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

Neural Control of Respiration01:18

Neural Control of Respiration

The neural regulation of respiration is a meticulously coordinated process primarily controlled by the respiratory centers located within the brainstem. These centers, composed of specialized neurons, transmit nerve impulses that control the contraction and relaxation of our respiratory muscles.
Respiratory Centers in the Brainstem
Two primary areas comprise the respiratory center: the medullary respiratory center in the medulla oblongata and the pontine respiratory group in the pons. The...

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 Low-Cost Vision-GPS Framework for the Unified Mapping of Vertical and Horizontal Road Assets Using Deep Learning.

Sensors (Basel, Switzerland)·2026
Same author

Influence of Traffic Input Data Quality on Road Noise Estimates Using the CNOSSOS-EU Method.

Sensors (Basel, Switzerland)·2026
Same author

Environmental Noise Dataset for Sound Event Classification and Detection.

Scientific data·2025
Same author

The Role of Bone Tacks in Sinus Floor Lift Surgery: A Single-Center Experience.

Journal of clinical medicine·2024
Same author

Features for Evaluating Source Localization Effectiveness in Sound Maps from Acoustic Cameras.

Sensors (Basel, Switzerland)·2024
Same author

Detection and Feature Extraction in Acoustic Sensor Signals.

Sensors (Basel, Switzerland)·2023

相关实验视频

Updated: Jun 26, 2026

Automated Image-Based Quantification of Neutrophil Extracellular Traps Using NETQUANT
07:33

Automated Image-Based Quantification of Neutrophil Extracellular Traps Using NETQUANT

Published on: November 27, 2019

7.7K

基于量子化卷积神经网络的实时低成本流量监控,用于CNOSSOS-EU噪声模型.

Domenico Profumo1, Gonzalo de León2, Alessandro Monticelli3

  • 1IPOOL S.R.L., Via Antonio Cocchi, 3, 56121 Pisa, Italy.

Sensors (Basel, Switzerland)
|March 14, 2026
PubMed
概括

本研究介绍了一种低成本的实时车辆识别系统,使用边缘计算来准确地绘制城市噪音图. 该系统有效地对车辆进行分类,大大提高了交通监测的准确性和环境声学建模的成本效益.

关键词:
在CNOSSOS-EU分类中.边缘计算是一种边缘计算.噪音评估支持 噪音评估支持量子化卷积神经网络的神经网络.实时车辆检测 实时车辆检测交通流量监控 交通流量监控

更多相关视频

Continuous Measurement of Biological Noise in Escherichia Coli Using Time-lapse Microscopy
08:25

Continuous Measurement of Biological Noise in Escherichia Coli Using Time-lapse Microscopy

Published on: April 27, 2021

4.2K

相关实验视频

Last Updated: Jun 26, 2026

Automated Image-Based Quantification of Neutrophil Extracellular Traps Using NETQUANT
07:33

Automated Image-Based Quantification of Neutrophil Extracellular Traps Using NETQUANT

Published on: November 27, 2019

7.7K
Continuous Measurement of Biological Noise in Escherichia Coli Using Time-lapse Microscopy
08:25

Continuous Measurement of Biological Noise in Escherichia Coli Using Time-lapse Microscopy

Published on: April 27, 2021

4.2K

科学领域:

  • 环境声学环境声学
  • 城市规划是城市规划.
  • 计算机视觉 计算机视觉 计算机视觉

背景情况:

  • 精确的城市噪音映射依赖于与声学模型 (如CNOSSOS-EU) 兼容的详细交通数据.
  • 当前的交通监控系统在分类,成本效益和可扩展性方面往往不足以广泛使用.

研究的目的:

  • 开发一个具有成本效益的,实时的多车辆识别系统,用于城市噪音映射.
  • 使用边缘计算,根据CNOSSOS-EU标准进行精确的车辆分类以进行聚合.

主要方法:

  • 量子化YOLOv8卷积神经网络 (CNN) 与树Pi 4和Coral TPU上的跟踪算法的集成.
  • 在15,000张图像数据集上训练CNN,并使用8位后训练定量化来优化推理速度.
  • 实时检测和分类车辆到五个不同的类别.

主要成果:

  • 在白天条件下实现了14 FPS的推断速度和92.2%的平均平均精度 (mAP@50).
  • 在嵌入式设备上展示了强大的性能,适用于资源有限的环境.
  • 在一个案例研究中,该系统实现了6.6%的加权百分比误差,远远超过商业解决方案 (59.9%) 并接近手动准确率 (1.4%).

结论:

  • 开发的边缘计算系统为实时城市交通监控提供了高度准确和具有成本效益的解决方案.
  • 这项技术弥合了手动数据收集和当前自动化系统之间的差距,增强了城市噪音映射能力.
  • 该系统的效率和准确性使其适合在智能城市计划中大规模部署.