[{"data":1,"prerenderedAt":-1},["ShallowReactive",2],{"item-4370":3,"related-4370":94},{"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":9,"secondary_topics":32,"classification":33,"search_phrases":61,"slug":64,"view_count":22,"doi":65,"paper":66,"created_at":93},4370,"Effects of different nesting materials on crushing risk and sow posture changes in a farrowing system with temporary confinement","https:\u002F\u002Fdoi.org\u002F10.3389\u002Ffanim.2026.1960568","Introduction The provision of nesting material around farrowing is considered an important measure to support sow welfare, yet its practical implementation under commercial farrowing conditions remains limited. Methods This study evaluated the effects of different nesting materials on piglet crushing risk and sow activity in a commercial farrowing system with temporary crating for approximately 9 to 10 days around farrowing. A total of 263 farrowings were assigned to one of three material treatments: hay, straw, and a jute bag as minimal enrichment control. Nesting material use, farrowing performance, and crushing losses were recorded. In addition, sow activity during the first 72 h postpartum was quantified using a computer vision-based approach. Results Although substantial inter-individual variation was observed, the results show that nesting material type had no significant effect on material use. During the first three days postpartum, the odds of crushing were 46 % lower in the straw group compared to the jute bag control (p \u003C 0.05), whereas no significant difference was detected between hay and the control. No significant treatment effects were observed for crushing losses at the end of lactation. Sows provided with straw showed approximately 28 % fewer posture changes than control sows (p \u003C 0.05), and odds of crushing increased by approximately 8 % for every 10 posture changes (p \u003C 0.05). Discussion These findings indicate that not only the presence but also the functional properties of nesting material are relevant for piglet protection. The provision of structured materials such as long-stemmed straw represents a practical management measure to improve welfare outcomes under commercially relevant conditions and may contribute to more stable and less restless sow behavior during the critical periparturient period, even in systems with temporary confinement.","引言 在分娩前后提供筑巢材料被认为是保障母猪福利的重要措施，但在商业化分娩条件下其实际应用仍然有限。方法 本研究评估了在商业化分娩系统中，不同筑巢材料对仔猪压死风险和母猪活动的影响，该系统在分娩前后约9至10天采用临时限位栏。共将263次分娩分配到三种材料处理之一：干草、秸秆和黄麻袋作为最低限度富集对照。记录筑巢材料使用情况、分娩性能和压死损失。此外，采用基于计算机视觉的方法量化产后最初72小时内的母猪活动。结果 尽管观察到显著的个体间差异，结果表明筑巢材料类型对材料使用无显著影响。在产后最初三天内，秸秆组压死风险比黄麻袋对照组低46%（p \u003C 0.05），而干草组与对照组之间未检测到显著差异。在哺乳期末，未观察到处理对压死损失的显著影响。提供秸秆的母猪姿势变化次数比对照组母猪约少28%（p \u003C 0.05），且每10次姿势变化，压死风险增加约8%（p \u003C 0.05）。讨论 这些发现表明，不仅筑巢材料的存在与否，其功能特性也与仔猪保护相关。提供长茎秸秆等结构化材料代表了一种在商业相关条件下改善福利结果的实用管理措施，并可能有助于在围产期这一关键阶段使母猪行为更加稳定、减少躁动，即使在采用临时限位栏的系统中也是如此。",null,"Frontiers in Animal Science","2026-10-06T00:00:00Z","论文",10,false,73,{"impact":17,"substance":18,"depth":19,"authority":20,"freshness":21,"relevant":22,"comment":23},12,22,18,13,8,1,"基于263窝商业猪场数据的实证研究，发现稻草垫料可降低46%压仔风险并减少母猪姿态变化，对智慧养殖与动物福利管理有参考价值。",[25],{"name":10,"url":6},[27,28,29,30,31],"计算机视觉","智慧养殖","生猪养殖","动物福利","精准畜牧",[],{"status":34,"locked":14,"version":35,"method":36,"evidence":37},"needs_review","2026-10-22.2","rules",{"candidates":38,"agricultural_evidence":42,"reason":60},[39,48,54],{"code":40,"score":41,"supported":42,"title":43,"abstract":44,"tags":47},"C1",7,true,[],[45,46],"母猪","piglet",[29],{"code":49,"score":41,"supported":42,"title":50,"abstract":51,"tags":53},"I2",[],[27,52],"computer vision",[27],{"code":55,"score":56,"supported":14,"title":57,"abstract":58,"tags":59},"C6",2,[],[],[30,31],"多个产业证据相当，需要确认主归属",[62,63],"母猪 临时限位栏 垫料 压仔","Frontiers in Animal Science 母猪 姿态变化","母猪临时限位栏垫料压仔-4370","10.3389\u002Ffanim.2026.1960568",{"doi":65,"openalex_id":67,"authors":68,"venue":10,"cited_by_count":83,"oa_url":84,"card":85,"direction":91,"ingested_from":92},"W7220744633",[69,71,74,77,80],{"name":70,"orcid":9},"Johann Wahmhoff",{"name":72,"orcid":73},"Martin Wutke","https:\u002F\u002Forcid.org\u002F0000-0001-7839-2751",{"name":75,"orcid":76},"Astrid L. van Asten","https:\u002F\u002Forcid.org\u002F0009-0001-9091-4732",{"name":78,"orcid":79},"Nicole Kemper","https:\u002F\u002Forcid.org\u002F0000-0003-0092-4302",{"name":81,"orcid":82},"Imke Traulsen","https:\u002F\u002Forcid.org\u002F0000-0001-9761-0291",0,"https:\u002F\u002Fwww.frontiersin.org\u002Fjournals\u002Fanimal-science\u002Farticles\u002F10.3389\u002Ffanim.2026.1960568\u002Fpdf",{"tldr":86,"method":87,"finding":88,"direction":89,"opportunity":90},"比较三种垫料对母猪压仔风险和姿势变化的影响","263头次分娩试验，计算机视觉量化产后72小时母猪活动","稻草组压仔几率降46%，姿势变化少28%，每10次姿势变化压仔几率增8%","智慧农业 \u002F 农业物联网","可结合计算机视觉实时监测母猪姿势，开发压仔风险预警模型","农业人工智能与决策模型","openalex","2026-10-07T23:30:43.774144Z",{"total":95,"page":22,"page_size":95,"items":96},6,[97,172,249,297,385,449],{"id":98,"title":99,"url":100,"summary":101,"summary_zh":102,"content":9,"source_name":103,"source_url":100,"published_at":11,"category":12,"cover_url":9,"hotness":13,"is_selected":14,"score":104,"score_detail":105,"sources":109,"tags":111,"primary_topic":114,"secondary_topics":119,"classification":125,"search_phrases":151,"slug":154,"view_count":22,"doi":155,"paper":156,"created_at":171},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",72,{"impact":17,"substance":106,"depth":19,"authority":107,"freshness":21,"relevant":22,"comment":108},20,14,"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。",[110],{"name":103,"url":100},[112,113,27,30,31],"智慧农业","农业人工智能",{"code":55,"slug":115,"name":116,"path":117,"parent_code":118},"smart-livestock","养殖环境与智慧畜牧","\u002Ftopic\u002Flivestock\u002Fsmart-livestock","C",[120],{"code":49,"slug":121,"name":122,"path":123,"parent_code":124},"agricultural-ai","农业AI与大模型","\u002Ftopic\u002Fdigital-agriculture\u002Fagricultural-ai","I",{"status":126,"locked":14,"version":35,"method":36,"evidence":127},"classified",{"candidates":128,"agricultural_evidence":42},[129,135,140,146],{"code":55,"score":130,"supported":42,"title":131,"abstract":133,"tags":134},19,[132],"animal welfare",[31,30,132],[30,31],{"code":49,"score":130,"supported":42,"title":136,"abstract":137,"tags":139},[52],[27,138,52],"artificial intelligence",[113,27],{"code":118,"score":95,"supported":42,"title":141,"abstract":142,"tags":145},[],[143,144],"畜牧","livestock",[],{"code":147,"score":22,"supported":14,"title":148,"abstract":149,"tags":150},"I1",[],[],[112],[152,153],"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":155,"openalex_id":157,"authors":158,"venue":103,"cited_by_count":83,"oa_url":165,"card":166,"direction":89,"ingested_from":92},"W7220695950",[159,162],{"name":160,"orcid":161},"Mariska Thalitha Bosschaert","https:\u002F\u002Forcid.org\u002F0000-0002-9160-7638",{"name":163,"orcid":164},"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":167,"method":168,"finding":169,"direction":89,"opportunity":170},"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":173,"title":174,"url":175,"summary":176,"summary_zh":177,"content":9,"source_name":178,"source_url":175,"published_at":179,"category":12,"cover_url":9,"hotness":13,"is_selected":14,"score":15,"score_detail":180,"sources":184,"tags":186,"primary_topic":187,"secondary_topics":188,"classification":189,"search_phrases":214,"slug":217,"view_count":201,"doi":218,"paper":219,"created_at":248},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","2026-09-14T00:00:00Z",{"impact":181,"substance":106,"depth":182,"authority":20,"freshness":21,"relevant":22,"comment":183},15,17,"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。",[185],{"name":178,"url":175},[112,113,27,29,31],{"code":49,"slug":121,"name":122,"path":123,"parent_code":124},[],{"status":126,"locked":14,"version":35,"method":36,"evidence":190},{"candidates":191,"agricultural_evidence":42},[192,196,200,206,210],{"code":49,"score":21,"supported":42,"title":193,"abstract":194,"tags":195},[],[27,52],[113,27],{"code":118,"score":95,"supported":42,"title":197,"abstract":198,"tags":199},[],[143,144],[],{"code":40,"score":201,"supported":42,"title":202,"abstract":203,"tags":205},4,[],[204],"生猪",[29],{"code":55,"score":201,"supported":42,"title":207,"abstract":208,"tags":209},[],[31],[31],{"code":147,"score":22,"supported":14,"title":211,"abstract":212,"tags":213},[],[],[112],[215,216],"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":218,"openalex_id":220,"authors":221,"venue":178,"cited_by_count":83,"oa_url":242,"card":243,"direction":89,"ingested_from":92},"W7212747795",[222,225,228,230,233,235,237,240],{"name":223,"orcid":224},"Miguel Angel Valles-Coral","https:\u002F\u002Forcid.org\u002F0000-0002-8806-2892",{"name":226,"orcid":227},"Kelvin Lleins Rojas-Córdova","https:\u002F\u002Forcid.org\u002F0009-0001-4097-3961",{"name":229,"orcid":9},"Lloy Pinedo",{"name":231,"orcid":232},"Richard Injante","https:\u002F\u002Forcid.org\u002F0000-0002-2449-8937",{"name":234,"orcid":9},"Pierre Vidaurre-Rojas",{"name":236,"orcid":9},"Jorge Saavedra-Ramírez",{"name":238,"orcid":239},"Fernando Ruiz-Saavedra","https:\u002F\u002Forcid.org\u002F0000-0003-4664-4867",{"name":241,"orcid":9},"Williams Ramirez","https:\u002F\u002Fwww.frontiersin.org\u002Fjournals\u002Fartificial-intelligence\u002Farticles\u002F10.3389\u002Ffrai.2026.1876396\u002Fpdf",{"tldr":244,"method":245,"finding":246,"direction":91,"opportunity":247},"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",{"id":250,"title":251,"url":252,"summary":253,"summary_zh":9,"content":9,"source_name":254,"source_url":9,"published_at":255,"category":12,"cover_url":9,"hotness":13,"is_selected":14,"score":256,"score_detail":257,"sources":259,"tags":261,"primary_topic":264,"secondary_topics":267,"classification":268,"search_phrases":283,"slug":286,"view_count":287,"doi":9,"paper":288,"created_at":296},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":19,"substance":18,"depth":19,"authority":107,"freshness":95,"relevant":22,"comment":258},"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。",[260],{"name":254,"url":252},[112,27,29,262,263],"3D姿态估计","动物健康监测",{"code":40,"slug":265,"name":204,"path":266,"parent_code":118},"pigs","\u002Ftopic\u002Flivestock\u002Fpigs",[],{"status":126,"locked":14,"version":35,"method":36,"evidence":269},{"candidates":270,"agricultural_evidence":42},[271,275,279],{"code":40,"score":17,"supported":42,"title":272,"abstract":273,"tags":274},[204],[204],[29],{"code":147,"score":22,"supported":14,"title":276,"abstract":277,"tags":278},[],[],[112],{"code":49,"score":22,"supported":14,"title":280,"abstract":281,"tags":282},[],[],[27],[284,285],"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",3,{"doi":9,"openalex_id":9,"authors":289,"venue":9,"cited_by_count":83,"oa_url":9,"card":290,"direction":91,"ingested_from":295},[],{"tldr":291,"method":292,"finding":293,"direction":91,"opportunity":294},"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":298,"title":299,"url":300,"summary":301,"summary_zh":302,"content":9,"source_name":303,"source_url":300,"published_at":304,"category":12,"cover_url":9,"hotness":13,"is_selected":42,"score":305,"score_detail":306,"sources":310,"tags":312,"primary_topic":314,"secondary_topics":319,"classification":326,"search_phrases":362,"slug":364,"view_count":287,"doi":365,"paper":366,"created_at":384},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":18,"substance":307,"depth":130,"authority":107,"freshness":308,"relevant":22,"comment":309},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。",[311],{"name":303,"url":300},[112,113,27,31,313],"智能养殖",{"code":315,"slug":316,"name":317,"path":318,"parent_code":118},"C3","poultry","家禽","\u002Ftopic\u002Flivestock\u002Fpoultry",[320,321],{"code":49,"slug":121,"name":122,"path":123,"parent_code":124},{"code":322,"slug":323,"name":324,"path":325,"parent_code":118},"C2","ruminants","草食牲畜","\u002Ftopic\u002Flivestock\u002Fruminants",{"status":126,"locked":14,"version":35,"method":36,"evidence":327},{"candidates":328,"agricultural_evidence":42},[329,334,338,343,348,352,358],{"code":49,"score":130,"supported":42,"title":330,"abstract":331,"tags":333},[52],[27,52,332],"decision support",[113,27],{"code":315,"score":107,"supported":42,"title":335,"abstract":336,"tags":337},[316],[317,316],[],{"code":118,"score":339,"supported":42,"title":340,"abstract":341,"tags":342},11,[144],[143],[],{"code":322,"score":339,"supported":42,"title":344,"abstract":346,"tags":347},[345],"cattle",[345],[],{"code":55,"score":201,"supported":42,"title":349,"abstract":350,"tags":351},[],[31],[31],{"code":353,"score":287,"supported":42,"title":354,"abstract":355,"tags":357},"I7",[],[356],"文献计量",[],{"code":147,"score":22,"supported":14,"title":359,"abstract":360,"tags":361},[],[],[112],[363,216],"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":365,"openalex_id":367,"authors":368,"venue":303,"cited_by_count":83,"oa_url":300,"card":379,"direction":89,"ingested_from":92},"W7212062011",[369,371,374,376],{"name":370,"orcid":9},"Alexey Ruchay",{"name":372,"orcid":373},"Vladimir Kolpakov","https:\u002F\u002Forcid.org\u002F0000-0001-9658-7034",{"name":375,"orcid":9},"Hao Guo",{"name":377,"orcid":378},"Andrea Pezzuolo","https:\u002F\u002Forcid.org\u002F0000-0002-9955-9896",{"tldr":380,"method":381,"finding":382,"direction":89,"opportunity":383},"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":386,"title":387,"url":388,"summary":389,"summary_zh":390,"content":9,"source_name":303,"source_url":388,"published_at":391,"category":12,"cover_url":9,"hotness":13,"is_selected":14,"score":392,"score_detail":393,"sources":395,"tags":397,"primary_topic":399,"secondary_topics":400,"classification":402,"search_phrases":417,"slug":420,"view_count":201,"doi":421,"paper":422,"created_at":448},2015,"Mitigating artificial intelligence-related animal welfare risks in animal farming","https:\u002F\u002Fdoi.org\u002F10.1016\u002Fj.compag.2026.112408","Mitigating artificial intelligence-related animal welfare risks in animal farming。Computers and Electronics in Agriculture","减轻畜牧业中与人工智能相关的动物福利风险。《计算机与电子农业》","2026-09-10T00:00:00Z",79,{"impact":19,"substance":106,"depth":182,"authority":107,"freshness":13,"relevant":22,"comment":394},"核心期刊新论文，聚焦AI在畜牧养殖中的动物福利风险与缓解路径，属智慧养殖前沿议题，具行业参考价值。",[396],{"name":303,"url":388},[113,28,398,30],"风险治理",{"code":55,"slug":115,"name":116,"path":117,"parent_code":118},[401],{"code":49,"slug":121,"name":122,"path":123,"parent_code":124},{"status":126,"locked":14,"version":35,"method":36,"evidence":403},{"candidates":404,"agricultural_evidence":42},[405,409,413],{"code":55,"score":181,"supported":42,"title":406,"abstract":407,"tags":408},[132],[30,132],[30],{"code":49,"score":17,"supported":42,"title":410,"abstract":411,"tags":412},[138],[138],[113],{"code":118,"score":287,"supported":42,"title":414,"abstract":415,"tags":416},[],[143],[],[418,419],"农业人工智能 动物福利 智慧养殖 风险治理","农业人工智能 动物福利","农业人工智能动物福利智慧养殖风险治理-2015","10.1016\u002Fj.compag.2026.112408",{"doi":421,"openalex_id":423,"authors":424,"venue":303,"cited_by_count":83,"oa_url":388,"card":443,"direction":89,"ingested_from":92},"W7211988489",[425,428,430,432,434,436,438,440],{"name":426,"orcid":427},"Joshua Jarvis‐Campbell","https:\u002F\u002Forcid.org\u002F0009-0008-7307-703X",{"name":429,"orcid":9},"Marina A.G. von Keyserlingk",{"name":431,"orcid":9},"Albert Didriksen",{"name":433,"orcid":9},"Maximus Rafla",{"name":435,"orcid":9},"Carmen Lopez",{"name":437,"orcid":9},"Jack Zhu",{"name":439,"orcid":9},"Alistair Bugg",{"name":441,"orcid":442},"Borbala Foris","https:\u002F\u002Forcid.org\u002F0000-0002-0901-3057",{"tldr":444,"method":445,"finding":446,"direction":89,"opportunity":447},"探讨如何缓解动物养殖中人工智能应用带来的动物福利风险。","综述分析AI在养殖中的福利风险与缓解策略。","需建立伦理框架与技术措施以降低AI对动物福利的负面影响。","可研究AI养殖中动物福利风险的量化评估与实时监测预警系统。","2026-09-10T23:30:01.332132Z",{"id":450,"title":451,"url":452,"summary":453,"summary_zh":454,"content":9,"source_name":455,"source_url":452,"published_at":456,"category":12,"cover_url":9,"hotness":13,"is_selected":14,"score":457,"score_detail":458,"sources":461,"tags":463,"primary_topic":464,"secondary_topics":465,"classification":466,"search_phrases":487,"slug":488,"view_count":287,"doi":489,"paper":490,"created_at":507},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":17,"substance":106,"depth":19,"authority":17,"freshness":459,"relevant":22,"comment":460},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。",[462],{"name":455,"url":452},[112,113,27,29],{"code":49,"slug":121,"name":122,"path":123,"parent_code":124},[],{"status":126,"locked":14,"version":35,"method":36,"evidence":467},{"candidates":468,"agricultural_evidence":42},[469,475,479,483],{"code":49,"score":470,"supported":42,"title":471,"abstract":473,"tags":474},16,[472],"deep learning",[27,52],[113,27],{"code":55,"score":287,"supported":42,"title":476,"abstract":477,"tags":478},[],[30],[],{"code":40,"score":22,"supported":14,"title":480,"abstract":481,"tags":482},[],[],[29],{"code":147,"score":22,"supported":14,"title":484,"abstract":485,"tags":486},[],[],[112],[215,216],"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":489,"openalex_id":491,"authors":492,"venue":455,"cited_by_count":83,"oa_url":501,"card":502,"direction":89,"ingested_from":92},"W7208756356",[493,495,497,499],{"name":494,"orcid":9},"Harry Aricibasi",{"name":496,"orcid":9},"Jessica Bode",{"name":498,"orcid":9},"Renée Bergeron",{"name":500,"orcid":9},"D Tulpan","https:\u002F\u002Fwww.frontiersin.org\u002Fjournals\u002Fbioinformatics\u002Farticles\u002F10.3389\u002Ffbinf.2026.1869902\u002Fpdf",{"tldr":503,"method":504,"finding":505,"direction":89,"opportunity":506},"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"]