Sight tracking method based on near-to-eye camera

Abstract

The invention discloses a sight tracking method based on a near-to-eye camera, and the method is characterized in that the method comprises the steps: employing the near-to-eye camera to collect an eye gray image, and also comprises the following steps: Step 1, preprocessing the eye image; step 2, carrying out sight line feature extraction; and step 3, estimating a sight line drop point. The Step1 comprises the following sub-steps: Step11, obtaining a region of interest: obtaining the region of interest containing a complete pupil part in an eye grayscale image; and step 12, median filtering: carrying out median filtering on the eye grayscale image of the obtained region of interest. The invention provides a sight tracking method based on a near-to-eye camera, the method solves the problem that shadow area noise and reflected light spots interfere pupil edge extraction, and meanwhile, a corresponding sampling point selection algorithm is provided according to different shielding conditions of pupils, so that the accuracy of pupil center positioning is improved. The sight tracking method has the advantages of being high in robustness, high in pupil center positioning precision, good in real-time performance and the like.

Description

technical field [0001] The present invention relates to the technical field of eye-tracking, in particular to a method for eye-tracking based on a near-eye camera. Background technique [0002] The line of sight of the human eye can reflect the information that people pay attention to. Eye tracking technology is a technology that uses various detection methods such as software algorithms, machinery, electronics, and optics to obtain the current line of sight direction of the subject. It is widely used in human-computer interaction, assisted driving, psychological Research, virtual reality and military and many other fields. [0003] In recent years, with the development of computer and image processing technology, eye-tracking technology based on video image processing has gradually become the mainstream. Today's eye-tracking systems are mainly divided into two categories: wearable and non-wearable. Among them, wearable means that the subjects wear helmets, glasses and oth...

AI Technical Summary

Problems solved by technology

Due to the fixed connection between the wearable device and the subject's head, it has the advantages of clear imaging and simple image background, but there are still factors such as eye shadows, eyelash occlusion, corneal reflection spots, and partially occluded pupils that affect the pupil center coordinates. The impact of the extraction of

Images