Eye-wearable head-mounted tracking and gaze estimation interactive machine system for human–machine interface

Abstract

In this study, a head-mounted camera was used to track eye behaviors and estimate the gaze point on the user's visual plane. The integration of the elastic mechanism design makes the headset adaptable for various users. The wearable cases were prototyped with low-cost cameras to produce an efficient eye tracking solution. This proposed system can effectively extract and estimate pupil ellipse from a few camera images of an eye and compute the corresponding threedimensional eye model. The system can match later images of the same pupil ellipse from a head-mounted camera to give the possible visual angles. To estimate the gaze point, the system uses multiple-point calibration to solve the related polynomial formula for future angle-to-gaze mapping. The proposed eye-tracking algorithms can provide a lowcomplexity solution with high accuracy, precision, and speed. This tracking system is a low-cost and promising system that can be used in headsets for virtual reality, auxiliary equipment, interactive machine, and human-machine interface applications. The proposed eye-tracking algorithm can achieve satisfactory performance without using a highend high-speed camera and can be detected under different lighting sources, and the average errors of the detection results are stably within 9 pixels and at a distance of 50 cm from the screen; while the average error of the fixation mapping results is within 3 .

Gaze Tracking and Point Estimation Using Low-Cost Head-Mounted Devices

“…Table 6 lists the results of open eye detection rate for four users, which reveal that the average accuracy, precision, and recall rates can exceed 97%. The results of accuracy shows that the average are better than Jen [16] and Dobeš [17] and less than Lee [18]. The results of precision and recall rates shows that the average are better than others.…”

“…Dobeš et al [17] developed a successful method of eye and eyelid localization on a computer by using a modified Hough transform. Lee et al [18] proposed a novel wearable eye-gaze tracking system with a webcam and used a screen to perform sight verification.…”

“…This study designed the experiments on eye detection based on Dong et al [32] study. This study adopted the head-mounted devices, while the studies of Jen et al [16], Dobeš et al [17], and Lee et al [18] used the desktop environments for eye tracking. The experiments are compared to those studies conducted by Lee et al [18], Jen et al [16], and Dobeš et al [17].…”

“…number of samples. P1 P2 P3 P4 P5 P6 P7 P8 P9 User1 516 58 56 56 57 60 57 58 58 56 User2 440 49 50 48 48 50 49 50 49 47 User3 440 50 49 50 49 49 48 47 50 48 User4 441 50 50 50 48 49 49 47 51 47 This eye detection experiment compares the eye detection accuracy, precision, and recall with the study of Lee [18], Jen [16], and Dobeš [17]. Table 6 lists the results of open eye detection rate for four users, which reveal that the average accuracy, precision, and recall rates can exceed 97%.…”

“…The results of precision and recall rates shows that the average are better than others. [18] 98.91% 98.87% 97.84% Jen [16] 96.86% 98.71% 96.57% Dobeš [17] 94.43% 98.98% 93.88%…”