A Customized Human Fall Detection System Using Omni-Camera Images and Personal Information

Abstract

This paper proposes a new approach to detect the fall of the elderly. The detection system uses a MapCam (omni-camera) to capture images and performs image processing over the images. The personal information of each individual is considered in the processing task. The MapCam is used to capture 360deg scenes simultaneously and eliminate any blind viewing zone. The personal information is combined into the system and makes it smarter by customizing the system for each individual. With personal information such as height, weight, and electronic health history, we can adjust the detection sensitivity on a case by case basis to reduce unnecessary alarms, and put more attention on the elderly with special diseases or conditions. We perform a simple experiment to verify the feasibility of our approach. The experimental results show that the successful rates of fall detections with and without personal information are 79.8% and 68%, respectively. The Kappa value of the system is 0.798 which is higher than 0.75, showing that we have a reliable system