[{"data":1,"prerenderedAt":-1},["ShallowReactive",2],{"item-4372":3,"related-4372":66},{"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":18,"tags":20,"primary_topic":9,"secondary_topics":21,"classification":22,"search_phrases":40,"slug":41,"view_count":15,"doi":42,"paper":43,"created_at":65},4372,"Camouflaged Object Segmentation Using a U-Net Based Deep Learning Approach","https:\u002F\u002Fdoi.org\u002F10.47392\u002Firjaeh.2026.0707","The paper focuses on the computer vision task of camouflaged object detection that has various applications, including, but not limited to, military, security, biology, and industry. From the perspective of machine vision, camouflage is a state in which the target’s texture, colour, and pattern are indistinguishable from the surrounding background, making it hard, if not impossible, to isolate those objects from the background. It implies that the COD problem statement extends far beyond the scope of ordinary object detection. To tackle the COD task, the authors used the 2D U-Net model that demonstrated its ability to address image segmentation problems through employing a contracting encoder and expansive decoder connected with skip links. In particular, the U-Net architecture was utilised due to its ability to maintain a high level of detail in an image, which is critical during camouflage detection, in contrast to typical bounding box estimation used in object detection tasks. The model was trained on MCSIK training sets and evaluated on MCSIK test sets, with an average accuracy of 70.14%. Overall, the U-Net architecture is promising for addressing camouflage object detection; however, there is a noticeable accuracy drop on real-world sensor data, which the paper tries to address further.","本文聚焦于伪装目标检测这一计算机视觉任务，其应用领域广泛，包括但不限于军事、安全、生物学和工业。从机器视觉的角度来看，伪装是指目标的纹理、颜色和图案与周围背景难以区分的一种状态，使得将这些目标从背景中分离出来变得困难甚至不可能。这意味着伪装目标检测（COD）的问题范畴远超普通目标检测的范围。为应对COD任务，作者采用了二维U-Net模型，该模型通过使用收缩编码器和扩张解码器并借助跳跃连接，展现了其解决图像分割问题的能力。特别地，选用U-Net架构是因为其能够保持图像中的高细节水平，这在伪装检测中至关重要，与目标检测任务中常用的边界框估计形成对比。该模型在MCSIK训练集上进行训练，并在MCSIK测试集上评估，平均准确率为70.14%。总体而言，U-Net架构在解决伪装目标检测方面具有前景；然而，在真实传感器数据上准确率有明显下降，本文试图进一步解决这一问题。",null,"International Research Journal on Advanced Engineering Hub (IRJAEH)","2026-10-05T00:00:00Z","论文",10,false,0,{"impact":15,"substance":15,"depth":15,"authority":15,"freshness":15,"relevant":15,"comment":17},"该论文为通用计算机视觉领域的伪装目标分割研究，未涉及农业场景或农业信息化应用，与三农主题无关，不建议进入每日精选。",[19],{"name":10,"url":6},[12],[],{"status":23,"locked":14,"version":24,"method":25,"evidence":26},"needs_review","2026-10-22.2","rules",{"candidates":27,"agricultural_evidence":14,"reason":39},[28],{"code":29,"score":30,"supported":31,"title":32,"abstract":34,"tags":38},"I2",17,true,[33],"deep learning",[35,36,37],"目标检测","计算机视觉","computer vision",[],"农业相关性需要复核",[],"CamouflagedObjectSegmentationUsingaU-Net-4372","10.47392\u002Firjaeh.2026.0707",{"doi":42,"openalex_id":44,"authors":45,"venue":10,"cited_by_count":15,"oa_url":57,"card":58,"direction":62,"ingested_from":64},"W7220389473",[46,48,50,52,54],{"name":47,"orcid":9},"Dharitree Devi",{"name":49,"orcid":9},"Arpita Prusty",{"name":51,"orcid":9},"Deepanjali Khadia",{"name":53,"orcid":9},"Basudev Patra",{"name":55,"orcid":56},"Jashasmita Pal","https:\u002F\u002Forcid.org\u002F0000-0002-8857-1734","https:\u002F\u002Firjaeh.com\u002Findex.php\u002Fjournal\u002Farticle\u002Fdownload\u002F2029\u002F1864",{"tldr":59,"method":60,"finding":61,"direction":62,"opportunity":63},"该论文用U-Net深度学习模型对伪装目标进行分割，在MCSIK数据集上平均准确率达70.14%。","采用2D U-Net编码器-解码器架构与跳跃连接，在MCSIK训练集训练、测试集","U-Net在伪装目标分割上表现良好，但真实传感器数据上准确率明显下降。","农业人工智能与决策模型","可将伪装目标分割迁移至农业场景，如田间害虫、病斑或杂草的隐蔽目标检测，并解决真实传感器数据泛化问题。","openalex","2026-10-07T23:30:44.883540Z",{"total":15,"page":67,"page_size":67,"items":68},1,[]]