Abstract:
Video surveillance in public places has witnessed tremendous growth over the last decade
with applications based on closed-circuit security systems to IP cameras. Among the
various aspects of surveillance, automatic detection and classification of abandoned objects
could serve as a valuable application reducing potential threats to public safety. The aim
of this project is to detect the unattended abandoned objects from videos of public places.
The developed system relies on background subtraction from the video stream and segment
out foreground objects. Humans are then detected from the foreground objects and are
distinguished from the static foreground objects. The owner of a static baggage object
is assumed to be the nearest human attending it. The owner is tracked and if abandons
the baggage for more than a predefined time the baggage is considered abandoned and an
alarm is generated. The proposed system is evaluated on videos from the benchmark PETS
database as well as a custom developed database and realized promising performances.
