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

Development and validation of a radiomics nomogram for predicting outcomes following combined radiotherapy and modern chemotherapy in early-stage extranodal nasal-type NK/T-cell lymphoma: a multicenter study.

Annals of hematology·2026
Same author

Satralizumab in the management of aquaporin-4 antibody-positive neuromyelitis optica spectrum disorder during pregnancy: a case report.

Frontiers in immunology·2026
Same author

Early diagnosis of extranodal NK/T lymphoma presenting with oral ulcer and lip swelling by metagenomics next-generation sequencing: a case report.

BMC oral health·2026
Same author

Zalcitabine induces ferroptosis in multiple myeloma through the TFAM-cGAS-STING-SLC7A11 axis.

Journal of translational medicine·2026
Same author

Rimegepant for the acute treatment of migraine: A phase 3, multicenter, open-label, long-term safety and effectiveness study in adults from China.

Cephalalgia : an international journal of headache·2025
Same author

Effectiveness and safety of subthalamic nucleus deep brain stimulation in isolated generalised or segmental dystonia (SUNDYS trial): a study protocol.

British journal of neurosurgery·2025

相关实验视频

Updated: May 10, 2025

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

428

基于EMBS-YOLOv8s的煤炭和河的多尺度融合轻量级目标检测方法

Lin Gao1, Pengwei Yu1, Hongjuan Dong2

  • 1Mechanical Engineering School, Inner Mongolia University of Science and Technology, Baotou 014010, China.

Sensors (Basel, Switzerland)
|April 28, 2025
PubMed
概括

这项研究介绍了EMBS-YOLOv8s,这是一种轻量级的煤炭检测模型,可以提高准确性和效率. 改进的模型实现了96.0%的平均精度,超过了原来的YOLOv8,同时降低了复杂性并增加了用于智能煤炭分类的检测速度.

关键词:
克拉赫 (Clahe) 是一种调味料.智能-SIoU损失函数的功能.这是YOLOv8s.煤炭检测检测器 煤炭检测器有效的多分支和规模特征金字塔网络 (EMBSFPN)

更多相关视频

Deep Learning-Based Segmentation of Cryo-Electron Tomograms
10:25

Deep Learning-Based Segmentation of Cryo-Electron Tomograms

Published on: November 11, 2022

8.3K
Machine Learning Algorithms for Early Detection of Bone Metastases in an Experimental Rat Model
07:15

Machine Learning Algorithms for Early Detection of Bone Metastases in an Experimental Rat Model

Published on: August 16, 2020

6.6K

相关实验视频

Last Updated: May 10, 2025

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

428
Deep Learning-Based Segmentation of Cryo-Electron Tomograms
10:25

Deep Learning-Based Segmentation of Cryo-Electron Tomograms

Published on: November 11, 2022

8.3K
Machine Learning Algorithms for Early Detection of Bone Metastases in an Experimental Rat Model
07:15

Machine Learning Algorithms for Early Detection of Bone Metastases in an Experimental Rat Model

Published on: August 16, 2020

6.6K

科学领域:

  • 计算机视觉 计算机视觉
  • 机器学习 机器学习
  • 人工智能的人工智能

背景情况:

  • 精确的煤检测对于智能煤炭分类至关重要.
  • 现有方法的准确性低,模型结构复杂.
  • 需要有效和精确的煤炭道检测系统.

研究的目的:

  • 提出一个多尺度的聚变轻型煤炭团目标检测方法.
  • 为了提高煤炭检测模型的准确性和降低复杂性.
  • 开发一个适合实时智能分类应用的模型.

主要方法:

  • 使用对比度有限的自适应式直方图平衡 (CLAHE) 进行图像预处理.
  • 在子网络中实施了增强的多尺度双向特征金字塔网络 (EMBSFPN).
  • 将CIoU损失函数替换为Wise-SIoU损失函数,以改善收和样本平衡.

主要成果:

  • 在定制数据集上,EMBS-YOLOv8s模型实现了96.0%的平均精度.
  • 与YOLOv8s相比,模型复杂性降低了:参数 (29.59%),FLOP (12.68%) 和大小 (28.44%) 相比.
  • 实现了每秒93.28的检测速度,展示了实时功能.
  • 有效地将错误和错过的检测最小化在具有挑战性的条件下,如低亮度和运动模糊.

结论:

  • 拟议的EMBS-YOLOv8s模型在煤探测方面提供了卓越的性能.
  • 该方法为智能煤炭分类提供了一个轻量级,准确和高效的解决方案.
  • 在复杂和不利的成像场景中,EMBS-YOLOv8s表现出强度.