Real-Time Action Recognition System for Elderly People Using Stereo Depth Camera

Abstract

Smart technologies are necessary for ambient assisted living (AAL) to help family members, caregivers, and health-care professionals in providing care for elderly people independently. Among these technologies, the current work is proposed as a computer vision-based solution that can monitor the elderly by recognizing actions using a stereo depth camera. In this work, we introduce a system that fuses together feature extraction methods from previous works in a novel combination of action recognition. Using depth frame sequences provided by the depth camera, the system localizes people by extracting different regions of interest (ROI) from UV-disparity maps. As for feature vectors, the spatial-temporal features of two action representation maps (depth motion appearance (DMA) and depth motion history (DMH) with a histogram of oriented gradients (HOG) descriptor) are used in combination with the distance-based features, and fused together with the automatic rounding method for action recognition of continuous long frame sequences. The experimental results are tested using random frame sequences from a dataset that was collected at an elder care center, demonstrating that the proposed system can detect various actions in real-time with reasonable recognition rates, regardless of the length of the image sequences.

An Efficient Feature Selection Method for Video-Based Activity Recognition Systems

“…Moreover, we will employ the proposed technique in healthcare domains in order to resolve the privacy concern. Existing works [42](%) [43] (%) [44] (%) [45] (%) [46] (%) [47] (%) [48] (%) [49]…”

Design of Sports Rehabilitation Training System Based on EEMD Algorithm

“…On one hand, it is necessary to grasp the physical state of the elderly in real time, so as to make timely prevention and treatment measures according to the changes of their physical signs [ 2 , 3 ]. On the other hand, there is bound to be a large number of patients with diseases in the elderly, especially those with severe and chronic diseases, which requires real-time monitoring of the health status and rehabilitation of the elderly [ 4 ].…”

Mathematical Criteria for a Priori Performance Estimation of Activities of Daily Living Recognition

“…To monitor health conditions at home, sensors must be deployed to acquire data such as physiological signals, environmental variables or the movements of the inhabitants. Various technologies can be used [ 2 , 3 , 4 ]: vision systems (cameras) [ 5 , 6 , 7 , 8 ], wearable devices (with on-board accelerometers, pedometers, heart rate sensors…) [ 9 , 10 , 11 , 12 , 13 ], binary sensors (motion detectors, door/window sensors, pressure sensors, etc.) [ 14 , 15 , 16 , 17 , 18 , 19 ], which can be combined into larger devices (smart floors with pressure sensors to detect falls) [ 20 , 21 ], or sensors that can be interpreted as n-ary with thresholds (water flow sensors, electricity consumption sensors, etc.)…”