YOLO-Based Leaf Disease Detection in Smart Agriculture: Evolution, Task Adaptation, and Deployment Challenges
综述了基于YOLO的叶片病害检测的演进、任务适配与部署挑战。
← 主题
#计算机视觉
An empirical performance comparison of deep learning models for apple leaf disease recognition
用UNet++分割苹果病叶并融合多种CNN与ViT分类，实现98.85%识别准确率。
Deep learning–based computer vision for rapid and accurate quantitative field assessment of powdery mildew severity: model comparison, validation, and agreement with human raters
开发并验证基于深度学习的计算机视觉流程，用手机图像快速定量评估豌豆白粉病严重度。
多尺度异构特征协同的棉花叶片病害检测模型(Multi-Scale Heterogeneous Synergistic Model for Cotton Leaf Disease Detection)
提出MHSF-DETR棉花叶片病害检测模型，提升精度并降低参数量与计算量。
Phage phenotyping by measuring plaque expansion dynamics
用平板扫描仪连续追踪噬菌体噬菌斑扩展，建立定量表型新方法。
SMART GREENHOUSE MEASUREMENT AND MONITORING SYSTEM BASED ON IOT AND COMPUTER VISION
集成物联网与计算机视觉的智能温室系统，实现非破坏性植物生长监测与远程管控。
Identifikasi Citra Digital dalam Kesalahan Gerakan Push-Up pada Pemula Menggunakan Metode Pose Estimation
用MediaPipe姿态估计与规则专家系统实时检测初学者俯卧撑动作错误。
Knowledge Distillation for Hybrid CNN–Vision Transformer Architectures: A Systematic Review
系统综述2015-2026年混合CNN-ViT架构的知识蒸馏方法，按迁移方向、知识类型和应用领域分类
ODOMETRY AND VISUAL DATA ANALYSIS INTEGRATIONFOR MONITORING MOBILE MULTICORE COMPUTER SYSTEMS IN GPS-DENIED ENVIRONMENTS
集成里程计与视觉数据，实现无GPS环境下无人机自主导航与基础设施监测。
Animal welfare in the world of digitalization: Computer Vision in the context of foundational structures
论文论证计算机视觉用于动物福利时，伦理问题须置于社会基础结构中理解。
Effects of different nesting materials on crushing risk and sow posture changes in a farrowing system with temporary confinement
比较三种垫料对母猪压仔风险和姿势变化的影响
A Survey of Computer Vision Applications in Industrial Environments
系统综述工业环境中计算机视觉在检测、安全、物流与机器人四领域的应用现状与挑战。
Zenodo (CERN European Organization for Nuclear Research)·10月5日 · 周一60 分 论文农业AI与大模型智慧农业 / 农业物联网2 个信源同时报道 阅读 2
Deep Learning for Early Disease Identification in Leaves: A Pathway to Sustainable Mango Production
综述深度学习与计算机视觉在芒果叶片病害早期识别中的应用，梳理三代技术并展望可持续种植。
Automated dairy cattle lameness assessment using a 38-keypoint whole-body YOLOv8 pose framework
构建38关键点全身YOLOv8姿态框架，实现奶牛跛行自动评估并与Sprecher评分比对。
Zenodo (CERN European Organization for Nuclear Research)·10月3日 · 周六58 分 论文农业AI与大模型农业遥感与作物表型2 个信源同时报道 阅读 4
A Comprehensive Review Of Image Processing Techniques: Classical Methods, Deep Learning, Applications, And Recent Advances
综述图像处理从经典方法到深度学习的技术演进、应用与挑战。
Completeness-aware underwater weight estimation of free-swimming sturgeon using binocular 3D reconstruction
提出完整性感知的双目3D重建方法，实现自由游动鲟鱼的水下体重估计。
WeedNet: a foundation model-based global-to-local AI approach for weed species identification and classification
提出WeedNet基础模型，实现全球杂草物种识别与区域微调。
Addressing scale Variation and texture confusion in strawberry phenology detection via a lightweight synergistic network
提出轻量协同网络，解决草莓物候检测中的尺度变化与纹理混淆问题。
Geometric representation-based facial keypoint matching for sheep identification across growth stages
提出基于面部关键点几何表示的绵羊识别方法，可跨生长阶段匹配。
International Journal of Emerging Technologies and Innovative Research·9月30日 · 周三56 分 论文薯类与杂粮农业人工智能与决策模型4 个信源同时报道 阅读 3
An Integrated Computer Vision and Machine Learning Framework for Sorghum Disease Severity Assessment and Yield Prediction
融合计算机视觉与机器学习，实现高粱病害严重度评估与产量预测。