[{"data":1,"prerenderedAt":-1},["ShallowReactive",2],{"item-2277":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":51},2277,"An improved RT-DETR approach for real-time detection of densely occluded blueberries and micro-calyxes","https:\u002F\u002Fdoi.org\u002F10.1016\u002Fj.compag.2026.112424","Accurate detection of blueberries and their micro-scale calyx regions is important for visual perception in robotic blueberry harvesting, especially in densely clustered scenes where fruits are frequently occluded and adjacent to each other. However, blueberry calyx detection remains challenging because the front calyx occupies only a small image region and is easily affected by background interference, illumination variation, and feature attenuation during deep feature extraction. To address these challenges, this study proposes MFE-DETR, an improved RT-DETR-based real-time detection model for densely occluded blueberries and micro-calyxes. A Micro-Feature Enhanced Attention (MFEA) module is introduced to strengthen the representation of weak calyx features by combining heterogeneous local receptive fields with a spatial prior bias. The proposed module is designed to enhance the association between micro-calyx regions and the surrounding fruit context while maintaining the end-to-end detection framework of RT-DETR. Experimental results on a self-constructed blueberry image dataset show that MFE-DETR achieved an overall mAP@0.5 of 94.2 %, with a Front calyx AP@0.5 of 91.5 %. In addition, deployment experiments on an NVIDIA Jetson AGX Orin platform showed that the proposed model achieved real-time edge-side inference under the tested configuration, suggesting its potential as a visual perception module for subsequent robotic blueberry harvesting systems.","准确检测蓝莓及其微尺度花萼区域对于机器人蓝莓采摘中的视觉感知具有重要意义，尤其是在果实频繁被遮挡且相互邻近的密集簇生场景中。然而，蓝莓花萼检测仍面临挑战，因为正面花萼仅占据很小的图像区域，且容易受到背景干扰、光照变化以及深度特征提取过程中特征衰减的影响。为解决这些挑战，本研究提出了MFE-DETR，一种基于改进RT-DETR的实时检测模型，用于密集遮挡蓝莓和微小花萼的检测。引入微特征增强注意力（MFEA）模块，通过结合异构局部感受野与空间先验偏置来增强弱花萼特征的表示。所提出的模块旨在增强微小花萼区域与周围果实上下文之间的关联，同时保持RT-DETR的端到端检测框架。在自建蓝莓图像数据集上的实验结果表明，MFE-DETR的总体mAP@0.5达到94.2%，正面花萼AP@0.5为91.5%。此外，在NVIDIA Jetson AGX Orin平台上的部署实验表明，所提出的模型在测试配置下实现了实时边缘端推理，表明其作为后续机器人蓝莓采摘系统视觉感知模块的潜力。",null,"Computers and Electronics in Agriculture","2026-09-12T00:00:00Z","论文",10,false,79,{"impact":17,"substance":18,"depth":19,"authority":20,"freshness":21,"relevant":22,"comment":23},16,22,18,14,9,1,"提出MFE-DETR改进模型实现密集遮挡下蓝莓及微小花萼的实时检测，mAP@0.5达94.2%并在Jetson边缘平台验证，对采摘机器人视觉感知有实质参考价值。",[25],{"name":10,"url":6},[27,28,29,30,31],"智慧农业","农业人工智能","目标检测","采摘机器人","蓝莓",0,"10.1016\u002Fj.compag.2026.112424",{"doi":33,"openalex_id":35,"authors":36,"venue":10,"cited_by_count":32,"oa_url":6,"card":44,"direction":48,"ingested_from":50},"W7212359038",[37,39,42],{"name":38,"orcid":9},"Sen Li",{"name":40,"orcid":41},"Xiaobin Li","https:\u002F\u002Forcid.org\u002F0000-0002-1099-6046",{"name":43,"orcid":9},"Zhumei Wang",{"tldr":45,"method":46,"finding":47,"direction":48,"opportunity":49},"提出改进RT-DETR的MFE-DETR模型，实现密集遮挡下蓝莓及微小花萼的实时检测。","在RT-DETR中引入微特征增强注意力模块MFEA，结合异构局部感受野与空间先验","自建数据集上mAP@0.5达94.2%，前花萼AP@0.5为91.5%，Jetson AGX Ori","农业人工智能与决策模型","可探索微小花萼特征增强模块向其他小目标果实器官检测的迁移，及采摘机器人视觉-控制闭环集成。","openalex","2026-09-13T23:30:01.494783Z"]