A face recognition method and system in a natural walking state

Abstract

The present invention proposes a face recognition method and system in a natural walking state. The steps of this method are as follows: S1. The video screen of the shooting person's goal naturally walks; S2, detect each specific personnel goal, identify before and after identificationThe relationship between each specific personnel goal in the two frames, and update the ID mark of each specific personnel in each specific personnel in the personnel goals; S3, based on the target ID mark of each specific personnel, calculate each specific onesThe cumulative score of personnel goals and determine the specific personnel goals, allocate close -up cameras; S4, the spatial location of the target of specific personnel, and adjust the direction of the cameraFace extraction and recognition of the face image of the positive human face, recorded the results, and release the adjustable camera that can be adjusted at the same time.It is conducive to the identification scene of expansion of face recognition technology and break the limitations of face recognition technology.

Description

technical field [0001] The present invention relates to the technical fields of video surveillance and face recognition, and more specifically relates to a face recognition method and system in a natural walking state. Background technique [0002] Face recognition technology is mainly based on human facial features. First, it is judged whether there is a face in the input face image or video stream. If there is a face, the position, size and location information of each major facial organ are obtained. And based on this information, further extract the identity features contained in the face, and compare it with known faces to identify the identity of the face. Therefore, face recognition needs to collect high-definition frontal face images , to ensure the reliability of recognition. [0003] At present, face recognition technology is widely used in various scenarios such as face recognition access control and attendance systems, face recognition anti-theft doors, public s...

AI Technical Summary

Problems solved by technology

[0003] At present, face recognition technology is widely used in various scenarios such as face recognition access control and attendance systems, face recognition anti-theft doors, public security and judicial agencies searching for fugitives, and tracking lost people. However, not all scenes can collect high-definition images. Frontal face images to meet the requirements of face recognition technology required for face images, for example, in video security monitoring scenarios, for people walking, due to the long shooting distance and the inability to obtain the cooperation of the people being photographed Naturally, it is impossible to perform face recognition through traditional face recognition technology

Images