[{"data":1,"prerenderedAt":-1},["ShallowReactive",2],{"item-2798":3,"related-2798":97},{"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,"primary_topic":32,"secondary_topics":38,"classification":39,"search_phrases":68,"slug":71,"view_count":55,"doi":72,"paper":73,"created_at":96},2798,"Deep Learning-Based Small-Object Detection in UAV Imagery: A Symmetry-Informed Review of Scale Variation and Scenario Constraints","https:\u002F\u002Fdoi.org\u002F10.3390\u002Fsym18091548","As UAV platforms are increasingly employed in military reconnaissance, disaster monitoring, precision agriculture, and other remote-sensing applications, small-object detection in UAV imagery is a critical yet challenging task. Existing reviews primarily address either general small-object detection or general object detection in UAV imagery, whereas reviews specifically devoted to small-object detection in UAV imagery remain scarce. This review examines existing deep learning-based research on small-object detection in UAV imagery from a problem-driven and deployment-oriented perspective. A symmetry-informed perspective was also adopted to analyze how variations in object-scale, viewpoint, imaging quality, and scene conditions affected feature representation and detection stability. Building on five major challenges in UAV small-object detection, a three-tier framework encompassing detection paradigms, key technical strategies, and scenario-specific constraints was established. Representative UAV datasets were further examined to characterize object-scale distributions, while existing methods were reviewed in terms of multiscale representation, feature enhancement, training optimization, and lightweight deployment. The applicability of different technical approaches was then discussed across five typical UAV scenarios. In addition, under relatively consistent experimental conditions, representative detection models based on two-stage, one-stage, and Transformer-based paradigms were analyzed in terms of detection accuracy, computational efficiency, and deployment feasibility. Finally, current limitations and future directions were summarized for scale-robust, scenario-adaptive, and resource-aware small-object detection in UAV imagery.","随着无人机平台在军事侦察、灾害监测、精准农业等遥感应用中的日益普及，无人机图像中的小目标检测成为一项关键但具有挑战性的任务。现有综述主要关注通用小目标检测或无人机图像中的通用目标检测，而专门针对无人机图像中小目标检测的综述仍然匮乏。本综述从问题驱动和部署导向的视角，审视了现有的基于深度学习的无人机图像小目标检测研究。同时采用对称性视角，分析了目标尺度、视角、成像质量和场景条件的变化如何影响特征表示和检测稳定性。基于无人机小目标检测中的五大挑战，构建了一个涵盖检测范式、关键技术策略和场景特定约束的三层框架。进一步考察了代表性无人机数据集以刻画目标尺度分布，同时从多尺度表示、特征增强、训练优化和轻量化部署等方面综述了现有方法。随后讨论了不同技术方法在五种典型无人机场景中的适用性。此外，在相对一致的实验条件下，对基于两阶段、单阶段和Transformer范式的代表性检测模型在检测精度、计算效率和部署可行性方面进行了分析。最后，总结了当前局限性及未来方向，以推动无人机图像中尺度鲁棒、场景自适应和资源感知的小目标检测研究。",null,"Symmetry","2026-09-16T00:00:00Z","论文",10,false,76,{"impact":17,"substance":18,"depth":19,"authority":20,"freshness":21,"relevant":22,"comment":23},16,20,18,13,9,1,"无人机小目标检测的系统性综述，提出对称性视角与三层框架，对农业遥感与精准农业部署有实质参考价值。",[25],{"name":10,"url":6},[27,28,29,30,31],"智慧农业","无人机","农业人工智能","农业遥感","目标检测",{"code":33,"slug":34,"name":35,"path":36,"parent_code":37},"I2","agricultural-ai","农业AI与大模型","\u002Ftopic\u002Fdigital-agriculture\u002Fagricultural-ai","I",[],{"status":40,"locked":14,"version":41,"method":42,"evidence":43},"classified","2026-10-22.2","rules",{"candidates":44,"agricultural_evidence":47},[45,53,61],{"code":33,"score":46,"supported":47,"title":48,"abstract":50,"tags":52},19,true,[49],"deep learning",[31,51,49],"深度学习",[29,31],{"code":54,"score":55,"supported":47,"title":56,"abstract":57,"tags":60},"I1",7,[],[58,59],"精准农业","precision agriculture",[27],{"code":62,"score":63,"supported":47,"title":64,"abstract":65,"tags":67},"I3",4,[],[66],"遥感",[30],[69,70],"农业人工智能 农业遥感 智慧农业 目标检测","农业人工智能 农业遥感","农业人工智能农业遥感智慧农业目标检测-2798","10.3390\u002Fsym18091548",{"doi":72,"openalex_id":74,"authors":75,"venue":10,"cited_by_count":88,"oa_url":6,"card":89,"direction":93,"ingested_from":95},"W7213430256",[76,78,81,83,85],{"name":77,"orcid":9},"Ling Wen",{"name":79,"orcid":80},"Anmin Gong","https:\u002F\u002Forcid.org\u002F0000-0002-2715-2296",{"name":82,"orcid":9},"Caihong Ma",{"name":84,"orcid":9},"Shengzhou Ma",{"name":86,"orcid":87},"Yanzhe Zhang","https:\u002F\u002Forcid.org\u002F0009-0008-6529-1247",0,{"tldr":90,"method":91,"finding":92,"direction":93,"opportunity":94},"综述无人机图像小目标检测的深度学习研究，提出对称性视角与三层框架。","文献综述，分析代表性数据集与两阶段、单阶段、Transformer模型。","尺度变化和场景约束是核心挑战，需尺度鲁棒、场景自适应和资源感知检测。","农业遥感与作物表型","可探索农业场景下尺度自适应与轻量化部署的平衡，以及跨场景泛化的小目标检测。","openalex","2026-09-17T23:30:37.479759Z",{"total":98,"page":22,"page_size":98,"items":99},6,[100,156,235,295,355,417],{"id":101,"title":102,"url":103,"summary":104,"summary_zh":105,"content":9,"source_name":106,"source_url":107,"published_at":108,"category":12,"cover_url":9,"hotness":13,"is_selected":14,"score":109,"score_detail":110,"sources":114,"tags":116,"primary_topic":117,"secondary_topics":118,"classification":119,"search_phrases":135,"slug":138,"view_count":139,"doi":140,"paper":141,"created_at":155},4373,"APPLICATION POTENTIAL OF UNMANNED AERIAL VEHICLES AND TRENDS IN THEIR DEVELOPMENT","https:\u002F\u002Fdoi.org\u002F10.5281\u002Fzenodo.23168044","This article examines the application potential and principal development trends of unmanned aerial vehicles across civilian, public-service, industrial, scientific, and defense-related domains. Particular attention is given to platform diversification, sensor and payload integration, artificial intelligence, autonomy, communications, energy efficiency, airspace integration, safety, cybersecurity, regulation, and human capital. The study applies a structured qualitative review of open official documents and peer-reviewed or professionally reviewed publications, combining international evidence with official sources from the Republic of Uzbekistan. The findings show that unmanned aerial vehicles are evolving from remotely piloted, task-specific platforms toward increasingly autonomous, networked, modular, data-driven aerial systems. Their strongest growth areas include precision agriculture, geospatial mapping, infrastructure inspection, environmental monitoring, emergency response, logistics, communications support, and selected security and defense functions. The article remains at the strategic, technological, regulatory, and systems-engineering level and does not address tactical employment procedures or operational vulnerabilities.","本文考察了无人机在民用、公共服务、工业、科学及国防相关领域的应用潜力与主要发展趋势，特别关注平台多样化、传感器与载荷集成、人工智能、自主性、通信、能效、空域整合、安全、网络安全、监管及人力资本等方面。研究采用结构化定性综述方法，对公开官方文件及经同行评审或专业评审的出版物进行分析，并将国际证据与乌兹别克斯坦共和国的官方来源相结合。研究结果表明，无人机正从远程驾驶的专用任务平台，向日益自主化、网络化、模块化、数据驱动的空中系统演进。其增长最为强劲的领域包括精准农业、地理空间测绘、基础设施巡检、环境监测、应急响应、物流、通信支持以及特定的安全与国防功能。本文保持在战略、技术、监管和系统工程层面，不涉及战术运用程序或作战脆弱性。","HSR (London)","https:\u002F\u002Fhoughtonstreetreview.com\u002Findex.php\u002Findex\u002Farticle\u002Fview\u002F2110","2026-10-05T00:00:00Z",67,{"impact":19,"substance":17,"depth":111,"authority":13,"freshness":112,"relevant":22,"comment":113},15,8,"综述性论文，将无人机与精准农业、农业遥感等智慧农业场景关联，有战略参考价值但非突破性成果。",[115],{"name":106,"url":107},[27,28,29,30,58],{"code":33,"slug":34,"name":35,"path":36,"parent_code":37},[],{"status":40,"locked":14,"version":41,"method":42,"evidence":120},{"candidates":121,"agricultural_evidence":47},[122,126,131],{"code":54,"score":112,"supported":47,"title":123,"abstract":124,"tags":125},[],[58,59],[27,58],{"code":33,"score":63,"supported":47,"title":127,"abstract":128,"tags":130},[],[129],"artificial intelligence",[29],{"code":62,"score":22,"supported":14,"title":132,"abstract":133,"tags":134},[],[],[30],[136,137],"无人机 精准农业 应用","农业人工智能 农业遥感 智慧农业 精准农业","无人机精准农业应用-4373",2,"10.5281\u002Fzenodo.23168044",{"doi":140,"openalex_id":142,"authors":143,"venue":106,"cited_by_count":88,"oa_url":107,"card":148,"direction":154,"ingested_from":95},"W7220406405",[144,146],{"name":145,"orcid":9},"Somitov Abdukadir Abdurayimovich",{"name":147,"orcid":9},"Worldly Knowledge Publishing Centre",{"tldr":149,"method":150,"finding":151,"direction":152,"opportunity":153},"综述无人机应用潜力与发展趋势，强调其向自主化、网络化、数据驱动系统演进。","结构化定性综述官方文件与同行评议文献，结合国际与乌兹别克斯坦证据。","无人机最强增长领域包括精准农业、地理空间测绘、基础设施巡检与环境监测等。","智慧农业 \u002F 农业物联网","可聚焦精准农业中无人机多源数据融合与自主决策的落地瓶颈及监管适配研究。","农业人工智能与决策模型","2026-10-07T23:30:46.084251Z",{"id":157,"title":158,"url":159,"summary":160,"summary_zh":161,"content":9,"source_name":162,"source_url":159,"published_at":163,"category":12,"cover_url":9,"hotness":13,"is_selected":14,"score":164,"score_detail":165,"sources":168,"tags":170,"primary_topic":172,"secondary_topics":176,"classification":178,"search_phrases":213,"slug":216,"view_count":63,"doi":217,"paper":218,"created_at":234},2906,"UAV remote sensing for crop lodging monitoring: A comprehensive review","https:\u002F\u002Fdoi.org\u002F10.1016\u002Fj.compag.2026.112446","Global agriculture is facing increasing pressure to improve productivity while minimizing losses caused by extreme climate events. Crop lodging poses a major threat to food security by reducing crop yield, deteriorating grain quality, and increasing harvesting costs. As a flexible, high-resolution remote sensing platform, unmanned aerial vehicles (UAVs) have emerged as an effective solution for eliminating the gap between labor-intensive ground surveys and low-resolution satellite observations. This review systematically synthesizes the current state of research on UAV-based crop lodging monitoring through a comprehensive analysis of peer-reviewed literature. It covers the complete technical workflow, from lodging mechanisms to lodging quantification. The capabilities of diverse sensing modalities, including RGB, multispectral imagery (MSI), hyperspectral imagery (HSI), thermal infrared (TIR), light detection and ranging (LiDAR), and synthetic aperture radar (SAR), are systematically evaluated for detecting lodging-induced variations in color, texture, spectral characteristics, canopy temperature, structural attributes, and radar backscatter. In addition, recent advances in analytical approaches are reviewed, encompassing traditional statistical analyses, machine learning techniques, and state-of-the-art deep learning models. Furthermore, the review summarizes UAV-based lodging assessments across a wide range of crop species and examines methods for quantifying key lodging parameters, including lodging severity, lodging type, and affected area. By identifying current research gaps and emerging opportunities, this review outlines future research directions and provides valuable guidance for advancing accurate, efficient, and real-time crop lodging monitoring in smart agriculture.","全球农业正面临日益增大的压力，既要提高生产力，又要尽量减少极端气候事件造成的损失。作物倒伏通过降低作物产量、恶化籽粒品质并增加收获成本，对粮食安全构成重大威胁。作为一种灵活的高分辨率遥感平台，无人机（UAV）已成为弥合劳动密集型地面调查与低分辨率卫星观测之间差距的有效解决方案。本文通过系统分析同行评议文献，全面综述了基于无人机的作物倒伏监测研究现状，涵盖从倒伏机理到倒伏量化的完整技术流程。系统评估了多种传感模态的能力，包括RGB影像、多光谱影像（MSI）、高光谱影像（HSI）、热红外（TIR）、激光雷达（LiDAR）和合成孔径雷达（SAR），用于检测倒伏引起的颜色、纹理、光谱特征、冠层温度、结构属性和雷达后向散射变化。此外，综述了分析方法的最新进展，涵盖传统统计分析、机器学习技术和前沿深度学习模型。同时，本文总结了针对多种作物类型的基于无人机的倒伏评估研究，并探讨了关键倒伏参数的量化方法，包括倒伏严重程度、倒伏类型和受影响面积。通过识别当前研究空白和新兴机遇，本文展望了未来研究方向，为推进智慧农业中准确、高效、实时的作物倒伏监测提供了有价值的指导。","Computers and Electronics in Agriculture","2026-09-18T00:00:00Z",81,{"impact":19,"substance":166,"depth":19,"authority":111,"freshness":112,"relevant":22,"comment":167},22,"核心期刊发表的无人机遥感作物倒伏监测综述，系统梳理多模态传感与深度学习分析路径，对智慧农业精准监测有实质参考价值。",[169],{"name":162,"url":159},[27,28,29,30,171],"作物倒伏",{"code":62,"slug":173,"name":174,"path":175,"parent_code":37},"remote-sensing","遥感与农情监测","\u002Ftopic\u002Fdigital-agriculture\u002Fremote-sensing",[177],{"code":33,"slug":34,"name":35,"path":36,"parent_code":37},{"status":40,"locked":14,"version":41,"method":42,"evidence":179},{"candidates":180,"agricultural_evidence":47},[181,188,194,199,206],{"code":62,"score":19,"supported":47,"title":182,"abstract":184,"tags":187},[183],"remote sensing",[66,183,185,186],"multispectral","hyperspectral",[30],{"code":33,"score":13,"supported":47,"title":189,"abstract":190,"tags":193},[],[51,191,192,49],"机器学习","machine learning",[29],{"code":54,"score":55,"supported":47,"title":195,"abstract":196,"tags":198},[],[27,197],"smart agriculture",[27],{"code":200,"score":98,"supported":47,"title":201,"abstract":202,"tags":205},"A8",[],[203,204],"粮食安全","food security",[],{"code":207,"score":98,"supported":47,"title":208,"abstract":209,"tags":212},"J3",[],[210,211],"全球农业","global agriculture",[],[214,215],"无人机 遥感 作物倒伏","UAV 倒伏 监测","无人机遥感作物倒伏-2906","10.1016\u002Fj.compag.2026.112446",{"doi":217,"openalex_id":219,"authors":220,"venue":162,"cited_by_count":88,"oa_url":159,"card":229,"direction":152,"ingested_from":95},"W7213542473",[221,224,226],{"name":222,"orcid":223},"Dashuai Wang","https:\u002F\u002Forcid.org\u002F0000-0002-3159-7175",{"name":225,"orcid":9},"Changxing Geng",{"name":227,"orcid":228},"Xiaoguang Liu","https:\u002F\u002Forcid.org\u002F0000-0002-0935-3094",{"tldr":230,"method":231,"finding":232,"direction":93,"opportunity":233},"综述无人机遥感在作物倒伏监测中的技术流程、传感器与分析模型。","系统综述RGB、多光谱、高光谱、热红外、LiDAR、SAR及机器学习深度学习方法","多模态遥感结合深度学习可实现倒伏程度、类型与面积的精准量化。","多源数据融合与实时轻量化模型是倒伏监测的潜在突破方向。","2026-09-19T23:30:01.740139Z",{"id":236,"title":237,"url":238,"summary":239,"summary_zh":240,"content":9,"source_name":241,"source_url":238,"published_at":242,"category":12,"cover_url":9,"hotness":13,"is_selected":14,"score":243,"score_detail":244,"sources":247,"tags":249,"primary_topic":251,"secondary_topics":252,"classification":253,"search_phrases":273,"slug":276,"view_count":268,"doi":277,"paper":278,"created_at":294},1970,"Real-time hass avocado ripeness detection using close-range UAV imagery and YOLO-based deep learning","https:\u002F\u002Fdoi.org\u002F10.1016\u002Fj.atech.2026.102547","Rapid and accurate assessment of Hass avocado ripeness is essential for improving harvest planning, optimizing picking time, increasing productivity, and reducing postharvest losses. This study presents a real-time system for Hass avocado ripeness detection using close-range UAV imagery and YOLO-based deep learning models. A UAV equipped with a camera captured field images, which were transmitted in real time to a processing station through SCRCPY for fruit detection and ripeness classification. The proposed approach consists of two sequential stages. First, a YOLOv8 object detection model was trained using a dataset of 340 manually annotated images generated through real-world adaptation and labeled in Roboflow. The detector achieved a precision of 0.7951, a recall of 0.7849, an mAP@0.5 of 0.8388, and an mAP@0.5:0.95 of 0.6308, demonstrating reliable fruit localization under field conditions. Second, a YOLOv8 classification model was trained on a dataset of 20,231 cropped fruit images derived from an initial collection of 14,710 images categorized into five ripeness stages (unripe, midripe, ripe, fullripe, and overripe). The classification model achieved an accuracy of 0.79 , a macro-average F1-score of 0.77, a weighted-average F1-score of 0.78, a Top-1 accuracy of 0.78, and a Top-5 accuracy of 1.00, confirming its effectiveness for ripeness assessment. The complete system was evaluated under real agricultural conditions with variable illumination and partial fruit occlusion, demonstrating that the integration of close-range UAV imagery and deep learning provides an effective tool for automated avocado ripeness assessment in precision agriculture. The proposed approach was evaluated using close-range UAV imagery acquired in a commercial orchard; therefore, additional validation under different orchards, environmental conditions, and acquisition scenarios is recommended to further assess its generalization capability.","对哈斯鳄梨成熟度的快速准确评估对于改进采收规划、优化采摘时间、提高生产率以及减少采后损失至关重要。本研究提出了一种基于近距无人机影像和YOLO深度学习模型的哈斯鳄梨成熟度实时检测系统。搭载摄像头的无人机采集田间图像，并通过SCRCPY实时传输至处理站进行果实检测和成熟度分类。所提出的方法包括两个连续阶段。首先，利用340张通过实际场景适配生成并在Roboflow中标注的人工标注图像数据集训练YOLOv8目标检测模型。该检测器实现了0.7951的精确率、0.7849的召回率、0.8388的mAP@0.5和0.6308的mAP@0.5:0.95，表明其在田间条件下具有可靠的果实定位能力。其次，利用从初始14,710张图像中提取的20,231张裁剪果实图像数据集训练YOLOv8分类模型，这些图像被分为五个成熟度阶段（未熟、半熟、成熟、完熟和过熟）。分类模型实现了0.79的准确率、0.77的宏平均F1分数、0.78的加权平均F1分数、0.78的Top-1准确率和1.00的Top-5准确率，证实了其在成熟度评估中的有效性。整个系统在光照变化和果实部分遮挡的真实农业条件下进行了评估，结果表明近距无人机影像与深度学习的集成为精准农业中的鳄梨成熟度自动评估提供了有效工具。所提出的方法是在商业果园中获取的近距无人机影像上评估的，因此建议在不同果园、环境条件和采集场景下进行额外验证，以进一步评估其泛化能力。","Smart Agricultural Technology","2026-09-06T00:00:00Z",71,{"impact":111,"substance":166,"depth":19,"authority":245,"freshness":63,"relevant":22,"comment":246},12,"研究提出基于无人机和YOLO的鳄梨成熟度实时检测系统，方法新颖且数据详实，对精准农业有参考价值。",[248],{"name":241,"url":238},[27,28,29,31,250],"鳄梨",{"code":33,"slug":34,"name":35,"path":36,"parent_code":37},[],{"status":40,"locked":14,"version":41,"method":42,"evidence":254},{"candidates":255,"agricultural_evidence":47},[256,262,266],{"code":33,"score":257,"supported":47,"title":258,"abstract":260,"tags":261},27,[49,259],"YOLO",[31,51,49,259],[29,31],{"code":54,"score":55,"supported":47,"title":263,"abstract":264,"tags":265},[],[58,59],[27],{"code":267,"score":268,"supported":47,"title":269,"abstract":270,"tags":272},"B2",3,[],[271],"orchard",[],[274,275],"农业人工智能 智慧农业 目标检测 无人机","农业人工智能 智慧农业","农业人工智能智慧农业目标检测无人机-1970","10.1016\u002Fj.atech.2026.102547",{"doi":277,"openalex_id":279,"authors":280,"venue":241,"cited_by_count":88,"oa_url":238,"card":289,"direction":152,"ingested_from":95},"W7210263003",[281,284,286],{"name":282,"orcid":283},"Verner Leonidas TUDELA TACO","https:\u002F\u002Forcid.org\u002F0009-0000-2214-3377",{"name":285,"orcid":9},"Wilson Emerson QUISPE ACCOSTUPA",{"name":287,"orcid":288},"Erasmo Sulla Espinoza","https:\u002F\u002Forcid.org\u002F0000-0002-1223-1223",{"tldr":290,"method":291,"finding":292,"direction":152,"opportunity":293},"用无人机近景图像和YOLO深度学习实时检测哈斯鳄梨成熟度，实现精准农业应用。","YOLOv8检测与分类模型，340张标注图像和20231张裁剪图像，通过SCRC","检测mAP@0.5达0.8388，分类准确率0.79，在田间条件下有效评估成熟度。","可研究多果园、多环境下的泛化性，或结合多光谱图像提升成熟度分类精度。","2026-09-09T23:30:03.462565Z",{"id":296,"title":297,"url":298,"summary":299,"summary_zh":9,"content":9,"source_name":300,"source_url":9,"published_at":301,"category":12,"cover_url":9,"hotness":13,"is_selected":14,"score":302,"score_detail":303,"sources":307,"tags":309,"primary_topic":312,"secondary_topics":318,"classification":320,"search_phrases":342,"slug":345,"view_count":88,"doi":9,"paper":346,"created_at":354},5532,"精准棉花病害管理：融合无人机影像与定制YOLO深度学习框架","https:\u002F\u002Farxiv.org\u002Fabs\u002F2610.24182","研究提出单阶段全卷积检测器Cotton-Vision，融合幽灵瓶颈通道注意力与跨阶段部分融合三项轻量化设计，参数减少20%。在巴基斯坦旁遮普省7个棉田采集的2700余幅高分辨率无人机影像上测试，精确率97.7%、召回率77.7%、mAP@50为85.6%，较主流基线提升10至20个百分点。预印本，仅在巴基斯坦单一区域验证。","arXiv 预印本 2026-10-16","2026-10-16T00:00:00Z",69,{"impact":17,"substance":304,"depth":305,"authority":21,"freshness":98,"relevant":22,"comment":306},21,17,"方法轻量化与实测数据有增量，但仅单区域预印本验证，属细分技术进展，可入精选备选。",[308],{"name":300,"url":298},[27,29,31,310,311],"无人机遥感","棉花病害",{"code":313,"slug":314,"name":315,"path":316,"parent_code":317},"A6","cash-crops","棉麻糖与特色经作","\u002Ftopic\u002Ffield-crops\u002Fcash-crops","A",[319],{"code":33,"slug":34,"name":35,"path":36,"parent_code":37},{"status":40,"locked":14,"version":41,"method":42,"evidence":321},{"candidates":322,"agricultural_evidence":47},[323,327,334,338],{"code":33,"score":19,"supported":47,"title":324,"abstract":325,"tags":326},[51,259],[],[29,31],{"code":313,"score":328,"supported":47,"title":329,"abstract":331,"tags":333},11,[330],"棉花",[332],"cotton",[],{"code":54,"score":22,"supported":14,"title":335,"abstract":336,"tags":337},[],[],[27],{"code":62,"score":22,"supported":14,"title":339,"abstract":340,"tags":341},[],[],[310],[343,344],"Cotton-Vision 棉花病害","无人机影像 棉花 检测","Cotton-Vision棉花病害-5532",{"doi":9,"openalex_id":9,"authors":347,"venue":9,"cited_by_count":88,"oa_url":9,"card":348,"direction":93,"ingested_from":353},[],{"tldr":349,"method":350,"finding":351,"direction":93,"opportunity":352},"提出轻量化检测器Cotton-Vision，用无人机影像精准识别棉花病害。","基于YOLO改进，融合幽灵瓶颈通道注意力与跨阶段部分融合，用2700余幅无人机影","精确率97.7%、mAP@50达85.6%，较主流基线提升10至20个百分点。","仅在巴基斯坦单一区域验证，可扩展至多区域多品种，并探索边缘设备实时部署。","agent","2026-10-22T00:07:09.816790Z",{"id":356,"title":357,"url":358,"summary":359,"summary_zh":360,"content":9,"source_name":361,"source_url":358,"published_at":362,"category":12,"cover_url":9,"hotness":13,"is_selected":14,"score":363,"score_detail":364,"sources":366,"tags":368,"primary_topic":369,"secondary_topics":370,"classification":371,"search_phrases":388,"slug":391,"view_count":88,"doi":392,"paper":393,"created_at":416},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":112,"substance":19,"depth":111,"authority":245,"freshness":112,"relevant":22,"comment":365},"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。",[367],{"name":361,"url":358},[27,29,31,66],{"code":33,"slug":34,"name":35,"path":36,"parent_code":37},[],{"status":40,"locked":14,"version":41,"method":42,"evidence":372},{"candidates":373,"agricultural_evidence":47},[374,380,384],{"code":33,"score":328,"supported":47,"title":375,"abstract":376,"tags":379},[],[31,51,377,49,378],"计算机视觉","computer vision",[29,31],{"code":62,"score":55,"supported":47,"title":381,"abstract":382,"tags":383},[],[66,183],[66],{"code":54,"score":22,"supported":14,"title":385,"abstract":386,"tags":387},[],[],[27],[389,390],"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":392,"openalex_id":394,"authors":395,"venue":361,"cited_by_count":88,"oa_url":358,"card":411,"direction":93,"ingested_from":95},"W7222920697",[396,399,402,405,408],{"name":397,"orcid":398},"Nikola Ivačko","https:\u002F\u002Forcid.org\u002F0000-0003-4367-119X",{"name":400,"orcid":401},"Ivan S Ciric","https:\u002F\u002Forcid.org\u002F0000-0003-0430-8937",{"name":403,"orcid":404},"Milica Tasić","https:\u002F\u002Forcid.org\u002F0009-0001-9160-6379",{"name":406,"orcid":407},"Ljiljana Radović","https:\u002F\u002Forcid.org\u002F0000-0002-4099-1289",{"name":409,"orcid":410},"Žarko Ćojbašić","https:\u002F\u002Forcid.org\u002F0000-0002-4581-1048",{"tldr":412,"method":413,"finding":414,"direction":154,"opportunity":415},"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":418,"title":419,"url":420,"summary":421,"summary_zh":422,"content":9,"source_name":423,"source_url":420,"published_at":424,"category":12,"cover_url":9,"hotness":13,"is_selected":14,"score":243,"score_detail":425,"sources":427,"tags":429,"primary_topic":432,"secondary_topics":433,"classification":434,"search_phrases":467,"slug":470,"view_count":88,"doi":471,"paper":472,"created_at":491},4985,"Hybrid deep ensemble learning for crop disease prediction and climate-resilient disaster management in smart agriculture","https:\u002F\u002Fdoi.org\u002F10.1007\u002Fs10791-026-10579-y","Abstract Accurate crop disease prediction and climate-resilient disaster management are essential for improving agricultural productivity and ensuring food security under increasingly dynamic environmental conditions. Existing deep learning approaches typically perform crop disease detection and climate forecasting independently and often rely on deterministic CNN–LSTM architectures without effective multimodal feature fusion, predictive uncertainty estimation, or comprehensive statistical validation. Consequently, their ability to provide reliable decision support under changing climatic conditions remains limited. To address these challenges, this paper proposes a novel hybrid deep ensemble learning framework for integrated crop disease prediction and climate-resilient disaster management in smart agriculture. The proposed framework combines convolutional neural networks (CNNs) for spatial crop image feature extraction with long short-term memory (LSTM) networks for temporal climate forecasting. An attention-based multimodal feature fusion mechanism is employed to integrate heterogeneous crop and climate information, while Bayesian uncertainty estimation and deep ensemble learning are incorporated to improve prediction reliability, robustness, and confidence-aware decision support. Experimental evaluation is performed using multimodal datasets comprising crop images and climate observations collected from the PlantVillage, NOAA, and NASA EOS datasets. The dataset is divided into training, validation, and testing subsets using a 70:15:15 ratio. The proposed framework is evaluated using classification and regression metrics, including Accuracy, Precision, Recall, F1-score, RMSE, MAE, MAPE, and AUC-ROC. To ensure reproducibility, all experiments are repeated five times using different random seeds, and the results are reported with mean $$\\pm$$ standard deviation, 95% confidence intervals, and paired Student’s $$t$$ -tests. Experimental results demonstrate that the proposed framework consistently outperforms conventional CNN, LSTM, and CNN–LSTM hybrid models by achieving higher classification accuracy, lower climate forecasting error, improved robustness under varying climate conditions, and statistically significant performance improvements. The proposed framework provides a reliable, scalable, and uncertainty-aware solution for intelligent climate-resilient smart agriculture and early agricultural disaster management.","摘要：准确的作物病害预测和气候适应性灾害管理对于在日益动态的环境条件下提高农业生产力和保障粮食安全至关重要。现有深度学习方法通常独立执行作物病害检测和气候预测，且往往依赖确定性CNN–LSTM架构，缺乏有效的多模态特征融合、预测不确定性估计或全面的统计验证。因此，其在气候变化条件下提供可靠决策支持的能力仍然有限。为应对这些挑战，本文提出了一种新颖的混合深度集成学习框架，用于智慧农业中的作物病害预测与气候适应性灾害管理一体化。该框架将用于空间作物图像特征提取的卷积神经网络（CNN）与用于时间气候预测的长短期记忆（LSTM）网络相结合。采用基于注意力的多模态特征融合机制整合异构的作物与气候信息，同时引入贝叶斯不确定性估计和深度集成学习，以提高预测可靠性、鲁棒性和置信感知决策支持能力。实验评估使用包含作物图像和气候观测数据的多模态数据集，数据来源于PlantVillage、NOAA和NASA EOS数据集。数据集按70：15：15的比例划分为训练集、验证集和测试集。采用分类和回归指标对所提框架进行评估，包括准确率、精确率、召回率、F1分数、RMSE、MAE、MAPE和AUC-ROC。为确保可复现性，所有实验使用不同随机种子重复五次，结果以均值$$\\pm$$标准差、95%置信区间和配对Student's $$t$$检验报告。实验结果表明，所提框架在分类准确率、气候预测误差、不同气候条件下的鲁棒性以及统计显著性性能提升方面均持续优于传统CNN、LSTM和CNN–LSTM混合模型。该框架为智能气候适应性智慧农业和早期农业灾害管理提供了一种可靠、可扩展且具有不确定性感知能力的解决方案。","Discover Computing","2026-10-14T00:00:00Z",{"impact":245,"substance":18,"depth":305,"authority":20,"freshness":21,"relevant":22,"comment":426},"提出CNN-LSTM注意力融合与贝叶斯不确定性估计的混合深度集成框架，多源数据与统计验证扎实，但属方法类论文，产业落地影响有限。",[428],{"name":423,"url":420},[27,29,30,430,431],"防灾减灾","作物病害预测",{"code":33,"slug":34,"name":35,"path":36,"parent_code":37},[],{"status":40,"locked":14,"version":41,"method":42,"evidence":435},{"candidates":436,"agricultural_evidence":47},[437,441,446,453,457,463],{"code":54,"score":111,"supported":47,"title":438,"abstract":439,"tags":440},[197],[27,197],[27],{"code":33,"score":13,"supported":47,"title":442,"abstract":443,"tags":445},[],[51,49,444],"decision support",[29],{"code":447,"score":55,"supported":47,"title":448,"abstract":449,"tags":452},"H7",[],[450,451],"气候变化","气候适应",[430],{"code":200,"score":98,"supported":47,"title":454,"abstract":455,"tags":456},[],[203,204],[],{"code":458,"score":268,"supported":47,"title":459,"abstract":460,"tags":462},"A7",[],[461],"间作",[],{"code":62,"score":22,"supported":14,"title":464,"abstract":465,"tags":466},[],[],[30],[468,469],"PlantVillage NOAA NASA 作物病害预测","CNN LSTM 气候韧性 智慧农业","PlantVillageNOAANASA作物病害预测-4985","10.1007\u002Fs10791-026-10579-y",{"doi":471,"openalex_id":473,"authors":474,"venue":423,"cited_by_count":88,"oa_url":420,"card":486,"direction":152,"ingested_from":95},"W7221778141",[475,478,481,483],{"name":476,"orcid":477},"Deepak Motwani","https:\u002F\u002Forcid.org\u002F0000-0002-0217-7155",{"name":479,"orcid":480},"Sellappan Palaniappan","https:\u002F\u002Forcid.org\u002F0009-0009-1168-2864",{"name":482,"orcid":9},"A. Daniel",{"name":484,"orcid":485},"Azween B. Abdullah","https:\u002F\u002Forcid.org\u002F0000-0003-4425-8604",{"tldr":487,"method":488,"finding":489,"direction":154,"opportunity":490},"提出混合深度集成框架，融合CNN与LSTM并引入注意力机制，实现作物病害预测与气候韧性灾害管理。","CNN提取图像特征、LSTM预测气候，注意力多模态融合，贝叶斯不确定性估计与深度","框架在分类精度与气候预测误差上均优于CNN、LSTM及CNN-LSTM基线，且性能提升具统计显著性。","可探索轻量化边缘部署与多作物跨区域迁移，结合实时物联网数据提升不确定性感知的灾害预警时效。","2026-10-15T23:30:08.408875Z"]