Speedup multi-camera video-surveillance systems for elder falling detection

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.