A Study Of Kye Technology In Desktop-Gaze Tracking System

Eyes are very important for human beings.People get most information throughs eyes.Studies have shown that more than 80 percent of the knowledge of human is obtained through the eyes.So,the eyes are a high quality and high efficiency information transmission channel.With the rapid development of science and technology,more and more scientific workers put themselves into the research of gaze tracking.In this paper some researches about gaze tracking technology are conducted and some corresponding simulation experiments are made.This paper first introduces the research background,development and status of gaze tracking technology.It also reviews the method and priciples of gaze tracking based on 3D eye model.In the first algorithm,a new method for remote,non-contact point-of-gaze estimation that tolerates head movements and requires a simple personal calibration procedure in which the subject has to fixate a single calibration point is described.All of this greatly reduce the difficulty of using the gaze tracking system,the running time of the calibration procedure and the system errors.The experiment results exhibit that the standard deviation of the error in the estimation of the angles between the optical and visual axes is 0.8°.The second calibration algorithm is a novel automatic calibration procedure that does not require active user participation.To estimate the angle between the optical and visual axes of each eye,this procedure minimizes the distance between the intersections of the visual axes of the left and right eyes with the surface of a display while subjects look naturaly at the display.It also needs a calibration procedure that before using the gaze tracking system,but this calibration procedure does not require user to accomplish any specific task.The calibration procedure run automatic in the background when the user view the screen.Simulation results show that the angle between the optical and visual axes converged to the true values after 15 iterations.The last one is a kind of gaze tracking technology completely free of calibration process.To estimate the real-time angles between the optical and visual axes of each eye before calculating the direction of the visual axes of the both eyes,this procedure uses differential evolution and Shuffled Frog-leaping Algorithm(DE-SLFA)to minimize the distance between the intersections of the visual axes of the left and the right eyes with the surface of a display while subjects look naturally at the display.As a consequence,the users can avoid the inconvenient calibration process which may produce possible calibration errors.For a subject sitting in front of an 19 inches display the standard deviation of the error in the estimation of the angles between the optical and visual axes is 1°.