Presentation 2023-01-26
[Short Paper] Improved Visual Intention Estimation Model with Object Detection Using YOLO
Masakiyo Okuhama, Sho Higa, Koji Yamada, Shihoko Kamisato,
PDF Download Page PDF download Page Link
Abstract(in Japanese) (See Japanese page)
Abstract(in English) There are two types of human eye contact: conscious eye contact and unconscious eye contact. Only conscious eye gaze should be selected in input interfaces that use eye gaze. Otherwise, the Midas Touch Problem, a phenomenon in which unintended eye gaze can cause erroneous operation, will occur. In this study, we improve the intention estimation model created to discriminate the gaze of a passenger of an electric wheelchair by adding objects in the field of view and distance to objects as new feature vectors. We created an object recognition model using YOLO and transition learning for detecting objects in the field of view. A depth camera is used to measure the distance to the object.
Keyword(in Japanese) (See Japanese page)
Keyword(in English) electric wheelchair / YOLO / Object Detection / sensor / gaze
Paper # MVE2022-34
Date of Issue 2023-01-19 (MVE)

Conference Information
Conference Date 2023/1/26(2days)
Place (in Japanese) (See Japanese page)
Place (in English) Nara Institute of Science and Technology
Topics (in Japanese) (See Japanese page)
Topics (in English)
Chair Kiyoshi Kiyokawa(NAIST)
Vice Chair Sumaru Niida(KDDI Research)
Secretary Sumaru Niida(NAIST) / (DNP) / (Univ. of ToKyo)
Assistant Hidehiko Shishido(Univ. of Tsukuba) / Atsushi Nakazawa(Kyoto Univ.) / Naoya Tojo(KDDI Research) / Naoki Hagiyama(NTT)

Paper Information
Registration To Technical Committee on Media Experience and Virtual Environment / Special Interest Group on Computer Vision and Image Media / SIG-MR
Language JPN
Title (in Japanese) (See Japanese page)
Sub Title (in Japanese) (See Japanese page)
Title (in English) [Short Paper] Improved Visual Intention Estimation Model with Object Detection Using YOLO
Sub Title (in English)
Keyword(1) electric wheelchair
Keyword(2) YOLO
Keyword(3) Object Detection
Keyword(4) sensor
Keyword(5) gaze
1st Author's Name Masakiyo Okuhama
1st Author's Affiliation University of Ryukyu(Univ Ryukyu)
2nd Author's Name Sho Higa
2nd Author's Affiliation University of Ryukyu(Univ Ryukyu)
3rd Author's Name Koji Yamada
3rd Author's Affiliation University of Ryukyu(Univ Ryukyu)
4th Author's Name Shihoko Kamisato
4th Author's Affiliation National Institute of Technology, Okinawa College(NIT Okinawa College)
Date 2023-01-26
Paper # MVE2022-34
Volume (vol) vol.122
Number (no) MVE-367
Page pp.pp.1-2(MVE),
#Pages 2
Date of Issue 2023-01-19 (MVE)