Biometrics in Surveillance Videos

Slides (pdf)  Size: 20.1MB

Abstract

There has been tremendous progress in face recognition since the introduction of deep learning techniques which have achieved stunningly high accuracies on large database studies. It appears that we have reached a point of diminishing returns in terms of database accuracy and moving from 6 million person databases to 12 million person databases and beyond is unlikely to yield significant further improvement. Unfortunately real-world video face recognition accuracy is much weaker than is indicated by these database studies, so we’ll discuss some of the remaining barriers to ideal surveillance performance. In particular we want to move beyond chokepoint face harvesting to recognizing people in a milling crowd or at a cocktail party. In this talk we will examine state of the art face recognition and detection performance and describe important practical bottlenecks and corner cases that require additional research in the biometrics community.

Biography

Brian C. Lovell was born in Brisbane, Australia in 1960. He received the BE in electrical engineering in 1982, the BSc in computer science in 1983, and the PhD in signal processing in 1991: all from the University of Queensland (UQ). Professor Lovell is Director of the Advanced Surveillance Group in the School of ITEE, UQ. He was President of the International Association for Pattern Recognition (IAPR) [2008-2010], and is Fellow of the IAPR, Senior Member of the IEEE, and voting member for Australia on the Governing Board of the IAPR. He was General Co-Chair of the International Conference on Biometrics (ICB2018) Gold Coast, Australia and was Program Co-Chair of the International Conference of Pattern Recognition (ICPR2016) in Cancún Mexico, and was General Co-Chair of the IEEE International Conference on Image Processing in Melbourne, 2013. His interests include non-cooperative Face Recognition, Surveillance, robust face detection, Biometrics, and Pattern Recognition. His work in biometrics and surveillance has won numerous international awards including the prestigious Best CCTV System at IFSEC2011, Birmingham for Face in the Crowd recognition. He also won the Asia Pacific ICT Trophy for Best R&D in the Asia Pacific Region in Phuket, Thailand in 2011.

Brian Lovell
University of Queensland, Australia