Human body fall-down preventing early warning method and human body fall-down preventing early warning device

Abstract

The invention relates to the technical field of human body fall-down detection and provides a human body fall-down preventing early warning method and a human body fall-down preventing early warning device. The method includes the steps that real-time detection is performed on the body posture of a monitored object, body posture information of the monitored object is collected, and detection data are obtained; fusion processing is performed on the detection data, and signal data are obtained after being processed; the processed signal data are compared with a set threshold, whether the monitored object inclines to fall down or not is judged, when the monitored object inclines to fall down, warning is given before the monitored object falls down; the body posture information of the monitored object includes triaxial acceleration information, triaxial angular velocity information and triaxial body angle of inclination information of the monitored object, the detection data are nine-axial inertia sensing data which are obtained through detection by an integrated chip, and collection of the body posture information, fusion processing of the detection data and the fall-down judgment of the monitored object are completed on the same circuit board. The human body fall-down preventing early warning method and the human body fall-down preventing early warning device achieve early warning before the human body falls down and are high in integration level.

Description

【Technical field】 [0001] The invention relates to the technical field of human body fall detection, in particular to a human body fall prevention early warning method and an early warning device. 【Background technique】 [0002] A fall is defined as a sudden, involuntary, involuntary change in position, such as falling onto the ground or a lower surface. According to statistics, about 424,000 deaths are directly related to falls every year in the world, and falls are the second leading cause of unintentional injury deaths in the world (after traffic accidents). Studies have shown that among the elderly over 65 years old, the proportion of one or more falls per year is as high as 1 / 3, and 20-30% of them will cause abrasions, hip fractures, head fractures, etc. during falls. Trauma, etc., and increase with age. In the United States, the total medical cost of falls exceeds $20 billion per year. There are currently about 130 million elderly people in my country, and about 20 m...

AI Technical Summary

Problems solved by technology

[0004] (1) Analysis based on video images: the real-time movement of objects is monitored by cameras, and its disadvantage is that it cannot guarantee the privacy of users

[0005] (2) Analysis based on audio signals: the fall event is judged by analyzing the frequency of the vibration caused by the impact, but its installation is more complicated and the capital investment is relatively large

[0008] (1) The early warning before the fall is not realized: the current common "fall alarm", the sensing module generally uses a single three-axis accelerometer, the measurement accuracy and data mode are limited, or the threshold algorithm used is not good enough , so it can only realize the alarm function after the human body falls and cannot realize the early warning before the fall, so it is impossible to realize the immediate anti-fall intervention measures and real-time protection

[0009] (2) It is not convenient to wear and use: some fall alarm devices adopt multi-module combination methods such as accelerometer module, attitude sensor module and pressure sensor module. Although it is beneficial to improve the accuracy of fall judgment in theory, multiple sensing modules must It will also increase the size and power consumption of the device, affecting the convenience of wearing and using

In addition, in theory, the closer the sensor module is to the human body, the more accurate the measured sensing data will be. In practical applications, whether the combination of multiple modules can really effectively improve the accuracy of fall judgment remains to be further verified.

[0010] (3) The accuracy of fall judgment is not ideal: most of the current fall judgment devices mainly rely on acceleration to judge the occurrence of fall events, but the daily movement of the human body is very complicated, and falls are usually accidental behaviors that occur in an instant (1-2 Seconds), the reliability of predicting falls by relying on less or a single human body movement and posture information is not high. Misjudgment will inevitably bring inconvenience to the wearer

Images