Algorithms to calculate unusual behavior

National ICT (Information and Communication Technology) Australia (NICTA) scientists are developing advanced surveillance technologies including software algorithms to track “inappropriate behavior” in public places.

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.

“Facial recognition algorithms have been around for a while, but one problem with existing algorithms is they depend on the geometry of the face to compare with faces stored in memory. We are producing quasi-face images from side on and more algorithms [to cope with] poor lighting conditions as simple facial recognition software has not solved these problems and this is what we are hardening up for real-world applications.”

Scott said NICTA has been working with Queensland Transport and Queensland Rail, which has about 6000 surveillance cameras on their networks.

“We were looking at the data produced by those, processing the information to characterize specific threats, managing resource distribution and allocation; but the sole focus of this project is for response and recovery from man-made and natural disasters and events,” Scott said.

He said the purpose of the project is to get away from the problem of individuals looking at monitors, which frequently induce sleep, and 90 percent of the time nothing happens at all. The algorithms would filter out uninteresting information and potentially characterize behavior.

Eventually satellite images, photographs of buildings and images of surveillance cameras could be integrated on one image with real-time data integrated with historical images for real-time mapping.

Would you recommend this article?


Thanks for taking the time to let us know what you think of this article!
We'd love to hear your opinion about this or any other story you read in our publication.

Jim Love, Chief Content Officer, IT World Canada

Featured Download

Featured Articles

Cybersecurity in 2024: Priorities and challenges for Canadian organizations 

By Derek Manky As predictions for 2024 point to the continued expansion...

Survey shows generative AI is a top priority for Canadian corporate leaders.

Leaders are devoting significant budget to generative AI for 2024 Canadian corporate...

Related Tech News

Tech Jobs

Our experienced team of journalists and bloggers bring you engaging in-depth interviews, videos and content targeted to IT professionals and line-of-business executives.

Tech Companies Hiring Right Now