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

Machine learning assisted sensor array based on ligand-regulated activity of nanozymes for the precise identification of polyphenols.

Biosensors & bioelectronics·2026
Same author

Sulfur-modified iron-based biochar via feature-sparsified cascade transfer learning: from interfacial structure regulation to phosphate adsorption performance optimization.

Bioresource technology·2026
Same author

Broad-spectrum degradation of emerging contaminants and industrial dyes by a robust CuCo<sub>(1:2)</sub>@N catalyst activating peroxymonosulfate.

Environmental research·2026
Same author

Hexapeptide-Liposome Nanosystem for the Delivery of Endosomal pH Modulator to Treat Acute Lung Injury.

Journal of functional biomaterials·2025
Same author

Intelligent coupling model for seasonal optimization of effluent total nitrogen in municipal wastewater treatment plants.

Environmental monitoring and assessment·2025
Same author

Super-sulfated cement incorporating gold tailings with lithium slag modification: Hydration behavior and heavy metal immobilization.

Environmental research·2025

相关实验视频

Updated: Sep 15, 2025

Detection and Quantification of Tunneling Nanotubes Using 3D Volume View Images
12:45

Detection and Quantification of Tunneling Nanotubes Using 3D Volume View Images

Published on: August 31, 2022

3.0K

研究基于多尺度特征的轻量级道电缆火灾识别算法.

Zimeng Liu1,2, Lei Zhang3, Huiqiang Ma4,5

  • 1College of Environmental and Safety Engineering, Liaoning Petrochemical University, Fushun, 113001, Liaoning, China. ameng679@163.com.

Scientific reports
|July 16, 2025
PubMed
概括
此摘要是机器生成的。

本研究介绍了一种更快,更准确的基于YOLO-v5的火灾检测系统,用于使用轻量级网络和注意力机制的道. 改进的算法显著提高了道电缆火灾的检测速度和精度.

关键词:
电缆火灾发生火灾.深度学习是一种深度学习.图像识别 图像识别 图像识别多个尺度的特征聚变聚变.这就是YOLO-v55.

更多相关视频

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

1.6K
Author Spotlight: Enhancement of Salient Object Detection for Smart Grid Applications
03:31

Author Spotlight: Enhancement of Salient Object Detection for Smart Grid Applications

Published on: December 15, 2023

644

相关实验视频

Last Updated: Sep 15, 2025

Detection and Quantification of Tunneling Nanotubes Using 3D Volume View Images
12:45

Detection and Quantification of Tunneling Nanotubes Using 3D Volume View Images

Published on: August 31, 2022

3.0K
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

1.6K
Author Spotlight: Enhancement of Salient Object Detection for Smart Grid Applications
03:31

Author Spotlight: Enhancement of Salient Object Detection for Smart Grid Applications

Published on: December 15, 2023

644

科学领域:

  • 计算机视觉 计算机视觉
  • 人工智能的人工智能
  • 消防安全工程 消防安全工程

背景情况:

  • 道火灾检测系统经常受到缓慢响应时间和高错误报警率的影响.
  • 使用计算机视觉的智能火灾检测是改善道安全的日益增长的研究领域.

研究的目的:

  • 开发一个轻量级和高效的YOLO-v5算法用于道电缆火灾识别.
  • 为了提高在道环境中火灾检测的速度和准确性.

主要方法:

  • 通过将Darknet53替换为Mobilenetv3-small并集成SimAM注意力机制,提出了一个轻量级的YOLO-v5算法.
  • 实现了双向特征金字塔网络 (BiFPN) 用于特征融合,并使用了GIou_Loss函数.
  • 在各种风条件下创建了一个道电缆火灾图像数据库,用于模型验证.

主要成果:

  • 经过修改的YOLO-v5网络实现了0.4%的平均平均精度 (mAP) 提高至99%.
  • 每秒 (FPS) 提高了46.7%,达到179,这表明检测速度有所提高.
  • 实验验证证了该模型对于道火灾检测的准确性和可行性.

结论:

  • 拟议的轻量级YOLO-v5算法有效地解决了传统道火灾检测的局限性.
  • 这种方法在精度和速度上提供了显著的改进,这对于有效的道火灾管理和损失预防至关重要.