Automatic real-time detection of infiltrated objects for security of airports and train stations
Funding: 2006: $117,000
Project Member(s): Piccardi, M.
Funding or Partner Organisation: Australian Research Council (ARC Linkage Projects)
iOmniscient Pty Limited
Australian Research Council (Other funds for ARC projects)
Start year: 2006
Summary: Infiltrated objects represent a very high security threat in critical areas such as airports and train stations. In order to neutralise such a threat, this project will develop computer vision-based technologies capable of detecting infiltrated objects in sensitive areas in real time and analysing the movements of their original carriers in the nearby areas. Objects and movements will be automatically classified as potentially dangerous or not and attention raised accordingly. The technologies will be based on new advanced automatic people tracking techniques and occlusion-robust classifiers. The potential of application is huge extending beyond airports and stations to any public areas.
Otoom, AF, Gunes, H & Piccardi, M 2008, 'Feature extraction techniques for abandoned object classification in video surveillance', Proceedings of 2008 IEEE International Conference on Image Processing - ICIP 2008, IEEE International Conference on Image Processing, IEEE, San Diego, CA, USA, pp. 1368-1371.
View/Download from: UTS OPUS or Publisher's site
Keywords: Visual surveillance, Security, Computer vision, Public security, Image analysis, Terrorism prevention,
FOR Codes: Causes and Prevention of Crime, Pattern Recognition and Data Mining, Property Services (incl. Security), Computer Vision