Mobile Robot Aided Silhouette Imaging and Robust Body Pose Recognition for Elderly-Fall Detection

Abstract

This article introduces a mobile infrared silhouette imaging and sparse representation-based pose recognition for building an elderly-fall detection system. The proposed imaging paradigm exploits the novel use of the pyroelectric infrared (PIR) sensor in pursuit of body silhouette imaging. A mobile robot carrying a vertical column of multi-PIR detectors is organized for the silhouette acquisition. Then we express the fall detection problem in silhouette image-based pose recognition. For the pose recognition, we use a robust sparse representation-based method for fall detection. The normal and fall poses are sparsely represented in the basis space spanned by the combinations of a pose training template and an error template. The 1 norm minimizations with linear programming (LP) and orthogonal matching pursuit (OMP) are used for finding the sparsest solution, and the entity with the largest amplitude encodes the class of the testing sample. The application of the proposed sensing paradigm to fall detection is addressed in the context of three scenarios, including: ideal non-obstruction, simulated random pixel obstruction and simulated random block obstruction. Experimental studies are conducted to validate the effectiveness of the proposed method for nursing and homeland healthcare.

Care Personnel's Attitudes and Fears Toward Care Robots in Elderly Care: A Comparison of Data from the Care Personnel in Finland and Japan

“…Previous research on social robots has focused particularly on robot seals (Jöranson et al., ; Moley et al., ; Robinson, MacDonald, & Kerse, ), whose purpose is to replace interaction, intimacy, and touch in the care of a patient. Also, research on interactive solutions using sensors to collect data has focused on monitoring falls (Liu & Liu, ), sleep (Kogure, Shirakawa, Shimokawa, & Hosokawa, ), and vital functions (Koroda et al., ).…”

Robotics Perception and Control: Key Technologies and Applications

“…In terms of human detection and tracking, Liu et al [90] developed a mobile robotassisted system for detecting elderly falls using Pyroelectric Infrared (PIR) sensors for body contour imaging and posture recognition. This innovative approach uses PIR sensors not just for motion detection but to create detailed contour images for posture analysis, thus employing sparse representation techniques for fall detection.…”

“…Infrared Sensors [85][86][87][89][90][91][92][93] Strong real-time performance, compact, low power consumption, low cost, flexible use, high accuracy, and unaffected by lighting conditions.…”

Review and Analysis of Patients’ Body Language From an Artificial Intelligence Perspective

“…Fall events are detected with an average accuracy of 98.2%, whereas run events were successfully detected at 96.72%. Study [66] introduces a low-cost, non-invasive motion sensing method, mobile infrared silhouette imaging, and sparse representation-based pose recognition for building an elderly-fall detection system. The pyroelectric infrared (PIR) sensor array is used for elderly pose acquisition, and robust fall detection is obtained via sparse representation.…”