• 文献检索
  • 文档翻译
  • 深度研究
  • 学术资讯
  • Suppr Zotero 插件Zotero 插件
  • 邀请有礼
  • 套餐&价格
  • 历史记录
应用&插件
Suppr Zotero 插件Zotero 插件浏览器插件Mac 客户端Windows 客户端微信小程序
定价
高级版会员购买积分包购买API积分包
服务
文献检索文档翻译深度研究API 文档MCP 服务
关于我们
关于 Suppr公司介绍联系我们用户协议隐私条款
关注我们

Suppr 超能文献

核心技术专利:CN118964589B侵权必究
粤ICP备2023148730 号-1Suppr @ 2026

文献检索

告别复杂PubMed语法,用中文像聊天一样搜索,搜遍4000万医学文献。AI智能推荐,让科研检索更轻松。

立即免费搜索

文件翻译

保留排版,准确专业,支持PDF/Word/PPT等文件格式,支持 12+语言互译。

免费翻译文档

深度研究

AI帮你快速写综述,25分钟生成高质量综述,智能提取关键信息,辅助科研写作。

立即免费体验

来自斯洛伐克道路在各种光照和天气条件下的摄像头及遥测数据。

Camera and telemetry data from Slovak roads in various light and weather conditions.

作者信息

Galinski Marek, Milesich Tomáš, Janeba Matej, Danko Ján, Lehoczký Peter, Magdolen Ľuboš, Šoltés Lukáš, Tomčala Adam

机构信息

Slovak University of Technology, Faculty of Informatics and Information Technologies, Bratislava, 842 16, Slovakia.

Slovak University of Technology, Faculty of Mechanical Engineering, Bratislava, 812 31, Slovakia.

出版信息

Sci Data. 2024 Dec 30;11(1):1450. doi: 10.1038/s41597-024-04276-y.

DOI:10.1038/s41597-024-04276-y
PMID:39738204
原文链接:https://pmc.ncbi.nlm.nih.gov/articles/PMC11685662/
Abstract

In this paper, we describe the dataset captured with our proprietary data capture solution mounted on top of a Land Rover Defender vehicle. The captured data are the real data of drives on various Slovak roads. The total dataset consist of almost 33 hours of driving with a automotive grade FPD Link camera with 30 fps and with additional sensors such as high-precision GNSS sensor and modem towards mobile data connectivity LTE and 5 G. There are various road types and weather and conditions. Road types are 2-lane highway, 3-lane highway, urban environment, 1st class road (main, national), 2nd class road (main, regional), 3rd class road (local). Weather and light conditions are direct sunlight, normal daylight, rain/fog and dawn/twilight. All frames have captured its position, velocity, heading and connectivity information.

摘要

在本文中,我们描述了通过安装在路虎卫士汽车顶部的专有数据采集解决方案捕获的数据集。捕获的数据是在斯洛伐克各种道路上行驶的真实数据。整个数据集由近33小时的驾驶数据组成,使用的是帧率为30fps的汽车级FPD Link摄像头,以及其他传感器,如高精度GNSS传感器和用于移动数据连接LTE和5G的调制解调器。存在各种道路类型、天气和条件。道路类型包括双车道高速公路、三车道高速公路、城市环境、一级道路(主要道路、国道)、二级道路(主要道路、地区道路)、三级道路(地方道路)。天气和光照条件包括直射阳光、正常日光、雨/雾以及黎明/黄昏。所有帧都捕获了其位置、速度、航向和连接信息。

https://cdn.ncbi.nlm.nih.gov/pmc/blobs/fb50/11685662/73be8011eca7/41597_2024_4276_Fig5_HTML.jpg
https://cdn.ncbi.nlm.nih.gov/pmc/blobs/fb50/11685662/01f132149c31/41597_2024_4276_Fig1_HTML.jpg
https://cdn.ncbi.nlm.nih.gov/pmc/blobs/fb50/11685662/7d0d876de3a4/41597_2024_4276_Figa_HTML.jpg
https://cdn.ncbi.nlm.nih.gov/pmc/blobs/fb50/11685662/61112876ba6f/41597_2024_4276_Fig2_HTML.jpg
https://cdn.ncbi.nlm.nih.gov/pmc/blobs/fb50/11685662/5880468b1217/41597_2024_4276_Fig3_HTML.jpg
https://cdn.ncbi.nlm.nih.gov/pmc/blobs/fb50/11685662/4e28e3035c54/41597_2024_4276_Fig4_HTML.jpg
https://cdn.ncbi.nlm.nih.gov/pmc/blobs/fb50/11685662/73be8011eca7/41597_2024_4276_Fig5_HTML.jpg
https://cdn.ncbi.nlm.nih.gov/pmc/blobs/fb50/11685662/01f132149c31/41597_2024_4276_Fig1_HTML.jpg
https://cdn.ncbi.nlm.nih.gov/pmc/blobs/fb50/11685662/7d0d876de3a4/41597_2024_4276_Figa_HTML.jpg
https://cdn.ncbi.nlm.nih.gov/pmc/blobs/fb50/11685662/61112876ba6f/41597_2024_4276_Fig2_HTML.jpg
https://cdn.ncbi.nlm.nih.gov/pmc/blobs/fb50/11685662/5880468b1217/41597_2024_4276_Fig3_HTML.jpg
https://cdn.ncbi.nlm.nih.gov/pmc/blobs/fb50/11685662/4e28e3035c54/41597_2024_4276_Fig4_HTML.jpg
https://cdn.ncbi.nlm.nih.gov/pmc/blobs/fb50/11685662/73be8011eca7/41597_2024_4276_Fig5_HTML.jpg

相似文献

1
Camera and telemetry data from Slovak roads in various light and weather conditions.来自斯洛伐克道路在各种光照和天气条件下的摄像头及遥测数据。
Sci Data. 2024 Dec 30;11(1):1450. doi: 10.1038/s41597-024-04276-y.
2
Effects of weather conditions, light conditions, and road lighting on vehicle speed.天气状况、光照条件和道路照明对车速的影响。
Springerplus. 2016 Apr 23;5:505. doi: 10.1186/s40064-016-2124-6. eCollection 2016.
3
Using ADAS to Future-Proof Roads-Comparison of Fog Line Detection from an In-Vehicle Camera and Mobile Retroreflectometer.利用 ADAS 为道路提供前瞻性保障-车载摄像头与移动反射器的雾线检测比较。
Sensors (Basel). 2021 Mar 3;21(5):1737. doi: 10.3390/s21051737.
4
Accident risk of road and weather conditions on different road types.不同类型道路的路况和天气条件下的事故风险。
Accid Anal Prev. 2019 Jan;122:181-188. doi: 10.1016/j.aap.2018.10.014. Epub 2018 Oct 29.
5
Leveraging Artificial Intelligence and Fleet Sensor Data towards a Higher Resolution Road Weather Model.利用人工智能和车队传感器数据构建更高分辨率的道路天气模型。
Sensors (Basel). 2022 Apr 2;22(7):2732. doi: 10.3390/s22072732.
6
3D Object Detection with SLS-Fusion Network in Foggy Weather Conditions.雾天条件下基于SLS融合网络的3D目标检测
Sensors (Basel). 2021 Oct 9;21(20):6711. doi: 10.3390/s21206711.
7
Analyzing Gaze During Driving: Should Eye Tracking Be Used to Design Automotive Lighting Functions?驾驶过程中的注视分析:是否应使用眼动追踪技术来设计汽车照明功能?
J Eye Mov Res. 2025 Apr 10;18(2):13. doi: 10.3390/jemr18020013. eCollection 2025 Apr.
8
Permeability of roads to movement of scrubland lizards and small mammals.道路对灌丛蜥蜴和小型哺乳动物活动的渗透性。
Conserv Biol. 2013 Aug;27(4):710-20. doi: 10.1111/cobi.12081. Epub 2013 Jun 14.
9
Optical and Mass Flow Sensors for Aiding Vehicle Navigation in GNSS Denied Environment.用于在全球导航卫星系统(GNSS)信号受阻环境中辅助车辆导航的光学和质量流量传感器。
Sensors (Basel). 2020 Nov 17;20(22):6567. doi: 10.3390/s20226567.
10
Analyzing the effect of fog weather conditions on driver lane-keeping performance using the SHRP2 naturalistic driving study data.利用 SHRP2 自然驾驶研究数据分析雾天条件对驾驶员车道保持性能的影响。
J Safety Res. 2019 Feb;68:71-80. doi: 10.1016/j.jsr.2018.12.015. Epub 2018 Dec 23.

本文引用的文献

1
Ultra Fast Deep Lane Detection With Hybrid Anchor Driven Ordinal Classification.基于混合锚点驱动有序分类的超快速深层车道检测
IEEE Trans Pattern Anal Mach Intell. 2024 May;46(5):2555-2568. doi: 10.1109/TPAMI.2022.3182097. Epub 2024 Apr 3.
2
Man vs. computer: benchmarking machine learning algorithms for traffic sign recognition.人与计算机的较量:用于交通标志识别的机器学习算法基准测试。
Neural Netw. 2012 Aug;32:323-32. doi: 10.1016/j.neunet.2012.02.016. Epub 2012 Feb 20.