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

Endoplasmic reticulum stress promotes colorectal cancer proliferation by regulating autophagy via XBP1s.

Translational cancer research·2026
Same author

Comparative study on the efficacy of conservative treatment and surgical treatment for simple Mason II radial head fracture.

Frontiers in surgery·2026
Same author

Progress in the treatment of complex osteoporotic proximal humeral fractures in elderly patients.

Frontiers in surgery·2026
Same author

Mathematical misdefinition of adjusted cloud-fraction change limits isolation of aerosol effects.

Proceedings of the National Academy of Sciences of the United States of America·2026
Same author

Microstructure and Cryogenic Mechanical Properties of a Heterostructured Al<sub>11</sub>Cr<sub>14</sub>Fe<sub>50</sub>Ni<sub>25</sub> High-Entropy Alloy Processed by Short-Time Annealing.

Materials (Basel, Switzerland)·2026
Same author

Knowledge mapping of alström syndrome research: a bibliometric and visualization analysis based on WoS data from 2000 to 2025.

Frontiers in genetics·2026

相关实验视频

Updated: May 21, 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

448

一种半监督的域名适应方法用于Sim2Real在自动采矿卡车中的对象检测.

Lunfeng Guo1,2,3, Yinan Guo1,2,3, Jiayin Liu1,4

  • 1School of Mechanical and Electrical Engineering, China University of Mining and Technology (Beijing), Beijing 100000, China.

Sensors (Basel, Switzerland)
|March 17, 2025
PubMed
概括

阿达米克斯是一个新的半监督域适应物体检测 (SSDA-OD) 框架,提高了开放式采矿中自动卡车的安全性. 它通过有效地弥合Sim2Real差距,大大减少了对昂贵的真实世界数据的需求.

关键词:
活跃域名适应的适应自动驾驶卡车的自动驾驶卡车.对象检测检测对象检测对象检测这是一座露天矿山.半监督的域名适应.

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

8.9K
Author Spotlight: Efficient Image Recognition Using Directional Gradient Histogram Technique and Support Vector Machines
08:27

Author Spotlight: Efficient Image Recognition Using Directional Gradient Histogram Technique and Support Vector Machines

Published on: January 5, 2024

933

相关实验视频

Last Updated: May 21, 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

448
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

8.9K
Author Spotlight: Efficient Image Recognition Using Directional Gradient Histogram Technique and Support Vector Machines
08:27

Author Spotlight: Efficient Image Recognition Using Directional Gradient Histogram Technique and Support Vector Machines

Published on: January 5, 2024

933

科学领域:

  • 计算机视觉 计算机视觉
  • 机器人技术 机器人技术 机器人技术
  • 人工智能的人工智能

背景情况:

  • 自动驾驶卡车对于开采采矿的安全性和生产率至关重要.
  • 高质量的注释数据对于训练物体检测模型至关重要,但在恶劣的采矿环境中,收集是昂贵和困难的.
  • 模拟为数据生成提供了解决方案,但受到Sim2Real域转移的影响,影响了模型性能.

研究的目的:

  • 介绍Adamix,一个新的半监督域适应物体检测 (SSDA-OD) 框架.
  • 为了减少Sim2Real域转移,并最大限度地降低对象检测模型的标签成本.
  • 在具有挑战性的开放式采矿环境中增强对象检测性能.

主要方法:

  • 亚达米克斯使用了一个平均教师架构,有两个新的模块:渐进式中间域构建 (PIDC) 和热启动自适应伪标签 (WSAPL).
  • PIDC采用混合策略来创建中间域,减少源域偏差并防止过拟合.
  • WSAPL使用适应性值进行伪标签,以减轻训练期间的检测错误.

主要成果:

  • 阿达米克斯在Sim2Real场景中展示了优越的域调整性能,超过了最先进的方法.
  • 与现有方法相比,该框架实现了更高的平均精度 (mAP).
  • 积极学习的整合需要50%的标记数据,显著减少了现实世界的数据收集需求.

结论:

  • 亚达米克斯通过尽量减少对昂贵的真实世界数据的依赖,为开放式采矿中对象检测提供了更有效的解决方案.
  • 拟议的框架有效地解决了Sim2Real领域转移的挑战.
  • 阿达米克斯提高了在工业环境中部署自主系统的实用性和成本效益.