Ultra-wideband radar-based old person tumble detection method

Abstract

The invention relates to an ultra-wideband radar-based old person tumble detection method and belongs to the field of radar target detection signal processing. According to the ultra-wideband radar-based old person tumble detection method, on the basis of the time, Doppler frequency and distance change characteristics of the radar echoes of the different actions of a human body, a multi-domain peak point tracking method is used to replace a traditional time-frequency analysis method; on the basis of the acquisition of the time characteristics and Doppler frequency characteristics of the actions of the human body, the distance characteristic information of the actions of the human body is obtained; and therefore, the influence of micro-Doppler frequency spectra on a result which is caused by the swinging of the limbs of the human body during the movement of the human body is avoided, and the realization of more accurate action characteristic analysis results can be benefitted. Compared with the prior art, the method disclosed by the invention can reserve time and frequency information obtained by a traditional time-frequency analysis method, realize the accurate detection of the action distance information of the human body and improve the recognition accuracy of the falling action of the human body.

Description

technical field [0001] The invention relates to a fall detection method for the elderly based on ultra-wideband radar, belonging to the field of radar target detection signal processing; Background technique [0002] Researchers at home and abroad have conducted a lot of research on the problem of human fall motion recognition, and obtained a series of valuable research results; according to different application scenarios and data acquisition methods, there are mainly human body fall motion recognition based on wearable sensors, There are three types of methods: human body fall action recognition based on video image information, and human body fall action recognition based on radar sensors; the first type of method monitors and recognizes human body fall action through a variety of micro sensors carried on the body, and the latter two methods use cameras, radar and other non-contact methods to obtain human body movement information; [0003] The fall motion recognition te...

AI Technical Summary

Problems solved by technology

[0010] The purpose of the present invention is to reduce the false alarm rate of existing detection methods, and provide a method for detecting falls of the elderly based on ultra-wideband radar; The algorithm cannot get the technical defect of distance information to achieve more accurate fall recognition results;

Images