Real-time accurate non-contact gesture recognition method and system based on RFID system

Abstract

The invention discloses a real-time accurate non-contact gesture recognition method and system based on an RFID system, and the method comprises the steps: a reader-writer collecting a gesture signalfrom a user, and the gesture signal comprising a timestamp and a phase value; preprocessing and gesture segmentation are carried out on the gesture signal; extracting coarse-grained statistical characteristics and fine-grained wavelet transformation characteristics of the signals subjected to gesture segmentation processing to construct a classifier of the system; and inputting the acquired data into the constructed classifier, and predicting the gesture. According to the invention, the identification time is greatly shortened, and the identification precision is ensured.

Description

technical field [0001] The present invention is mainly applied to the field of the Internet of Things, RFID technology, gesture recognition, and machine learning fields, especially a real-time, accurate and contactless gesture recognition method and system based on the RFID system. Background technique [0002] With the development of computer technology, computers have brought earth-shaking changes to our lives in all aspects. People are already inseparable from computers, and the information interaction Human-Machine Interface (HMI) [5] between people and computers is very important. The most common way of interaction in human-computer interaction is through simple mechanical devices, such as keyboards and mice, and touch screens. Although the above-mentioned methods are in the mainstream position in our current life, we still can't help but think about whether we want a more natural and human-computer interaction method that is more in line with human habits. [0003] S...

AI Technical Summary

Problems solved by technology

From our understanding, the time complexity of the algorithm is relatively high, and the specific time complexity will be analyzed later. It takes a long time to match the template and has a high lag

At the same time, its scalability is not good. With the increase of actions, the number of templates will also increase, which will not only affect the accuracy of recognition, but also increase the lag of the system.

Images