Method for identifying gaits of terminal user based on mobile terminal data and server

Abstract

The invention relates to a method for identifying gaits of a terminal user based on mobile terminal data. According to the method, the rectangular window with the window length W larger than the length of one gait cycle of the terminal user is adopted, so that the acquired gait feature data of the terminal user at least comprises all information data in one complete gait cycle of the terminal user, and comprehensive and complete information is provided for gait identification of the terminal user; besides, the sliding length delta W of the rectangular window is smaller than the length W of thewindow; according to the method, the motion segmentation data of the terminal user with different initial states in a specific advancing mode can be obtained; therefore, the user gait feature data acquired based on the sub-data obtained by re-segmenting the motion segmentation data can more fully use the internal information of the motion segmentation data, the gait features of the terminal userare objectively and comprehensively reflected, and the accuracy of user gait recognition is improved.

Description

technical field [0001] The present invention relates to a gait recognition technology, in particular to a method and a server for recognizing a user's gait. Background technique [0002] Individual or group identification of end users has received high attention. Among them, individual or group identification based on the unique biometric characteristics of end users is an important identification method in the prior art. 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 the traveling posture (the traveling posture is the unique posture of the user or user group under a specific traveling mode, wherein the traveling mode may include walking, running, etc.), since the gait is unique to the end user or the end user group, Therefore, it can also be called individual identification or group identification. In the prior art...

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 gait recognition effect, resulting in the user's gait recognition effect not meeting actual needs

Images