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

Sub-grain boundaries by cold-rolling copper nanoparticles for boosting alkaline HER.

Chemical communications (Cambridge, England)·2026
Same author

[Research on the changing trends of filter inlet pressure and extracorporeal circuit coagulation degree in patients with sepsis-induced coagulopathy undergoing continuous renal replacement therapy].

Zhonghua wei zhong bing ji jiu yi xue·2026
Same author

A Quantitative Efflux Ratio-Integrated Model for Passive Permeability Estimation from Caco-2 Assays.

Drug metabolism and bioanalysis·2026
Same author

Predicting Massive Transfusion Needs in Trauma Using Machine Learning: Systematic Review and Meta-Analysis.

Journal of trauma nursing : the official journal of the Society of Trauma Nurses·2026
Same author

Multisite Coadsorption of the *OOH Intermediate on NiFeOOH Hierarchical Nanosheet Arrays Boost Water Electro-Oxidation at Ultrahigh Current Densities.

ACS applied materials & interfaces·2026
Same author

Repression of EEF1D by KSHV RTA promotes viral lytic reactivation.

Journal of virology·2026

相关实验视频

Updated: Jun 6, 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

470

在智能运输场景中的小规模物体检测算法.

Junzi Song1, Chunyan Han1, Chenni Wu1

  • 1School of Software, Northeastern University (NEU), Shenyang 110169, China.

Entropy (Basel, Switzerland)
|November 27, 2024
PubMed
概括
此摘要是机器生成的。

这项研究通过融合方法提高了智能运输中用于小目标的物体检测. 改进的YOLOv4微型模型在复杂的交通场景中提高了中小型目标的检测精度.

关键词:
YOLOv4小小的小小的小小的小小的小小的小小的小小的小小的特征金字塔的特征是金字塔的特征.信息的信息.智能运输是一种智能运输.小物体检测 小物体检测

更多相关视频

SwarmSight: Real-time Tracking of Insect Antenna Movements and Proboscis Extension Reflex Using a Common Preparation and Conventional Hardware
08:13

SwarmSight: Real-time Tracking of Insect Antenna Movements and Proboscis Extension Reflex Using a Common Preparation and Conventional Hardware

Published on: December 25, 2017

8.1K
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

相关实验视频

Last Updated: Jun 6, 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

470
SwarmSight: Real-time Tracking of Insect Antenna Movements and Proboscis Extension Reflex Using a Common Preparation and Conventional Hardware
08:13

SwarmSight: Real-time Tracking of Insect Antenna Movements and Proboscis Extension Reflex Using a Common Preparation and Conventional Hardware

Published on: December 25, 2017

8.1K
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

科学领域:

  • 计算机视觉 计算机视觉
  • 人工智能的人工智能
  • 智能运输系统 智能运输系统

背景情况:

  • 对象检测模型在复杂的智能运输场景中与小规模目标作斗争.
  • 混乱的背景和交通图像中的冗余信息阻碍了准确的检测.
  • 数据不平衡和次优先前界限框适应影响自定义流量数据集.

研究的目的:

  • 提高智能运输中小型和中型目标的检测精度.
  • 为了加强模型的重点,在杂乱的背景中关注相关的交通目标.
  • 为了解决数据不平衡,并改善定制流量数据集的界限框适应.

主要方法:

  • 一种基于YOLOv4微型框架的融合方法,通过特征金字塔网络 (FPN) 增强浅层和中层特征利用.
  • 集成卷积块注意模块 (CBAM) 来改进模型对交通目标的注意力.
  • 实施了改进的复制粘贴数据增强方法和K-means算法,用于修改数据集增强的距离测量.

主要成果:

  • 与标准YOLOv4微型模型相比,提出的算法在平均平均精度 (mAP) 中表现出4.9%的改进.
  • 增强型号保持了实时性能,这对于智能运输应用至关重要.
  • 在复杂的交通环境中检测小型和中型目标方面观察到显著的改进.

结论:

  • 拟议的融合方法有效地提高了特征利用率和模型注意力,以改善智能运输中的小规模目标检测.
  • 数据增强和集群技术成功地解决了与定制流量数据集相关的挑战.
  • 该算法为智能交通系统中的实时,准确的对象检测提供了可行的解决方案.