期刊文献+

基于视频处理技术的路网交通运行状态模糊识别 被引量:6

Traffic Condition Estimation for Highway Networks based on Video Processing Technology
原文传递
导出
摘要 利用视频图像处理技术,结合交通流状态估计技术,开展交通运行状态监测,为发布实时路况信息提供基础数据支撑。我国大多数高速公路建立了比较完善的视频监控系统,安装了密集的监控设备,在一定程度上实现了无缝监控。因此,从数据采集来看,利用视频数据进行交通流的检测与估计将比起传统的交通流断面检测更有数据基础。随着信号处理和模式识别的理论突破,视频图像分析技术已经在交通领域有所应用。为了解决实际应用需求,通过视频图像处理技术和交通流理论研究相结合,提出基于视频处理技术提取路段的空间交通流信息,直接进行高速公路交通运行状态估计。 By means of video image processing technology and combining with the traffic flow state estimation technique, traffic performance situation monitoring is conducted which can provide basic data support for the release of real-time traffic information. Video monitoring system with intensive cameras has been set up on most of the expressways in China, which has realized to a certain extent the seamless monitoring. Therefore, from data collection perspective, detection and estimation of traffic flow will be better than the traditional traffic flow detection. With the breakthrough in theory of signal processing and pattern recognition, video image analysis technique has been applied in the transportation field, which can realize vehicle count, in the smooth flow of traffic under the condition of speed calculation section detection function. In order to meet the demand of practical application, in this paper, through the combination of video image processing technology and the traffic flow theory study, the video processing technology is proposed to extract spatial traffic flow information based on road, and directly calculate highway traffic state.
出处 《公路》 北大核心 2016年第2期166-171,共6页 Highway
基金 中国博士后科学基金"基于视频图象处理的路网交通状态检测技术研究" 项目编号2014M560060
关键词 高速公路 交通运行状态估计 视频处理 expressway traffic condition estimation video processing
  • 相关文献

参考文献20

  • 1David Beymer. A Real-time Computer Vision System for Measuring Traffic Parameters[J]. IEEE Computer Society Conference on Computer Vision and Pattern Recognition, 1997:495-501.
  • 2Akio Yoneyama. Moving cast shadow elimination for rohust vehicle extraction based on 2D ioint vehicle/ shadow models[C]// Proceedings of the IEEE Confer- ence on Advanced Video and Signal Based Surveil lance, 2003.
  • 3Kais Siala. Moving shadow detection with support vec- tor domain description in the color ratios space[J].Proceedings of the 17th International Conference on Pattern Recognition, 2004, 4: 384-387.
  • 4Mlche[e L Jamrozik, Monson H Hayes. A Compressed Domain Video Object Segmentation System[C]// Im- age Processing. 2002.
  • 5Proceedings. International Con- ference on, 2002. Zhanhui Wang, Guizhong liu, Long I.iu. A Fast and Accurate Video Object Detection and Segmentation Method in the Compressed Domain[C]// IEEE Int. Conf. Neural Networks g>. Signal Processing, Nan- jing, China, 2003.
  • 6Tsai L W Hsieh J W,Fan K C. Vehicle detection using normalized color and edge map[J]. Image Processing, IEEE Transactions on,2007,16(3):850 864.
  • 7Techawatcharapaikul C, Kaewtrakulpong P, Siddhich- ai S. Outdoor vehicle and shadow segmentation bytemporal edge density information of adjacent frames[J]. IEEE, 2008,1 : 433-436.
  • 8Mo G, Zhang S. Vehicles detection in traffic flow[J]. Image Processing, IEEE, 2010,2 : 751 -754.
  • 9Wang C C R, Lien J J. Automatic vehicle detection using local features-a statistical approach[J].Intelligent Transportation Systems, IEEE,2008,9(1) : 83-96.
  • 10Haidarian Shahri H, Namata G, Navlakha S, Desh- pande A, Roussopoulos N. A graph-based approach to vehicle tracking in traffic camera video streams [C]//Proceedings of the 4th International Workshop on Data Management for Sensor Networks. 2007.

共引文献2

同被引文献35

引证文献6

二级引证文献12

相关作者

内容加载中请稍等...

相关机构

内容加载中请稍等...

相关主题

内容加载中请稍等...

浏览历史

内容加载中请稍等...
;
使用帮助 返回顶部