Visual line estimation method and visual line estimation device based on three-dimensional active shape model

Abstract

The invention discloses a visual line estimation method based on a three-dimensional active shape model. The visual line estimation method comprises the steps of a first step, utilizing a user face front image which is acquired by two cameras as training data; a second step, performing two-dimensional key point positioning on the acquired image, wherein the two-dimensional key point positioning comprises pupil positioning and active shape model (ASM) positioning the user face in the image; a third step, performing three-dimensional coordinate reconstruction on the two-dimensional key point, obtaining three-dimensional coordinates of the pupil centers of a left eye and a right eye in a world coordinate system, and obtaining a face three-dimensional ASM shape; a fourth step, representing the visual line characteristics of the left eye and the right eye by means of relative position relationship between contours of double eyes and the pupil centers; and a fifth step, establishing a front viewpoint estimation model according to the obtained visual line characteristic; wherein the front viewpoint estimation model is used for performing human eye visual line estimation on a prediction sample. According to the visual line estimation method and the visual line estimation device provided by the technical solution of the invention, through establishing the user face three-dimensional ASM, the head gesture of man is estimated and displayed, thereby improving adaptability of visual line estimation to head motion.

Description

technical field [0001] The invention relates to the technical field of line of sight estimation, in particular to a line of sight estimation method and system based on a three-dimensional active shape model. Background technique [0002] The development of line-of-sight estimation has gone through a long process, from the early direct observation method, mechanical recording method, current recording method, electromagnetic induction method and optical recording method to the current line-of-sight estimation method based on vision. improvement. Especially in the past three decades, line-of-sight estimation technology has developed rapidly and has been applied in fields such as human-computer interaction, helping the elderly and the disabled, vehicle assisted driving, psychological analysis, virtual reality, and military affairs. Some relatively successful commercial systems have appeared, such as a series of eye trackers developed by Tobii Company in Sweden, SMI Company in ...

AI Technical Summary

Problems solved by technology

Although this method has good adaptability to head movement, it is difficult to ensure that multiple bright spots are clearly imaged in the cornea at the same time in an actual system

[0010] However, the feature-based method usually uses the reflection point information of the infrared light source in the cornea, and the bright spot information is easily affected by head movement, posture changes, and ambient light, which limits the applicable conditions of this technology.

[0011] In the existing appearance-based gaze estimation method, the appearance features of the entire eye are used, so the adaptability to head movement is poor

[0012] In the existing line-of-sight estimation method based on PCCR technology, the position information of the center of the bright spot is used, and the bright spot information is easily affected by head movement, posture change and ambient light, etc., which limits the applicable conditions of this technology

[0013] In the existing line-of-sight estimation method based on the pupil center and the corner of the eye, only the two-dimensional pupil center and the corner of the eye are used, which is not enough to express the change of the line of sight of the human eye, and has poor adaptability to head movement

Images