A method, device, and property service robot for identifying user identity

Abstract

The invention provides a method and device for identifying user identity and a property service robot. The method includes: performing in-depth processing on the first video image information acquired by the first camera to obtain a depth map and a color map; processing the color map and the depth map to determine at least one user in the first video image information; The positioning method calculates the face position of each user in the first video image information; determines the face area of ​​each user in the second video image information acquired by the second camera; Feature extraction is performed on each face area, and the face feature information corresponding to each face area is obtained respectively; the obtained face feature information is compared with the stored preset face feature information; when the comparison is consistent, the preset The preset user identity information corresponding to the facial feature information is determined as the identity of the user. The present invention improves user experience.

Description

technical field [0001] The invention relates to the technical field of robot manufacturing, in particular to a deep learning-based method, device and property service robot for a robot to identify a user's identity. Background technique [0002] With the rapid development of science and technology, robot manufacturing technology has also developed rapidly, and the application of robots has gradually entered the home service industry. [0003] A property service robot is a robot that is not affected by the environment and temperature, and can dynamically realize user identification. This type of robot needs to have excellent identification ability in user identification. [0004] Based on the current machine vision processing technology, the recognition of user identity by robots is still a technical difficulty, especially in non-specific perspectives, it is almost impossible to realize user identity recognition. At present, when the robot recognizes the user's identity, it ...

AI Technical Summary

Problems solved by technology

[0004] Based on the current machine vision processing technology, it is still a technical difficulty for the robot to identify the user's identity, especially in the non-specific angle to realize the identification of the user's identity is almost impossible to achieve

At present, when the robot recognizes the user's identity, it needs to require the user to be fixed or stationary at a certain height and / or angle to perform the recognition. Obviously, this reduces the user's experience in the actual application process.

Images