Robust and transparent crop-row detection from RGB field imagery for vision-based agricultural guidance systems
Robust and transparent crop-row detection from RGB field imagery for vision-based agricultural guidance systems。Precision Agriculture
智慧农业总论
智慧农业总体路径、模式与数字化转型
技术筛选 · 已选 1 项
21 篇内容清除全部筛选
Automation, Robotics, and Precision Agriculture Transformation Through Smart Harvest Systems
Automation, Robotics, and Precision Agriculture Transformation Through Smart Harvest Systems。OpenAlex
PLANT-GPK v2.7: Spatial Heterogeneity and Predictive Digital Twin for Plant Phenotyping
将植物图像分3x3网格反演ODE参数，构建空间生理热图与预测数字孪生。
Scientific Messenger of LNU of Veterinary Medicine and Biotechnologies·10月15日 · 周四63 分 论文智慧农业总论数字乡村与农业信息化阅读 1
Assessment of the efficiency of resource potential utilization in the agricultural sector of the economy under investment and innovation development
评估乌克兰波尔塔瓦地区农业企业资源潜力利用效率并提出改进措施。
Entomopathogenic nematode recent applications in precision agriculture: Methods, challenges, and future perspectives
Entomopathogenic nematode recent applications in precision agriculture: Methods, challenges, and future perspectives。Journal of Invertebrate Pathology
Impact of Digital Technologies on Quality Learning Engagement in Agricultural Science Among Students in Secondary Schools in Rivers State
研究数字技术对尼日利亚河流州中学农业科学学习投入的影响。
3D modeling for crop applications in precision agriculture: a review
3D modeling for crop applications in precision agriculture: a review。Precision Agriculture
A Gateway-Based Approach for Integrating Digital Compass Data into Controller Area Network (CAN) in Precision Farming Systems
设计微控制器网关，将数字罗盘NMEA数据转换为CAN总线消息，用于精准农业自主平台。
[预印本]植物病害数据集的数据中心综述:分类、关键分析、环境变异性与精准农业启示(A Data-Centric Review of Plant Disease Datasets: Taxonomy, Critical Analysis, Environmental Variability, and Implications for Precision Agriculture)
综述植物病害数据集分类与不平衡问题，提出融合环境参数的方向。
A data-centric multi-modal ai framework for weed detection and classification in smart agriculture
A data-centric multi-modal ai framework for weed detection and classification in smart agriculture。Discover Applied Sciences
A multiplexed wearable microfluidic platform for non-invasive sweat-inspired monitoring of plant guttation biomarkers
开发可穿戴微流控电化学平台PlantIonics，实时无创监测植物吐水液生物标志物。
China’s changing diets improve human health but increase environmental pressures
分析1990-2021年中国城乡膳食转型对健康与环境的权衡，并模拟优化路径。
Factors influencing digital technology investments on French farms
Factors influencing digital technology investments on French farms。Precision Agriculture
A comprehensive survey on machine vision applications in precision agriculture: current trends and future perspectives
综述机器视觉在精准农业中的应用现状与未来趋势。
Plant Wearable Sensors: A Comparative Review of Invasive and Non-Invasive Approaches for Real-Time Plant Health Monitoring
综述植物可穿戴传感器，按侵入性分类比较，提出选择框架。
Advances in electrochemical sensors for smart farming and precision agriculture: a focus on phytohormone quantification
Advances in electrochemical sensors for smart farming and precision agriculture: a focus on phytohormone quantification。Analytical and Bioanalytical Chemistry
Applying task division techniques on wireless multimedia sensor networks to improve lifetime
提出两种任务分配技术，利用时空冗余优化无线多媒体传感器网络，提升能效和寿命。
Reinforcement Learning加Visual SLAM融合高光谱成像实现精准农业UAV作物水分胁迫自动检测:92%检测率vs固定路径61%,飞行时间减32%
Arsalan Iqbal在《engrXiv》预印本平台发布研究,提出一种基于强化学习引导的自主四旋翼无人机平台,融合机载视觉同步定位与建图(Visual SLAM)与推扫式高光谱成像载荷,在近实时构建地理参考的、冠层配准的作物水分胁迫指数(CWSI)地图。平台采用近端策略优化(PPO)训练的自适应采样策略,根据飞行中积累的证据将飞行时间和传感器驻留时间重新分配到新兴水分胁迫区域。在0.8公顷试验田模拟田间试验中,强化学习引导策略实现了92%的水分胁迫区域检测率(固定网格基线为61%),同时任务飞行时间减少约32%。研究还报告了SLAM衍生的冠层结构对CWSI精度的贡献消融研究、田间复杂性敏感性和全误差预算分析。注:本研究为预印本,未经实地验证。
AgriAgent: A Heterogeneous Multi-Agent Orchestration Framework for Autonomous, Knowledge-Grounded Precision Agriculture
面向精准农业受限于多模遥测难以实时自治的认知瓶颈,提出 AgriAgent 分层多智能体(MAS)框架,将大语言模型从被动分析工具重塑为目标导向的协调器,采用包含感知、认知、执行三层的三层编排(TLO)拓扑。构建基于 APSIM 生物物理模型并经 GAN 扩展的高保真 10,000 状态合成库,引入黑天鹅环境胁迫。基准测试显示推理成功率 98.2%,决策时延降低 97%,将传统人在回路模式转为智能体驱动,为生物-数字自治农场提供蓝图。
A TinyMLOps Pipeline for Coarse-Grained Plant Disease Classification in Precision Agriculture
本文提出TinyMLOps管道,涵盖模型设计、优化、量化及跨多种边缘设备部署,在受控实验室条件下评估。基于PlantVillage基准推导的数据集,将39个细粒度类别聚合成3个超类(健康叶、不健康叶、无叶),系统执行植物健康状态分类和背景过滤功能,而不是诊断特定疾病。训练基于MobileNet的卷积神经网络,联合优化分类精度和计算效率;选择5个模型(Pareto前沿4个+最大HPO模型)转换为LiteRT和ONNX,在Raspberry Pi Zero 2 W和STM32H743ZI微控制器上以float32和后训练int8精度评估。在float32下,LiteRT比ONNX Runtime快1.87-2.65倍;int8 LiteRT模型比float32小2.83-3.67倍,快21.3-31.2%,F1-score损失仅0.0010-0.0068;在微控制器上,两个最小模型int8变体比float32快4.3倍,MCU闪存占用小3.85倍。