Pose recognition method, device and system for object of interest to human eyes

Abstract

The invention belongs to the field of three-dimensional staring point recognition and computer vision, and particularly discloses a pose recognition method, device and system for an object of interestto human eyes. The method comprises the steps of utilizing a left eye camera and a right eye camera to recognize the centers of the left and right pupils of a user respectively so as to extract the information of the human eyes; mapping the identified left and right pupil centers into a foreground left camera to obtain the two-dimensional staring points; extracting an object anchor frame in the foreground left camera by utilizing a target identification and tracking algorithm, and then determining an object of interest of the user according to the position relation between the two-dimensionalstaring point and the object anchor frame; performing three-dimensional reconstruction and attitude estimation on the object of interest of the user to obtain a pose of the object of interest in theforeground left camera; and converting the pose of the object of interest in the foreground left camera into a world coordinate system so as to determine the pose of the object of interest of the user. The method, device and system can identify the object of interest of the user and estimate the pose of the object, and has the advantages of high identification accuracy, high pose estimation precision and the like.

Description

technical field [0001] The present invention belongs to the fields of three-dimensional gaze point recognition and computer vision, and more specifically relates to a pose recognition method, device and system for objects of interest to human eyes. Background technique [0002] On the one hand, the gaze point of the human eye can be sent out effortlessly, and contains rich information, reflecting the psychological activities and state of the human being. On the other hand, in daily life, the behavior of the human eye can convey information to the outside world. Certain information, for example, by observing a person's eyes, the approximate direction and position of the person's gaze can be known, combined with scene information, the object of interest to the person can also be known. In summary, designing a 3D eye tracker that is easy to operate and can capture the gaze point of the human eye is of great help to psychological research and human-computer interaction operation...

AI Technical Summary

Problems solved by technology

[0004] However, the above-mentioned prior art still has the following problems: 1) the positioning of the human head cannot be realized, so the gaze point cannot be converted into the world coordinate system for further operation, and the head posture must be fixed during use, which greatly limits the user 2) only one eye camera is used, and the information of both eyes cannot be extracted, which reduces the accuracy of gaze point recognition; 3) the recognition and pose estimation of objects of interest cannot be realized, so it cannot be used 4) CN107773248A uses multiple foreground cameras, which increases the cost while consuming space resources, while US10007336B2 uses a depth camera, resulting in a bulky device and high cost

Images