Abstract
Detect moving object from a video sequence is a fundamental and critical task in many computer vision application. In video surveillance of high-speed railway transport hub, detection of moving object aims to accurately and timely find congestion of passenger flow and other dangerous behaviors in hub. With comparative study on existing methods of moving object detection, a modified background model was proposed in this paper. The model was integrated existing background model with gray division and Dempster-Shafer theory to improve processing speed and accuracy of background modeling. Availability and efficiency of modified model was proved by experiment on data from highspeed railway transport hub video surveillance.
Sign-in/Register to access full text options 
Free) 
Talk to us
Join us for a 30 min session where you can share your feedback and ask us any queries you have
Schedule a call
