Jove
Visualize
联系我们
JoVE
x logofacebook logolinkedin logoyoutube logo
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 JournalMethods CollectionsJoVE Encyclopedia of Experiments存档
教育
JoVE CoreJoVE BusinessJoVE Science EducationJoVE Lab Manual教师资源中心教师网站
使用条款与条件
隐私政策
政策

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

Multifunctional biohybrid nanoplatform interferes electron transport chain amplifying mitochondrial metabolism-mediated anti-tumor therapy.

Materials today. Bio·2026
Same author

Hydrocarbon generation kinetics and history of source rocks in different salinity environments, Dongpu Depression, Bohai Bay Basin, China.

PloS one·2026
Same author

Kartogenin-Loaded Selenium-Prussian Blue Nanogel through ROS scavenging and cartilage regeneration for the mitigation of osteoarthritis.

International journal of pharmaceutics·2026
Same author

Identification and Optimization of Pyridone Derivatives as Pan-MEK/RAF Nondegrading Molecular Glues for the Treatment of RAS-Driven Cancers.

Journal of medicinal chemistry·2026
Same author

Structure-based design and synthesis of KX-01 analogs as potent antitumor agents targeting the tubulin colchicine binding site.

European journal of medicinal chemistry·2026
Same author

Reliable WSe<sub>2</sub> Memristors Enabled by van der Waals Electrode Integration for Advanced Reservoir Computing and Nociceptive Receptors.

ACS applied materials & interfaces·2026

相关实验视频

Updated: Jul 5, 2025

Author Spotlight: UAV Remote Sensing for Efficient Invasive Plant Biomass Estimation
08:47

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

Published on: February 9, 2024

1.4K

基于机器视觉和深度学习的堆叠建筑固体废物的快速数据集生成方法.

Tianchen Ji1, Jiantao Li1, Huaiying Fang1

  • 1College of Mechanical Engineering and Automation, Huaqiao University, Xiamen, Fujian, China.

PloS one
|January 16, 2024
PubMed
概括
此摘要是机器生成的。

本研究介绍了一种快速,自动化的方法,用于使用机器视觉生成和注释建筑固体废物数据集. 这种方法显著提高了检测准确度,特别是在复杂的环境中,超过了手动标签的性能.

更多相关视频

Combining Eye-tracking Data with an Analysis of Video Content from Free-viewing a Video of a Walk in an Urban Park Environment
08:25

Combining Eye-tracking Data with an Analysis of Video Content from Free-viewing a Video of a Walk in an Urban Park Environment

Published on: May 7, 2019

9.0K
A Method for 3D Reconstruction and Virtual Reality Analysis of Glial and Neuronal Cells
12:49

A Method for 3D Reconstruction and Virtual Reality Analysis of Glial and Neuronal Cells

Published on: September 28, 2019

12.8K

相关实验视频

Last Updated: Jul 5, 2025

Author Spotlight: UAV Remote Sensing for Efficient Invasive Plant Biomass Estimation
08:47

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

Published on: February 9, 2024

1.4K
Combining Eye-tracking Data with an Analysis of Video Content from Free-viewing a Video of a Walk in an Urban Park Environment
08:25

Combining Eye-tracking Data with an Analysis of Video Content from Free-viewing a Video of a Walk in an Urban Park Environment

Published on: May 7, 2019

9.0K
A Method for 3D Reconstruction and Virtual Reality Analysis of Glial and Neuronal Cells
12:49

A Method for 3D Reconstruction and Virtual Reality Analysis of Glial and Neuronal Cells

Published on: September 28, 2019

12.8K

科学领域:

  • 计算机视觉 计算机视觉
  • 环境科学 环境科学
  • 机器人技术 机器人技术 机器人技术

背景情况:

  • 城市化产生大量建筑固体废物,需要有效的分类解决方案.
  • 机器视觉算法比传统方法提供更快,更稳定的固体废物检测.
  • 准确的机器视觉需要大量的数据集,但现场数据稀缺,手动注释成本高昂.

研究的目的:

  • 开发快速,自动的方法来生成和注释建筑固体废物数据集.
  • 提高基于机器视觉的固体废物分类的准确性和效率.
  • 为了解决稀缺的现场数据和高手工注释成本的局限性.

主要方法:

  • 建立了一个采集和检测平台,用于自动RGB-D图像收集和实例标签.
  • 使用分发点和数据增强,用于合成建筑固体废物数据集的快速生成方法.
  • 现实数据集的两个自动注释方法:半监督自训和RGB-D融合边缘检测.

主要成果:

  • 在简单的条件下,生成的数据集在简单的条件下获得了95.98F1分,超过了手动标签 (94.81).
  • 在复杂的条件下,快速生成方法达到97.74F1得分,明显超过手动标签 (85.97).
  • 使用提出的方法生成和注释的数据集产生了卓越的模型训练结果.

结论:

  • 建议的快速数据集生成和自动注释方法对于建筑固体废物是有效的.
  • 这些自动化方法克服了手动注释和稀缺现场数据的局限性.
  • 开发的方法提高了固体废物分类机器视觉算法的性能.