A Study on Gaze-driven Image Presentation on Automotive HUDs

2023 Fiscal Year Final Research Report

• Project/Area Number: 21K03964
• Research Category: Grant-in-Aid for Scientific Research (C)
• Allocation Type: Multi-year Fund
• Section: 一般
• Review Section: Basic Section 20020:Robotics and intelligent system-related
• Research Institution: Osaka University
• Principal Investigator: Ikeda Sei 大阪大学, 大学院基礎工学研究科, 准教授 (40432596)
• Project Period (FY): 2021-04-01 – 2024-03-31
• Keywords: 拡張現実間 / 視線計測 / 固視検出

Outline of Final Research Achievements

The aim of this study was to establish a technology that enhances visibility by changing the AR image displayed based on the user's estimated three-dimensional gaze position on an in-vehicle transparent window display. In line with this objective, specific achievements included the development of a self-calibration method for head-mounted eye tracker and a three-dimensional gaze position estimation method. The self-calibration method for eye tracker confirmed the effectiveness of detecting fixations and using fixation dispersion as an evaluation criterion in a 3D scene involving head movement. Similarly, the three-dimensional gaze position estimation method demonstrated that detecting fixations on various object surfaces in similar conditions enables the determination of the gaze target.

Free Research Field

拡張現実間

Academic Significance and Societal Importance of the Research Achievements

本研究の成果は，視線計測を伴うバーチャルリアリティ（VR）や拡張現実感（AR）技術において基礎となる成果である．現在，これらの研究分野では視線計測の重要性が増してきており，VR／ARヘッドセットに視線計測器が標準搭載されるようになってきている．いずれのヘッドセットにおいても本研究の成果を応用することが可能であるためその意義は大きいと考えられる．