Apply Image Processing and Pattern Recognition Techniques to Develop the Video Surveillance System for Elder Falling Detection

Nowadays, all countries have to face the growing populations of elders. 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 happen. Traditional secure or video surveillance systems need someone to monitor a centralized screen continuously, or need an elder to wear sensors to detect accidental falling signals, which explicitly waste resources of care-staffs or cause inconvenience for an elder This is a two-year project. In this project, we will propose an intelligent video-surveillance system to detect falling accidents, and design an alarm mechanism for consequent emergency rescue services. The functions we deliver include: (1) The system will detect falling accidents via the image processing and pattern recognition techniques. Also, the system will automatically issue the alarm to care-staffs in case the accident occurs. (2) The care-staffs can monitor the surveillance video-streams via mobile devices in any places at anytime, without the limitation of the centralized monitor screen. (3) In case the system detects that a falling accident possibly occurs, the elder who falls will be identified, and his or her high-risk factors causing the falling will be recognized for later emergency processing. (4) The system supports multiple cameras, and the video streams will be executed concurrently like pipeline (5) The front-end cameras are implemented by embedded systems, which can filter unnecessary images from video streams. Also, when the care-staff takes the mission to rescue a falling elder, his handheld mobile device will setup an Ad-Hoc channel with the camera system for two-way video/audio communications. Through the implementation of this project, the crews can obtain the following trainings: (1) learn how to apply the IT techniques to implement an elder healthcare system, (2) learn how to apply the parallel programming technique to enhance software or hardware parallelism, (3) learn how to apply the distributed architecture to built up a large scale information system, and (4) learn the hardware/software co-design technique to design the embedded systems.

Project ID:PB9808-2401
External Project ID:NSC98-2221-E182-032