Summary
International Conference on Emerging Technologies for Communications
2023
Session Number:P1
Session:
Number:P1-3
Prototype Design of a Human Activity Recognition and Fall Prediction System Based on Infrared Array Sensors.
NISHAT TASNIM NEWAZ, Eisuke Hanada,
pp.-
Publication Date:2023/11/29
Online ISSN:2188-5079
Summary:
The development of a prototype system for human activity recognition and fall prediction is crucial to addressing the safety concerns of elderly persons. Utilizing surveillance cameras and computer vision to detect falls presents an ideal alternative to existing systems, ensuring protection for anyone within the camera's monitoring scope. However, privacy concerns regarding the use of surveillance cameras for this application remain a significant consideration. In this paper, we present the design of our prototype for such a system that utilizes an infrared array sensor to capture relevant data and that does preliminary mapping of multiple interpolations. The system compares the actual image and the mapped image, providing results based on the person's body temperature. When a person is detected, the system can determine their posture, distinguishing between sitting, standing, lying, or falling.