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

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

Extracellular vesicles derived from cancer-associated fibroblasts facilitate NSCLC progression and metastasis via miR-664b-5p-mediated activation of the CXCL12/CXCR4 chemokine pathway.

Biochimica et biophysica acta. Molecular basis of disease·2026

Same author

A CNN-injected transformer network with lesion reconstruction for multi-view diabetic retinopathy grading.

Medical image analysis·2026

Same author

Novel HD-Zip transcription factor PCD8 integrates developmental gene networks to shape rice panicle morphogenesis.

BMC plant biology·2026

Same author

ViGNet: A clinical data-supported deep learning approach for NSCLC immunotherapy response prediction in digital pathology.

Medical image analysis·2026

Same author

Revealing the Dynamic Association Between Lymphatic Endothelial Cell Markers and Intervertebral Disk Degeneration.

Biomedicines·2026

Same author

Genome-Wide Analysis of the <i>PR1</i> Gene Family in <i>Pinus massoniana</i> Under <i>Bursaphelenchus xylophilus</i> Stress.

Plants (Basel, Switzerland)·2026

Search research articles

相关实验视频

Updated: Jun 12, 2025

Micron-scale Phenotyping Techniques of Maize Vascular Bundles Based on X-ray Microcomputed Tomography

Micron-scale Phenotyping Techniques of Maize Vascular Bundles Based on X-ray Microcomputed Tomography

Published on: October 9, 2018

米-SVBDete:一种检测算法,用于小血管捆在米茎的横截面.

Xiaoying Zhu¹, Weiyu Zhou¹, Jianguo Li^2,3

¹Guangxi Colleges and Universities Key Laboratory of Intelligent Software, Wuzhou University, Wuzhou, China.

Frontiers in plant science

|June 10, 2025

概括

米-SVBDete使用深度学习准确地检测大米截面中的小血管捆. 这种专用算法显著提高了检测准确度,有助于米育种和精准农业.

关键词:

这是一个YOLO YOLO.深度学习是一种深度学习.可以变形的卷积卷积.大米血管捆绑包装小物体检测小物体检测

更多相关视频

Using High Resolution Computed Tomography to Visualize the Three Dimensional Structure and Function of Plant Vasculature

Using High Resolution Computed Tomography to Visualize the Three Dimensional Structure and Function of Plant Vasculature

Published on: April 5, 2013

Transverse Sectioning of Mature Rice Oryza sativa L. Kernels for Scanning Electron Microscopy Imaging Using Pipette Tips as Immobilization Support

Transverse Sectioning of Mature Rice Oryza sativa L. Kernels for Scanning Electron Microscopy Imaging Using Pipette Tips as Immobilization Support

Published on: January 25, 2022

相关实验视频

Last Updated: Jun 12, 2025

Micron-scale Phenotyping Techniques of Maize Vascular Bundles Based on X-ray Microcomputed Tomography

Micron-scale Phenotyping Techniques of Maize Vascular Bundles Based on X-ray Microcomputed Tomography

Published on: October 9, 2018

Using High Resolution Computed Tomography to Visualize the Three Dimensional Structure and Function of Plant Vasculature

Using High Resolution Computed Tomography to Visualize the Three Dimensional Structure and Function of Plant Vasculature

Published on: April 5, 2013

Transverse Sectioning of Mature Rice Oryza sativa L. Kernels for Scanning Electron Microscopy Imaging Using Pipette Tips as Immobilization Support

Transverse Sectioning of Mature Rice Oryza sativa L. Kernels for Scanning Electron Microscopy Imaging Using Pipette Tips as Immobilization Support

Published on: January 25, 2022

科学领域:

植物科学植物科学
农业技术农业技术
计算机视觉计算机视觉

背景情况:

血管束对于大米的生长和产量至关重要.
准确测量血管束对于米育种至关重要.
在显微镜图像中检测小血管束是具有挑战性的,因为大小和背景噪声.

研究的目的:

开发一种专门的深度学习算法,用于检测大米茎截面中的小血管捆.
改进现有的物体检测架构,以提高小,复杂的生物结构的性能.

主要方法:

建议使用Rice-SVBDete算法,增强YOLOv8架构.
集成的动态蛇形卷积 (DSConv) 适应性特征提取.
实施了多级特征融合 (MFF) 和一个新的强大的交叉在欧盟 (PIoU) 损失函数.

主要成果:

赖斯-SVBDete的精度为0.789,回忆率为0.771,mAP@.5的精度为0.728.
与基线YOLOv8相比,显著改善,精度,回忆和mAP@.5分别增加了0.179,0.201和0.227.
在复杂的背景中有效检测到小的血管束.

结论:

在具有挑战性的生物成像中,Rice-SVBDete为小型物体检测提供了强大的解决方案.
为大米解剖分析,精准农业和植物科学研究提供了宝贵的工具.
促进了作物改进和种植策略的进步.