Sight line estimation method, system and device and storage medium

Abstract

The invention discloses a sight line estimation method, system and device and a storage medium, and the method comprises the steps: obtaining a face image, and carrying out the key point detection and 3D model fitting processing, and obtaining a human eye image and a 3D head rotation vector; performing data regularization on the human eye image and the 3D head rotation vector to obtain a regularized human eye image and a head posture estimation vector; and inputting the regularized human eye image and the head posture estimation vector into a pre-trained CNN network, and converting network output into a 3D sight line direction vector. The system comprises an image preprocessing module, a data regularization module and a result output module. The device comprises a memory and a processor used for executing the sight line estimation method. According to the invention, a high-precision sight line estimation result can be obtained. The sight line estimation method, system and device and the storage medium can be widely applied to the field of sight line estimation.

Description

technical field [0001] The present invention relates to the field of line of sight estimation, in particular to a line of sight estimation method, system, device and storage medium. Background technique [0002] Line of sight estimation technology is a technology that studies how to accurately track human visual direction and visual attention. Line of sight estimation technology has a wide range of application scenarios and great application value in real life. It can be applied in cognitive science, psychology, medical research, Car driving, entertainment, advertising and marketing research and other fields bring convenience to people's lives and comprehensively improve the level of social science and technology. With the continuous improvement of optical imaging technology and image processing capabilities, especially the development of computer vision, image-based line of sight Estimation methods have begun to become dominant. The current line-of-sight estimation methods ...

AI Technical Summary

Problems solved by technology

[0002] Line of sight estimation technology is a technology that studies how to accurately track human visual direction and visual attention. Line of sight estimation technology has a wide range of application scenarios and great application value in real life. It can be applied in cognitive science, psychology, medical research, Car driving, entertainment, advertising and marketing research and other fields bring convenience to people's lives and comprehensively improve the level of social science and technology. With the continuous improvement of optical imaging technology and image processing capabilities, especially the development of computer vision, image-based line of sight Estimation methods have begun to become dominant. The current line-of-sight estimation methods include model-based methods and performance-based line-of-sight. However, the existing methods have low estimation accuracy, slow estimation speed, strong dependence on the scene, complex experimental process, and poor user experience. Bad question

Images