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

相关实验视频

Updated: Jul 9, 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

559

基于轻量级网络和微小物体检测的驾驶员分心检测.

Zhiqin Zhu1, Shaowen Wang1, Shuangshuang Gu1

  • 1College of Automation, Chongqing University of Posts and Telecommunications, Chongqing 400065, China.

Mathematical biosciences and engineering : MBE
|December 5, 2023
PubMed
概括
此摘要是机器生成的。

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

The relationship between the pore architecture of MFI zeolites and isoamylene oligomerization.

Physical chemistry chemical physics : PCCP·2026
Same author

An explainable prognostic prediction panel for sepsis based on serum amino acid profiles.

Frontiers in immunology·2026
Same author

Engineered decellularized muscle extracellular matrix fabrics enable functional volumetric muscle loss repair.

Bioactive materials·2026
Same author

When the image loses its shape: a comparative study of college students' understanding pathways of abstract and figurative art.

Frontiers in psychology·2026
Same author

Whole-genome resequencing revealed genetic diversity and the haplotype containing MC1R associated with black coat color in Liangshan sheep.

BMC genomics·2026
Same author

In-plane anomalous Hall effect in a low-dimensional system.

Nature materials·2026

一个新的轻量级模型,MTNet,增强了边缘设备的驾驶员分心检测. 它在不牺牲效率的情况下提高了微小的目标精度,提高了道路安全.

科学领域:

  • 计算机视觉 计算机视觉
  • 人工智能的人工智能
  • 道路安全工程 道路安全工程

背景情况:

  • 实时驾驶员分心检测对于道路安全和先进的驾驶辅助系统至关重要.
  • 轻量级模型对于车载边缘计算至关重要,但往往会损害微小目标检测的准确性.
  • 现有的方法优先考虑效率,而不是在检测小,关键的视觉线索时保持性能.

研究的目的:

  • 推出MTNet,一种新的轻量级深度学习模型,用于高效准确地检测驾驶员的分心.
  • 为了应对在资源有限的环境中检测小目标时保持高精度的挑战.
  • 为了提高边缘设备上的驾驶员监控系统的性能.

主要方法:

  • 开发了MTNet,具有具有集成注意力机制的多维自适应特征提取块.
  • 实现了一个轻量级的功能融合块,以减少计算复杂性和内存访问.
  • 使用了一种专门用于增强微小目标检测的IoU-NWD加权损失功能.
  • 整合了CFSM和EPIEM模块以优化特征图计算和精确平衡模型重量.

主要成果:

  • 与LDDB基准中的多个先进检测模型相比,MTNet表现优越.
  • 拟议的方法有效地平衡了轻量级设计与更高的准确性,特别是对于小型目标.
关键词:
驾驶员分心检测检测 驾驶员分心检测轻量级网络轻量级的网络.微小的物体检测检测微小的物体检测

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

3.8K
Design and Analysis for Fall Detection System Simplification
08:05

Design and Analysis for Fall Detection System Simplification

Published on: April 6, 2020

10.7K

相关实验视频

Last Updated: Jul 9, 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

559
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

3.8K
Design and Analysis for Fall Detection System Simplification
08:05

Design and Analysis for Fall Detection System Simplification

Published on: April 6, 2020

10.7K
  • 实验结果验证了模型在实时驾驶员分心检测场景中的效率和有效性.

    • 结论:

    • 在边缘设备上,MTNet为实时驾驶员分心检测提供了一个有前途的解决方案.
    • 该模型的设计成功地克服了轻量级架构和微小目标检测性能之间的权衡.
    • 这一进步有助于提高道路交通安全,并开发更具能力的辅助驾驶系统.