Method for acquiring gait characteristic data of terminal user based on mobile terminal data and server

Abstract

The invention relates to a method for acquiring gait characteristic data of a terminal user based on mobile terminal data, which comprises the following steps: step 100, acquiring at least one piece of motion data C1(n), C2(n),..., Cm(n) of a mobile terminal, the xth piece of motion data Cx(n) being acquired by the mobile terminal according to a first preset acquisition frequency F within a time period T=[t1,t2]; step 200, respectively sliding the rectangular window Rt with the window length of W on C1(n), C2(n),..., Cm(n) according to a preset sliding length delta W to obtain motion segmentation data D10, D20,..., Dm0, wherein D11, D21,..., Dm1,..., D1u, D2u,..., Dmu, and Dxi is data obtained by processing data in a rectangular window Rt when the rectangular window Rt slides on the Cx(n)for the ith time; step 300, obtaining first gait feature data K0, K1,..., Ku of the terminal user based on the motion segmentation data D10, D20,..., Dm0, D11, D21,..., Dm1,..., D1u, D2u,..., Dmu, wherein Ki is obtained by extracting time domain and / or frequency domain features of the motion segmentation data D1i, D2i,..., Dmi; furthermore, W is larger than or equal to the standard gait cycle length, and the standard gait cycle length is the maximum value in the multiple known gait cycle lengths.

Description

Technical field [0001] The present invention relates to gait recognition technology, in particular to a method and server for obtaining terminal user gait characteristic data. Background technique [0002] The individual or group recognition of end users has received great attention. Among them, individual or group recognition based on the unique biological characteristics of the end user is an important recognition method in the prior art. The biological characteristics can be, for example, the user’s facial features, Fingerprint features and gait, and individual or group identification based on gait is a relatively new part of the current identification technology. [0003] Gait recognition is the process of recognizing traveling postures (a traveling posture is a posture unique to a user or user group in a specific traveling mode, where the traveling mode may include walking, running, etc.). Since gait is unique to end users or end user groups, Therefore, it can also be called ...

AI Technical Summary

Problems solved by technology

However, the above method based on the peak detection method to obtain the estimated gait cycle is only applicable to the laboratory environment, that is to say, in an ideal environment, the above method can have a better recognition effect; in the actual environment, there will be In various situations such as uneven roads (such as potholes on the road), if the peak detection method is used to estimate the user's gait cycle, the error between the estimated gait cycle and the accurate gait cycle will be large due to the appearance of false peaks At this time, if the segmented synthetic acceleration data is obtained according to the estimated gait cycle and the time-frequency domain features (that is, the user's gait feature data) are extracted, the acquired user gait feature data is not the user's gait cycle Complete gait feature data, which will affect the effect of gait recognition

Images