2022 Fiscal Year Final Research Report
Localization using scene reflection on cornea
| Project/Area Number |
21K19800
|
|---|
| Research Category |
Grant-in-Aid for Challenging Research (Exploratory)
|
| Allocation Type | Multi-year Fund |
|---|
| Review Section |
Medium-sized Section 61:Human informatics and related fields
|
|---|
| Research Institution | Tokai University |
|---|
Principal Investigator |
|
|---|
| Co-Investigator(Kenkyū-buntansha) |
長松 隆 神戸大学, 海事科学研究科, 教授 (80314251)
|
|---|
| Project Period (FY) |
2021-07-09 – 2023-03-31
|
| Keywords | 視線計測 / 位置推定 |
|---|
| Outline of Final Research Achievements |
Localization was challenged using the scene reflection on the cornea without a scene camera that takes an environmental view. A 3D environmental map was obtained using a 3D LiDAR in advance, and the virtual eye images were generated on each position and rotation. Virtual tangent-plane images were generated as undistorted images from the obtained virtual eye images by applying corneal imaging. The estimator was trained using the virtual tangent-plane images. In the estimation, tangent-plane images were input to the estimator, and Monte Carlo Localization was implemented with IMU to enable probabilistic estimation.
|
| Free Research Field |
知覚情報処理
|
| Academic Significance and Societal Importance of the Research Achievements |
頭部装着型の視線計測装置は環境カメラによるプライバシーの侵害があると指摘され，視線計測装置の常時利用を進める上で大きな課題となっていた．これに対して本研究は，角膜に反射する限られた情報から注視対象の情報に加えて，ユーザの位置を推定することを達成した．環境カメラの無い視線計測装置の実現可能性を示した本研究の成果は，プライバシーの問題を解決し，装着型のカメラシステムの普及に貢献すると期待しており，その社会的意義は非常に大きい.
|
