The project -which aims to prevent, detect and predict acts of terrorism - is partly funded by a A$634,000 (US$485,000) grant from the Department of Prime Minister and Cabinet.

Dubbed the SAFE (Smart Applications for Emergencies) project, the team has already developed a proposed specification for a Tsunami-type warning language used to characterize and disseminate threat levels.

Chris Scott, research director of NICTA's Queensland laboratory, said the focus of the project is to provide as much information to front-line decision makers as possible when responding to an incident. A lot of the work so far has gone into "hardening up" algorithms used for facial recognition.

"Identifying a particular person is one thing but we are focusing on looking at unusual behavior in an open environment," Scott said.

"There is technology available to alert people when, say a briefcase is left unattended in a public place, but we are working on algorithms not just to search for a person based on facial recognition but to analyze the level of threat based on their actual behavior, to gather preliminary information to see if anything unusual is happening which would increase the probability of detecting an actual threat.