Sign In

Communications of the ACM

ACM TechNews

Self-Training Video Analytic Software Developed to Monitor Crowds

View as: Print Mobile App Share:

Curtin University of Technology (CUT) researchers have developed software that can detect unusual behavior in crowds, providing a new tool in the fight against crime and terrorism. The software learns typical behavior in busy environments and then reports on unusual activity. "It identifies events of interest which may never have been foreseen by the user, and can alert security officers to their occurrence in real time," says CUT professor Svetha Venkatesh, who led the research effort.

The software was tested in Belmont, Australia, for the past six months with encouraging results. "During this pilot program, the software was able to identify behavior such as loitering in a normal social and built environment, arson attempts, unusual-sized groups, incorrect vehicle traffic direction, and anti-social and illegal behavior," Venkatesh says. The software also is being adapted for use in video surveillance systems.

From Curtin News
View Full Article


Abstracts Copyright © 2010 Information Inc., Bethesda, Maryland, USA


No entries found

Sign In for Full Access
» Forgot Password? » Create an ACM Web Account