2022 Fiscal Year Final Research Report
Understanding and control of mind through gaze
| Project/Area Number |
18H03312
|
|---|
| Research Category |
Grant-in-Aid for Scientific Research (B)
|
| Allocation Type | Single-year Grants |
|---|
| Section | 一般 |
|---|
| Review Section |
Basic Section 61050:Intelligent robotics-related
|
|---|
| Research Institution | Hiroshima City University |
|---|
Principal Investigator |
|
|---|
| Project Period (FY) |
2018-04-01 – 2022-03-31
|
| Keywords | 視線推定 / 心的状態推定 / 眼球・頭部協調運動 / VR |
|---|
| Outline of Final Research Achievements |
This research project aims to estimate individuals' mental states through their gazing behavior. To achieve this, we developed technologies that measure and estimate gaze, along with ones for estimating mental states using this data. This project involves the following four topics; 1) modeling the eye-head coordination movement, an unconscious reflex of people, to estimate the direction of gaze through machine learning, 2) visual search behavior analysis under a VR environment to estimate mental health, and 3) analysis of the students' gazing behavior to estimate their level of understanding during lectures. We also revealed that the eye-head coordination model is not only useful for gaze estimation but also for mental state estimation.
|
| Free Research Field |
コンピュータビジョン
|
| Academic Significance and Societal Importance of the Research Achievements |
本研究は，心的状態推定の問題を，大量データと機械学習手法によって人の内部での減少に立ち入らずに取り扱うのではなく，心的影響を強く受けるが外部からの観測が可能な注視行動に着眼し，認知科学・心理学的の知見を踏まえて解決を図った点で独自性があり，その成果には一定の学術的価値があると考えている．本研究では，成果概要で述べたとおりさまざまなトピックを取り扱ったが，特に眼球・頭部協調運動のモデル化は，利用範囲が広いことを踏まえ，定量的で信頼性の高い性能評価を行った上で，この技術を容易に利活用できるようPythonライブラリとして整理しており，その学術的・社会的な意義は大きい．
|
