New 2D pupil and spot center positioning technology under real — Time eye tracking

摘要

Eye tracking technology is an important technology in the field of artificial intelligence(AI). Eye tracking will promote the development of human-computer interaction(HCI). Spot Center Corneal Reflex (PCCR) is an eye tracking technique that relies on pupils and reflected light spots. Therefore, it is significant to accurately locate the pupil position and reflected spot position. The traditional algorithm used the edge and the gray information of the image to extract the contours of the pupil and the spot, and then determine the location through the fitting. However, the collected images will be affected by many environmental factors, the boundary point and the fitting calculation will greatly affect the efficiency and stability of the algorithm. In this paper, a new method combining image gradient information with threshold segmentation is proposed. Gradient detection and threshold segmentation are carried out in the region of interest, and the pupil and reflection spot are extracted directly. So, this paper use the centroid method to calculate the center coordinates more accurately. The algorithm has a good robust performance to avoid noise and environmental effects. The algorithm used to develop human eye tracking system to achieve real-time eye tracking, while ensuring accuracy.