User identity recognition method and system in combination with user gait information

Abstract

The invention provides a user identity recognition method and system combined with user gait information, and the method comprises the steps: carrying out the posture detection of each frame of pedestrian object in a video sequence of an original data set through a two-dimensional posture estimation system, and extracting the posture information; preprocessing the extracted joint coordinate sequence to generate a human skeleton data set; and finally, constructing a space-time diagram convolutional network model, dividing the skeleton diagram into six sub-diagrams, sharing joints among the sixsub-diagrams, learning an identification model by using the diagram convolutional network, training by using the constructed data set, and optimizing network parameters by using a multi-loss strategycombining classification loss and comparison loss and random gradient descent. And predicting the accuracy of the trained model by using the verification set. According to the method, effective information of the joint points is fully utilized, the motion state in the time dimension is reserved as much as possible, high robustness is achieved for clothes changes and carrying states, and good generalization capacity is achieved on a cross-view task.

Description

technical field [0001] The invention belongs to the field of gait recognition in computer vision, and more specifically relates to a user identity recognition method and system combined with user gait information. Background technique [0002] In the task of human recognition, there are various biometrics, such as irises, fingerprints, faces, etc., and gait is also a kind of behavioral biometrics. Compared with other biological features, gait has the advantages of being difficult to steal and imitate due to its unique non-contact characteristics, especially suitable for long-distance human identification, and has attracted more and more attention in the field of video surveillance. To date, gait recognition is still a very challenging problem, because it relies on video sequences taken in controlled or uncontrolled environments, and since the shape characteristics of pedestrians will change over time, the change of capturing perspective has a great impact on people. Appeara...

AI Technical Summary

Problems solved by technology

[0005] Aiming at the defects of the prior art, the purpose of the present invention is to provide a user identity recognition method and system combined with user gait information, aiming at solving the problem that the outline of a person in the existing gait task is easily affected by objects such as clothes and carrying objects. The change of shape due to the influence of covariates directly leads to the decline of recognition rate, and the lack of full use of effective information of human joint points in the traditional algorithm based on pose key points

Images