User identity recognition method, electronic equipment and medium

Abstract

The invention provides a user identity recognition method, electronic equipment and a medium. The method comprises the steps that: a video stream sent by a photographing device is received, and human body recognition is carried out on an image in the video stream; when it is determined that a human body is recognized, human body feature data are extracted and compared with human body feature data in a registration database, and when it is determined that a corresponding registered user is recognized, a response corresponding to the detected registered user is started; when it is determined that the corresponding registered user is not recognized, the human body in the image is tracked according to the received video stream, and other identity recognition information corresponding to the human body is collected; according to the other identity recognition information, when it is determined that the corresponding registered user is recognized, the human body feature data are stored in the registration database. According to the method, by updating the registration database, various conditions of the human body can be covered, the accuracy rate of human body recognition is increased, the effect of human body recognition is optimized, recognition becomes more and more accurate, and the problem that human body recognition is difficult in various scenes is solved.

Description

technical field [0001] The invention relates to the field of cross-media fusion identification, in particular to a user identity identification method, electronic equipment and media. Background technique [0002] At present, the scope of smart home applications in various fields is expanding day by day, and various manufacturers are also developing towards the goal of realizing the whole house intelligence. Identity, location, and living habits can better understand users' behavior habits and preferences, so as to provide users with more accurate services. [0003] At present, the identity of the user is generally determined by first identifying the face and then the human body with the camera device in the house. In daily home scenes, it is difficult for the camera device to directly capture the user's facial information in many cases. When the facial information cannot be recognized , as an alternative, the identification of the human body is generally used to determine ...

AI Technical Summary

Problems solved by technology

[0004] As described in the background technology, the features extracted by the recognition device in the initial registration image are not rich, which leads to complex family scenes, even if the image of the human body is captured, but due to the complex lighting in the room and the installation position of the shooting device It is difficult to match the captured human body image with the initially recorded human body image due to the problem of unfixed, changeable personnel position and posture, and occlusion. This makes it difficult for the human body to accurately determine the identity information of household personnel in complex daily home life. The initially registered face or human body image has limitations in identifying the identity of the person, and the recognition rate for the identity of the person is low and the false detection rate is high. However, the present invention solves the problem of difficulty in identifying the human body in various scenarios

Images