iCetana | A²I² Artificial Intelligence at Deakin

Challenge

When examining video from hundreds of cameras, how should we select which camera an operator should prioritise?

Impact

We discovered new techniques that allow camera operators to focus on the one per cent of events that indicate possible security risks.

Awards

Broadband Innovation Award, Tech23, 2010
WA Innovator of the Year Award, 2011

Weblinks

iCetana

Security cameras help keep us safe, but they produce hours of benign footage for operators to sift through.

iCetana detects potential security threats in large data sets from video surveillance footage. Algorithms that we developed drive iCetana’s innovative anomaly detection software.

The software uses ideas from compressed sensing to enable simultaneous surveillance of many cameras deployed in all sorts of environments.

A local city council first used iCetana to detect anti-social behaviour and traffic violations. It’s now being used around the world.

Solution

We discovered new techniques that allow camera operators to focus on the one per cent of events that indicate possible security risks.

To deal with the problem of data deluge, we formulated a novel theoretical solution based on compressed sensing, a powerful paradigm that takes a ‘random projection’ of a signal by multiplying the original signal by a random matrix to derive a much smaller ‘compressed sensed signal’.

Our algorithms power innovative anomaly detection software called iCetana, which is now used in video surveillance worldwide.

Learn more about iCetana