Eye recognition tracking method and device based on monocular camera

Abstract

The invention provides an eye recognition tracking method and device based on a monocular camera. The method comprises the following steps: continuously acquiring a plurality of frames comprising a human face through a monocular camera; performing face detection on a current frame except the initial frame in the plurality of frames to obtain a face region of the current frame; performing human eye detection on the face area of the current frame to obtain a human eye detection window of the current frame; performing human eye tracking based on the human face region of the current frame and the human face region of the previous frame of the current frame to obtain a human eye tracking window of the current frame; and analyzing the human eye detection window of the current frame, the human eye tracking window of the current frame, the human eye detection window of the previous frame and the human eye tracking window of the previous frame based on a predetermined model to obtain a human eye region of the current frame.

Description

technical field [0001] The present disclosure relates to the field of eye movement tracking. Specifically, the present disclosure provides a method for eye recognition and tracking based on a monocular camera and a device using the method. Background technique [0002] In the prior art, the relationship between eye movement and human mental activities has been explored by analyzing eye movement data. With the continuous development of society, technological progress and breakthroughs in target recognition and deep learning in computer technology have made eye recognition and tracking an increasingly important indicator in psychology. The development of modern computer vision technology can improve eye recognition and tracking technology, which has important practical significance for promoting psychology and functional science. [0003] The eye recognition and tracking technology in the prior art generally requires the use of equipment such as an eye tracker for eye recogni...

AI Technical Summary

Problems solved by technology

The flashing time interval of the light source in this way is very short, the flashing time is not easy to control, and multiple cameras need to be placed at specific angles, which may not be able to meet the angle requirements in practical application scenarios

In addition, it takes time for the lights to flicker, and the use of multiple images for joint calculations at the same time will increase the amount of calculations, and real-time performance is difficult to guarantee

In addition, the configuration of multiple cameras and multiple light sources will also lead to an increase in cost

[0006] Both the infrared camera and the depth camera require specific camera equipment, which is expensive, and the depth camera requires the cooperation of active light, and can only be calculated based on time series

Images