Human body gait verification method based on artificial intelligence and cloud server

Abstract

The invention discloses a human body gait verification method based on artificial intelligence and a cloud server. According to the method, evaluation of the quality of human body images of continuous video frame images in a time period is carried out, so that high-quality human body pictures are screened out, and a picture sequence is generated; a human body region range of each picture can be determined based on the picture sequence, a human body picture sequence is generated, and human body gait feature recognition is carried out; and then human body gait feature verification is carried out through a artificial intelligence model. Therefore, the recognition of the identity of a person through the human body gait can be realized under the condition that the face of the person is shielded or facial features are fuzzy, and the accuracy of the human body gait verification under different conditions and scenes is improved.

Description

technical field [0001] The invention belongs to the technical field of artificial intelligence, and in particular relates to an artificial intelligence-based human gait verification method and a cloud server. Background technique [0002] In recent years, with the continuous development of artificial intelligence technology, more and more biometric features can be extracted and used for identity verification. At present, face verification, fingerprint verification, voiceprint verification, etc. are widely used in the market, and the threshold is relatively low. Advanced human gait verification technology is relatively rare in landing applications. [0003] Existing biometric verification technology, such as face verification technology, only extracts facial feature information and requires the active cooperation of personnel. It is difficult to play a role in situations where personnel wear masks, or the lighting is dark, the shooting angle is not good, and the hat is blocke...

AI Technical Summary

Problems solved by technology

[0004] In order to overcome the above-mentioned deficiencies in the prior art, the present disclosure provides an artificial intelligence-based human gait verification method and a cloud server, by evaluating the human body image quality of continuous video frame images within a time period, thereby screening out high-quality The human body picture generates a picture sequence, so the human body area range of each picture can be determined based on the picture sequence to generate a human body picture sequence and perform human gait feature recognition, and then verify the human body gait feature through the artificial intelligence model, so that it can realize face occlusion In the case of blurred or facial features, human gait can be used to identify people, improving the accuracy of human gait verification under different lighting conditions and weather conditions

Images