[{"data":1,"prerenderedAt":-1},["ShallowReactive",2],{"item-4218":3,"related-4218":90},{"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":25,"classification":26,"search_phrases":60,"slug":63,"view_count":64,"doi":65,"paper":66,"created_at":89},4218,"YOLO-BASED SYSTEMS FOR DETECTING EXPLOSIVE REMNANTS OF WAR: A REVIEW FOR HUMANITARIAN DEMINING","https:\u002F\u002Fdoi.org\u002F10.20998\u002F2522-9052.2026.4.10","Relevance. Humanitarian demining remains a critical safety challenge because explosive remnants of war, landmines, and unexploded ordnance continue to endanger civilians and hinder post-conflict recovery. In this context, artificial intelligence and computer vision are increasingly used to support hazardous-object detection in UAVs-based survey operations. The purpose of this paper is to synthesize contemporary approaches to the detection of landmines, unexploded ordnance, and other explosive remnants of war, and to define the role of YOLO models in an integrated technological pipeline for surveying hazardous areas. The object of the review is technological solutions for detecting hazardous objects using UAVs, sensor systems, geoinformation technologies, and YOLO-family models. The subject of the paper is the application of YOLO-based systems in integrated pipelines for localizing potential explosive objects from visual and spectral data. Research results. The review shows that modern approaches combine ground-penetrating radar, magnetometry, thermal sensing, multispectral imaging, hyperspectral imaging, UAV-based inspection, GIS platforms, and edge\u002Fcloud architectures. YOLO demonstrates strong potential for rapid localization of visually or spectrally expressed indicators of hazardous objects, especially when combined with other sensing modalities. Conclusions. At the same time, YOLO cannot serve as the sole basis for declaring an area safe. Its use is constrained by small target size, camouflage, domain shift, limited annotated datasets, and the high cost of false negatives. Therefore, YOLO-based detection should be treated as one component of a multisensor, human-supervised decision-support system.","相关性。人道主义排雷仍然是一项关键的安全挑战，因为战争遗留爆炸物、地雷和未爆弹药继续危及平民并阻碍冲突后恢复。在此背景下，人工智能和计算机视觉越来越多地被用于支持基于无人机（UAV）的勘察作业中的危险物体检测。本文旨在综合当前对地雷、未爆弹药和其他战争遗留爆炸物的检测方法，并明确YOLO模型在危险区域勘察集成技术流程中的作用。综述的对象是利用无人机、传感器系统、地理信息技术和YOLO系列模型检测危险物体的技术解决方案。论文的主题是基于YOLO的系统在集成流程中从视觉和光谱数据定位潜在爆炸物体的应用。研究结果。综述表明，现代方法结合了探地雷达、磁力测量、热传感、多光谱成像、高光谱成像、基于无人机的检查、GIS平台以及边缘\u002F云架构。YOLO在快速定位视觉或光谱上可表现出的危险物体指标方面展现出强大潜力，尤其是与其他传感模态结合使用时。结论。与此同时，YOLO不能作为宣布某一区域安全的唯一依据。其应用受到目标尺寸小、伪装、域偏移、标注数据集有限以及假阴性成本高的制约。因此，基于YOLO的检测应被视为多传感器、人工监督的决策支持系统中的一个组成部分。",null,"Advanced Information Systems","2026-10-02T00:00:00Z","论文",10,false,0,{"impact":15,"substance":15,"depth":15,"authority":15,"freshness":15,"relevant":15,"comment":17},"主题为人道主义排雷中的YOLO目标检测综述，属军事安全与遥感交叉领域，与三农、农业信息化无直接关联，不建议进入每日精选。",[19],{"name":10,"url":6},[21,22,23,24],"无人机","人工智能","目标检测","遥感",[],{"status":27,"locked":14,"version":28,"method":29,"evidence":30},"needs_review","2026-10-22.2","rules",{"candidates":31,"agricultural_evidence":14,"reason":59},[32,43,51],{"code":33,"score":34,"supported":35,"title":36,"abstract":38,"tags":42},"I2",19,true,[37],"YOLO",[39,40,41,37],"计算机视觉","artificial intelligence","computer vision",[22,23],{"code":44,"score":45,"supported":35,"title":46,"abstract":47,"tags":50},"I3",7,[],[48,49],"multispectral","hyperspectral",[24],{"code":52,"score":53,"supported":35,"title":54,"abstract":55,"tags":58},"I4",6,[],[56,57],"地理信息","GIS",[],"农业相关性需要复核",[61,62],"YOLO 排雷 无人机","未爆弹药 遥感 检测","YOLO排雷无人机-4218",2,"10.20998\u002F2522-9052.2026.4.10",{"doi":65,"openalex_id":67,"authors":68,"venue":10,"cited_by_count":15,"oa_url":80,"card":81,"direction":87,"ingested_from":88},"W7216173401",[69,71,73,75,78],{"name":70,"orcid":9},"Andrii Podorozhniak",{"name":72,"orcid":9},"Denys Levchenko",{"name":74,"orcid":9},"Nataliia Liubchenko",{"name":76,"orcid":77},"Іслам Ісламов","https:\u002F\u002Forcid.org\u002F0000-0001-8645-0640",{"name":79,"orcid":9},"Oleksandr Skorlupin","https:\u002F\u002Fais.khpi.edu.ua\u002Farticle\u002Fdownload\u002F372728\u002F356290",{"tldr":82,"method":83,"finding":84,"direction":85,"opportunity":86},"综述YOLO模型在无人机人道排雷中检测地雷与未爆弹药的技术管线。","综述探地雷达、磁力、热成像、多\u002F高光谱、无人机与GIS结合YOLO的方法。","YOLO可快速定位危险目标，但受小目标、伪装、域偏移等限制，不能单独判定区域安全。","农业遥感与作物表型","可将多传感器+YOLO的排雷管线迁移到农田未爆物检测与农业遥感安全评估中。","智慧农业 \u002F 农业物联网","openalex","2026-10-05T23:30:11.995589Z",{"total":53,"page":91,"page_size":53,"items":92},1,[93,140,203,306,373,432],{"id":94,"title":95,"url":96,"summary":7,"summary_zh":97,"content":9,"source_name":98,"source_url":96,"published_at":11,"category":12,"cover_url":9,"hotness":13,"is_selected":14,"score":15,"score_detail":99,"sources":101,"tags":103,"primary_topic":9,"secondary_topics":105,"classification":106,"search_phrases":121,"slug":123,"view_count":15,"doi":9,"paper":124,"created_at":139},4220,"Системи на основі YOLO для виявлення вибухонебезпечних залишків війни: огляд для гуманітарного розмінування","https:\u002F\u002Fais.khpi.edu.ua\u002Farticle\u002Fview\u002F372728","相关性。人道主义排雷仍然是一项关键的安全挑战，因为战争遗留爆炸物、地雷和未爆弹药继续危及平民并阻碍冲突后恢复。在此背景下，人工智能和计算机视觉越来越多地被用于支持基于无人机（UAV）的勘察作业中的危险物体检测。本文旨在综合当前对地雷、未爆弹药和其他战争遗留爆炸物的检测方法，并明确YOLO模型在危险区域勘察集成技术流程中的作用。综述的对象是利用无人机、传感器系统、地理信息技术和YOLO系列模型检测危险物体的技术解决方案。论文的主题是基于YOLO的系统在集成流程中的应用，用于从视觉和光谱数据中定位潜在爆炸物体。研究结果。综述表明，现代方法结合了探地雷达、磁力测量、热传感、多光谱成像、高光谱成像、基于无人机的检查、GIS平台以及边缘\u002F云架构。YOLO在快速定位视觉或光谱上可表现出的危险物体指标方面展现出强大潜力，尤其是与其他传感模态结合使用时。结论。与此同时，YOLO不能作为宣布某一区域安全的唯一依据。其使用受到小目标尺寸、伪装、域偏移、标注数据集有限以及假阴性高成本的制约。因此，基于YOLO的检测应被视为多传感器、人工监督决策支持系统的一个组成部分。","The Scientific Issues of Ternopil Volodymyr Hnatiuk National Pedagogical University Series pedagogy",{"impact":15,"substance":15,"depth":15,"authority":15,"freshness":15,"relevant":15,"comment":100},"主题为人道主义排雷中的YOLO目标检测综述，属军事\u002F人道安全领域，与三农及农业信息化无直接关联，不予入选。",[102],{"name":98,"url":96},[21,104,23,24],"农业人工智能",[],{"status":27,"locked":14,"version":28,"method":29,"evidence":107},{"candidates":108,"agricultural_evidence":14,"reason":59},[109,113,117],{"code":33,"score":34,"supported":35,"title":110,"abstract":111,"tags":112},[37],[39,40,41,37],[104,23],{"code":44,"score":45,"supported":35,"title":114,"abstract":115,"tags":116},[],[48,49],[24],{"code":52,"score":53,"supported":35,"title":118,"abstract":119,"tags":120},[],[56,57],[],[61,122],"人道主义排雷 遥感","YOLO排雷无人机-4220",{"doi":9,"openalex_id":125,"authors":126,"venue":98,"cited_by_count":15,"oa_url":96,"card":134,"direction":87,"ingested_from":88},"W7218146160",[127,128,131,132,133],{"name":70,"orcid":9},{"name":129,"orcid":130},"Денис Левченко","https:\u002F\u002Forcid.org\u002F0009-0005-4102-6236",{"name":74,"orcid":9},{"name":76,"orcid":77},{"name":79,"orcid":9},{"tldr":135,"method":136,"finding":137,"direction":85,"opportunity":138},"综述YOLO模型在无人机人道排雷中检测战争爆炸残留物的应用与局限。","综述探地雷达、磁力、热成像、多\u002F高光谱、无人机、GIS与YOLO集成方案。","YOLO可快速定位危险目标，但受小目标、伪装、域偏移、数据少和高漏检代价限制，不能单独判定区域安全。","可探索多源遥感与YOLO融合的轻量边缘检测，并构建农业场景下小目标、域偏移的鲁棒性评估基准。","2026-10-05T23:30:12.187482Z",{"id":141,"title":142,"url":143,"summary":144,"summary_zh":145,"content":9,"source_name":146,"source_url":143,"published_at":147,"category":12,"cover_url":9,"hotness":13,"is_selected":14,"score":148,"score_detail":149,"sources":156,"tags":158,"primary_topic":160,"secondary_topics":165,"classification":166,"search_phrases":180,"slug":183,"view_count":154,"doi":184,"paper":185,"created_at":202},3503,"Adversarial Patch and Camouflage Attacks on Aerial Object Detection: A Geometry-Aware Review","https:\u002F\u002Fdoi.org\u002F10.3390\u002Fs26196057","Uncrewed aerial vehicles increasingly rely on on-board deep object detectors for applications such as surveillance, delivery, agriculture, and traffic monitoring. The vulnerability of these detectors to adversarial patches has therefore become a practical safety concern. Research on adversarial patch and camouflage attacks against aerial object detection has expanded rapidly, yet existing reviews consider aerial systems only as one application domain among many and do not examine the unique geometric conditions of aerial imagery. This review surveys adversarial patch and camouflage attacks, together with the corresponding defense mechanisms, for aerial, UAV, and remote sensing object detection. The literature is organized using a taxonomy based on two dimensions: the physical medium of the perturbation and the application domain it targets. Existing methods are then compared with respect to physical robustness, evaluation datasets and detectors, threat models, and their treatment of viewpoint variation. A recurring observation across the literature is that viewpoint variation is represented primarily through object scale, while explicit modeling of viewing geometry remains limited. This trend is closely linked to the characteristics of the aerial datasets used for evaluation, which typically provide realistic imagery but limited geometric information. Consequently, questions concerning viewpoint-dependent placement, degradation, and naturalness remain only partially explored. The review concludes by identifying the major research gaps, future directions, and deployment challenges that are likely to shape the next generation of aerial adversarial attack and defense research.","无人驾驶飞行器（UAV）在监视、配送、农业和交通监测等应用中日益依赖机载深度目标检测器。因此，这些检测器对对抗性补丁的脆弱性已成为一个实际的安全问题。针对空中目标检测的对抗性补丁与伪装攻击研究迅速扩展，然而现有综述仅将空中系统视为众多应用领域之一，并未考察航空影像独特的几何条件。本综述考察了针对空中、无人机及遥感目标检测的对抗性补丁与伪装攻击以及相应的防御机制。文献按照基于两个维度的分类体系进行组织：扰动的物理介质及其所针对的应用领域。随后，现有方法在物理鲁棒性、评估数据集与检测器、威胁模型以及其对视角变化的处理方面进行了比较。文献中反复出现的一个观察是，视角变化主要通过目标尺度来表示，而对观察几何的显式建模仍然有限。这一趋势与用于评估的航空数据集的特征密切相关，这些数据集通常提供真实影像但几何信息有限。因此，关于视角依赖的放置、退化及自然性的问题仅得到部分探讨。本综述最后指出了可能塑造下一代空中对抗攻击与防御研究的主要研究空白、未来方向及部署挑战。","Sensors","2026-09-24T00:00:00Z",67,{"impact":150,"substance":151,"depth":152,"authority":153,"freshness":154,"relevant":91,"comment":155},8,20,17,13,9,"系统梳理航空与无人机目标检测的对抗补丁与伪装攻击及防御，指出视角几何建模不足的研究空白，对农业遥感与无人机应用安全有参考价值。",[157],{"name":146,"url":143},[21,104,23,24,159],"对抗攻击",{"code":44,"slug":161,"name":162,"path":163,"parent_code":164},"remote-sensing","遥感与农情监测","\u002Ftopic\u002Fdigital-agriculture\u002Fremote-sensing","I",[],{"status":167,"locked":14,"version":28,"method":29,"evidence":168},"classified",{"candidates":169,"agricultural_evidence":35},[170,175],{"code":44,"score":45,"supported":35,"title":171,"abstract":172,"tags":174},[],[24,173],"remote sensing",[24],{"code":33,"score":176,"supported":35,"title":177,"abstract":178,"tags":179},5,[],[23],[104,23],[181,182],"无人机 对抗补丁 目标检测","航空图像 对抗攻击","无人机对抗补丁目标检测-3503","10.3390\u002Fs26196057",{"doi":184,"openalex_id":186,"authors":187,"venue":146,"cited_by_count":15,"oa_url":143,"card":197,"direction":85,"ingested_from":88},"W7214217753",[188,191,194],{"name":189,"orcid":190},"Sandesh Shrestha","https:\u002F\u002Forcid.org\u002F0000-0001-5298-4468",{"name":192,"orcid":193},"K. T. Y. Mahima","https:\u002F\u002Forcid.org\u002F0000-0003-4975-9408",{"name":195,"orcid":196},"Asanka G. Perera","https:\u002F\u002Forcid.org\u002F0000-0003-4021-3943",{"tldr":198,"method":199,"finding":200,"direction":85,"opportunity":201},"综述无人机与遥感目标检测中的对抗补丁与伪装攻击及防御，并提出几何感知分类体系。","基于扰动介质与应用领域的分类法，比较物理鲁棒性、数据集、威胁模型与视角处理。","现有研究多以目标尺度代替视角变化，缺乏显式视角几何建模，因数据集几何信息有限。","可构建含视角几何标注的农业航拍数据集，研究视角依赖的对抗补丁放置与自然性防御。","2026-09-25T23:30:31.219576Z",{"id":204,"title":205,"url":206,"summary":207,"summary_zh":208,"content":9,"source_name":209,"source_url":206,"published_at":210,"category":12,"cover_url":9,"hotness":13,"is_selected":14,"score":211,"score_detail":212,"sources":217,"tags":219,"primary_topic":223,"secondary_topics":229,"classification":231,"search_phrases":258,"slug":261,"view_count":15,"doi":262,"paper":263,"created_at":305},5567,"Capturing Spatial Heterogeneity Using UAV-Derived Multispectral Phenotypes and Random Regression Models Improves Genetic Evaluation in Alfalfa Breeding Trials","https:\u002F\u002Fdoi.org\u002F10.64898\u002F2026.10.14.759249","Spatial heterogeneity is a major source of environmental noise in field trials, reducing genetic evaluation accuracy. Conventional spatial correction methods use field layout and plot proximity but often fail to capture in-season dynamics or leverage temporal data from high-throughput phenotyping. We hypothesized that longitudinal UAV-derived multispectral measurements could characterize field-scale environmental heterogeneity and improve genetic evaluation in breeding trials. Multispectral imagery was collected throughout the growing season across eight alfalfa trials in New York and New Mexico (20222023). Vegetation indices were evaluated for heritability and association with biomass yield using univariate and multi-trait models. Longitudinal measurements were modeled with random regression (RR) to estimate plot-specific permanent environmental effects (PEE), incorporated into genomic mixed models within a two-stage framework. Model performance was compared with conventional autoregressive (AR) and baseline (no correction) models using metrics of consistency and accuracy of estimated genetic effects across replicates. Vegetation indices showed moderate to high heritability, with GNDVI consistently outperforming NDVI and NDRE. Both univariate and multi-trait analyses revealed substantial spatial variability, particularly in New Mexico trials. RR-derived PEE captured field-scale spatial patterns and improved genetic signal recovery relative to baseline and AR models, with the largest gains under strong spatial heterogeneity and comparable performance where variability was limited. The RR framework improved reproducibility of genetic effect estimates across independent field subsets without compromising agreement with full-trial evaluations. These findings show that integrating UAV data via random regression enhances genetic signal recovery and selection accuracy, with broader potential for precision agriculture and biosensor-driven crop management.","空间异质性是田间试验中环境噪声的主要来源，会降低遗传评估的准确性。传统空间校正方法利用田间布局和小区邻近性，但往往无法捕捉生育期内的动态变化，也未能充分利用高通量表型分析产生的时间序列数据。我们假设，基于无人机（UAV）的纵向多光谱测量能够表征田块尺度的环境异质性，并改善育种试验中的遗传评估。在2022—2023年纽约州和新墨西哥州的8个紫花苜蓿试验中，于整个生长季收集了多光谱影像。采用单性状和多性状模型评估了植被指数的遗传力及其与生物量产量的关联。纵向测量数据采用随机回归（RR）建模，以估计小区特异性永久环境效应（PEE），并在两阶段框架中将其纳入基因组混合模型。利用重复间估计遗传效应的一致性和准确性指标，将模型性能与传统的自回归（AR）模型和基线（无校正）模型进行比较。植被指数表现出中到高的遗传力，其中GNDVI始终优于NDVI和NDRE。单性状和多性状分析均揭示了显著的空间变异，尤其在新墨西哥州的试验中更为明显。RR衍生的PEE捕捉到了田块尺度的空间格局，相对于基线模型和AR模型改善了遗传信号的恢复，在强空间异质性条件下增益最大，而在变异有限时性能相当。RR框架提高了遗传效应估计在独立田间子集间的可重复性，同时未损害与全试验评估的一致性。这些结果表明，通过随机回归整合UAV数据可增强遗传信号恢复和选择准确性，在精准农业和生物传感器驱动的作物管理方面具有更广泛的潜力。","bioRxiv (Cold Spring Harbor Laboratory)","2026-10-20T00:00:00Z",79,{"impact":213,"substance":214,"depth":213,"authority":215,"freshness":154,"relevant":91,"comment":216},18,22,12,"该研究利用无人机多光谱表型与随机回归模型校正田间空间异质性，显著提升苜蓿育种遗传评估精度，方法新颖、数据覆盖两州八组试验，对智慧育种有实质参考价值。",[218],{"name":209,"url":206},[220,21,221,24,222],"智慧农业","育种","紫花苜蓿",{"code":224,"slug":225,"name":226,"path":227,"parent_code":228},"A7","forage-cropping","饲草与耕作制度","\u002Ftopic\u002Ffield-crops\u002Fforage-cropping","A",[230],{"code":44,"slug":161,"name":162,"path":163,"parent_code":164},{"status":167,"locked":14,"version":28,"method":29,"evidence":232},{"candidates":233,"agricultural_evidence":35},[234,241,245,252],{"code":224,"score":235,"supported":35,"title":236,"abstract":238,"tags":240},15,[237],"alfalfa",[239,237],"苜蓿",[222],{"code":44,"score":215,"supported":35,"title":242,"abstract":243,"tags":244},[48],[48],[24],{"code":246,"score":45,"supported":35,"title":247,"abstract":248,"tags":251},"I1",[],[249,250],"精准农业","precision agriculture",[220],{"code":253,"score":254,"supported":35,"title":255,"abstract":256,"tags":257},"C4",4,[],[239],[222],[259,260],"无人机 多光谱 苜蓿 育种","随机回归 空间异质性 遗传评估","无人机多光谱苜蓿育种-5567","10.64898\u002F2026.10.14.759249",{"doi":262,"openalex_id":264,"authors":265,"venue":209,"cited_by_count":15,"oa_url":206,"card":300,"direction":85,"ingested_from":88},"W7223083966",[266,269,272,275,278,280,282,285,288,291,294,297],{"name":267,"orcid":268},"Dinesh Ghimire","https:\u002F\u002Forcid.org\u002F0009-0008-2281-1396",{"name":270,"orcid":271},"Ranjita Thapa","https:\u002F\u002Forcid.org\u002F0000-0001-6116-7611",{"name":273,"orcid":274},"Karl H. Kunze","https:\u002F\u002Forcid.org\u002F0000-0003-4548-1808",{"name":276,"orcid":277},"Felipe Sabadin","https:\u002F\u002Forcid.org\u002F0000-0003-2937-1465",{"name":279,"orcid":9},"Julie Hansen",{"name":281,"orcid":9},"Christopher Pierce",{"name":283,"orcid":284},"Liam Wickes-Do","https:\u002F\u002Forcid.org\u002F0009-0003-2927-4590",{"name":286,"orcid":287},"Nicholas Santantonio","https:\u002F\u002Forcid.org\u002F0000-0002-4351-4023",{"name":289,"orcid":290},"Ian M. Ray","https:\u002F\u002Forcid.org\u002F0000-0003-2056-536X",{"name":292,"orcid":293},"Michael A. Gore","https:\u002F\u002Forcid.org\u002F0000-0001-6896-8024",{"name":295,"orcid":296},"Virginia Mae Moore","https:\u002F\u002Forcid.org\u002F0000-0001-7888-3366",{"name":298,"orcid":299},"Kelly R. Robbins","https:\u002F\u002Forcid.org\u002F0000-0001-9522-9585",{"tldr":301,"method":302,"finding":303,"direction":85,"opportunity":304},"用无人机多光谱时序表型和随机回归模型校正田间空间异质性，提升苜蓿育种遗传评估精度。","八项苜蓿试验的无人机多光谱植被指数，随机回归估计小区永久环境效应并嵌入基因组混合","随机回归提取的环境效应能捕捉田块尺度空间格局，在强异质性下显著提升遗传信号恢复与选择准确性。","可将无人机时序表型与随机回归框架推广到其他作物育种试验，并探索多源遥感与基因组选择的联合建模。","2026-10-22T11:20:32.655394Z",{"id":307,"title":308,"url":309,"summary":310,"summary_zh":311,"content":9,"source_name":312,"source_url":309,"published_at":313,"category":12,"cover_url":9,"hotness":13,"is_selected":14,"score":314,"score_detail":315,"sources":317,"tags":319,"primary_topic":320,"secondary_topics":324,"classification":325,"search_phrases":343,"slug":346,"view_count":15,"doi":347,"paper":348,"created_at":372},5393,"IMPLEMENTATION OF META-HEURISTIC OPTIMIZATION ALGORITHMS IN CONVOLUTIONAL NEURAL NETWORKS FOR OBJECT DETECTION AND CLASSIFICATION","https:\u002F\u002Fdoi.org\u002F10.22190\u002Ffuacr251214006i","CNNs have grown to form the backbone of modern computer vision systems, producing outstanding object detection and classification performance within diverse application domains. However, the manual development of suitable CNN architectures and, correspondingly, the selection of optimal hyperparameter sets are still inconvenient and time-consuming processes. The aim of this survey is to contribute a comprehensive review regarding how meta-heuristic optimization algorithms such as Genetic Algorithms, Particle Swarm Optimization, and other swarm intelligence-based methods are embedded in the CNN-based pipelines with the intent to achieve better detection and classification results. We gather recent progress regarding automated architecture search, hyperparameter tuning, model compression, and ensemble learning. We identify how hybrid optimization approaches consistently yield superior accuracy with computational efficiency by systematically reviewing applications in medical imaging, agriculture, vehicular recognition, and remote sensing. Optimized CNN models outperform their baseline versions many times, especially in health diagnostics, where several fine-tuned architectures reach accuracies greater than 99%. This survey provides a structured and updated overview of methodological developments, implementation practices, and emerging research directions for those practitioners and researchers who will apply meta-heuristic optimization within deep learning-based computer vision systems.","卷积神经网络（CNNs）已发展成为现代计算机视觉系统的核心骨干，在多个应用领域中展现出卓越的目标检测与分类性能。然而，人工设计合适的CNN架构并相应地选择最优超参数集仍然是繁琐且耗时的过程。本综述旨在全面回顾遗传算法、粒子群优化及其他群体智能方法等元启发式优化算法如何嵌入基于CNN的流程中以获得更优的检测与分类结果。我们汇集了自动化架构搜索、超参数调优、模型压缩和集成学习方面的最新进展。通过系统梳理在医学影像、农业、车辆识别和遥感领域的应用，我们揭示了混合优化方法如何以计算效率持续实现更优的精度。优化后的CNN模型在多数情况下远超其基线版本，尤其在健康诊断领域，若干精细调优的架构达到了超过99%的准确率。本综述为将在基于深度学习的计算机视觉系统中应用元启发式优化的从业者和研究者，提供了关于方法学进展、实施实践和新兴研究方向的结构化且更新的概述。","Facta Universitatis Series Automatic Control and Robotics","2026-10-18T00:00:00Z",61,{"impact":150,"substance":213,"depth":235,"authority":215,"freshness":150,"relevant":91,"comment":316},"综述系统梳理元启发式优化在CNN视觉任务中的嵌入方法，含农业应用，但属通用方法综述，非农业专属突破。",[318],{"name":312,"url":309},[220,104,23,24],{"code":33,"slug":321,"name":322,"path":323,"parent_code":164},"agricultural-ai","农业AI与大模型","\u002Ftopic\u002Fdigital-agriculture\u002Fagricultural-ai",[],{"status":167,"locked":14,"version":28,"method":29,"evidence":326},{"candidates":327,"agricultural_evidence":35},[328,335,339],{"code":33,"score":329,"supported":35,"title":330,"abstract":331,"tags":334},11,[],[23,332,39,333,41],"深度学习","deep learning",[104,23],{"code":44,"score":45,"supported":35,"title":336,"abstract":337,"tags":338},[],[24,173],[24],{"code":246,"score":91,"supported":14,"title":340,"abstract":341,"tags":342},[],[],[220],[344,345],"元启发式优化 卷积神经网络","CNN 目标检测","元启发式优化卷积神经网络-5393","10.22190\u002Ffuacr251214006i",{"doi":347,"openalex_id":349,"authors":350,"venue":312,"cited_by_count":15,"oa_url":309,"card":366,"direction":85,"ingested_from":88},"W7222920697",[351,354,357,360,363],{"name":352,"orcid":353},"Nikola Ivačko","https:\u002F\u002Forcid.org\u002F0000-0003-4367-119X",{"name":355,"orcid":356},"Ivan S Ciric","https:\u002F\u002Forcid.org\u002F0000-0003-0430-8937",{"name":358,"orcid":359},"Milica Tasić","https:\u002F\u002Forcid.org\u002F0009-0001-9160-6379",{"name":361,"orcid":362},"Ljiljana Radović","https:\u002F\u002Forcid.org\u002F0000-0002-4099-1289",{"name":364,"orcid":365},"Žarko Ćojbašić","https:\u002F\u002Forcid.org\u002F0000-0002-4581-1048",{"tldr":367,"method":368,"finding":369,"direction":370,"opportunity":371},"综述元启发式算法嵌入CNN流程以优化目标检测与分类的研究进展。","系统综述遗传算法、粒子群等群智能方法用于CNN架构搜索与超参调优。","混合优化方法在医学影像、农业等领域兼顾精度与效率，部分模型准确率超99%。","农业人工智能与决策模型","农业场景下元启发式优化CNN的架构搜索与轻量化部署仍缺乏系统基准与田间验证。","2026-10-20T23:30:19.233167Z",{"id":374,"title":375,"url":376,"summary":377,"summary_zh":9,"content":9,"source_name":378,"source_url":376,"published_at":379,"category":12,"cover_url":9,"hotness":13,"is_selected":14,"score":380,"score_detail":381,"sources":385,"tags":387,"primary_topic":389,"secondary_topics":393,"classification":394,"search_phrases":414,"slug":417,"view_count":91,"doi":418,"paper":419,"created_at":431},4973,"Barley head detection using UAV imagery and YOLOv10","https:\u002F\u002Fdoi.org\u002F10.1007\u002Fs11119-026-10468-w","Barley head detection using UAV imagery and YOLOv10。Precision Agriculture","Precision Agriculture","2026-10-14T00:00:00Z",75,{"impact":382,"substance":151,"depth":152,"authority":383,"freshness":150,"relevant":91,"comment":384},16,14,"将YOLOv10用于无人机大麦穗检测，方法新颖、数据可靠，属细分领域技术进展，值得精选。",[386],{"name":378,"url":376},[220,21,104,24,388],"大麦",{"code":246,"slug":390,"name":391,"path":392,"parent_code":164},"smart-agriculture","智慧农业总论","\u002Ftopic\u002Fdigital-agriculture\u002Fsmart-agriculture",[],{"status":167,"locked":14,"version":28,"method":29,"evidence":395},{"candidates":396,"agricultural_evidence":35},[397,401,406,410],{"code":246,"score":254,"supported":35,"title":398,"abstract":399,"tags":400},[],[250],[220],{"code":402,"score":91,"supported":14,"title":403,"abstract":404,"tags":405},"A5",[],[],[388],{"code":33,"score":91,"supported":14,"title":407,"abstract":408,"tags":409},[],[],[104],{"code":44,"score":91,"supported":14,"title":411,"abstract":412,"tags":413},[],[],[24],[415,416],"无人机 大麦 穗检测","YOLOv10 大麦 遥感","无人机大麦穗检测-4973","10.1007\u002Fs11119-026-10468-w",{"doi":418,"openalex_id":420,"authors":421,"venue":378,"cited_by_count":15,"oa_url":9,"card":9,"direction":9,"ingested_from":88},"W7221758985",[422,425,428],{"name":423,"orcid":424},"Ameer Tamoor Khan","https:\u002F\u002Forcid.org\u002F0000-0001-6838-992X",{"name":426,"orcid":427},"Saiful Azim","https:\u002F\u002Forcid.org\u002F0000-0002-2686-7150",{"name":429,"orcid":430},"Signe Marie Jensen","https:\u002F\u002Forcid.org\u002F0000-0002-7738-5231","2026-10-15T23:30:02.421798Z",{"id":433,"title":434,"url":435,"summary":436,"summary_zh":437,"content":9,"source_name":438,"source_url":435,"published_at":439,"category":12,"cover_url":9,"hotness":13,"is_selected":14,"score":440,"score_detail":441,"sources":443,"tags":445,"primary_topic":9,"secondary_topics":449,"classification":450,"search_phrases":468,"slug":471,"view_count":15,"doi":472,"paper":473,"created_at":494},4610,"UAV-based estimation of aboveground biomass carbon in the Sundarbans mangrove forest of Bangladesh","https:\u002F\u002Fdoi.org\u002F10.1088\u002F2515-7620\u002Faeb18f","Abstract Reliable biomass and carbon assessments are essential for understanding mangrove forest dynamics and their role in global carbon cycling. However, field-based biomass estimation is time-consuming, labour-intensive, and costly. Remote sensing provides a practical and cost-effective alternative, particularly with unmanned aerial vehicles (UAVs) that can capture high-resolution imagery. The assessment of biomass carbon in the Sundarbans Mangrove Forest (SMF) using high-resolution remote sensing remains understudied. This study develops an integrated carbon assessment framework for estimating aboveground biomass carbon in the SMF using UAV-derived canopy metrics and field measurements. Error propagation and feature importance analyses were performed to quantify uncertainty and assess predictor influence, providing a robust and uncertainty-aware approach for mangrove biomass carbon assessment. CPA was used to estimate proxy DBH using linear, polynomial, logarithmic, power, and exponential regression models. All CPA–DBH models showed comparable performance (R2 = 0.73-0.75). The linear and polynomial models achieved the lowest RMSE (1.77 cm), while the polynomial model produced the lowest MAE (1.22 cm) and was therefore selected for estimating Proxy DBH. Field-based AGBC was calculated from measured tree height and DBH using species-specific and generic allometric equations applicable to the Sundarbans, whereas UAV-based AGBC was estimated using UAV-derived Mean DSM Height and CPA-derived Proxy DBH. Simple linear regression (SLR), multiple linear regression (MLR), and machine-learning (ML) models (Random Forest, Support Vector Machine, Artificial Neural Network, and Extreme Gradient Boosting) were evaluated for AGBC prediction. The MLR model showed the best performance on the validation\u002Fmodel-selection subset (R² = 0.86, RMSE = 14.70 Mg C ha⁻¹, MedAE = 4.58 Mg C ha⁻¹). UAV-derived AGBC estimates closely matched field measurements and previously reported values for the Sundarbans, demonstrating the potential of high-resolution UAV metrics for reliable mangrove AGBC estimation and supporting carbon monitoring, REDD+ initiatives, and sustainable mangrove management in Bangladesh.","可靠的生物量和碳评估对于理解红树林动态及其在全球碳循环中的作用至关重要。然而，基于实地调查的生物量估算耗时、费力且成本高昂。遥感提供了一种实用且具有成本效益的替代方案，尤其是利用能够获取高分辨率影像的无人机（UAV）。利用高分辨率遥感对孙德尔本斯红树林（SMF）进行生物量碳评估的研究仍较为缺乏。本研究开发了一个综合碳评估框架，利用无人机获取的冠层指标和实地测量数据估算SMF的地上生物量碳。通过误差传播和特征重要性分析量化不确定性并评估预测因子的影响，为红树林生物量碳评估提供了一种稳健且考虑不确定性的方法。采用CPA（冠层投影面积）通过线性、多项式、对数、幂函数和指数回归模型估算代理DBH（胸径）。所有CPA–DBH模型均表现出相近的性能（R² = 0.73–0.75）。线性模型和多项式模型取得了最低的RMSE（1.77 cm），而多项式模型产生了最低的MAE（1.22 cm），因此被选用于估算代理DBH。基于实地的AGBC（地上生物量碳）通过实测树高和DBH，采用适用于孙德尔本斯的物种特异性异速生长方程和通用异速生长方程计算，而基于无人机的AGBC则利用无人机获取的平均DSM高度和CPA衍生的代理DBH进行估算。采用简单线性回归（SLR）、多元线性回归（MLR）和机器学习（ML）模型（随机森林、支持向量机、人工神经网络和极端梯度提升）评估AGBC预测性能。MLR模型在验证\u002F模型选择子集上表现最佳（R² = 0.86，RMSE = 14.70 Mg C ha⁻¹，MedAE = 4.58 Mg C ha⁻¹）。无人机获取的AGBC估算值与实地测量结果及先前报道的孙德尔本斯数值高度吻合，表明高分辨率无人机指标在可靠估算红树林AGBC方面具有潜力，可支持孟加拉国的碳监测、REDD+倡议和可持续红树林管理。","Environmental Research Communications","2026-10-07T00:00:00Z",80,{"impact":213,"substance":214,"depth":213,"authority":383,"freshness":150,"relevant":91,"comment":442},"该研究利用无人机高分辨率影像与机器学习模型估算孟加拉国孙德尔本斯红树林地上生物量碳，方法新颖、数据可靠，对林业碳汇监测与REDD+具有参考价值，但属境外案例、应用范围有限，可作为专业资讯收录。",[444],{"name":438,"url":435},[21,24,446,447,448],"智慧林业","红树林","碳汇计量",[],{"status":27,"locked":14,"version":28,"method":29,"evidence":451},{"candidates":452,"agricultural_evidence":14,"reason":59},[453,457,463],{"code":44,"score":45,"supported":35,"title":454,"abstract":455,"tags":456},[],[24,173],[24],{"code":33,"score":458,"supported":35,"title":459,"abstract":460,"tags":462},3,[],[461],"机器学习",[],{"code":464,"score":91,"supported":14,"title":465,"abstract":466,"tags":467},"H6",[],[],[447],[469,470],"孟加拉国 孙德尔本斯 红树林 无人机","无人机 生物量碳 遥感估算","孟加拉国孙德尔本斯红树林无人机-4610","10.1088\u002F2515-7620\u002Faeb18f",{"doi":472,"openalex_id":474,"authors":475,"venue":438,"cited_by_count":15,"oa_url":487,"card":488,"direction":493,"ingested_from":88},"W7220935167",[476,479,482,484],{"name":477,"orcid":478},"Md Abul Hashem","https:\u002F\u002Forcid.org\u002F0009-0006-2712-3168",{"name":480,"orcid":481},"Md Sarwar Hossain","https:\u002F\u002Forcid.org\u002F0000-0001-6101-659X",{"name":483,"orcid":9},"Md. Tauhidor Rahaman",{"name":485,"orcid":486},"Brian Barrett","https:\u002F\u002Forcid.org\u002F0000-0002-4380-4020","https:\u002F\u002Fiopscience.iop.org\u002Farticle\u002F10.1088\u002F2515-7620\u002Faeb18f\u002Fpdf",{"tldr":489,"method":490,"finding":491,"direction":85,"opportunity":492},"利用无人机冠层指标与地面数据估算孟加拉孙德尔本斯红树林地上生物量碳。","无人机高分辨率影像提取冠层指标，结合CPA估算DBH，用MLR与机器学习模型预测","多元线性回归表现最佳（R²=0.86），无人机估算值与实测及历史值高度吻合。","可探索多时相无人机与卫星融合，提升红树林碳储量动态监测及不确定性量化能力。","农业绿色发展与碳","2026-10-10T23:31:07.399747Z"]