A Gait Recognition Method Based on Dynamic Vision Sensor

Abstract

The invention relates to the technical field of gait recognition, and discloses a gait recognition method based on a dynamic vision sensor. The invention provides a spatio-temporal pattern analysis method based on a dynamic visual sensor, and through the pulse neural network model based on the Tempotron algorithm, the gait data recorded by the dynamic visual sensor can be trained and recognized, so that the final gait Gait recognition has extremely high biological authenticity, so that it can not only perform gait recognition on multiple objects, solve the difficult problem of gait detection in complex backgrounds, but also ensure high accuracy of gait recognition. At the same time, two encoding methods are provided, which can quickly converge during the training process and achieve a better recognition accuracy rate, especially by combining the data segment sample segmentation method with a fixed-period moving window, which can make the gait recognition correct The rate reaches more than 85%, which has extremely high practical value and is convenient for practical popularization and application.

Description

technical field [0001] The invention relates to the technical field of gait recognition, in particular to a gait recognition method based on a dynamic visual sensor. Background technique [0002] A large number of surveillance cameras have been installed in large-space buildings such as banks, shopping malls, airports, and subway stations, but manual surveillance methods cannot fully meet the current security needs, because it not only consumes a lot of manpower and financial resources, Moreover, the physiological visual fatigue of monitoring personnel makes it difficult to achieve the purpose of safety warning. Therefore, these security-sensitive public places urgently need an intelligent early warning method. An ideal intelligent surveillance system should be able to automatically analyze the image data collected by the camera, and provide early warning before vicious events occur, thereby minimizing personal injury and economic loss. This requires the monitoring system ...

AI Technical Summary

Problems solved by technology

[0007] Since gait recognition technology is still in its infancy, there are mainly the following difficulties: (1) In traditional gait recognition research, the basis of recognition can be formed by defining the kinematic parameters of human gait, but in gait Obvious limitations in the data acquisition process make it difficult to accurately identify and record all parameters affecting gait (even if the accuracy of measuring some gait parameters improves, it is still not known whether the acquired parameters provide sufficient (2) The gait features captured by traditional cameras are easily affected or changed, that is, gait, as a biological feature, is easily affected and changed by various factors, such as clothing, Shoes, walking surface, walking speed, emotional state, physical condition, etc., and the truly effective features should be irrelevant or not affected by these factors; (3) Gait detection in complex backgrounds is difficult, and most current The assumption of the gait recognition algorithm for the data acquisition environment is that the camera is still, only the observed person is moving in the field of view, and the background is usually static and uncomplicated. However, in practical applications, the background is usually complex, and the pedestrians in the field of view are often more than one

Images