Event detection in the parking lot

Hajar Sadeghi Sokeh (RSISE)

COMPUTER VISION AND ROBOTICS SERIES PhD monitoring

DATE: 2011-10-13
TIME: 15:15:00 - 15:45:00
LOCATION: RSISE Seminar Room, ground floor, building 115, cnr. North and Daley Roads, ANU
CONTACT: JavaScript must be enabled to display this email address.

ABSTRACT:
These days what is needed is a continuous 24-hour monitoring system to recognize some interested events and behaviors or alert a suspicious event while is still time to prevent that, in the other word a system to help us have an efficient and safe environment. So, these systems have to be able to detect objects and their movements in an environment to recognize some interested events without any human assistance. The ambitious goal is that these systems could act without any need to oversee with humans and even behave more effective than them, to reach this goal we need to use computer vision, pattern recognition and artificial intelligence technologies. In order to understand what happens in the scene, the majority of these systems have a low level image processing techniques to detect objects of interest feeding into tracking algorithms and the result in turn is fed into higher level behavior analysis modules. In this work, we want to design an automated system that can detect all events occurred in the parking lot or even sometimes predict them.