Motion sensor-based gait recognition method

Abstract

The invention discloses a motion sensor-based gait recognition method. The method comprises the following steps that: gait data are generated in the walking process of a user who wears a motion sensor are acquired through the motion sensor; gait cycle estimation is performed on the gait data, localization segmentation is performed on the gait data, and the feature value extraction of the gait data is realized; and on the basis of the matching and comparison of the extending length of the rising edge and time span of a gait data feature curve, candidates whose matching degrees are higher than a judgment threshold value are screened out from a matching library, and error integration is performed on the feature values of the gait data and gait data of each candidate to be identified which have been subjected to Fourier transformation in the frequency domain, so that the matching degree of each candidate to be identified can be obtained, and a candidate whose matching degree is the largest is determined as an identity matching successful result. According to the motion sensor-based gait recognition method of the invention, the identify recognition of a user is based on the gait features of the user, and therefore, the method is more difficult to counterfeit and has higher security compared with traditional technology such as fingerprint recognition; a verification process is completed in the natural walking process of the user, and use experience can be smoother.

Description

technical field [0001] The invention relates to the technical field of human body biometrics, in particular to a motion sensor-based gait recognition method. Background technique [0002] In today's world, information technology innovation is changing with each passing day, and the wave of informatization characterized by digitization, networking, and intelligence is booming. Wearable devices have entered people's lives. On people's belongings, smart chips and other devices are integrated, which can collect data related to users' physiology and usage habits, and can record habits and improve experience through the Internet and other means. function extension, etc. However, with the rapid development of information technology, it also brings risks to the security of users' personal data, which leads to a certain degree of contradiction between personal data security and device convenience. [0003] The current research on gait recognition is basically based on machine visio...

AI Technical Summary

Problems solved by technology

However, with the rapid development of information technology, it also brings risks to the security of users' personal data, which makes there is a certain degree of contradiction between the security of personal data and the convenience of equipment use.

[0003] The current research on gait recognition is basically based on machine vision and deep learning. Multiple cameras are required to acquire gait videos for data analysis at the same time, which will greatly increase the cost of gait recognition.

Images