• 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

在不同天气条件下的稳健车辆检测：使用 MIPM。

Robust vehicle detection in different weather conditions: Using MIPM.

机构信息

E.T.S. de Ingenieros de Telecomunicación, Universidad Politécnica de Madrid, Madrid, Spain.

出版信息

PLoS One. 2018 Mar 7;13(3):e0191355. doi: 10.1371/journal.pone.0191355. eCollection 2018.

DOI:10.1371/journal.pone.0191355
PMID:29513664
原文链接:https://pmc.ncbi.nlm.nih.gov/articles/PMC5841654/
Abstract

Intelligent Transportation Systems (ITS) allow us to have high quality traffic information to reduce the risk of potentially critical situations. Conventional image-based traffic detection methods have difficulties acquiring good images due to perspective and background noise, poor lighting and weather conditions. In this paper, we propose a new method to accurately segment and track vehicles. After removing perspective using Modified Inverse Perspective Mapping (MIPM), Hough transform is applied to extract road lines and lanes. Then, Gaussian Mixture Models (GMM) are used to segment moving objects and to tackle car shadow effects, we apply a chromacity-based strategy. Finally, performance is evaluated through three different video benchmarks: own recorded videos in Madrid and Tehran (with different weather conditions at urban and interurban areas); and two well-known public datasets (KITTI and DETRAC). Our results indicate that the proposed algorithms are robust, and more accurate compared to others, especially when facing occlusions, lighting variations and weather conditions.

摘要

智能交通系统 (ITS) 使我们能够获得高质量的交通信息，从而降低潜在危急情况的风险。传统的基于图像的交通检测方法由于透视和背景噪声、光线和天气条件差等原因，难以获取良好的图像。在本文中，我们提出了一种新的方法来准确地分割和跟踪车辆。使用修正逆透视映射 (MIPM) 去除透视后，应用霍夫变换提取道路线和车道。然后，使用高斯混合模型 (GMM) 分割运动目标，并解决汽车阴影效应，我们应用基于色度的策略。最后，通过三个不同的视频基准进行性能评估：在马德里和德黑兰录制的自有视频（具有城市和城乡地区不同天气条件）；以及两个著名的公共数据集（KITTI 和 DETRAC）。我们的结果表明，与其他方法相比，所提出的算法更稳健、更准确，尤其是在面对遮挡、光照变化和天气条件时。

https://cdn.ncbi.nlm.nih.gov/pmc/blobs/08d2/5841654/6d818edbf0bb/pone.0191355.g014.jpg
https://cdn.ncbi.nlm.nih.gov/pmc/blobs/08d2/5841654/7c865042fda6/pone.0191355.g001.jpg
https://cdn.ncbi.nlm.nih.gov/pmc/blobs/08d2/5841654/205b6c650ff8/pone.0191355.g002.jpg
https://cdn.ncbi.nlm.nih.gov/pmc/blobs/08d2/5841654/396974f4c1fa/pone.0191355.g003.jpg
https://cdn.ncbi.nlm.nih.gov/pmc/blobs/08d2/5841654/85bee8de7759/pone.0191355.g004.jpg
https://cdn.ncbi.nlm.nih.gov/pmc/blobs/08d2/5841654/8f835cafa472/pone.0191355.g005.jpg
https://cdn.ncbi.nlm.nih.gov/pmc/blobs/08d2/5841654/051120986e70/pone.0191355.g006.jpg
https://cdn.ncbi.nlm.nih.gov/pmc/blobs/08d2/5841654/de503e6c103c/pone.0191355.g007.jpg
https://cdn.ncbi.nlm.nih.gov/pmc/blobs/08d2/5841654/a72a7036bcd0/pone.0191355.g008.jpg
https://cdn.ncbi.nlm.nih.gov/pmc/blobs/08d2/5841654/5a0d8fac95bd/pone.0191355.g009.jpg
https://cdn.ncbi.nlm.nih.gov/pmc/blobs/08d2/5841654/9622044ce36e/pone.0191355.g010.jpg
https://cdn.ncbi.nlm.nih.gov/pmc/blobs/08d2/5841654/716891474e2b/pone.0191355.g011.jpg
https://cdn.ncbi.nlm.nih.gov/pmc/blobs/08d2/5841654/c7ef4a7bffcd/pone.0191355.g012.jpg
https://cdn.ncbi.nlm.nih.gov/pmc/blobs/08d2/5841654/84bb1664ad95/pone.0191355.g013.jpg
https://cdn.ncbi.nlm.nih.gov/pmc/blobs/08d2/5841654/6d818edbf0bb/pone.0191355.g014.jpg
https://cdn.ncbi.nlm.nih.gov/pmc/blobs/08d2/5841654/7c865042fda6/pone.0191355.g001.jpg
https://cdn.ncbi.nlm.nih.gov/pmc/blobs/08d2/5841654/205b6c650ff8/pone.0191355.g002.jpg
https://cdn.ncbi.nlm.nih.gov/pmc/blobs/08d2/5841654/396974f4c1fa/pone.0191355.g003.jpg
https://cdn.ncbi.nlm.nih.gov/pmc/blobs/08d2/5841654/85bee8de7759/pone.0191355.g004.jpg
https://cdn.ncbi.nlm.nih.gov/pmc/blobs/08d2/5841654/8f835cafa472/pone.0191355.g005.jpg
https://cdn.ncbi.nlm.nih.gov/pmc/blobs/08d2/5841654/051120986e70/pone.0191355.g006.jpg
https://cdn.ncbi.nlm.nih.gov/pmc/blobs/08d2/5841654/de503e6c103c/pone.0191355.g007.jpg
https://cdn.ncbi.nlm.nih.gov/pmc/blobs/08d2/5841654/a72a7036bcd0/pone.0191355.g008.jpg
https://cdn.ncbi.nlm.nih.gov/pmc/blobs/08d2/5841654/5a0d8fac95bd/pone.0191355.g009.jpg
https://cdn.ncbi.nlm.nih.gov/pmc/blobs/08d2/5841654/9622044ce36e/pone.0191355.g010.jpg
https://cdn.ncbi.nlm.nih.gov/pmc/blobs/08d2/5841654/716891474e2b/pone.0191355.g011.jpg
https://cdn.ncbi.nlm.nih.gov/pmc/blobs/08d2/5841654/c7ef4a7bffcd/pone.0191355.g012.jpg
https://cdn.ncbi.nlm.nih.gov/pmc/blobs/08d2/5841654/84bb1664ad95/pone.0191355.g013.jpg
https://cdn.ncbi.nlm.nih.gov/pmc/blobs/08d2/5841654/6d818edbf0bb/pone.0191355.g014.jpg

相似文献

1
Robust vehicle detection in different weather conditions: Using MIPM.在不同天气条件下的稳健车辆检测：使用 MIPM。
PLoS One. 2018 Mar 7;13(3):e0191355. doi: 10.1371/journal.pone.0191355. eCollection 2018.
2
Illumination normalization with time-dependent intrinsic images for video surveillance.用于视频监控的基于时间相关固有图像的光照归一化
IEEE Trans Pattern Anal Mach Intell. 2004 Oct;26(10):1336-47. doi: 10.1109/TPAMI.2004.86.
3
Improving vehicle tracking rate and speed estimation in dusty and snowy weather conditions with a vibrating camera.利用振动相机提高沙尘和雪天天气条件下的车辆跟踪率和速度估计
PLoS One. 2017 Dec 20;12(12):e0189145. doi: 10.1371/journal.pone.0189145. eCollection 2017.
4
Highly accurate moving object detection in variable bit rate video-based traffic monitoring systems.基于可变比特率视频的交通监控系统中的高精度移动物体检测。
IEEE Trans Neural Netw Learn Syst. 2013 Dec;24(12):1920-31. doi: 10.1109/TNNLS.2013.2270314.
5
A video-based real-time adaptive vehicle-counting system for urban roads.一种用于城市道路的基于视频的实时自适应车辆计数系统。
PLoS One. 2017 Nov 14;12(11):e0186098. doi: 10.1371/journal.pone.0186098. eCollection 2017.
6
Novel vehicle detection system based on stacked DoG kernel and AdaBoost.基于堆叠型 DOG 核和 AdaBoost 的新型车辆检测系统。
PLoS One. 2018 Mar 7;13(3):e0193733. doi: 10.1371/journal.pone.0193733. eCollection 2018.
7
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.
8
Unmanned aerial vehicle (UAV) images of road vehicles dataset.道路车辆数据集的无人机（UAV）图像
Data Brief. 2024 Mar 2;54:110264. doi: 10.1016/j.dib.2024.110264. eCollection 2024 Jun.
9
Adverse weather conditions and fatal motor vehicle crashes in the United States, 1994-2012.1994 - 2012年美国的恶劣天气状况与致命机动车撞车事故
Environ Health. 2016 Nov 8;15(1):104. doi: 10.1186/s12940-016-0189-x.
10
Robust ellipse detection based on hierarchical image pyramid and Hough transform.基于分层图像金字塔和霍夫变换的鲁棒椭圆检测
J Opt Soc Am A Opt Image Sci Vis. 2011 Apr 1;28(4):581-9. doi: 10.1364/JOSAA.28.000581.

引用本文的文献

1
A differential correction based shadow removal method for real-time monitoring.基于微分修正的实时监测阴影去除方法。
PLoS One. 2023 Feb 7;18(2):e0276284. doi: 10.1371/journal.pone.0276284. eCollection 2023.

本文引用的文献

1
Street Viewer: An Autonomous Vision Based Traffic Tracking System.街景视图：一种基于自主视觉的交通跟踪系统。
Sensors (Basel). 2016 Jun 3;16(6):813. doi: 10.3390/s16060813.
2
A vision based top-view transformation model for a vehicle parking assistant.基于视觉的车辆泊车辅助顶视图变换模型。
Sensors (Basel). 2012;12(4):4431-46. doi: 10.3390/s120404431. Epub 2012 Mar 30.
3
A self-organizing approach to background subtraction for visual surveillance applications.一种用于视觉监控应用的背景减除自组织方法。
IEEE Trans Image Process. 2008 Jul;17(7):1168-77. doi: 10.1109/TIP.2008.924285.
4
Inverse perspective mapping simplifies optical flow computation and obstacle detection.逆透视映射简化了光流计算和障碍物检测。
Biol Cybern. 1991;64(3):177-85. doi: 10.1007/BF00201978.