[{"data":1,"prerenderedAt":-1},["ShallowReactive",2],{"item-3479":3,"related-3479":110},{"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":9,"secondary_topics":32,"classification":33,"search_phrases":80,"slug":83,"view_count":74,"doi":84,"paper":85,"created_at":109},3479,"Artificial Intelligence-Enabled Mangrove Ecosystem Monitoring Using Remote Sensing and Environmental Data","https:\u002F\u002Fdoi.org\u002F10.68012\u002Fair.v1i2.252","Mangrove ecosystems play a critical role in coastal protection, carbon sequestration, biodiversity conservation, and climate change mitigation; however, increasing anthropogenic pressures and environmental changes have accelerated mangrove degradation, creating an urgent need for efficient and scalable monitoring approaches. This study aims to develop an Artificial Intelligence-Enabled framework for monitoring mangrove ecosystem conditions by integrating remote sensing imagery with environmental datasets to improve the accuracy and timeliness of ecosystem assessment in tropical coastal regions. The proposed method combines multispectral satellite images, including vegetation indices derived from remote sensing data, with environmental variables such as temperature, precipitation, salinity, and tidal information, which are subsequently processed using a deep learning-based classification model to identify and categorize mangrove health conditions. Experimental evaluation demonstrates that the integration of remote sensing and environmental data significantly enhances model performance compared with approaches relying solely on satellite imagery, achieving high classification accuracy and improving the detection of early signs of ecosystem degradation. The findings further reveal that environmental parameters contribute substantially to distinguishing healthy, moderately degraded, and severely degraded mangrove areas across heterogeneous coastal environments. Consequently, the proposed framework provides an intelligent and reliable decision support tool for environmental monitoring agencies and policymakers while contributing to the development of resilient coastal ecosystem management and sustainable environmental governance in tropical archipelagic regions.","红树林生态系统在海岸防护、碳固存、生物多样性保护及气候变化减缓中发挥着关键作用；然而，日益加剧的人为压力和环境变化加速了红树林退化，亟需高效且可扩展的监测方法。本研究旨在开发一个人工智能驱动的框架，通过整合遥感影像与环境数据集来监测红树林生态系统状况，以提高热带沿海地区生态系统评估的准确性和时效性。所提出的方法将多光谱卫星影像（包括由遥感数据衍生的植被指数）与温度、降水、盐度和潮汐信息等环境变量相结合，随后使用基于深度学习的分类模型进行处理，以识别和分类红树林健康状况。实验评估表明，与仅依赖卫星影像的方法相比，遥感与环境数据的整合显著提升了模型性能，实现了较高的分类精度，并改善了对生态系统退化早期迹象的检测。研究结果进一步揭示，环境参数对于区分异质性沿海环境中健康、中度退化和严重退化的红树林区域具有重要贡献。因此，所提出的框架为环境监测机构和政策制定者提供了一种智能且可靠的决策支持工具，同时有助于热带群岛地区韧性沿海生态系统管理和可持续环境治理的发展。",null,"AI Innovation and Resilience for the Environment (AIR)","2026-09-22T00:00:00Z","论文",10,false,76,{"impact":17,"substance":18,"depth":19,"authority":20,"freshness":21,"relevant":22,"comment":23},18,21,17,12,8,1,"将遥感与环境数据融合的深度学习框架用于红树林健康监测，方法有创新且结论可靠，对沿海生态治理有参考价值，但属细分领域研究，公共影响有限。",[25],{"name":10,"url":6},[27,28,29,30,31],"农业人工智能","深度学习","遥感监测","生态监测","红树林",[],{"status":34,"locked":14,"version":35,"method":36,"evidence":37},"needs_review","2026-10-22.2","rules",{"candidates":38,"agricultural_evidence":14,"reason":79},[39,49,57,64,72],{"code":40,"score":41,"supported":42,"title":43,"abstract":45,"tags":48},"I2",19,true,[44],"artificial intelligence",[28,46,44,47],"deep learning","decision support",[27,28],{"code":50,"score":17,"supported":42,"title":51,"abstract":53,"tags":56},"I3",[52],"remote sensing",[54,52,55],"遥感","multispectral",[29],{"code":58,"score":21,"supported":42,"title":59,"abstract":60,"tags":63},"H6",[],[61,62],"生物多样性","biodiversity",[30,31],{"code":65,"score":66,"supported":42,"title":67,"abstract":68,"tags":71},"H7",6,[],[69,70],"气候变化","climate change",[],{"code":73,"score":74,"supported":42,"title":75,"abstract":76,"tags":78},"H4",3,[],[77],"carbon sequestration",[],"农业相关性需要复核",[81,82],"红树林 遥感 人工智能","红树林生态系统 监测","红树林遥感人工智能-3479","10.68012\u002Fair.v1i2.252",{"doi":84,"openalex_id":86,"authors":87,"venue":10,"cited_by_count":99,"oa_url":100,"card":101,"direction":107,"ingested_from":108},"W7213895268",[88,91,94,96],{"name":89,"orcid":90},"Dirvi Surya Abbas","https:\u002F\u002Forcid.org\u002F0000-0002-7819-2837",{"name":92,"orcid":93},"Asep Sutarman","https:\u002F\u002Forcid.org\u002F0009-0002-1029-7963",{"name":95,"orcid":9},"Ryan Davis",{"name":97,"orcid":98},"Maulana Abbas","https:\u002F\u002Forcid.org\u002F0009-0009-0137-9650",0,"https:\u002F\u002Fjournal.sundarapublishing.com\u002Findex.php\u002Fair\u002Farticle\u002Fdownload\u002F252\u002F142",{"tldr":102,"method":103,"finding":104,"direction":105,"opportunity":106},"融合遥感影像与环境数据，用深度学习构建红树林生态系统健康监测框架。","多光谱卫星影像与植被指数，结合温度、降水、盐度、潮汐等环境变量，训练深度学习分类","融合环境数据显著提升分类精度，能更早识别红树林退化迹象，有效区分不同退化程度。","农业遥感与作物表型","可探索多源时序遥感与环境数据融合的早期退化预警，并迁移至其他滨海湿地生态系统监测。","智慧农业 \u002F 农业物联网","openalex","2026-09-25T23:30:14.373467Z",{"total":66,"page":22,"page_size":66,"items":111},[112,178,255,317,367,405],{"id":113,"title":114,"url":115,"summary":116,"summary_zh":117,"content":9,"source_name":118,"source_url":115,"published_at":119,"category":12,"cover_url":9,"hotness":13,"is_selected":14,"score":120,"score_detail":121,"sources":124,"tags":126,"primary_topic":128,"secondary_topics":133,"classification":138,"search_phrases":161,"slug":164,"view_count":21,"doi":165,"paper":166,"created_at":177},3618,"Multi-Target Remote Sensing Segmentation with Cross-Scale Attention for Urban-Ecological Intelligence","https:\u002F\u002Fdoi.org\u002F10.56201\u002Fijgem.vol.12.no1.2026.pg131.154","Remote sensing image segmentation is essential to extract valuable information from satellite and aerial images to achieve significant applications such as urban planning and ecological monitoring. Yet, it is hard to accurately segment diverse and complicated features because of the constraints of conventional approaches and the requirement to process variable object sizes and complicated boundaries. This research aims to address the above difficulties through the use and assessment of advanced deep learning models specifically UNet, SegNet, and TransU-Net in multi target semantic segmentation. These networks have been applied in single-object segmentation tasks with a focus on structures and roads, while the UNet architecture was additionally utilized for multi-object segmentation comprising buildings, woods, grasslands, water bodies, and cultivated land. Using appropriate remote sensing datasets, the accuracy of the models was thoroughly evaluated using common evaluation metrics, including pixel accuracy, Intersection over Union (IoU), and F1-score. The experimental outcomes illustrate the capabilities of these deep learning methods to provide accurate identification of essential features. Notably, the maximum attainable accuracy for single-object building segmentation was 96.85%, whereas the overall accuracy for multi-object segmentation with the UNet was 84.2%. The experimental results show these deep learning algorithms can effectively separate different targets from remote sensing imagery, thus making them fundamental tools for geospatial analysis and related fields.","遥感图像分割对于从卫星和航空图像中提取有价值信息，以实现城市规划和生态监测等重要应用至关重要。然而，由于传统方法的局限以及处理可变目标尺寸和复杂边界的需要，准确分割多样且复杂的地物十分困难。本研究旨在通过使用和评估先进的深度学习模型，特别是UNet、SegNet和TransU-Net在多目标语义分割中的应用，来解决上述难题。这些网络已被应用于单目标分割任务，重点关注建筑物和道路，而UNet架构还被额外用于多目标分割，包括建筑物、林地、草地、水体和耕地。利用适当的遥感数据集，通过常用评价指标对模型的精度进行了全面评估，包括像素精度、交并比（IoU）和F1分数。实验结果表明了这些深度学习方法在准确识别关键地物方面的能力。值得注意的是，单目标建筑物分割的最高可达精度为96.85%，而使用UNet进行多目标分割的总体精度为84.2%。实验结果表明，这些深度学习算法能够有效地从遥感图像中分离出不同目标，从而使其成为地理空间分析及相关领域的基础工具。","IIARD INTERNATIONAL JOURNAL OF GEOGRAPHY AND ENVIRONMENTAL MANAGEMENT","2026-09-25T00:00:00Z",63,{"impact":20,"substance":17,"depth":122,"authority":13,"freshness":21,"relevant":22,"comment":123},15,"将UNet、SegNet、TransU-Net用于多目标遥感语义分割，建筑单目标精度96.85%、多目标84.2%，方法常规但结论对农业与生态遥感监测有参考价值。",[125],{"name":118,"url":115},[27,28,127,54,30],"语义分割",{"code":50,"slug":129,"name":130,"path":131,"parent_code":132},"remote-sensing","遥感与农情监测","\u002Ftopic\u002Fdigital-agriculture\u002Fremote-sensing","I",[134],{"code":40,"slug":135,"name":136,"path":137,"parent_code":132},"agricultural-ai","农业AI与大模型","\u002Ftopic\u002Fdigital-agriculture\u002Fagricultural-ai",{"status":139,"locked":14,"version":35,"method":36,"evidence":140},"classified",{"candidates":141,"agricultural_evidence":42},[142,146,151,157],{"code":50,"score":122,"supported":42,"title":143,"abstract":144,"tags":145},[52],[54,52],[54],{"code":40,"score":147,"supported":42,"title":148,"abstract":149,"tags":150},9,[],[28,46],[27,28,127],{"code":152,"score":74,"supported":42,"title":153,"abstract":154,"tags":156},"I4",[],[155],"空间分析",[],{"code":58,"score":22,"supported":14,"title":158,"abstract":159,"tags":160},[],[],[30],[162,163],"UNet 遥感 多目标分割","TransU-Net 城市生态 遥感","UNet遥感多目标分割-3618","10.56201\u002Fijgem.vol.12.no1.2026.pg131.154",{"doi":165,"openalex_id":167,"authors":168,"venue":118,"cited_by_count":99,"oa_url":171,"card":172,"direction":107,"ingested_from":108},"W7214298981",[169],{"name":170,"orcid":9},"Chibueze Favour Aririguzo","https:\u002F\u002Fiiardjournals.org\u002Fget\u002FIJGEM\u002FVOL. 12 NO. 1 2026\u002FMulti-Target Remote Sensing Segmentation 131-154.pdf",{"tldr":173,"method":174,"finding":175,"direction":105,"opportunity":176},"评估UNet、SegNet和TransU-Net在多目标遥感语义分割中的性能，用于城市与生态监测。","使用UNet、SegNet、TransU-Net模型，在遥感数据集上以像素精度、","单目标建筑分割最高精度96.85%，UNet多目标分割总体精度84.2%。","可探索跨尺度注意力机制提升多目标分割精度，并迁移至耕地与作物精细分类。","2026-09-27T23:30:28.366758Z",{"id":179,"title":180,"url":181,"summary":182,"summary_zh":183,"content":9,"source_name":184,"source_url":181,"published_at":185,"category":12,"cover_url":9,"hotness":13,"is_selected":14,"score":186,"score_detail":187,"sources":191,"tags":193,"primary_topic":197,"secondary_topics":201,"classification":202,"search_phrases":238,"slug":241,"view_count":99,"doi":242,"paper":243,"created_at":254},5563,"AI-Powered Early Detection of Crop Diseases and Pest Infestations: A New Paradigm for Plantation Risk Management","https:\u002F\u002Fdoi.org\u002F10.5281\u002Fzenodo.23531525","Abstract: Crop diseases and pest infestations remain persistent threats to plantation productivity, with pests estimated to destroy up to 40% of global crop production and plant diseases and invasive insects imposing substantial economic losses worldwide (Food and Agriculture Organization of the United Nations [FAO], 2019). Climate change is intensifying these risks by altering the geographic range, seasonality, and population dynamics of pathogens and pests (Gullino et al., 2021; Skendžić et al., 2021). This paper examines how artificial intelligence (AI) — including convolutional neural networks (CNNs), vision transformers (ViTs), unmanned aerial vehicle (UAV)-based multispectral and hyperspectral sensing, and Internet of Things (IoT)-enabled monitoring — can strengthen the early detection of biotic stress in plantation crops and thereby support plantation risk management. Drawing on recent peer-reviewed and industry literature, the paper synthesises evidence on detection performance, deployment modalities, and pathways for integration into enterprise risk-management systems. It proposes a conceptual framework in which AI-enabled early-warning systems operate as a continuous, spatially explicit risk-sensing layer linking agronomic observations with operational, financial, and insurance decision-making. AI can improve the timeliness, spatial precision, and consistency of surveillance; however, its risk-management value depends on field validation, representative training data, reliable infrastructure, affordable deployment, and appropriate governance. AI should therefore currently be positioned as decision support that augments, rather than replaces, agronomic expertise and ground-truthing. Keywords: artificial intelligence; plant disease detection; pest infestation; precision agriculture; plantation risk management; machine learning; remote sensing. Title: AI-Powered Early Detection of Crop Diseases and Pest Infestations: A New Paradigm for Plantation Risk Management Author: Dr. Geetha Govindan K Gopalakrishnan International Journal of Management and Commerce Innovations ISSN 2348-7585 (Online) Vol. 14, Issue 2, October 2026 - March 2027 Page No: 54-59 Research Publish Journals Website: www.researchpublish.com Published Date: 21-October-2026 DOI: https:\u002F\u002Fdoi.org\u002F10.5281\u002Fzenodo.23531526 Paper Download Link (Source) https:\u002F\u002Fwww.researchpublish.com\u002Fpapers\u002Fai-powered-early-detection-of-crop-diseases-and-pest-infestations-a-new-paradigm-for-plantation-risk-management","摘要：作物病害与虫害侵染始终是种植园生产力的持续威胁，据估计，害虫每年可摧毁全球高达40%的作物产量，植物病害与入侵昆虫在全球范围内造成重大经济损失（联合国粮食及农业组织[FAO]，2019）。气候变化通过改变病原体与害虫的地理分布范围、季节性规律及种群动态，正在加剧这些风险（Gullino等，2021；Skendžić等，2021）。本文探讨人工智能（AI）——包括卷积神经网络（CNN）、视觉变换器（ViT）、基于无人机（UAV）的多光谱与高光谱遥感，以及物联网（IoT）赋能的监测技术——如何强化种植园作物生物胁迫的早期检测，从而支撑种植园风险管理。本文基于近期同行评审文献与行业文献，综合梳理了检测性能、部署模式及其融入企业风险管理系统的路径等方面的证据。文章提出一个概念框架，其中AI赋能的预警系统作为持续运行、空间显性的风险感知层，将农艺观测与运营、财务及保险决策相衔接。AI能够提升监测的及时性、空间精度与一致性；然而，其风险管理价值取决于田间验证、具有代表性的训练数据、可靠的基础设施、可负担的部署成本以及适当的治理。因此，当前应将AI定位为决策支持工具，用以增强而非替代农艺专业知识与实地核验。关键词：人工智能；植物病害检测；虫害侵染；精准农业；种植园风险管理；机器学习；遥感。题目：AI驱动的作物病害与虫害侵染早期检测：种植园风险管理的新范式。作者：Geetha Govindan K Gopalakrishnan博士。《国际管理与商业创新期刊》ISSN 2348-7585（在线）第14卷第2期，2026年10月—2027年3月，第54-59页。研究出版期刊网站：www.researchpublish.com。发布日期：2026年10月21日。DOI：https:\u002F\u002Fdoi.org\u002F10.5281\u002Fzenodo.23531526。论文下载链接（来源）：https:\u002F\u002Fwww.researchpublish.com\u002Fpapers\u002Fai-powered-early-detection-of-crop-diseases-and-pest-infestations-a-new-paradigm-for-plantation-risk-ma","Zenodo (CERN European Organization for Nuclear Research)","2026-10-21T00:00:00Z",56,{"impact":20,"substance":188,"depth":189,"authority":66,"freshness":147,"relevant":22,"comment":190},16,13,"综述性论文，系统梳理AI与遥感在作物病虫害早期预警中的应用并提出风险管理框架，有参考价值但方法创新与数据规模有限，信源为普通出版平台。",[192],{"name":184,"url":181},[194,27,29,195,196],"智慧农业","风险管理","病虫害监测",{"code":132,"slug":198,"name":199,"path":200,"parent_code":9},"digital-agriculture","数字农业与前沿技术","\u002Ftopic\u002Fdigital-agriculture",[],{"status":203,"locked":14,"version":35,"method":36,"evidence":204},"partial",{"candidates":205,"agricultural_evidence":42,"reason":237},[206,212,217,225,233],{"code":40,"score":13,"supported":42,"title":207,"abstract":208,"tags":211},[],[209,210,44,47],"机器学习","machine learning",[27],{"code":50,"score":13,"supported":42,"title":213,"abstract":214,"tags":216},[],[54,52,55,215],"hyperspectral",[29],{"code":218,"score":147,"supported":42,"title":219,"abstract":220,"tags":224},"I5",[],[221,222,223],"物联网","internet of things","IoT",[],{"code":226,"score":227,"supported":42,"title":228,"abstract":229,"tags":232},"I1",7,[],[230,231],"精准农业","precision agriculture",[194],{"code":65,"score":66,"supported":42,"title":234,"abstract":235,"tags":236},[],[69,70],[],"一级领域明确，二级方向需要细分",[239,240],"AI 作物病害 早期检测","无人机 多光谱 病虫害监测","AI作物病害早期检测-5563","10.5281\u002Fzenodo.23531525",{"doi":242,"openalex_id":244,"authors":245,"venue":184,"cited_by_count":99,"oa_url":181,"card":248,"direction":107,"ingested_from":108},"W7223085400",[246],{"name":247,"orcid":9},"Dr. Geetha Govindan K Gopalakrishnan",{"tldr":249,"method":250,"finding":251,"direction":252,"opportunity":253},"综述AI（CNN、ViT、无人机遥感、物联网）用于作物病虫害早期检测并融入种植园风险管理。","文献综述，整合CNN、ViT、无人机多\u002F高光谱与IoT监测的检测性能与部署方式。","AI可提升监测及时性与空间精度，但价值取决于田间验证、代表性数据与治理，应作决策支持而非替代专家。","农业人工智能与决策模型","可将AI预警层与保险、金融风控系统对接，研究跨域数据融合与可解释风险定价的空白。","2026-10-22T11:20:24.428080Z",{"id":256,"title":257,"url":258,"summary":259,"summary_zh":260,"content":9,"source_name":261,"source_url":258,"published_at":262,"category":12,"cover_url":9,"hotness":13,"is_selected":14,"score":263,"score_detail":264,"sources":266,"tags":268,"primary_topic":271,"secondary_topics":277,"classification":279,"search_phrases":297,"slug":300,"view_count":99,"doi":301,"paper":302,"created_at":316},5387,"LIGHTWEIGHT FEATURE FUSED ATTENTION DRIVEN MULTI LEVEL HYBRID MOBILENET V2 FRAMEWORK FOR EARLY TOMATO LEAF DISEASE DETECTION","https:\u002F\u002Fdoi.org\u002F10.62441\u002Factainnovations.vi.1918","It is crucial to find and treat tomato crop diseases early and accurately to improve crop efficiency and make sure there is no scarcity of crop. However, computerized analysis is provocative due to lighting differences, compound backgrounds, and graphic likenesses among infection regions. Research work proposed a lightweight Attention Driven Multi Level Hybrid MobileNet-V2 algorithm that fuses the handcrafted texture structures with Deep Learning (DL) features, then image preprocessing is incorporated using Gaussian, Bilateral, and Guided filters to minimize noise by preserving the disease lesions. LAB color model along with Contrast Limited Adaptive Histogram Equalization (CLAHE) are used to improve the contrast. Otsu thresholding is involved to effectively separate the leaf segment from diseased parts. Local Binary Pattern (LBP) and Gray Level Co-occurrence Matrix (GLCM) descriptors are used to obtain fine-grained features, while high level features are gained by pretrained MobileNet-V2 model. Features fusion is fed to the fully connected layers of deep learning model for training and validation purpose. Results have revealed that the suggested model attains better classification performance as compared to existing models, making it an effective explanation for real time tomato leaf disease detection for smart agriculture applications.","早期准确发现并治疗番茄作物病害，对于提高作物效率、确保作物不短缺至关重要。然而，由于光照差异、复杂背景以及感染区域之间的图形相似性，计算机化分析具有挑战性。研究提出了一种轻量级注意力驱动多层混合MobileNet-V2算法，该算法将手工纹理结构与深度学习（DL）特征相融合，然后结合高斯、双边和引导滤波器进行图像预处理，以在保留病害病变的同时最小化噪声。采用LAB颜色模型和对比度受限自适应直方图均衡化（CLAHE）来提高对比度。引入Otsu阈值分割以有效分离叶片片段与病害部分。使用局部二值模式（LBP）和灰度共生矩阵（GLCM）描述符获取细粒度特征，同时通过预训练的MobileNet-V2模型获取高层特征。特征融合后输入深度学习模型的全连接层进行训练和验证。结果表明，与现有模型相比，所提出的模型取得了更好的分类性能，使其成为智慧农业应用中实时番茄叶片病害检测的有效解决方案。","Acta Innovations","2026-10-18T00:00:00Z",64,{"impact":20,"substance":17,"depth":188,"authority":13,"freshness":21,"relevant":22,"comment":265},"提出融合手工纹理特征与MobileNet-V2的轻量番茄叶病检测方法，有一定方法新颖性，但属单篇论文、应用范围有限，未达每日精选门槛。",[267],{"name":261,"url":258},[194,27,28,269,270],"番茄病害","图像识别",{"code":272,"slug":273,"name":274,"path":275,"parent_code":276},"B1","vegetables","蔬菜","\u002Ftopic\u002Fhorticulture\u002Fvegetables","B",[278],{"code":40,"slug":135,"name":136,"path":137,"parent_code":132},{"status":139,"locked":14,"version":35,"method":36,"evidence":280},{"candidates":281,"agricultural_evidence":42},[282,288,292],{"code":272,"score":122,"supported":42,"title":283,"abstract":285,"tags":287},[284],"tomato",[286,284],"番茄",[269],{"code":40,"score":147,"supported":42,"title":289,"abstract":290,"tags":291},[],[28,46],[27,270,28],{"code":226,"score":227,"supported":42,"title":293,"abstract":294,"tags":296},[],[194,295],"smart agriculture",[194],[298,299],"MobileNet-V2 番茄叶片病害","番茄叶病 深度学习 检测","MobileNet-V2番茄叶片病害-5387","10.62441\u002Factainnovations.vi.1918",{"doi":301,"openalex_id":303,"authors":304,"venue":261,"cited_by_count":99,"oa_url":310,"card":311,"direction":107,"ingested_from":108},"W7222977034",[305,307],{"name":306,"orcid":9},"Mrs. Vijetalaxmi A Hegde",{"name":308,"orcid":309},"Abhay Ramakant Kasetwar","https:\u002F\u002Forcid.org\u002F0000-0002-5800-8764","https:\u002F\u002Factainnovations.com\u002Findex.php\u002Fpub\u002Farticle\u002Fdownload\u002F1918\u002F981",{"tldr":312,"method":313,"finding":314,"direction":252,"opportunity":315},"提出轻量注意力多级混合MobileNet-V2框架，融合手工纹理与深度学习特征实现番茄叶片病害早期检","高斯\u002F双边\u002F引导滤波去噪，LAB+CLAHE增强，Otsu分割，LBP与GLCM","所提模型分类性能优于现有模型，可有效用于智慧农业实时番茄叶片病害检测。","可探索多作物跨域泛化、田间复杂光照下轻量模型部署与可解释性，及病害早期分级检测。","2026-10-20T23:30:10.424511Z",{"id":318,"title":319,"url":320,"summary":321,"summary_zh":322,"content":9,"source_name":323,"source_url":320,"published_at":262,"category":12,"cover_url":9,"hotness":13,"is_selected":14,"score":186,"score_detail":324,"sources":326,"tags":328,"primary_topic":331,"secondary_topics":332,"classification":333,"search_phrases":353,"slug":356,"view_count":99,"doi":357,"paper":358,"created_at":366},5385,"A Comprehensive Review of Deep Learning and Computer Vision Techniques for Fruit Quality Assessment and Classification","https:\u002F\u002Fdoi.org\u002F10.25258\u002Fijddt.16.75s.151","Fruit image analysis has become an essential research area in precision agriculture, enabling automated fruit classification, quality grading, maturity estimation, disease diagnosis, yield prediction, and intelligent harvesting through advances in computer vision and artificial intelligence (AI).Recent progress in imaging technologies, large-scale benchmark datasets, and deep learning has substantially improved the accuracy, robustness, and scalability of automated fruit analysis systems.This survey presents a comprehensive and systematic review of image processing and AI techniques for fruit image analysis.It covers the complete image analysis pipeline, including image acquisition, preprocessing, enhancement, color space transformation, segmentation, feature extraction, and handcrafted texture descriptors.Furthermore, conventional machine learning algorithms are reviewed alongside state-of-the-art deep learning architectures, including Convolutional Neural Networks (CNNs), Vision Transformers (ViTs), and Vision Mamba models, for applications such as fruit recognition, quality assessment, disease detection, ripeness estimation, and object detection.Publicly available benchmark datasets, evaluation metrics, and performance comparison strategies are also summarized to facilitate objective assessment of existing approaches.In addition, the survey discusses key research challenges, including illumination variations, occlusion, complex orchard environments, limited annotated datasets, computational complexity, and domain adaptation, while highlighting emerging research trends such as self-supervised learning, multimodal learning, explainable AI, lightweight deep networks, foundation models, and edge intelligence for real-time deployment.By providing a unified review of methodologies, datasets, evaluation protocols, challenges, and future research directions, this survey offers a comprehensive reference for researchers and practitioners developing intelligent and scalable fruit image analysis systems for precision agriculture.","水果图像分析已成为精准农业中的一个重要研究领域，借助计算机视觉和人工智能（AI）的进步，实现了果实自动分类、品质分级、成熟度估计、病害诊断、产量预测和智能采收。成像技术、大规模基准数据集和深度学习的最新进展显著提升了自动化水果分析系统的准确性、鲁棒性和可扩展性。本综述对用于水果图像分析的图像处理和AI技术进行了全面而系统的回顾。内容涵盖完整的图像分析流程，包括图像采集、预处理、增强、颜色空间变换、分割、特征提取和手工纹理描述符。此外，综述了传统机器学习算法以及最先进的深度学习架构，包括卷积神经网络（CNN）、视觉Transformer（ViT）和视觉Mamba模型，用于果实识别、品质评估、病害检测、成熟度估计和目标检测等应用。同时总结了公开可用的基准数据集、评价指标和性能比较策略，以便对现有方法进行客观评估。此外，本综述讨论了关键研究挑战，包括光照变化、遮挡、复杂果园环境、标注数据集有限、计算复杂度和域适应，并重点介绍了新兴研究趋势，如自监督学习、多模态学习、可解释AI、轻量级深度网络、基础模型和面向实时部署的边缘智能。通过提供方法、数据集、评价协议、挑战和未来研究方向的统一综述，本综述为开发面向精准农业的智能且可扩展的水果图像分析系统的研究人员和实践者提供了全面的参考。","International Journal of Drug Delivery Technology",{"impact":21,"substance":17,"depth":188,"authority":66,"freshness":21,"relevant":22,"comment":325},"系统性综述覆盖CNN、ViT、Vision Mamba等前沿方法，信息量足，但期刊权威性一般且偏学术综述，公共价值有限，适合主题聚合而非每日精选头条。",[327],{"name":323,"url":320},[194,27,329,28,330],"计算机视觉","水果品质检测",{"code":40,"slug":135,"name":136,"path":137,"parent_code":132},[],{"status":139,"locked":14,"version":35,"method":36,"evidence":334},{"candidates":335,"agricultural_evidence":42},[336,343,347],{"code":40,"score":337,"supported":42,"title":338,"abstract":340,"tags":342},28,[46,339],"computer vision",[341,28,209,329,210,46,44,339],"目标检测",[27,28,329],{"code":226,"score":227,"supported":42,"title":344,"abstract":345,"tags":346},[],[230,231],[194],{"code":348,"score":74,"supported":42,"title":349,"abstract":350,"tags":352},"B2",[],[351],"orchard",[],[354,355],"水果品质 计算机视觉 深度学习","农业人工智能 水果品质检测 计算机视觉 智慧农业","水果品质计算机视觉深度学习-5385","10.25258\u002Fijddt.16.75s.151",{"doi":357,"openalex_id":359,"authors":360,"venue":323,"cited_by_count":99,"oa_url":320,"card":361,"direction":107,"ingested_from":108},"W7222892831",[],{"tldr":362,"method":363,"finding":364,"direction":105,"opportunity":365},"系统综述深度学习与计算机视觉在水果品质评估与分级中的全流程方法。","综述图像采集到分割、特征提取及CNN、ViT、Vision Mamba等模型与公","深度学习显著提升水果分析精度与鲁棒性，但光照、遮挡和小样本仍是主要瓶颈。","可探索自监督与轻量化模型在复杂果园遮挡、小样本场景下的边缘实时部署。","2026-10-20T23:30:10.066042Z",{"id":368,"title":369,"url":370,"summary":371,"summary_zh":372,"content":9,"source_name":323,"source_url":370,"published_at":373,"category":12,"cover_url":9,"hotness":13,"is_selected":14,"score":99,"score_detail":374,"sources":376,"tags":378,"primary_topic":9,"secondary_topics":379,"classification":380,"search_phrases":387,"slug":390,"view_count":99,"doi":391,"paper":392,"created_at":404},5242,"Enhanced Convolutional Neural Network Architecture with Attention-Guided Feature Refinement for Robust Image Classification","https:\u002F\u002Fdoi.org\u002F10.25258\u002Fijddt.16.88s.43","Image classification remains a foundational problem in computer vision, underpinning applications that range from medical diagnostics to autonomous navigation. Although deep convolutional neural networks (CNNs) have substantially advanced classification accuracy over the last decade, standard architectures such as VGG, ResNet, and plain CNNs often struggle to jointly optimize accuracy, parameter efficiency, and robustness to intra-class variation. This paper proposes an AttentionGuided Refinement Network (AGR-Net), a CNN architecture that integrates a lightweight channel-and-spatial attention module with residual feature refinement blocks to improve discriminative feature learning while maintaining a compact parameter footprint. The proposed model is evaluated on the CIFAR-10 benchmark dataset using a rigorous experimental protocol that includes data augmentation, learning-rate scheduling, and five-fold cross-validation. Comparative experiments against baseline architectures, including a plain CNN, VGG-16, ResNet-18, and MobileNetV2, demonstrate that AGR-Net achieves a top-1 accuracy of 94.6%, outperforming the strongest baseline by 1.8 percentage points while using 27% fewer parameters than ResNet-18. Ablation studies confirm that the attention module and refinement blocks each contribute measurably to the accuracy gain. The results indicate that attention-guided refinement offers a favorable trade-off between accuracy, efficiency, and robustness, making the proposed architecture suitable for deployment in resource-constrained and real-time image classification systems. The paper further discusses the advantages, practical applications, limitations, and future research directions of the proposed approach.","图像分类仍然是计算机视觉中的一个基础性问题，支撑着从医学诊断到自主导航等诸多应用。尽管深度卷积神经网络（CNN）在过去十年中大幅提升了分类准确率，但VGG、ResNet和普通CNN等标准架构往往难以在准确率、参数效率和对类内变化的鲁棒性之间实现联合优化。本文提出了一种注意力引导细化网络（AttentionGuided Refinement Network，AGR-Net），这是一种CNN架构，它将轻量级的通道与空间注意力模块与残差特征细化模块相结合，以改进判别性特征学习，同时保持紧凑的参数规模。所提出的模型在CIFAR-10基准数据集上使用严格的实验方案进行评估，该方案包括数据增强、学习率调度和五折交叉验证。与基线架构（包括普通CNN、VGG-16、ResNet-18和MobileNetV2）的对比实验表明，AGR-Net实现了94.6%的top-1准确率，比最强基线高出1.8个百分点，同时使用的参数比ResNet-18少27%。消融研究证实，注意力模块和细化模块各自对准确率提升都有可测量的贡献。结果表明，注意力引导细化在准确率、效率和鲁棒性之间提供了有利的权衡，使所提出的架构适合部署在资源受限和实时的图像分类系统中。本文进一步讨论了所提出方法的优势、实际应用、局限性和未来研究方向。","2026-10-17T00:00:00Z",{"impact":99,"substance":99,"depth":99,"authority":99,"freshness":99,"relevant":99,"comment":375},"该文为通用计算机视觉论文，未涉及农业场景，与三农及农业信息化无关，不宜入选。",[377],{"name":323,"url":370},[27,28,270],[],{"status":34,"locked":14,"version":35,"method":36,"evidence":381},{"candidates":382,"agricultural_evidence":14,"reason":79},[383],{"code":40,"score":147,"supported":42,"title":384,"abstract":385,"tags":386},[],[329,339],[27,270,28],[388,389],"农业人工智能 图像识别 深度学习","农业人工智能 图像识别","农业人工智能图像识别深度学习-5242","10.25258\u002Fijddt.16.88s.43",{"doi":391,"openalex_id":393,"authors":394,"venue":323,"cited_by_count":99,"oa_url":370,"card":399,"direction":107,"ingested_from":108},"W7222796569",[395,397],{"name":396,"orcid":9},"KRISHNA SANDEEP JONNALA",{"name":398,"orcid":9},"K VENKAT RAJU",{"tldr":400,"method":401,"finding":402,"direction":252,"opportunity":403},"提出注意力引导细化网络AGR-Net，在CIFAR-10上兼顾精度与参数效率。","轻量通道-空间注意力模块+残差特征细化块，五折交叉验证对比基线。","AGR-Net达94.6%准确率，超最强基线1.8个百分点且参数比ResNet-18少27%。","可将该轻量注意力架构迁移至作物病害识别等农业图像任务，验证田间复杂场景鲁棒性。","2026-10-18T23:30:13.674128Z",{"id":406,"title":407,"url":408,"summary":409,"summary_zh":410,"content":9,"source_name":411,"source_url":408,"published_at":373,"category":12,"cover_url":9,"hotness":13,"is_selected":14,"score":412,"score_detail":413,"sources":416,"tags":418,"primary_topic":421,"secondary_topics":427,"classification":428,"search_phrases":445,"slug":448,"view_count":22,"doi":449,"paper":450,"created_at":464},5234,"A smart agriculture-oriented cross-attention multiscale CNN for sugarcane disease diagnosis","https:\u002F\u002Fdoi.org\u002F10.1080\u002F23080477.2026.2749739","Sugarcane leaf diseases can adversely affect crop health and yield, making timely disease identification important for smart agriculture. Manual inspection of leaf diseases is time-consuming and requires expert knowledge, particularly when large cultivation areas need to be monitored. To tackle this problem, this study proposes a Cross-Attention Multiscale Parallel Convolutional Neural Network for automatic classification of sugarcane leaf diseases. This framework comprises a Parallel Feature Extraction Stem, cross-attention mechanism, Dense Connection Blocks, and Inception Blocks to learn disease features at various spatial scales. The PFES extracts fine and broad disease patterns using parallel convolutional branches, while the cross-attention mechanism refines the extracted features by emphasizing disease-related information. The DCB supports feature propagation and reuse, and the IB further captures multi-scale feature representations. The proposed model was tested on two benchmark datasets of leaf diseases for sugarcane plants. The proposed framework obtained an accuracy (98.79%), precision (98.31%), recall (97.81%), specificity (98.60%), and F1-Score (98.05%). For assessing the classification accuracy and consistency of the framework, the comparative study, ablation studies, and five-fold cross-validation are carried out. The results show that CA-MPCNN provides accurate sugarcane leaf disease classification and can support automated disease diagnosis in smart agriculture applications.","甘蔗叶片病害会对作物健康与产量造成不利影响，因此及时识别病害对智慧农业具有重要意义。人工检查叶片病害耗时且需要专业知识，尤其是在需要监测大面积种植区域时。为解决该问题，本研究提出一种用于甘蔗叶片病害自动分类的交叉注意力多尺度并行卷积神经网络（Cross-Attention Multiscale Parallel Convolutional Neural Network）。该框架由并行特征提取主干（Parallel Feature Extraction Stem）、交叉注意力机制、密集连接块（Dense Connection Blocks）和Inception块组成，用于学习不同空间尺度上的病害特征。PFES通过并行卷积分支提取细粒度与广域病害模式，而交叉注意力机制通过强调病害相关信息对提取的特征进行细化。DCB支持特征传播与复用，IB进一步捕获多尺度特征表示。所提出的模型在两个甘蔗植株叶片病害基准数据集上进行了测试。该框架取得了准确率（98.79%）、精确率（98.31%）、召回率（97.81%）、特异性（98.60%）和F1分数（98.05%）。为评估该框架的分类准确性和一致性，开展了对比研究、消融研究和五折交叉验证。结果表明，CA-MPCNN能够实现准确的甘蔗叶片病害分类，并可支持智慧农业应用中的自动化病害诊断。","Smart Science",69,{"impact":20,"substance":414,"depth":188,"authority":20,"freshness":147,"relevant":22,"comment":415},20,"该研究提出一种面向甘蔗叶部病害自动分类的交叉注意力多尺度CNN，在两个基准数据集上准确率达98.79%，方法新颖、实验充分，但属于细分作物应用研究，产业影响有限，时效性强，值得进入每日精选。",[417],{"name":411,"url":408},[194,27,419,28,420],"甘蔗","病害诊断",{"code":422,"slug":423,"name":424,"path":425,"parent_code":426},"A6","cash-crops","棉麻糖与特色经作","\u002Ftopic\u002Ffield-crops\u002Fcash-crops","A",[],{"status":139,"locked":14,"version":35,"method":36,"evidence":429},{"candidates":430,"agricultural_evidence":42},[431,436,440],{"code":422,"score":122,"supported":42,"title":432,"abstract":434,"tags":435},[433],"sugarcane",[419,433],[419],{"code":226,"score":122,"supported":42,"title":437,"abstract":438,"tags":439},[295],[194,295],[194],{"code":40,"score":441,"supported":14,"title":442,"abstract":443,"tags":444},2,[],[],[27,28],[446,447],"甘蔗 叶部病害 智能诊断","CA-MPCNN 甘蔗 病害","甘蔗叶部病害智能诊断-5234","10.1080\u002F23080477.2026.2749739",{"doi":449,"openalex_id":451,"authors":452,"venue":411,"cited_by_count":99,"oa_url":9,"card":459,"direction":107,"ingested_from":108},"W7222832245",[453,455,457],{"name":454,"orcid":9},"Bala Subramanian Chokkalingam",{"name":456,"orcid":9},"Uvarani Meenrajan",{"name":458,"orcid":9},"Shanmugapriya Sankaran",{"tldr":460,"method":461,"finding":462,"direction":252,"opportunity":463},"提出交叉注意力多尺度并行CNN，实现甘蔗叶病自动分类。","并行卷积分支、交叉注意力、密集连接与Inception块，两个基准数据集验证。","模型准确率达98.79%，消融与五折交叉验证证明其有效稳定。","可探索田间复杂背景与轻量化部署，并扩展到多作物病害实时诊断。","2026-10-18T23:30:07.777036Z"]