Did you know that fall is one of the leading causes of fatal and non-fatal injuries among the elderly community? Timely treatment is critical where immediate treatment may reduce the risk of serious injuries.
SEGi College Subang Jaya student, Koh Zheng Long, enrolled in the BA (Hons) Computing Programme in collaboration with University of Greenwich (under the supervision of Lecturer Ms Hazlina) has developed an image-based fall detection system in monitoring elderly fall event to solve the problem! This project was, later on, is awarded a silver medal in Virtual Innovation Competition 2020 (VIC2020)!
In this project, the image-based fall detection system integrates two algorithms: “You Only Look Once” (YOLO) object detection algorithm and the Image-based Fall Detection system algorithm to detect fall events. The system will track the person in the video frame using the object detection algorithm, followed by the fall detection algorithm to detect the person’s height. This will ensure the fall events detection is done as immediate and accurate as possible to notify the caregivers.
The system was evaluated with different scenarios of use cases and conditions. The result shows the system managed to detect fall events with an accuracy of 92% under daylight and 60% under the low light condition. The quick fall detection and notification of system able to ensure the safety of the elderly were well monitored and timely treatment can take place when fall events were detected by the system.
