期刊文献+
共找到1篇文章
< 1 >
每页显示 20 50 100
Real-time traffic information extraction based on compressed video with interframe motion vector
1
作者 黄庆明 王聪 《Journal of Harbin Institute of Technology(New Series)》 EI CAS 2003年第3期284-289,共6页
Extraction of traffic information from image or video sequence is a hot research topic in intelligenttransportation system and computer vision. A real-time traffic information extraction method based on com-pressed vi... Extraction of traffic information from image or video sequence is a hot research topic in intelligenttransportation system and computer vision. A real-time traffic information extraction method based on com-pressed video with interframe motion vectors for speed, density and flow detection, has been proposed for ex-traction of traffic information under fixed camera setting and well-defined environment. The motion vectors arefirst separated from the compressed video streams, and then filtered to eliminate incorrect and noisy vectors u-sing the well-defined environmental knowledge. By applying the projective transform and using the filtered mo-tion vectors, speed can be calculated from motion vector statistics, density can be estimated using the motionvector occupancy, and flow can be detected using the combination of speed and density. The embodiment of aprototype system for sky camera traffic monitoring using the MPEG video has been implemented, and experi-mental results proved the effectiveness of the method proposed. 展开更多
关键词 extraction of traffic information Interframe motion vector compressed video stream
下载PDF
上一页 1 下一页 到第
使用帮助 返回顶部