TY - GEN
T1 - Speedup multi-camera video-surveillance systems for elder falling detection
AU - Shieh, Wann Yun
AU - Lin, Ting Yu
AU - Huang, Ju Chin
PY - 2011
Y1 - 2011
N2 - For most elders, unpredictable falling accidents may occur at the corner of stairs or a long corridor due to body functional decay. If we delay to rescue a falling elder who is likely fainting, more serious consequent injury may occur. Traditional secure or video surveillance systems need care staffs to monitor a centralized screen continuously, or need an elder to wear sensors to detect accidental falling signals, which explicitly require higher human resource or cause inconvenience for elders. In this work, we propose an automatic falling-detection algorithm and implement this algorithm in a multi-camera video surveillance system. The algorithm uses each single camera to fetch the images from the regions required to monitor. It then uses a falling-pattern recognition approach to determine if an accidental falling has occurred. If yes, system will send short messages to someone needs to notice. The algorithm has been implemented in a DSP-based evaluation board for functionality proof. The results show that the throughput can be improved by about 2.12 times for a four-camera surveillance system.
AB - For most elders, unpredictable falling accidents may occur at the corner of stairs or a long corridor due to body functional decay. If we delay to rescue a falling elder who is likely fainting, more serious consequent injury may occur. Traditional secure or video surveillance systems need care staffs to monitor a centralized screen continuously, or need an elder to wear sensors to detect accidental falling signals, which explicitly require higher human resource or cause inconvenience for elders. In this work, we propose an automatic falling-detection algorithm and implement this algorithm in a multi-camera video surveillance system. The algorithm uses each single camera to fetch the images from the regions required to monitor. It then uses a falling-pattern recognition approach to determine if an accidental falling has occurred. If yes, system will send short messages to someone needs to notice. The algorithm has been implemented in a DSP-based evaluation board for functionality proof. The results show that the throughput can be improved by about 2.12 times for a four-camera surveillance system.
UR - http://www.scopus.com/inward/record.url?scp=79952496671&partnerID=8YFLogxK
U2 - 10.3850/978-981-08-7615-9-RE04
DO - 10.3850/978-981-08-7615-9-RE04
M3 - 会议稿件
AN - SCOPUS:79952496671
SN - 9789810876159
T3 - ISOB 2011 - Proceedings of the 1st International Symposium ISOB 2011 - Proceedings of the 1st International Symposium on Bioengineering
SP - 188
EP - 195
BT - ISOB 2011 - Proceedings of the 1st International Symposium on Bioengineering
T2 - 1st International Symposium on Bioengineering, ISOB 2011
Y2 - 19 January 2011 through 19 January 2011
ER -