Title :
Auto-detection of unusual events in metro stations via security cameras
Author :
Dagli, M.A. ; Erdem, Cigdem Eroglu
Author_Institution :
Elektrik-Elektron. Muhendisligi Bolumu, Bahcesehir Univ., İstanbul, Turkey
Abstract :
Due to the excess of the security cameras on the metro stations; staff is unable to track all of the cameras at same time. So that he may miss many of the important events. In order to detect these events automatically and generate warnings to the staff for preventing events before dangerous results occurred is the main goal of the research. With this study functions like train detection, yellow line intrusion, fallen passenger detection, restricted area violation and open door detection are realized. According to the 200 hours tests system reaches more than 99% success rate about detecting events.
Keywords :
closed circuit television; object detection; railway rolling stock; railway safety; security; video cameras; video surveillance; fallen passenger detection; metro station; open door detection; restricted area violation; security camera; train detection; unusual event autodetection; yellow line intrusion; Adaptation models; Cameras; Conferences; Image processing; Rail transportation; Security; US Department of Defense; metro; train detection; unusual event detection;
Conference_Titel :
Signal Processing and Communications Applications Conference (SIU), 2013 21st
Conference_Location :
Haspolat
Print_ISBN :
978-1-4673-5562-9
Electronic_ISBN :
978-1-4673-5561-2
DOI :
10.1109/SIU.2013.6531414