Gaze Estimation for Near-Eye Display Based on Fusion of Starburst Algorithm and FERN Natural Features
نویسندگان
چکیده
In future, near-eye display devices will be commonly used by people with or without prescription glasses, with different eye topologies, and under different lighting variations. Gaze tracking is an important task for these near-eye devices. New robust gaze tracking methods should be explored for these sophisticated devices. The proposed method overcomes the problem of adaptability to eye topology and occluded objects by employing advantages of natural FERN features tracking, strong model-based Viola Jones object detector and a fusion of these algorithms with the Starburst algorithm.
منابع مشابه
Adaptive Object Tracking for Improved Gaze Estimation Based on Fusion of Starburst Algorithm and Natural Features Tracking
Gaze tracking is an important task for near-eye devices. One of the sophisticated problems in gaze tracking is tracker robustness due to high eye topology variation, lighting variations, and partial occlusions of the eye. The proposed method overcomes this problem by employing advantages of adaptive feature based approach based on natural FERN features, strong model-based Viola Jones object det...
متن کاملStarburst: A robust algorithm for video-based eye tracking
Knowing the user’s point of gaze has significant potential to enhance current humancomputer interfaces. The primary obstacle of integrating eye movements into interfaces is the availability of a reliable, low-cost open-source eye-tracking system. Towards making such a system available to interface designers, we have developed a hybrid eye-tracking algorithm that integrates feature-based and mod...
متن کاملGazeProjector: Location-independent gaze interaction on and across multiple displays
Mobile gaze-based interaction with multiple displays may occur from arbitrary positions and orientations. However, maintaining high gaze estimation accuracy still represents a significant challenge. To address this, we present GazeProjector, a system that combines accurate point-of-gaze estimation with natural feature tracking on displays to determine the mobile eye tracker’s position relative ...
متن کاملImplementation of EOG-based Gaze Estimation in HMD with Head-tracker
Head-mounted displays (HMDs) are effective devices for creating immersive virtual environments. Intuitive movement field-of view (FOV) is possible in virtual reality (VR) space with a HMD equipped with a head-tracker. However, gaze targets are not accurately detectable by the measurement of head movements alone. An eye-tracker is needed to determine gaze positions; however, such trackers curren...
متن کاملDetermining the Proper compression Algorithm for Biomedical Signals and Design of an Optimum Graphic System to Display Them (TECHNICAL NOTES)
In this paper the need for employing a data reduction algorithm in using digital graphic systems to display biomedical signals is firstly addressed and then, some such algorithms are compared from different points of view (such as complexity, real time feasibility, etc.). Subsequently, it is concluded that Turning Point algorithm can be a suitable one for real time implementation on a microproc...
متن کامل