NEW KEY POINT DETECTION TECHNOLOGY UNDER REAL -TIME EYE TRACKING

Jiancheng ZOU, Honggen ZHANG

Keywords

Eye tracking, CNN, Pupil positioning, Spot positioning

Abstract

Eye tracking technology is critical for artificial intelligence (AI), and has been an important part of human-computer interaction. It is hopefully applied in Virtual Reality and Augmented Reality. But the accuracy and stability of the eye tracking algorithms limit the application. This paper presents a method of detecting eye pupil and spot based on convolution neural network (CNN). The CNN is used to overcome the weak robustness of traditional eye tracking algorithm. At the same time, we adopt an improved segmentation algorithm to position the pupil and infrared spot, which make the positioning more accurate and faster. Experiments show that the algorithm proposed in this paper can be applied in the eye tracking software and reach the real-time eye tracking effects.

Important Links:

Go Back