Communications of the ACM
Pedestrian Crossings Could Be Monitored
A multi-agent artificial intelligence system developed by UCLM researchers can detect whether the vehicles and pedestrians are moving "normally."
Credit: wikimedia.org
A surveillance system for monitoring whether cars and pedestrians are acting normally at crosswalks has been developed by researchers at Spain's University of Castilla-La Mancha (UCLM). "We have developed an intelligence surveillance software and related theoretical model in order to define 'normality' in any setting one wishes to monitor, such as a traffic scenario," says UCLM's David Vallejo.
Normal behavior is defined as moving when lights are green, and stopping and not crossing safety lines when they are red. The artificial intelligence system makes use of software agents to monitor pedestrian crossings. The team developed the monitoring tool to determine the effectiveness of its model. "In this way we are able to identify any drivers and pedestrians behaving abnormally, meaning the program could be used in order to penalize such behaviors," Vallejo says.
The researchers say the intelligent surveillance system also could be used to analyze behavior indoors, such as at museums, or to detect overcrowding.
From Plataforma SINC
View Full Article
Abstracts Copyright © 2009 Information Inc., Bethesda, Maryland, USA 
No entries found