,"tags":235},[233],"cattle",[233],[],{"code":67,"score":61,"supported":46,"title":237,"abstract":238,"tags":239},[],[31],[31],{"code":241,"score":242,"supported":46,"title":243,"abstract":244,"tags":246},"I7",3,[],[245],"文献计量",[],{"code":72,"score":22,"supported":14,"title":248,"abstract":249,"tags":250},[],[],[27],[252,78],"农业人工智能 计算机视觉 智慧农业 智能养殖","农业人工智能计算机视觉智慧农业智能养殖-2017","10.1016\u002Fj.compag.2026.112419",{"doi":254,"openalex_id":256,"authors":257,"venue":190,"cited_by_count":104,"oa_url":187,"card":268,"direction":112,"ingested_from":113},"W7212062011",[258,260,263,265],{"name":259,"orcid":9},"Alexey Ruchay",{"name":261,"orcid":262},"Vladimir Kolpakov","https:\u002F\u002Forcid.org\u002F0000-0001-9658-7034",{"name":264,"orcid":9},"Hao Guo",{"name":266,"orcid":267},"Andrea Pezzuolo","https:\u002F\u002Forcid.org\u002F0000-0002-9955-9896",{"tldr":269,"method":270,"finding":271,"direction":112,"opportunity":272},"伞式综述112篇综述，梳理牛猪禽精准养殖计算机视觉应用与部署差距。","伞式综述，多标签编码328项，AMSTAR 2与ROBIS评估方法学质量。","模型性能普遍高于农场部署证据，平均性能-部署差距0.63，验证与基准报告不足。","可研究外部验证、标准化基准与农场工作流集成，弥合性能到部署的鸿沟。","2026-09-10T23:30:01.497855Z",{"id":275,"title":276,"url":277,"summary":278,"summary_zh":279,"content":9,"source_name":280,"source_url":277,"published_at":281,"category":12,"cover_url":9,"hotness":13,"is_selected":14,"score":282,"score_detail":283,"sources":286,"tags":288,"primary_topic":289,"secondary_topics":290,"classification":291,"search_phrases":312,"slug":313,"view_count":242,"doi":314,"paper":315,"created_at":332},1763,"Identifying mounting behaviour in boars using deep learning-based instance segmentation and binary classification - a pilot study","https:\u002F\u002Fdoi.org\u002F10.3389\u002Ffbinf.2026.1869902","Introduction Mounting behaviour in group-housed pigs poses significant welfare and productivity challenges, often resulting in injuries and stress. To address this issue, we developed a novel computer vision-based approach for the automatic detection of mounting behaviour in pigs. Methods The pilot study was conducted on eight boars, aged 4–5 months and weighing between 60 and 90 kg, housed in two groups of four. Continuous video footage was collected over a 1-week period using an overhead camera, resulting in 766 2-s video clips. The proposed hybrid approach integrates Mask Region-based Convolutional Neural Network (Mask R-CNN) instance segmentation with a binary classifier. To evaluate the model’s performance under varying data conditions, the dataset was divided into training, validation, and testing sets using three data grouping scenarios: by frame, by clip, and by day. Results Among the five evaluated binary classification algorithms, Support Vector Machine (SVM) was selected based on its superior performance. The hybrid system achieved a balanced accuracy and F1-score of 95% with the clip-based split, rising to 99% with the frame-based split and falling to 74% with the day-based split. Discussion Under pilot conditions, the system offers a feasible proof-of-concept for continuous monitoring of mounting behaviour in group-housed pigs, operating at a processing rate of five frames per second. This capability offers strong potential for supporting early intervention and proactive welfare management, subject to future multi-site validation. Moving forward, future research will focus on integrating individual animal tracking and conducting larger-scale studies to further explore the system’s scalability and enhance its performance.","引言 群养公猪中的爬跨行为对动物福利和生产性能构成重大挑战，常导致损伤和应激。为解决此问题，我们开发了一种基于计算机视觉的新方法，用于自动检测猪的爬跨行为。方法 本试验研究在8头4-5月龄、体重介于60-90公斤的公猪上进行，分为两组，每组4头。使用顶置摄像头连续采集一周的视频资料，共获得766段2秒的视频片段。所提出的混合方法结合了基于掩码区域的卷积神经网络（Mask R-CNN）实例分割与二元分类器。为评估模型在不同数据条件下的表现，数据集被划分为训练集、验证集和测试集，采用三种数据分组方案：按帧、按片段和按天划分。结果 在评估的五种二元分类算法中，基于其优越性能选择了支持向量机（SVM）。混合系统在按片段划分时达到了95%的平衡准确率和F1分数，在按帧划分时提升至99%，而在按天划分时降至74%。讨论 在试验条件下，该系统为群养公猪爬跨行为的持续监测提供了一个可行的概念验证，处理速度为每秒五帧。这一能力为支持早期干预和主动福利管理提供了强大潜力，但需在未来进行多地点验证。展望未来，研究将集中于整合个体动物追踪并进行更大规模的研究，以进一步探索系统的可扩展性并提升其性能。","Frontiers in Bioinformatics","2026-09-04T00:00:00Z",67,{"impact":127,"substance":18,"depth":128,"authority":127,"freshness":284,"relevant":22,"comment":285},5,"基于深度学习的猪只爬跨行为自动检测研究，方法新颖，数据详实，对智慧养殖有参考价值。",[287],{"name":280,"url":277},[27,28,29,30],{"code":33,"slug":34,"name":35,"path":36,"parent_code":37},[],{"status":40,"locked":14,"version":41,"method":42,"evidence":292},{"candidates":293,"agricultural_evidence":46},[294,300,304,308],{"code":33,"score":295,"supported":46,"title":296,"abstract":298,"tags":299},16,[297],"deep learning",[29,49],[28,29],{"code":67,"score":242,"supported":46,"title":301,"abstract":302,"tags":303},[],[134],[],{"code":60,"score":22,"supported":14,"title":305,"abstract":306,"tags":307},[],[],[30],{"code":72,"score":22,"supported":14,"title":309,"abstract":310,"tags":311},[],[],[27],[77,78],"农业人工智能计算机视觉智慧农业生猪养殖-1763","10.3389\u002Ffbinf.2026.1869902",{"doi":314,"openalex_id":316,"authors":317,"venue":280,"cited_by_count":104,"oa_url":326,"card":327,"direction":112,"ingested_from":113},"W7208756356",[318,320,322,324],{"name":319,"orcid":9},"Harry Aricibasi",{"name":321,"orcid":9},"Jessica Bode",{"name":323,"orcid":9},"Renée Bergeron",{"name":325,"orcid":9},"D Tulpan","https:\u002F\u002Fwww.frontiersin.org\u002Fjournals\u002Fbioinformatics\u002Farticles\u002F10.3389\u002Ffbinf.2026.1869902\u002Fpdf",{"tldr":328,"method":329,"finding":330,"direction":112,"opportunity":331},"提出基于Mask R-CNN和SVM的猪爬跨行为自动检测方法，实现群养公猪连续监测。","结合Mask R-CNN实例分割与SVM二分类，按帧、片段、天划分数据集评估。","系统在片段划分下平衡准确率与F1达95%，帧划分99%，天划分74%，处理速度5fps。","未来可集成个体追踪与多场地验证，提升模型泛化性，探索实时预警系统在猪福利管理的应用。","2026-09-06T23:30:10.059635Z",{"id":334,"title":335,"url":336,"summary":337,"summary_zh":338,"content":9,"source_name":339,"source_url":336,"published_at":340,"category":12,"cover_url":9,"hotness":13,"is_selected":14,"score":341,"score_detail":342,"sources":344,"tags":346,"primary_topic":349,"secondary_topics":350,"classification":351,"search_phrases":368,"slug":371,"view_count":104,"doi":372,"paper":373,"created_at":387},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":128,"depth":19,"authority":127,"freshness":13,"relevant":22,"comment":343},"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。",[345],{"name":339,"url":336},[27,28,29,347,348],"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":352},{"candidates":353,"agricultural_evidence":46},[354,359,363],{"code":33,"score":355,"supported":46,"title":356,"abstract":357,"tags":358},24,[153,49],[29,49],[28,29],{"code":72,"score":22,"supported":14,"title":360,"abstract":361,"tags":362},[],[],[27],{"code":364,"score":22,"supported":14,"title":365,"abstract":366,"tags":367},"I3",[],[],[347],[369,370],"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":372,"openalex_id":374,"authors":375,"venue":339,"cited_by_count":104,"oa_url":336,"card":382,"direction":110,"ingested_from":113},"W7223104380",[376,378,380],{"name":377,"orcid":9},"Tigist Alemu Gebremariam",{"name":379,"orcid":9},"Hawi Tesfaye Desta",{"name":381,"orcid":9},"Mulugeta Bekele Wolde",{"tldr":383,"method":384,"finding":385,"direction":110,"opportunity":386},"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":389,"title":390,"url":391,"summary":392,"summary_zh":393,"content":9,"source_name":339,"source_url":391,"published_at":340,"category":12,"cover_url":9,"hotness":13,"is_selected":14,"score":394,"score_detail":395,"sources":397,"tags":399,"primary_topic":402,"secondary_topics":403,"classification":404,"search_phrases":420,"slug":423,"view_count":104,"doi":424,"paper":425,"created_at":439},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":127,"substance":194,"depth":128,"authority":20,"freshness":13,"relevant":22,"comment":396},"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。",[398],{"name":339,"url":391},[27,28,29,400,401],"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":405},{"candidates":406,"agricultural_evidence":46},[407,411,416],{"code":33,"score":355,"supported":46,"title":408,"abstract":409,"tags":410},[153,49],[29,49],[28,29],{"code":412,"score":22,"supported":14,"title":413,"abstract":414,"tags":415},"H7",[],[],[401],{"code":72,"score":22,"supported":14,"title":417,"abstract":418,"tags":419},[],[],[27],[421,422],"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":424,"openalex_id":426,"authors":427,"venue":339,"cited_by_count":104,"oa_url":391,"card":434,"direction":110,"ingested_from":113},"W7223087892",[428,430,432],{"name":429,"orcid":9},"Kossi Afeli",{"name":431,"orcid":9},"Akouvi Amegashie",{"name":433,"orcid":9},"Komlan Sélom Dossou",{"tldr":435,"method":436,"finding":437,"direction":110,"opportunity":438},"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":441,"title":442,"url":443,"summary":444,"summary_zh":445,"content":9,"source_name":446,"source_url":443,"published_at":447,"category":12,"cover_url":9,"hotness":13,"is_selected":14,"score":448,"score_detail":449,"sources":451,"tags":453,"primary_topic":456,"secondary_topics":457,"classification":458,"search_phrases":482,"slug":485,"view_count":104,"doi":486,"paper":487,"created_at":496},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",56,{"impact":21,"substance":128,"depth":295,"authority":53,"freshness":21,"relevant":22,"comment":450},"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。",[452],{"name":446,"url":443},[27,28,29,454,455],"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":459},{"candidates":460,"agricultural_evidence":46},[461,469,476],{"code":33,"score":462,"supported":46,"title":463,"abstract":464,"tags":468},28,[297,49],[465,454,466,29,467,297,153,49],"目标检测","机器学习","machine learning",[28,454,29],{"code":72,"score":470,"supported":46,"title":471,"abstract":472,"tags":475},7,[],[473,474],"精准农业","precision agriculture",[27],{"code":477,"score":242,"supported":46,"title":478,"abstract":479,"tags":481},"B2",[],[480],"orchard",[],[483,484],"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":486,"openalex_id":488,"authors":489,"venue":446,"cited_by_count":104,"oa_url":443,"card":490,"direction":112,"ingested_from":113},"W7222892831",[],{"tldr":491,"method":492,"finding":493,"direction":494,"opportunity":495},"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"]