Advanced Surveillance

HomeResearchPublicationsActivitiesCollaboratorsPeople[PhD and Internship Projects]DatasetsContact

The Advanced Surveillance team is developing faster and more robust methods to analyse visual information.

Our team is applying advanced Computer Vision and Pattern Recognition techniques to develop algorithms and advanced embedded systems to address video forensics and surveillance needs.  Two grants by the Department of Prime Minister and Cabinet in 2006 and 2009 awarded over $1.5 million to our research and development of these security solutions. The project has also attracted national and international interest from various security agencies. This on-going work is currently being evaluated at several sites in Australia and overseas.




International usage and interest in surveillance of public spaces is growing at an unprecedented pace in response to crime and global terrorism. However, whilst it is relatively easy, albeit expensive, to install increasing numbers of cameras, it is quite another issue to adequately monitor the video feeds with security personnel. 

A pressing need is emerging to monitor all surveillance cameras in an attempt to detect events and persons-of-interest. The problem is that human monitoring requires a large number of personnel, resulting in high ongoing costs and questionable reliability as the attention span of humans decreases rapidly when performing such mundane tasks. A solution may be found in advanced computer surveillance systems to monitor all video feeds and deliver alerts to human responders for triage -- a well-designed computer system is never caught "off guard".

What this Research will Achieve

The NICTA Advanced Surveillance team is conducting research to develop advanced computer surveillance methods which meet these pressing needs.

One key outcome so far is a fast and robust CCTV-based face matching and search framework, which can be used to detect persons of interest.  Unlike many existing solutions, it is designed to work with low-resolution images of 'uncooperative' subjects (people who are not posing for the camera).  It is robust to variations in environmental conditions, quality and pose.  Additionally, it has a comparatively small computational footprint and can be parallelised, thus making it easily scalable.

As it is often difficult to acquire good face images, this technology is being combined with further research in person tracking so that a better estimate of identity can be inferred through combining several CCTV-based biometric techniques over time.

Who Will Benefit

Our work aims to benefit people in Australia and potentially worldwide by providing  better security through non-intrusive, intelligent surveillance. This tool can assist in forensic examination of video after an incident or potentially proactively alert the authorities at the outset.  The techniques can also be applied outside of security and surveillance, such as facial recognition for photo-tagging in consumer products.

For more details about our group please look at our research, people, related activities, collaborators, and publications.  Please contact us regarding any feedback or inquiries.