Title :
Automated surveillance and detection of foreign stationary objects
Author :
Kiewiet, N.G. ; Roodt, Y. ; Roos, H. ; Clarke, W.A.
Author_Institution :
HyperVision Res. Lab., Univ. of Johannesburg, Johannesburg, South Africa
Abstract :
CCTV systems are frequently monitored manually by a human observer. This human observer is typically responsible for dealing with tens or hundreds of cameras at a time. Potential security threats may easily be missed by the system´s human operators due to fatigue or being overwhelmed by the amount of change in the images. The timely detection of security threats is an important attribute for any security system. A robust algorithm for detecting potential threats from a surveillance video is presented.
Keywords :
closed circuit television; object detection; video signal processing; video surveillance; CCTV system; closed circuit television; foreign stationary object; object detection; object surveillance; security system; security threat detection; video surveillance; Detectors; Graphics processing unit; Histograms; Lighting; Noise; Noise measurement; Security; GPGPU; illumination invariant; noise rejection; video surveillance;
Conference_Titel :
AFRICON, 2011
Conference_Location :
Livingstone
Print_ISBN :
978-1-61284-992-8
DOI :
10.1109/AFRCON.2011.6072153