Apparent sight line estimation method based on human body posture analysis

Abstract

The invention relates to a method for estimating a sight line by combining human body posture information. A deep convolutional neural network comprising a salient target detection branch, a head posture estimation branch and a human body posture estimation branch is designed to estimate a sight line direction. And finally, prediction of a fixation point position is given through point multiplication according to the feature maps of the three branches, wherein a connecting line of the fixation point position and a head center position is used as thesight line direction. Through the method forestimating a sight line by combining human body posture information, the accuracy and robustness of the sight line estimation algorithm can be improved.

Description

technical field [0001] The invention belongs to the technical field of apparent line of sight estimation, in particular to an apparent line of sight estimation method based on human body posture analysis. Background technique [0002] Line of sight refers to the gaze direction of people's eyes, which usually represents the focus of people's attention. Line-of-sight information can assist machines in understanding human behavior, intentions, and the environment in which characters are located. Gaze estimation has great application value in human-computer interaction, attention analysis and video surveillance. [0003] As a tool for attention analysis, gaze estimation has the characteristics of quantification and visualization. For example, in reading research, through sight estimation, you can record where you pause, where you skip, where you look back, etc. When designing the pages of websites, magazines, and posters, using line-of-sight estimation technology, it is possi...

AI Technical Summary

Problems solved by technology

Model-based methods are not widely used because they require complex equipment (one or more cameras and infrared light sources)

Images