Gaze estimation method for head-mounted device based on iris and pupil

Abstract

The invention discloses a gaze estimation method for a head-mounted device based on iris and pupil. The method is characterized by utilizing a single camera, a single infrared light source and centre calibration points in four equal regions of a screen, extracting eye movement two-dimensional center features and carrying out three-dimensional space modeling on iris and pupil, establishing a three-dimensional gaze direction vector, and with gaze direction angle information being combined, estimating human eye gaze point position. Features of the head-mounted device are taken into full consideration; gaze point estimation precision under the head-mounted device is ensured, and meanwhile, complexity of the whole system structure and calibration process is greatly reduced; and the method is a high-precision and low-complexity solution method for eye-gaze tracking under the head-mounted device.

Description

technical field [0001] The invention relates to the technical field of sight tracking in a human-computer interaction mode, in particular to a sight estimation method for head-mounted devices based on iris and pupils. Background technique [0002] As the most novel human-computer interaction method, eye-tracking technology has the advantages of high precision, ease of use, good stability, and low interference to users. Therefore, gaze tracking technology has broad application prospects in many fields such as medical aided diagnosis, auxiliary equipment for the disabled, advertising and market analysis, and daily human-computer interaction. In addition, augmented reality has penetrated more and more into people's lives, how to combine eye-tracking technology with augmented reality to build a real-time interactive visual augmented reality has become the focus of more and more attention. [0003] Augmented Reality AR (Augmented Reality) is to enhance the real information in th...

AI Technical Summary

Problems solved by technology

In the current line-of-sight mapping model, the two-dimensional mapping model has a simple algorithm and does not need to know the location information of the system equipment and users in advance, but in order to establish a two-dimensional mapping equation, it is often necessary to use multiple infrared light sources or more calibration points on the screen; and The algorithm of the 3D mapping model is complex. In order to obtain the mapping relationship between the 3D center of the eye and the gaze point of the screen, complex stereo cameras or multiple cameras are required to collect human eye images, and the hardware of the entire gaze tracking system is complex.

Images