Search research articles

关于 JoVE

概览领导团队博客 JoVE 帮助中心

作者

出版流程编辑委员会范围与政策同行评审常见问题投稿

图书馆员

用户评价订阅访问资源图书馆顾问委员会常见问题

研究

JoVE Journal Methods Collections JoVE Encyclopedia of Experiments 存档

教育

JoVE Core JoVE Business JoVE Science Education JoVE Lab Manual 教师资源中心教师网站

使用条款与条件

Search research articles

相关实验视频

Updated: May 1, 2026

Author Spotlight: UAV Remote Sensing for Efficient Invasive Plant Biomass Estimation

Author Spotlight: UAV Remote Sensing for Efficient Invasive Plant Biomass Estimation

Published on: February 9, 2024

实时在设备上的杂草识别使用硬件高效的轻量级CNN CNN.

Yuxuan Zhang^1,2, Yuchen Lu³, Luciano Sebastian Martinez-Rau^2,4

¹College of Intelligent Science and Engineering, Beijing University of Agriculture, Beijing, China.

Frontiers in plant science

|March 4, 2026

概括

此摘要是机器生成的。

相关概念视频

您也可能阅读

相关文章

通过共同作者、期刊和引用图与本文相关的文章。

排序

Same author

Multi-indicator water-quality prediction in mining areas using a feature-tokenizer transformer with spatiotemporal features.

Environmental research·2026

Same author

Measurement of Serum Parameters Attributes the Therapeutic Effects of Music Therapy to Augmented Stress-Coping Ability and Diminished Systemic Inflammation.

Depression and anxiety·2026

Same author

Alleviating the Adverse Effects of Lipopolysaccharide on Production Performance, Immune Function, and Intestinal Damage in Broilers via Dietary Alkaline Phosphatase.

Animals : an open access journal from MDPI·2026

Same author

A bibliometric analysis of <i>Moringa oleifera</i> during 2000-2024.

Open life sciences·2026

Same author

LILRB2 inhibition by blocking antibody ES009 reprograms immunosuppressive myeloid cells and enhances T-cell-mediated tumor immunity.

Human vaccines & immunotherapeutics·2026

Same author

Patient-centered gastrointestinal function assessment technologies: a paradigm shift from traditional approaches to non-invasive innovations.

Frontiers in physiology·2026

一个新的轻量级深度学习模型,TinyWeedNet,可以实时在设备上识别杂草,用于自主农业. 这种节能解决方案非常适合低功率的农业设备,增强精密农业战略.

科学领域:

农业工程农业工程
计算机科学计算机科学
机器学习机器学习

背景情况:

准确的杂草识别对于自主农业系统中可持续的作物管理至关重要.
现有的深度学习模型通常需要大量的计算资源 (例如GPU),限制它们在低功耗领域设备上部署.

研究的目的:

开发一个硬件效率高,轻量级的卷积神经网络 (CNN),用于实时,设备上的杂草识别.
为了使资源有限的精准农业平台能够部署先进的杂草识别能力.

主要方法:

提议TinyWeedNet,一个CNN集成多尺度的特征提取,深度可分离的反转剩余块,以及紧的频道注意力.
在DeepWeeds数据集上训练和测试模型.
在STM32H7微控制器上实现TinyWeedNet,使用TinyML工作流进行嵌入式执行.

主要成果:

仅用0.48万个参数实现了97.26%的分类准确度.
在微控制器上证明了90毫秒以下的推断时间和低能耗.
TinyWeedNet在准确性,速度和能源效率之间取得了良好的平衡.

结论:

关键词:

在TinyML中使用TinyML.嵌入式系统嵌入式系统节能计算是一种节能计算.轻质卷积神经网络 (CNN) 是一种神经网络.在设备上推断推断.精准农业精准农业精准农业杂草识别标识杂草识别标识

更多相关视频

Integration of Animal Behavioral Assessment and Convolutional Neural Network to Study Wasabi-Alcohol Taste-Smell Interaction

Integration of Animal Behavioral Assessment and Convolutional Neural Network to Study Wasabi-Alcohol Taste-Smell Interaction

Published on: August 16, 2024

相关实验视频

Last Updated: May 1, 2026

Author Spotlight: UAV Remote Sensing for Efficient Invasive Plant Biomass Estimation

Author Spotlight: UAV Remote Sensing for Efficient Invasive Plant Biomass Estimation

Published on: February 9, 2024

Integration of Animal Behavioral Assessment and Convolutional Neural Network to Study Wasabi-Alcohol Taste-Smell Interaction

Integration of Animal Behavioral Assessment and Convolutional Neural Network to Study Wasabi-Alcohol Taste-Smell Interaction

Published on: August 16, 2024

TinyWeedNet提供了一个实用的解决方案,用于将实时,低功耗的杂草识别集成到野外机器人,无人机和传感器中.

这有助于在精准农业中实现更自主和更节能的杂草管理策略.