[{"data":1,"prerenderedAt":-1},["ShallowReactive",2],{"item-2311":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":18,"tags":20,"view_count":15,"doi":24,"paper":25,"created_at":57},2311,"WD-CD: a large-scale high-resolution optical remote sensing benchmark for fine-grained change detection in war scenarios","https:\u002F\u002Fdoi.org\u002F10.3389\u002Ffrsen.2026.1930744","Introduction Rapid detection of war-induced damage is vital for humanitarian response and post-war reconstruction, yet large-scale, well-annotated benchmarks for war-damage change detection are still lacking. Methods We present a large-scale, high-resolution bi-temporal optical remote sensing benchmark for war-damage change detection, named WD-CD. WD-CD contains 9,687 bi-temporal image pairs of 512 × 512 pixels collected from five conflict-affected theaters across Europe, Africa, and Asia, covering a total area of 1,055.83 km 2 . It provides annotations for 16 target categories and up to six change states. We evaluated representative deep learning models, performed cross-dataset comparisons, and conducted intercontinental transfer experiments. Results The benchmark evaluations demonstrated consistent and competitive performance while revealing the challenges of damage-state discrimination. The intercontinental transfer experiments showed that building geometry generalized well across regions, whereas damage morphology and background landscapes were region-specific. Discussion WD-CD addresses the lack of large-scale, fine-grained benchmarks for war-damage change detection and provides a foundation for evaluating model performance and cross-regional generalization. To support open science and reproducibility, the dataset will be made available upon request for non-commercial academic research.","引言 快速检测战争造成的破坏对于人道主义响应和战后重建至关重要，但目前仍缺乏大规模、标注完善的战争损毁变化检测基准。方法 我们提出了一个大规模、高分辨率的双时相光学遥感基准，用于战争损毁变化检测，命名为WD-CD。WD-CD包含9，687对512 × 512像素的双时相影像，采集自欧洲、非洲和亚洲五个受冲突影响的战区，覆盖总面积1，055.83 km²。该数据集提供了16个目标类别和最多六种变化状态的标注。我们评估了具有代表性的深度学习模型，进行了跨数据集比较，并开展了跨洲迁移实验。结果 基准评估在展现一致且有竞争力的性能的同时，也揭示了损毁状态判别所面临的挑战。跨洲迁移实验表明，建筑几何形态在不同区域间具有良好的泛化能力，而损毁形态和背景景观则具有区域特异性。讨论 WD-CD弥补了战争损毁变化检测领域缺乏大规模、细粒度基准的不足，为评估模型性能和跨区域泛化能力提供了基础。为支持开放科学和可重复性，该数据集将在收到请求后开放用于非商业学术研究。",null,"Frontiers in Remote Sensing","2026-09-10T00:00:00Z","论文",10,false,0,{"impact":15,"substance":15,"depth":15,"authority":15,"freshness":15,"relevant":15,"comment":17},"面向战争损毁变化检测的遥感基准数据集，属遥感与灾害评估领域，与三农、农业信息化、智慧农业无直接关联，不建议进入每日精选。",[19],{"name":10,"url":6},[21,22,23],"数据集","遥感","变化检测","10.3389\u002Ffrsen.2026.1930744",{"doi":24,"openalex_id":26,"authors":27,"venue":10,"cited_by_count":15,"oa_url":48,"card":49,"direction":55,"ingested_from":56},"W7212174981",[28,30,32,34,36,39,42,45],{"name":29,"orcid":9},"D. J. Li",{"name":31,"orcid":9},"Lei Ma",{"name":33,"orcid":9},"Guangjun He",{"name":35,"orcid":9},"Yaohui Chu",{"name":37,"orcid":38},"Yingnan Guo","https:\u002F\u002Forcid.org\u002F0009-0002-3426-543X",{"name":40,"orcid":41},"Ruikun Wang","https:\u002F\u002Forcid.org\u002F0000-0002-5712-7438",{"name":43,"orcid":44},"Ying Liang","https:\u002F\u002Forcid.org\u002F0000-0002-2727-3311",{"name":46,"orcid":47},"Pengming Feng","https:\u002F\u002Forcid.org\u002F0000-0001-5853-8100","https:\u002F\u002Fwww.frontiersin.org\u002Fjournals\u002Fremote-sensing\u002Farticles\u002F10.3389\u002Ffrsen.2026.1930744\u002Fpdf",{"tldr":50,"method":51,"finding":52,"direction":53,"opportunity":54},"构建了面向战争损毁变化检测的大规模高分辨率双时相光学遥感基准WD-CD。","收集欧非亚5个战区9687对512×512影像，标注16类目标与6种变化状态，评","模型表现有竞争力但损毁状态判别仍难；建筑几何跨区泛化好，损毁形态与背景具区域特异性。","农业遥感与作物表型","可借鉴其细粒度变化检测与跨区泛化评估框架，迁移至农田损毁、撂荒与复耕监测。","智慧农业 \u002F 农业物联网","openalex","2026-09-13T23:30:12.771841Z"]