Activity Recognition for Indoor Fall Detection Using Convolutional Neural Network.

Abstract

Falls are a major health problem in the elderly population. Therefore, a dedicated monitoring system is highly desirable to improve independent living. This paper presents a video based fall detection system in an indoor environment using convolution neural network. Identifying human poses is important in detecting fall events as specific ”change of pose” defines a fall. Knowledge of series of poses is a key detecting fall or non-fall events. A lying pose which may be considered as an after-fall pose is different from other normal activities such as standing, sitting, bending or crawling.This paper uses Convolutional Neural Networks (CNN) to recognise different poses. Using Kinect, the following image combinations are explored: RGB, Depth, RGB-D and background subtracted RGBD. We have constructed our own dataset by recording different activities performed by different people in different indoor set-ups. Our results suggest that combining background subtracted RGB and Depth with CNN gives the best possible solution for monitoring indoor video based falls.