A fall detection method, system, terminal and storage medium

Abstract

The present application relates to a fall detection method, system, terminal and storage medium. The method includes: extracting the combined acceleration and attitude angle data from the motion data of the monitored person; sampling and analyzing the combined acceleration during the falling process of the monitored person, and according to the waveform change rate of the combined acceleration during the falling process and The trough value identifies the fall-like action of the monitored person; identifies the fall direction of the fall-like action according to the attitude angle data, and determines whether the fall-like action is genuine according to the attitude angle limit threshold of each fall direction fall action. The application can quickly identify the fall action of the monitored person within the lead time of the fall warning, and perform real-time early warning of the fall action, with short warning time and high accuracy.

Description

technical field [0001] The present application belongs to the technical field of human fall detection, and in particular, relates to a fall detection method, system, terminal and storage medium. Background technique [0002] In order to maintain a delicate balance when walking or standing, the human body adjusts its posture through ankles, hips, trunk and striding strategies voluntarily. The control of this balance is affected by the motor system and the central nervous system. When the balance is broken and the body cannot be adjusted to maintain stability, or the balance ability and neurocognitive function are severely damaged and cannot be adjusted independently, the balance cannot be maintained and falls will occur. With age, the ability to balance gradually deteriorate, the risk of falling will also increase, and the body's ability to take remedial measures on its own after a fall also slows down. Hip fracture is a common serious injury in the elderly. More than 90% of...

AI Technical Summary

Problems solved by technology

[0007] In summary, the shortcomings of the fall warning algorithm are that it needs to rely on a high-performance computing platform and machine learning algorithm, the calculation process is complex, and the calculation amount is large. Generally, offline methods are used for research, and real-time monitoring and real-time monitoring of motion data cannot be performed. fall warning

Images