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

Detection of Black Holes01:10

Detection of Black Holes

2.5K
Although black holes were theoretically postulated in the 1920s, they remained outside the domain of observational astronomy until the 1970s.
Their closest cousins are neutron stars, which are composed almost entirely of neutrons packed against each other, making them extremely dense. A neutron star has the same mass as the Sun but its diameter is only a few kilometers. Therefore, the escape velocity from their surface is close to the speed of light.
Not until the 1960s, when the first neutron...
2.5K

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

BMR-YOLO: A deep learning approach for fall detection in complex environments.

PloS one·2025
Same author

MythPose: Enhanced Detection of Complex Poses in Thangka Figures.

Sensors (Basel, Switzerland)·2025
Same author

Anodic Dissolution Characteristics of GH4169 Alloy in NaNO<sub>3</sub> Solutions by Roll-Print Mask Electrochemical Machining Using the Linear Cathode.

Materials (Basel, Switzerland)·2024
Same author

Construct a Magnetic Pt/Ru Alloy Peroxidase Mimic As a Reusable and Cost-Effective "Signal-Off" Sensing Platform for Sensitive and Wide-Linear-Range Assay.

Analytical chemistry·2024
Same author

ANXA5: A Key Regulator of Immune Cell Infiltration in Hepatocellular Carcinoma.

Medical science monitor : international medical journal of experimental and clinical research·2024
Same author

Burden of liver cancer attributable to high fasting plasma glucose: a global analysis based on the global burden of disease study 2019.

The journal of nutrition, health & aging·2024

相关实验视频

Updated: Jan 17, 2026

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

1.0K

在thangka图像中使用gabor,波形和颜色特征融合增强对象检测.

Yukai Xian1, Yurui Lee2, Te Shen1

  • 1School of Information Science and Technology, Tibet University, Lhasa 850000, China.

Sensors (Basel, Switzerland)
|September 19, 2025
PubMed
概括

这项研究引入了一种新的频率和预先增强的对象检测框架,用于复杂的Thangka图像. 该方法显著提高了检测精度和复杂细节和小目标的回忆.

关键词:
卡检测探测器可以检测到.多尺度物体识别多尺度物体识别预先引导的注意力.波形变换波形变换波形变换.

更多相关视频

Transient Optical Clearing Using Absorbing Molecules for Ex Vivo and In Vivo Imaging
07:15

Transient Optical Clearing Using Absorbing Molecules for Ex Vivo and In Vivo Imaging

Published on: July 11, 2025

2.4K
Detection of Architectural Distortion in Prior Mammograms via Analysis of Oriented Patterns
13:44

Detection of Architectural Distortion in Prior Mammograms via Analysis of Oriented Patterns

Published on: August 30, 2013

43.6K

相关实验视频

Last Updated: Jan 17, 2026

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

1.0K
Transient Optical Clearing Using Absorbing Molecules for Ex Vivo and In Vivo Imaging
07:15

Transient Optical Clearing Using Absorbing Molecules for Ex Vivo and In Vivo Imaging

Published on: July 11, 2025

2.4K
Detection of Architectural Distortion in Prior Mammograms via Analysis of Oriented Patterns
13:44

Detection of Architectural Distortion in Prior Mammograms via Analysis of Oriented Patterns

Published on: August 30, 2013

43.6K

科学领域:

  • 计算机视觉 计算机视觉
  • 人工智能的人工智能
  • 数字遗产是数字遗产的一部分.

背景情况:

  • 卡图像分析由于复杂的图像形象,密集的小尺寸元素和独特的色彩纹理组成而带来了挑战.
  • 现有的物体检测模型往往无法在这样的专业图像中捕捉全球结构和本地细节.
  • 在当前的文化遗产文物检测框架中,域特定的视觉先验很少被使用.

研究的目的:

  • 开发一个先进的物体检测框架,以适应卡图像的具体挑战.
  • 增强模型检测全球结构和细粒度局部细节的能力.
  • 将特定领域的视觉先验,包括色彩和方向线索,纳入检测过程中.

主要方法:

  • 提出了一个基于YOLOv11.11的频率和预先增强检测框架.
  • 引入了一个可学习的升起波形块 (LLWB) 用于频率分解和多尺度融合.
  • 设计了一种颜色加博区块 (CGBlock) 和颜色加博交叉门 (C2CG),以结合色彩和定向特征.
  • 重新设计的检测头具有分离的分支,中心性预测,以及用于小目标的额外浅头.

主要成果:

  • 在一个精心策划的Thangka数据集上实现了89.5%的mAP@0.5和59.4%的mAP@[0.5:0.95].
  • 达到84.7%的召回率,超过了基线检测器.
  • 保持了2090万参数的紧型号尺寸.

结论:

  • 拟议的框架为复杂的遗产图像中细粒度物体检测提供了强大的和可解释的解决方案.
  • 频率分解和特定域的先前集成显著提高了检测性能.
  • 该模型有效地解决了卡艺术中复杂的细节和小物体所带来的挑战.