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 7, 2026

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

确保SOTIF:用于自动驾驶的增强物体检测技术

Sifen Wang1, Zhangyu Wang2, Sheng Hong3

  • 1School of Transportation Science and Engineering, Beihang University, China; Beijing Institute of Control Engineering, Beijing 100190, China.

Accident; analysis and prevention
|May 10, 2025
PubMed
概括

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

A novel copper oxide/titanium membrane integrated with peroxymonosulfate activation for efficient phenolic pollutants degradation.

Journal of colloid and interface science·2023
Same author

SARS-CoV-2 main protease cleaves MAGED2 to antagonize host antiviral defense.

mBio·2023
Same author

The Effect of Low-Dose Esketamine on Postoperative Neurocognitive Dysfunction in Elderly Patients Undergoing General Anesthesia for Gastrointestinal Tumors: A Randomized Controlled Trial.

Drug design, development and therapy·2023
Same author

The mechanisms of Huangqi Guizhi Wuwu decoction in treating ischaemic stroke based on network pharmacology and experiment verification.

Pharmaceutical biology·2023
Same author

The tumor-stroma ratio and the immune microenvironment improve the prognostic prediction of pancreatic ductal adenocarcinoma.

Discover oncology·2023
Same author

Chromosome-level Asian elephant genome assembly and comparative genomics of long-lived mammals reveal the common substitutions for cancer resistance.

Aging cell·2023

这项研究通过改进对象检测来提高自动驾驶的安全性. 修改后的YOLOv5算法带有预测扩展框可以提高感知精度和目标覆盖率,解决预期功能安全问题.

科学领域:

  • 计算机视觉 计算机视觉
  • 人工智能的人工智能
  • 自主系统 自主系统

背景情况:

  • 自动驾驶中的神经网络面临解释性挑战,影响预期功能的安全性 (SOTIF).
  • 当前的物体检测方法可能并不总是保证准确的感知结果,在安全关键的应用中存在风险.
  • 确保可靠的感知对于自动驾驶汽车的安全运行至关重要.

研究的目的:

  • 为自动驾驶提供一个增强的物体检测算法.
  • 提高感知系统的准确性和可靠性.
  • 解决和减轻因感知不准确性而产生的预期功能安全性 (SOTIF) 问题.

主要方法:

  • 使用YOLOv5一阶段物体检测算法作为基线.
  • 在YOLOv5架构中引入了一个新的预测扩展框.
  • 在检测过程中考虑目标覆盖范围和冗余性.

主要成果:

  • 拟议的算法显著增加了检测到的目标的覆盖范围.
  • 改进后的模型在感知系统中显示出更高的准确性.
  • 这些修改有助于保证图像感知安全.

结论:

关键词:
自动驾驶自动驾驶的自动驾驶对象检测检测对象检测对象检测预测扩展框的预测.SOTIFIF 公司

更多相关视频

End-To-End Deep Neural Network for Salient Object Detection in Complex Environments
03:31

End-To-End Deep Neural Network for Salient Object Detection in Complex Environments

Published on: December 15, 2023

相关实验视频

Last Updated: Jul 7, 2026

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

End-To-End Deep Neural Network for Salient Object Detection in Complex Environments
03:31

End-To-End Deep Neural Network for Salient Object Detection in Complex Environments

Published on: December 15, 2023

  • 开发的物体检测算法增强了自动驾驶中的感知安全性.
  • 预测扩展框通过改进目标检测,有效地解决了SOTIF的担忧.
  • 这种方法为更安全的自动驾驶汽车感知系统提供了一个有希望的解决方案.