[{"data":1,"prerenderedAt":-1},["ShallowReactive",2],{"item-414":3,"related-414":46},{"id":4,"title":5,"url":6,"summary":7,"summary_zh":8,"content":9,"source_name":10,"source_url":8,"published_at":11,"category":12,"cover_url":8,"hotness":13,"is_selected":14,"score":15,"score_detail":16,"sources":24,"tags":26,"primary_topic":8,"secondary_topics":33,"classification":34,"search_phrases":41,"slug":44,"view_count":20,"doi":8,"paper":8,"created_at":45},414,"GROW: One-Time Training for All Grains: Open-Set Grain Recognition and Quantitative Analysis","https:\u002F\u002Farxiv.org\u002Fabs\u002F2608.09345","Qihe Su、Mengyu Sun、Yuxi Ke、Zhuoyan Jiang、Wanneng Yang、Chenglong Huang、Ziyuan Yang于arXiv(2026-08-10)发表预印本。GROW是面向开放集谷物识别与定量分析的统一框架,无需重新训练即可识别新品种并完成定量分析。方法上,GROW首先进行类无关谷物定位,将混合谷物图像转换为独立实例用于品种计数和表型测量,然后将视觉嵌入与形态描述符融合为谷物描述符存储在可扩展的GrainBank中,查询谷物通过秩相似度加权top-k检索识别,新品种通过追加描述符纳入而无需更新部署模型。在渐进式品种扩展、不同谷物密度、背景域偏移场景下展现良好的可扩展性、鲁棒性和适应性,与联合重训练相比,GROW将平均类别注册时间从4153秒降至仅39秒,同时保持有竞争力的识别性能。",null,"[View PDF](https:\u002F\u002Farxiv.org\u002Fpdf\u002F2608.09345)[HTML (experimental)](https:\u002F\u002Farxiv.org\u002Fhtml\u002F2608.09345v1)\n\n> Abstract:Advances in crop breeding have introduced an increasing number of grain varieties, creating a growing demand for efficient variety recognition and quantitative analysis. However, existing methods are typically trained on a fixed variety set, and incorporating newly introduced varieties requires additional data collection and model retraining. To address this limitation, we propose GROW, a framework for Grain Recognition and quantitative analysis in Open sets Without retraining. GROW first performs class-agnostic grain localization, converting mixed-grain images into individual instances for variety-wise counting and phenotypic measurement. It then combines visual embeddings and morphological descriptors into fused grain descriptors stored in an extensible GrainBank. Query grains are recognized through rank-similarity weighted top-k retrieval, and newly introduced varieties are incorporated by appending their descriptors without updating the deployed models. Extensive experiments under progressive variety expansion, varying grain densities, and background domain shifts demonstrate the scalability, robustness, and adaptability of GROW. Compared with joint retraining, GROW reduced the average category-registration time from 4153 s to only 39 s while maintaining competitive recognition performance. These results demonstrate that GROW provides an efficient and maintainable solution for extensible grain recognition, counting, and phenotypic analysis without repeated model retraining.\n\nComments:15 pages, 15 figures\nSubjects:Computer Vision and Pattern Recognition (cs.CV)\nCite as:[arXiv:2608.09345](https:\u002F\u002Farxiv.org\u002Fabs\u002F2608.09345) [cs.CV]\n(or [arXiv:2608.09345v1](https:\u002F\u002Farxiv.org\u002Fabs\u002F2608.09345v1) [cs.CV] for this version)\n[https:\u002F\u002Fdoi.org\u002F10.48550\u002FarXiv.2608.09345](https:\u002F\u002Fdoi.org\u002F10.48550\u002FarXiv.2608.09345)\n\narXiv-issued DOI via DataCite (pending registration)\n\n## Submission history\n\nFrom: Qihe Su [[view email](https:\u002F\u002Farxiv.org\u002Fshow-email\u002Fd3ebe409\u002F2608.09345)] \n\n**[v1]** Mon, 10 Aug 2026 09:21:51 UTC (42,162 KB)","arXiv 2608.09345 2026-08-10","2026-08-10T01:00:00Z","论文",10,false,74,{"impact":17,"substance":18,"depth":19,"authority":20,"freshness":21,"relevant":22,"comment":23},15,20,18,12,9,1,"提出无需重训练的开放集谷物识别框架，显著降低品种注册时间，对农业信息化有实质贡献。",[25],{"name":10,"url":6},[27,28,29,30,31,32],"预印本","谷物识别","开放集","视觉嵌入","表型分析","GROW",[],{"status":35,"locked":14,"version":36,"method":37,"evidence":38},"needs_review","2026-10-22.2","rules",{"candidates":39,"agricultural_evidence":14,"reason":40},[],"农业相关性需要复核",[42,43],"表型分析 视觉嵌入 谷物识别 开放集","表型分析 视觉嵌入","表型分析视觉嵌入谷物识别开放集-414","2026-08-11T23:57:03.167448Z",{"total":47,"page":22,"page_size":47,"items":48},6,[49,115,193,239,284,343],{"id":50,"title":51,"url":52,"summary":53,"summary_zh":54,"content":8,"source_name":55,"source_url":52,"published_at":56,"category":12,"cover_url":8,"hotness":13,"is_selected":14,"score":57,"score_detail":58,"sources":62,"tags":64,"primary_topic":8,"secondary_topics":69,"classification":70,"search_phrases":84,"slug":87,"view_count":88,"doi":89,"paper":90,"created_at":114},3126,"Poplar-Studio: skeleton-guided reconstruction of editable 3D poplar seedling models from multi-view point clouds","https:\u002F\u002Fdoi.org\u002F10.1016\u002Fj.compag.2026.112454","Accurate, topologically consistent 3D plant models are important for quantitative phenotyping and for initializing functional–structural plant models (FSPMs). Structure-from-motion and multi-view stereo (SfM–MVS) reconstruction yields dense plant point clouds at low cost, but these clouds lack explicit organ connectivity, structural roles, and editable geometry. We developed Poplar-Studio, an integrated topology-preserving modelling framework that converts multi-view-derived poplar seedling point clouds into editable, organ-resolved structural models in standard Blender\u002FOBJ formats. Three design properties define this framework. First, a two-class segmentation separates leaves from the aggregated stem system, which is contracted into a skeleton graph by Laplacian contraction and minimum-spanning-tree construction. Main-stem, petiole, junction, and terminal roles are recovered from this graph without point-level main-stem\u002Fpetiole labels and converted into differentiated parametric geometry. Second, each lamina is reconstructed directly from its own point cloud as a boundary-constrained open surface in a PCA-aligned local frame, rather than instantiated from generic leaf templates. Third, the two branches are integrated into a common metric coordinate system in which the main stem, individual petioles, and individual leaves remain as separately editable organ-level objects, so that the framework terminates in a complete digital plant model rather than an intermediate structural representation. Across 240 fully expanded leaves, reconstructed leaf area agreed closely with independent measurements (R 2 = 0.943, relative RMSE = 10.3%, bias = 0.65 cm 2 ), with all leaves reconstructed as complete, hole-free laminae and the proposed method providing the best overall balance of accuracy, completeness, and efficiency among four reconstruction methods. Across four Populus genotypes, mean stem-system Chamfer distance to the source point clouds ranged from 0.143 to 0.227 cm. In a paired comparison on 40 plants at the 1-cm petiole-matching threshold, the graph-guided workflow showed higher mean petiole-branch precision than a geometry-first segment-then-fit baseline (78.4% vs 74.2%; Holm-adjusted p = 0.015). Recall and F1 did not differ significantly, whereas surface agreement with the source point clouds favoured the baseline (mean Chamfer distance 0.14 vs 0.20 cm). Starting from prepared point clouds, the proposed reconstruction workflow required less than 2.5 min per plant, corresponding to at least 24 plants h⁻ 1 on a single workstation. Poplar-Studio therefore provides a quantitatively characterized route from unordered plant point clouds to physically scaled, editable, topology-resolved models for phenotyping, structural analysis, and FSPM-oriented applications.","准确且拓扑一致的三维植物模型对于定量表型分析和功能-结构植物模型（FSPMs）的初始化具有重要意义。运动恢复结构与多视角立体（SfM–MVS）重建能够以低成本生成密集的植物点云，但这些点云缺乏明确的器官连接关系、结构角色和可编辑几何。我们开发了Poplar-Studio，一个集成的拓扑保持建模框架，可将多视角衍生的杨树幼苗点云转换为标准Blender\u002FOBJ格式的可编辑、器官解析的结构模型。该框架由三个设计特性定义。第一，通过两类分割将叶片与聚合茎系统分离，聚合茎系统经拉普拉斯收缩和最小生成树构建被压缩为骨架图。主茎、叶柄、连接点和末端角色从该图中恢复，无需点级别的主茎\u002F叶柄标签，并转换为差异化的参数化几何。第二，每个叶片直接从其自身点云重建，在PCA对齐的局部坐标系中作为边界约束的开放曲面，而非从通用叶片模板实例化。第三，两个分支被集成到统一的度量坐标系中，其中主茎、各叶柄和各叶片保持为可单独编辑的器官级对象，使框架最终输出完整的数字植物模型，而非中间结构表示。在240片完全展开的叶片中，重建叶面积与独立测量结果高度一致（R² = 0.943，相对RMSE = 10.3%，偏差 = 0.65 cm²），所有叶片均重建为完整、无孔洞的叶片，且在四种重建方法中，所提方法在精度、完整性和效率方面提供了最佳的整体平衡。在四种杨属基因型中，茎系统与源点云的平均Chamfer距离范围为0.143至0.227 cm。在40株植物上以1 cm叶柄匹配阈值进行的配对比较中，图引导工作流显示出比几何优先的分割后拟合基线更高的平均叶柄-分支精确率（78.4% vs 74.2%；Holm校正p = 0.015）。召回率和F1无显著差异，而与源点云的表面一致性则有利于基线（平均Chamfer距离0.14 vs 0.20 cm）。从准备好的点云出发，所提出的重建工作流每株所需时间少于2.5分钟。","Computers and Electronics in Agriculture","2026-09-22T00:00:00Z",83,{"impact":19,"substance":59,"depth":19,"authority":60,"freshness":13,"relevant":22,"comment":61},23,14,"提出从多视角点云重建可编辑杨树幼苗三维结构模型的框架，方法新颖、数据扎实，对作物表型与功能-结构模型研究有实用价值。",[63],{"name":55,"url":52},[65,66,31,67,68],"智慧农业","农业人工智能","三维重建","杨树",[],{"status":35,"locked":14,"version":36,"method":37,"evidence":71},{"candidates":72,"agricultural_evidence":14,"reason":40},[73,79],{"code":74,"score":75,"supported":14,"title":76,"abstract":77,"tags":78},"I2",2,[],[],[67,66],{"code":80,"score":22,"supported":14,"title":81,"abstract":82,"tags":83},"I1",[],[],[65],[85,86],"Poplar-Studio 杨树 三维重建","多视角点云 苗木 表型","Poplar-Studio杨树三维重建-3126",4,"10.1016\u002Fj.compag.2026.112454",{"doi":89,"openalex_id":91,"authors":92,"venue":55,"cited_by_count":106,"oa_url":52,"card":107,"direction":111,"ingested_from":113},"W7213933678",[93,95,98,101,103],{"name":94,"orcid":8},"Zhencan Wang",{"name":96,"orcid":97},"Huichun Zhang","https:\u002F\u002Forcid.org\u002F0000-0002-6479-0641",{"name":99,"orcid":100},"Liming Bian","https:\u002F\u002Forcid.org\u002F0000-0003-4739-0918",{"name":102,"orcid":8},"Lei Zhou",{"name":104,"orcid":105},"Yufeng Ge","https:\u002F\u002Forcid.org\u002F0000-0002-6460-0780",0,{"tldr":108,"method":109,"finding":110,"direction":111,"opportunity":112},"提出Poplar-Studio框架，从多视角点云重建可编辑的杨树幼苗三维结构模型。","SfM-MVS点云、两类分割、拉普拉斯收缩骨架图、PCA局部叶面重建，Blend","叶面积R²=0.943，叶柄分支精度78.4%优于基线，茎Chamfer距离0.143–0.227 ","农业遥感与作物表型","可扩展至更多物种与生长阶段，并将可编辑模型接入FSPM实现表型-功能联动模拟。","openalex","2026-09-22T23:30:01.467174Z",{"id":116,"title":117,"url":118,"summary":119,"summary_zh":120,"content":8,"source_name":121,"source_url":118,"published_at":122,"category":12,"cover_url":8,"hotness":13,"is_selected":14,"score":123,"score_detail":124,"sources":127,"tags":129,"primary_topic":132,"secondary_topics":137,"classification":138,"search_phrases":168,"slug":171,"view_count":88,"doi":172,"paper":173,"created_at":192},2802,"Advanced olive leaf area prediction using machine learning methods","https:\u002F\u002Fdoi.org\u002F10.1038\u002Fs41598-026-71390-9","Abstract Accurate leaf area estimation is essential for understanding olive tree physiology, productivity, and stress adaptationThis study developed and evaluated machine learning models for non-destructive olive leaf area prediction using linear measurements (length and width) from 30 diverse cultivars at the Tarom Olive Research Station, Iran. Six machine learning algorithms, Artificial Neural Network (ANN), Support Vector Regression (SVR), Random Forest, Decision Tree, AdaBoost, and XGBoost were optimized using Bayesian optimization, Genetic Algorithm (GA), and Particle Swarm Optimization (PSO). Results demonstrated that PSO consistently outperformed other optimization methods across most models. The ANN model optimized with PSO achieved the highest prediction accuracy (R 2 = 0.9828, RMSE = 0.3009 cm 2 ). External validation using eight additional cultivars confirmed model generalizability, with the universal ANN model maintaining R 2 > 0.98. This study provides a robust, non-destructive methodology for olive leaf area estimation applicable across diverse cultivars, offering practical implications for precision agriculture, phenotyping, and orchard management under changing climatic conditions.","摘要 准确的叶面积估算对于理解油橄榄树的生理特性、生产力及逆境适应性至关重要。本研究在伊朗塔罗姆油橄榄研究站，利用来自30个不同品种的线性测量数据（长度和宽度），开发并评估了用于无损油橄榄叶面积预测的机器学习模型。采用贝叶斯优化、遗传算法（GA）和粒子群优化（PSO）对六种机器学习算法——人工神经网络（ANN）、支持向量回归（SVR）、随机森林、决策树、AdaBoost和XGBoost——进行了优化。结果表明，在大多数模型中，PSO始终优于其他优化方法。经PSO优化后的ANN模型取得了最高的预测精度（R² = 0.9828，RMSE = 0.3009 cm²）。利用另外八个品种进行的外部验证证实了模型的泛化能力，通用ANN模型保持R² > 0.98。本研究为适用于不同品种的油橄榄叶面积估算提供了一种稳健的无损方法，为气候变化条件下的精准农业、表型分析和果园管理提供了实际应用价值。","Scientific Reports","2026-09-17T00:00:00Z",73,{"impact":20,"substance":18,"depth":125,"authority":60,"freshness":13,"relevant":22,"comment":126},17,"基于30个品种的机器学习叶片面积无损预测研究，方法新颖、验证充分，对精准农业与表型分析有实用价值，但属细分领域技术进展，影响范围有限。",[128],{"name":121,"url":118},[65,66,130,131,31],"机器学习","精准农业",{"code":74,"slug":133,"name":134,"path":135,"parent_code":136},"agricultural-ai","农业AI与大模型","\u002Ftopic\u002Fdigital-agriculture\u002Fagricultural-ai","I",[],{"status":139,"locked":14,"version":36,"method":37,"evidence":140},"classified",{"candidates":141,"agricultural_evidence":144},[142,149,155,162],{"code":74,"score":143,"supported":144,"title":145,"abstract":147,"tags":148},16,true,[146],"machine learning",[130,146],[66,130],{"code":80,"score":150,"supported":144,"title":151,"abstract":152,"tags":154},8,[],[131,153],"precision agriculture",[65,131],{"code":156,"score":157,"supported":144,"title":158,"abstract":159,"tags":161},"B2",3,[],[160],"orchard",[],{"code":163,"score":157,"supported":144,"title":164,"abstract":165,"tags":167},"H7",[],[166],"气候变化",[],[169,170],"农业人工智能 智慧农业 机器学习 精准农业","农业人工智能 智慧农业","农业人工智能智慧农业机器学习精准农业-2802","10.1038\u002Fs41598-026-71390-9",{"doi":172,"openalex_id":174,"authors":175,"venue":121,"cited_by_count":106,"oa_url":118,"card":186,"direction":191,"ingested_from":113},"W7213449017",[176,179,181,183],{"name":177,"orcid":178},"Ahmad Reza Dadras","https:\u002F\u002Forcid.org\u002F0000-0001-8591-5813",{"name":180,"orcid":8},"Hossein Sabouri",{"name":182,"orcid":8},"Ali Tanhaei",{"name":184,"orcid":185},"Sayed Javad Sajadi","https:\u002F\u002Forcid.org\u002F0000-0002-6555-080X",{"tldr":187,"method":188,"finding":189,"direction":111,"opportunity":190},"用机器学习基于叶长宽非破坏性预测30个橄榄品种叶面积，PSO优化ANN精度最高。","30个品种叶长宽数据，六种ML算法结合贝叶斯、GA、PSO优化。","PSO优化ANN最优（R²=0.9828），外部8品种验证R²>0.98，通用性好。","可拓展至多物种、多环境及无人机\u002F手机图像自动测量，构建通用叶面积表型平台。","农业人工智能与决策模型","2026-09-17T23:30:59.169744Z",{"id":194,"title":195,"url":196,"summary":197,"summary_zh":8,"content":8,"source_name":198,"source_url":8,"published_at":199,"category":12,"cover_url":8,"hotness":13,"is_selected":14,"score":200,"score_detail":201,"sources":203,"tags":205,"primary_topic":210,"secondary_topics":214,"classification":215,"search_phrases":226,"slug":229,"view_count":75,"doi":8,"paper":230,"created_at":238},2401,"基于三维点云的家畜体尺表型智能测定技术研究进展","https:\u002F\u002Fwww.toutiao.com\u002Farticle\u002F7684241920620626478","智慧农业(中英文) 2026, 8(4): 17-34（2026-09-11网络首发）。华中农业大学徐学文教授团队王海燕等系统梳理基于三维点云的家畜体尺测量研究进展。三维点云技术能够在保持非接触测量优势的基础上重建家畜三维体型结构，不仅可用于体长、体宽、体高等线性体尺测量，还可支持胸围、腹围、管围等围度体尺测量。","智慧农业(中英文) | 2026-09-11","2026-09-11T00:00:00Z",78,{"impact":19,"substance":18,"depth":19,"authority":60,"freshness":150,"relevant":22,"comment":202},"核心期刊综述，系统梳理三维点云家畜体尺测量进展，方法新颖、结论可靠，对智慧养殖有实质参考价值。",[204],{"name":198,"url":196},[206,31,207,208,209],"智慧养殖","三维点云","家畜体尺","智能测量",{"code":80,"slug":211,"name":212,"path":213,"parent_code":136},"smart-agriculture","智慧农业总论","\u002Ftopic\u002Fdigital-agriculture\u002Fsmart-agriculture",[],{"status":139,"locked":14,"version":36,"method":37,"evidence":216},{"candidates":217,"agricultural_evidence":144},[218,222],{"code":80,"score":157,"supported":144,"title":219,"abstract":220,"tags":221},[],[65],[],{"code":74,"score":22,"supported":14,"title":223,"abstract":224,"tags":225},[],[],[207],[227,228],"三维点云 家畜体尺 智慧养殖 智能测量","三维点云 家畜体尺","三维点云家畜体尺智慧养殖智能测量-2401",{"doi":8,"openalex_id":8,"authors":231,"venue":8,"cited_by_count":106,"oa_url":8,"card":232,"direction":111,"ingested_from":237},[],{"tldr":233,"method":234,"finding":235,"direction":111,"opportunity":236},"系统梳理基于三维点云的家畜体尺非接触测量技术研究进展。","综述三维点云重建与线性、围度体尺测量方法。","三维点云可非接触重建家畜体型，支持线性与围度体尺测量。","家畜三维点云表型标准化数据集与实时轻量化测量算法仍待突破。","agent","2026-09-14T00:06:33.424791Z",{"id":240,"title":241,"url":242,"summary":243,"summary_zh":8,"content":8,"source_name":244,"source_url":8,"published_at":245,"category":12,"cover_url":8,"hotness":13,"is_selected":14,"score":246,"score_detail":247,"sources":249,"tags":251,"primary_topic":255,"secondary_topics":260,"classification":261,"search_phrases":272,"slug":275,"view_count":157,"doi":8,"paper":276,"created_at":283},2396,"[预印本]Multi-Task Learning for Sparsely-Labeled Time Series: A Case Study on Cold-Hardiness Modeling","https:\u002F\u002Farxiv.org\u002Fabs\u002F2609.09062","arXiv 2609.09062（2026-09-10）。研究针对葡萄抗寒性的时间序列过程建模问题（数据有限且标签时序稀疏），提出基于RNN的多任务学习方法。实验证明某些MTL架构优于单任务学习和现有科学模型，并在相关萌芽期预测任务上展现良好潜力。","arXiv | 2026-09-10","2026-09-10T00:00:00Z",66,{"impact":20,"substance":19,"depth":143,"authority":20,"freshness":150,"relevant":22,"comment":248},"预印本提出RNN多任务学习用于葡萄抗寒性稀疏标签时序建模，方法新颖但尚属早期研究，产业影响有限，可作为农业AI前沿动态收录。",[250],{"name":244,"url":242},[66,27,252,253,254],"葡萄","抗寒育种","时间序列",{"code":156,"slug":256,"name":257,"path":258,"parent_code":259},"fruit","果树","\u002Ftopic\u002Fhorticulture\u002Ffruit","B",[],{"status":139,"locked":14,"version":36,"method":37,"evidence":262},{"candidates":263,"agricultural_evidence":144},[264,268],{"code":156,"score":88,"supported":144,"title":265,"abstract":266,"tags":267},[],[252],[252],{"code":74,"score":22,"supported":14,"title":269,"abstract":270,"tags":271},[],[],[66],[273,274],"农业人工智能 抗寒育种 时间序列 预印本","农业人工智能 抗寒育种","农业人工智能抗寒育种时间序列预印本-2396",{"doi":8,"openalex_id":8,"authors":277,"venue":8,"cited_by_count":106,"oa_url":8,"card":278,"direction":191,"ingested_from":237},[],{"tldr":279,"method":280,"finding":281,"direction":191,"opportunity":282},"提出RNN多任务学习方法，用于标签稀疏的葡萄抗寒时间序列建模。","基于RNN的多任务学习，处理有限且时序稀疏的标签数据。","部分MTL架构优于单任务学习和现有科学模型，并利于萌芽期预测。","可探索多任务学习在更多稀疏标签农业时序场景（如病虫害、物候）中的迁移与泛化。","2026-09-14T00:06:33.014967Z",{"id":285,"title":286,"url":287,"summary":288,"summary_zh":289,"content":8,"source_name":55,"source_url":287,"published_at":199,"category":12,"cover_url":8,"hotness":13,"is_selected":14,"score":290,"score_detail":291,"sources":293,"tags":295,"primary_topic":298,"secondary_topics":302,"classification":303,"search_phrases":320,"slug":322,"view_count":157,"doi":323,"paper":324,"created_at":342},2282,"Mushroom cap phenotype extraction based on YOLOv11-SMD","https:\u002F\u002Fdoi.org\u002F10.1016\u002Fj.compag.2026.112402","Mushroom cap phenotype extraction based on YOLOv11-SMD。Computers and Electronics in Agriculture","基于YOLOv11-SMD的蘑菇菌盖表型提取。《农业计算机与电子》",75,{"impact":17,"substance":18,"depth":19,"authority":60,"freshness":150,"relevant":22,"comment":292},"核心期刊论文，提出YOLOv11-SMD用于蘑菇菌盖表型提取，方法有创新且面向食用菌智能化生产，但属细分技术进展，影响力有限。",[294],{"name":55,"url":287},[65,66,296,297,31],"目标检测","食用菌",{"code":299,"slug":300,"name":297,"path":301,"parent_code":259},"B5","mushrooms","\u002Ftopic\u002Fhorticulture\u002Fmushrooms",[],{"status":139,"locked":14,"version":36,"method":37,"evidence":304},{"candidates":305,"agricultural_evidence":144},[306,312,316],{"code":299,"score":17,"supported":144,"title":307,"abstract":309,"tags":311},[308],"mushroom",[310,308],"蘑菇",[297],{"code":74,"score":75,"supported":14,"title":313,"abstract":314,"tags":315},[],[],[66,296],{"code":80,"score":22,"supported":14,"title":317,"abstract":318,"tags":319},[],[],[65],[321,170],"农业人工智能 智慧农业 目标检测 表型分析","农业人工智能智慧农业目标检测表型分析-2282","10.1016\u002Fj.compag.2026.112402",{"doi":323,"openalex_id":325,"authors":326,"venue":55,"cited_by_count":106,"oa_url":8,"card":337,"direction":111,"ingested_from":113},"W7212266027",[327,330,332,334],{"name":328,"orcid":329},"Yang Zhou","https:\u002F\u002Forcid.org\u002F0000-0002-0100-2652",{"name":331,"orcid":8},"Quanlong Miao",{"name":333,"orcid":8},"Yuefeng Chen",{"name":335,"orcid":336},"Jiajia Yu","https:\u002F\u002Forcid.org\u002F0000-0002-8764-8429",{"tldr":338,"method":339,"finding":340,"direction":111,"opportunity":341},"提出YOLOv11-SMD模型，用于蘑菇菌盖表型自动提取。","基于YOLOv11改进的SMD模型，结合图像数据提取菌盖表型。","YOLOv11-SMD能有效提取蘑菇菌盖表型，提升检测精度。","可探索多品种、多生长阶段菌盖表型动态监测与三维重建。","2026-09-13T23:30:01.859046Z",{"id":344,"title":345,"url":346,"summary":347,"summary_zh":348,"content":8,"source_name":349,"source_url":346,"published_at":350,"category":12,"cover_url":8,"hotness":13,"is_selected":14,"score":351,"score_detail":352,"sources":356,"tags":358,"primary_topic":361,"secondary_topics":362,"classification":363,"search_phrases":376,"slug":379,"view_count":157,"doi":380,"paper":381,"created_at":398},1730,"PAT: An Image Analysis Tool for Automated Scoring of Pollen in Alexander-Stained Anthers","https:\u002F\u002Fdoi.org\u002F10.1093\u002Fjxb\u002Ferag436","Abstract Quantitative pollen viability analysis is a critical but labor-intensive step in plant reproductive biology. Existing deep-learning Segment Anything Models (SAM) fail to reliably segment viable pollen in Alexander-stained anthers. To address this, we fine-tuned an existing Cellpose-SAM model for pollen segmentation. We integrated it into PAT (Pollen Analysis Tool), a cross-platform desktop application. PAT features instance segmentation with interactive quality control, an in-app model retraining module, and publication-ready statistical outputs. We deployed PAT in an EMS suppressor screen of semi-sterile Arabidopsis smg7-6 mutants, enabling efficient candidate prioritization for whole genome sequencing and mapping candidate mutation. This screen led to the identification of a point mutation in CAP-D2 ( capd2-2 ), a Condensin I subunit, that rescues the smg7-6 meiotic phenotype. Notably, mutation in a Condensin II subunits (CAP-D3 and CAP-H2) does not confer rescue. Further characterization suggests the capd2-2 allele is hypomorphic, showing no defects in vegetative growth, chromocenter compaction, or transposable element silencing. Collectively, we demonstrate that accessible AI tools have the potential to bridge gaps in plant phenotyping and accelerate the pace of biological discovery. Highlight We combined AI-powered image analysis with an easy-to-use desktop app to automate plant pollen counting, then used it to identify a new genetic suppressor of meiotic defects.","定量花粉活力分析是植物生殖生物学中一个关键但劳动密集的步骤。现有的深度学习分割一切模型（SAM）在亚历山大染色花药中无法可靠地分割有活力的花粉。为解决此问题，我们对现有的Cellpose-SAM模型进行了微调，用于花粉分割。我们将其整合到PAT（花粉分析工具）中，这是一个跨平台的桌面应用程序。PAT具备实例分割及交互式质量控制、应用内模型再训练模块以及可直接用于发表的统计输出功能。我们在半不育拟南芥smg7-6突变体的EMS抑制子筛选中部署了PAT，从而能够高效地对候选突变体进行优先级排序，以进行全基因组测序和候选突变定位。该筛选鉴定出CAP-D2（capd2-2）中的一个点突变，该基因编码凝缩蛋白I的一个亚基，该突变能够挽救smg7-6的减数分裂表型。值得注意的是，凝缩蛋白II亚基（CAP-D3和CAP-H2）的突变并未赋予挽救效果。进一步的特征分析表明，capd2-2等位基因属于亚效等位基因，在营养生长、染色质中心压缩或转座子沉默方面未显示任何缺陷。总体而言，我们证明了易于使用的人工智能工具具有弥合植物表型分析差距并加速生物学发现的潜力。亮点：我们将人工智能驱动的图像分析与易于使用的桌面应用相结合，实现了植物花粉计数的自动化，并利用该方法鉴定了一个新的减数分裂缺陷遗传抑制子。","Journal of Experimental Botany","2026-09-04T00:00:00Z",79,{"impact":19,"substance":353,"depth":19,"authority":60,"freshness":354,"relevant":22,"comment":355},22,7,"AI工具用于花粉活力自动分析，加速遗传筛选，对育种和表型分析有实用价值。",[357],{"name":349,"url":346},[65,66,359,31,360],"育种","图像识别",{"code":74,"slug":133,"name":134,"path":135,"parent_code":136},[],{"status":139,"locked":14,"version":36,"method":37,"evidence":364},{"candidates":365,"agricultural_evidence":144},[366,372],{"code":74,"score":367,"supported":144,"title":368,"abstract":369,"tags":371},5,[],[370],"深度学习",[66,360],{"code":80,"score":22,"supported":14,"title":373,"abstract":374,"tags":375},[],[],[65],[377,378],"农业人工智能 图像识别 智慧农业 表型分析","农业人工智能 图像识别","农业人工智能图像识别智慧农业表型分析-1730","10.1093\u002Fjxb\u002Ferag436",{"doi":380,"openalex_id":382,"authors":383,"venue":349,"cited_by_count":106,"oa_url":346,"card":393,"direction":111,"ingested_from":113},"W7160664980",[384,387,390],{"name":385,"orcid":386},"Darya Volkava","https:\u002F\u002Forcid.org\u002F0009-0003-3578-6592",{"name":388,"orcid":389},"Karel Říha","https:\u002F\u002Forcid.org\u002F0000-0002-6124-0118",{"name":391,"orcid":392},"Vivek K. Raxwal","https:\u002F\u002Forcid.org\u002F0000-0002-5182-6377",{"tldr":394,"method":395,"finding":396,"direction":191,"opportunity":397},"开发了花粉分析工具PAT，自动化评估花粉活力，并用于发现新的减数分裂抑制因子。","微调Cellpose-SAM模型，集成到跨平台桌面应用PAT，支持交互式质量控制","PAT高效筛选拟南芥突变体，发现CAP-D2点突变可挽救smg7-6表型，而Condensin II","将AI图像分析工具扩展到其他作物表型，如种子活力、果实发育，结合交互式平台加速遗传筛选。","2026-09-05T23:30:19.596351Z"]