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

X-ray Imaging01:24

X-ray Imaging

10.8K
German physicist Wilhelm Röntgen (1845–1923) was experimenting with electrical current when he discovered that a mysterious and invisible "ray" would pass through his flesh but leave an outline of his bones on a screen coated with a metal compound. In 1895, Röntgen made the first durable record of the internal parts of a living human: an "X-ray" image (as it came to be called) of his wife’s hand. Scientists worldwide quickly began their own experiments with...
10.8K

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

Dual blockade of PD-1 and NKG2A prevents NK cell senescence and reprograms the immunosuppressive microenvironment in pancreatic cancer.

Cell reports·2026
Same author

Editorial: Reviews in gastroenterology 2025.

Frontiers in medicine·2026
Same author

Clinical efficacy of PPAR agonists in the treatment of nonalcoholic fatty liver disease.

Frontiers in pharmacology·2026
Same author

Three decades of continuous warming in temperate forests destabilizes persistent forms of soil organic matter.

The Science of the total environment·2026
Same author

Domain-adapted discovery of PET depolymerisation routes using in-house curated scientific literature.

Chemical communications (Cambridge, England)·2026
Same author

Three Decades of Litter Manipulation Distinctly Shifts Soil Organic Matter Composition and Constrains Soil Carbon Sequestration in Temperate Forest Soils.

Environmental science & technology·2026

相关实验视频

Updated: May 5, 2026

Design and Use of an Apparatus for Presenting Graspable Objects in 3D Workspace
09:11

Design and Use of an Apparatus for Presenting Graspable Objects in 3D Workspace

Published on: August 8, 2019

5.3K

一个轻量级的多尺度检测框架X射线图像与监督的对比学习.

Qi Diao1,2, WengHowe Chan3,4, Azlan Mohd Zain5

  • 1Faculty of Artificial Intelligence, Zhejiang Dongfang Polytechnic, Wenzhou, 325000, Zhejiang, China. diaoqi@graduate.utm.my.

Scientific reports
|February 24, 2026
PubMed
概括

本研究介绍了YOLOv8-DWConv-CSAF,这是一个高效的X射线安全对象检测模型. 它增强了在安全扫描中检测具有挑战性的项目,改善了自动威胁识别.

关键词:
注意力机制注意力机制这是一个DWConvConvConv.对象检测检测对象检测对象检测这就是YOLOv8的意义.

更多相关视频

Author Spotlight: Addressing Technical and Subjective Challenges in Measuring Classroom Attention
06:37

Author Spotlight: Addressing Technical and Subjective Challenges in Measuring Classroom Attention

Published on: December 15, 2023

4.5K
Author Spotlight: Customized Light-Sheet Imaging for Investigating Myocardial Structures in Rodent Hearts
05:58

Author Spotlight: Customized Light-Sheet Imaging for Investigating Myocardial Structures in Rodent Hearts

Published on: March 29, 2024

1.7K

相关实验视频

Last Updated: May 5, 2026

Design and Use of an Apparatus for Presenting Graspable Objects in 3D Workspace
09:11

Design and Use of an Apparatus for Presenting Graspable Objects in 3D Workspace

Published on: August 8, 2019

5.3K
Author Spotlight: Addressing Technical and Subjective Challenges in Measuring Classroom Attention
06:37

Author Spotlight: Addressing Technical and Subjective Challenges in Measuring Classroom Attention

Published on: December 15, 2023

4.5K
Author Spotlight: Customized Light-Sheet Imaging for Investigating Myocardial Structures in Rodent Hearts
05:58

Author Spotlight: Customized Light-Sheet Imaging for Investigating Myocardial Structures in Rodent Hearts

Published on: March 29, 2024

1.7K

科学领域:

  • 计算机视觉 计算机视觉
  • 人工智能的人工智能
  • 安全技术 安全技术

背景情况:

  • 自动化X射线安全检查面临着封闭和小物体的挑战.
  • 现有的物体探测器在X射线图像中扎着密集的遮蔽和混乱的背景.
  • 有限的计算资源阻碍了当前检测系统的现实应用.

研究的目的:

  • 为X射线安全检查开发一种轻量级和有区别的多尺度物体检测框架.
  • 提高在具有挑战性的条件下识别禁止物品的准确性和效率.
  • 加强对象检测在安全查中的实际应用.

主要方法:

  • 拟议的YOLOv8-DWConv-CSAF框架整合了架构压缩,注意力引导的功能增强和对比的表示学习.
  • 用深度可分离卷曲 (DWConv) 取代标准卷曲,以减少参数和计算成本.
  • 引入了一个新的通道空间注意力融合 (CSAF) 模块和混合损失函数 (PIoU + InfoNCE对比损失).

主要成果:

  • 在CLCXray和HiXray基准测试中,YOLOv8-DWConv-CSAF实现了最先进的性能.
  • 该模型展示了高精度与实时效率相结合的高精度.
  • 通过DWConv集成实现了参数和计算成本的显著降低.

结论:

  • 拟议的YOLOv8-DWConv-CSAF框架非常适合用于实际的安全查系统.
  • 该方法有效地解决了X射线图像中小型,重叠和严重遮蔽物体的挑战.
  • 实现了强大的通用化能力,以加强安全检查.