Research carried out by University of Southampton Masters students has identified the most effective ways of identifying individuals in public spaces.
In two separate research projects, two final year students of the MEng Master of Engineering Degree within the School of Electronics & Computer Science (ECS), Sarah Deane and Matthew Sharifi, who will graduate this month, addressed the growing importance of being able to identify individuals within a given environment, both from a security and marketing perspective.
Sarah’s project, A Comparison of Background Subtraction Techniques, highlighted the fact that most current Closed-Circuit Television (CCTV) footage fails to give a clear image of an object because it is often obscured by background information.
Having reviewed several existing methods for taking away the background information and not finding any of them particularly effective, Sarah used several of these theories, combining them into her own implementation.
‘I found that background subtraction, although being simply defined as a difference between the background image without objects of interest and an observed image, has many difficult issues to overcome,’ said Sarah. ‘It was apparent that a simple subtraction algorithm was needed to allow the high computational efficiency that is required by CCTV applications.’
Matthew’s project, Audience Recognition in Public Spaces compared the effectiveness of face recognition and Bluetooth as a means of recognising individuals within a public space.
He found that a camera positioned in a reception area was able to detect all of the frontal faces that came into contact with the system, whereas Bluetooth only managed to recognise 8.33% of those who passed and was dependant on these individuals carrying Bluetooth devices.
The results have inspired Matthew to conduct a much larger video dataset, so that he can carry out further experiments.
‘Having observed the advantages and disadvantages of both Bluetooth and face recognition, it would be interesting to combine the two techniques into a multi-modal identification technology which could couple the ubiquity of face recognition with the recognition accuracy of Bluetooth,’ he said.
Cite This Page: