[{"data":1,"prerenderedAt":-1},["ShallowReactive",2],{"item-2511":3},{"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,"view_count":32,"doi":33,"paper":34,"created_at":66},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",0,"10.3389\u002Ffrai.2026.1876396",{"doi":33,"openalex_id":35,"authors":36,"venue":10,"cited_by_count":32,"oa_url":57,"card":58,"direction":64,"ingested_from":65},"W7212747795",[37,40,43,45,48,50,52,55],{"name":38,"orcid":39},"Miguel Angel Valles-Coral","https:\u002F\u002Forcid.org\u002F0000-0002-8806-2892",{"name":41,"orcid":42},"Kelvin Lleins Rojas-Córdova","https:\u002F\u002Forcid.org\u002F0009-0001-4097-3961",{"name":44,"orcid":9},"Lloy Pinedo",{"name":46,"orcid":47},"Richard Injante","https:\u002F\u002Forcid.org\u002F0000-0002-2449-8937",{"name":49,"orcid":9},"Pierre Vidaurre-Rojas",{"name":51,"orcid":9},"Jorge Saavedra-Ramírez",{"name":53,"orcid":54},"Fernando Ruiz-Saavedra","https:\u002F\u002Forcid.org\u002F0000-0003-4664-4867",{"name":56,"orcid":9},"Williams Ramirez","https:\u002F\u002Fwww.frontiersin.org\u002Fjournals\u002Fartificial-intelligence\u002Farticles\u002F10.3389\u002Ffrai.2026.1876396\u002Fpdf",{"tldr":59,"method":60,"finding":61,"direction":62,"opportunity":63},"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"]