Paper Info
Title
A real-time and color-based computer vision for traffic monitoring system
Abstract
The work presents a vision-based traffic monitoring system using the analysis of color image sequences of traffic scenes recorded by a stationary camera mounted on a tall building or pedestrian crossing bridge near a traffic light. The system algorithms consist of building the initial background, segmenting the foreground, shadow separation, vehicle location, vehicle tracking, and background updating. The YCrCb color space is adopted. It provides us an accurate and robust device for foreground and shadow detection. Our system can accurately locate and track vehicles from image sequences. It is fast enough to operate in real time, insensitive to lighting and weather conditions, and only requires a minimal amount of initialization. Experimental results from town scenes demonstrate the effectiveness of our system.
Year
DOI
Venue
2004
10.1109/ICME.2004.1394685
ICME
Keywords
Field
DocType
monitoring,ycrcb color space,image segmentation,vehicle location,traffic scenes,color image sequences,shadow separation,optical tracking,image sequences,vehicle tracking,vision-based traffic monitoring system,object detection,color-based computer vision system,real-time traffic monitoring system,weather conditions,computer vision,initial background construction,background updating,road traffic,lighting conditions,image colour analysis,foreground segmentation,image analysis,color image,real time systems,color space,layout,real time
Computer vision,Object detection,Shadow,Color space,Computer science,Pedestrian crossing,Image segmentation,Artificial intelligence,Initialization,Vehicle tracking system,Color image
Conference
Volume
ISBN
Citations 
3
0-7803-8603-5
4
PageRank 
References 
Authors
0.52
5
2
Name
Order
Citations
PageRank
Mao-chi Huang140.52
Shwu-huey Yen2429.07