Title :
Motion-based machine vision techniques for the management of large crowds
Author :
Boghossian, B.A. ; Velastin, S.A.
Author_Institution :
Dept. of Electron. & Electr. Eng., King´´s Coll., London, UK
Abstract :
The early detection and the prevention of crowd-related emergencies are the main aims of large crowd management Closed Circuit Television (CCTV) systems. However, environmental and psychological factors play a role in degrading the performance of CCTV operators, hence causing a threat to crowd safety. We present computer vision techniques that estimate the paths and directions of crowd flows in CCTV images and improve the perception of scene dynamics by offering online illustrations. Moreover, we present motion-based algorithms to detect crowd-related emergencies and assist CCTV operators in ensuring crowd safety
Keywords :
closed circuit television; computer vision; human factors; safety; television applications; CCTV images; closed circuit television systems; computer vision techniques; crowd flows; crowd safety; crowd-related emergencies; large crowd management; motion-based algorithms; motion-based machine vision techniques; scene dynamics perception improvement; Circuits; Computer vision; Degradation; Disaster management; Layout; Machine vision; Motion detection; Psychology; Safety; TV;
Conference_Titel :
Electronics, Circuits and Systems, 1999. Proceedings of ICECS '99. The 6th IEEE International Conference on
Conference_Location :
Pafos
Print_ISBN :
0-7803-5682-9
DOI :
10.1109/ICECS.1999.813392
