Joint sight line direction calculation method of left and right eye images of human eyes

Abstract

The invention provides a joint sight line direction calculation method of left and right eye images of human eyes. The method includes: a two-eye information extraction model, in which a human eye image is input, and left eye and right eye information features contained in the image are respectively and automatically extracted through the two-channel model; and a joint human-eye information feature extraction model, in which two-eye images of a user are input, and two-eye information is combined to extract joint human-eye information features by the model. According to a joint algorithm provided by the invention, a three-dimensional sight line direction is calculated and obtained through inputting feature information. One of the applications of the method is virtual reality and human-machine interaction, and a principle thereof is to calculate the sight line direction of the user through shooting the eye image of the user, and thus carry out interaction with an intelligent system interface or a virtual-reality object. The method can also be widely used in the fields of training and cultivating, games and entertainment, video surveillance, medical care and the like.

Description

technical field [0001] The invention relates to the fields of computer vision and image processing, in particular to a method for calculating the line of sight direction of human left and right eye images. Background technique [0002] Gaze tracking / eye tracking is of great significance for user behavior understanding and efficient human-computer interaction. More than 80% of human perceptible information is received by the human eye, and more than 90% of it is processed by the visual system. Therefore, line of sight is an important clue to reflect the interaction process between people and the outside world. In recent years, due to the rapid development of virtual reality technology and human-computer interaction technology, the application value of gaze tracking technology has gradually become prominent; on the other hand, gaze direction calculation is still a very challenging problem in the field of computer vision. [0003] The current eye-tracking technology is fundam...

AI Technical Summary

Problems solved by technology

[0006] The technology of the present invention solves the problem: overcomes the deficiencies of the prior art, and provides a method for calculating the line of sight direction of the left and right eye images of the human eye, by using the neural network to extract the information factors contained in the image, and adjusting the neural The network model finally predicts the gaze direction of both eyes, mainly by combining the image information of both eyes, so as to solve the problem of large noise in the input monocular image in the appearance-based gaze tracking method, thus realizing high-precision 3D gaze direction prediction

Images