Human body falling intelligent detection method and system, and information data processing terminal

Abstract

The invention belongs to the technical field of wireless communication, and discloses an intelligent detection method and system for human body tumble and an information data processing terminal. The intelligent detection method for human body tumble comprises the steps: acquiring the original CSI data through WIFI equipment; extracting a dynamic path related to human body motion, performing joint estimation on dynamic path information, and calculating a human body motion track and a motion speed; judging and extracting a time window of the falling action according to the current human body movement speed and a preset falling speed threshold value; the DFS and the human body movement speed obtained through joint estimation are combined with the CSI amplitude and the phase difference to serve as statistics of falling action judgment, and falling action features are extracted; dynamically screening the features through a classification model, and performing tumble action recognition by using the remaining features to obtain a result. The problems that in the prior art, the detection precision is low, and the detection result is prone to being influenced by environment changes are solved, the privacy of the user is protected, computing resources are saved, and the detection precision of the falling action is improved.

Description

Technical field [0001] The present invention belongs to the technical field of wireless communications, particularly to a human fall intelligent detection methods, systems, information data processing terminal. Background technique [0002] Now, with the fifth generation mobile communication technology (5G) rapid development, mankind has entered the era of things all interconnected, machine-centric computing model is moving to shift to human-centered computing model. Human behavior recognition as one of the key things, has always been an important research topic. According to the World Health Organization survey shows that each year about 30% of the elderly were injured by the fall. Fall is a very dangerous act, especially for the elderly, may cause direct damage or indirect damage internal organs of the body. If detected in time to fall action of the human body, and notify the nursing or medical personnel can be avoided miss the best treatment time. With the improvement of peopl...

AI Technical Summary

Problems solved by technology

[0010] Aiming at the problems existing in the prior art, the present invention provides a human body fall intelligent detection method, system, and information data processing terminal, and particularly relates to a WIFI-based human body fall intelligent detection method, system, and information data processing terminal, aiming at To solve the problems existing in the current indoor fall detection method, such as insufficient description of the fall action, difficulty in accurately extracting the fall time window, and the detection results are easily affected by environmental changes.

Images