Realization of Corneal Feedback AR

2017 Fiscal Year Final Research Report

• Project/Area Number: 15H02738
• Research Category: Grant-in-Aid for Scientific Research (B)
• Allocation Type: Single-year Grants
• Section: 一般
• Research Field: Human interface and interaction
• Research Institution: Nara Institute of Science and Technology (2017); Osaka University (2015-2016)
• Principal Investigator: Kiyokawa Kiyoshi 奈良先端科学技術大学院大学, 情報科学研究科, 教授 (60358869)
• Co-Investigator(Kenkyū-buntansha): 間下 以大 大阪大学, サイバーメディアセンター, 准教授 (00467606) ; 中澤 篤志 京都大学, 情報学研究科, 准教授 (20362593)
• Project Period (FY): 2015-04-01 – 2018-03-31
• Keywords: 拡張現実 / 角膜反射 / 視線推定 / ユーザインタフェース

Outline of Final Research Achievements

Targeting augmented reality (AR) using optical see-through head mounted displays (HMD), we worked on the research and development of a new AR concept "cornea feedback AR" that optimizes the user experience by corneal imaging. Specifically, we developed a method for automatically calibrating the eyeball center in the HMD coordinate system from corneal reflection images, and a method for accurately estimating the gaze direction with an error of about 1.7 degrees using corneal reflection images. We also developed a method to robustly and accurately match corneal images with images of a scene camera, and based on this, developed a system that automatically finds eye contacts. In addition, we developed a system that automatically diagnoses anomaly eye movement from gaze behaviors and a system that a user can replay a fast 3D motion at a slower speed slow around the area of point of gaze.

Free Research Field

拡張現実感