Abstract
skill in human communication. Eye behavior is an important, yet implicit communication cue. In this work, we focus on enabling people to see the users' gaze associated with objects in the 3D space, namely, we present users the history of gaze linked to real 3D objects. Our 3D gaze visualization system automatically segments objects in the workspace and projects user's gaze trajectory onto the objects in 3D for visualizing user's intention. By combining automated object segmentation and head tracking via the firstperson video from a wearable eye tracker, our system can visualize user's gaze behavior more intuitively and efficiently compared to 2D based methods and 3D methods with manual annotation. We performed an evaluation of the system to measure the accuracy of object-wise gaze mapping. In the evaluation, the system achieved 94% accuracy of gaze mapping onto 40, 30, 20, 10-centimeter cubes. We also conducted a case study of through a case study where the user looks at food products, we showed that our system was ableto predict products that the user is interested in.
| Original language | English |
|---|---|
| Title of host publication | Proceedings of the 9th Augmented Human International Conference, AH 2018 |
| Publisher | Association for Computing Machinery |
| Volume | Part F134484 |
| ISBN (Electronic) | 9781450354158 |
| DOIs | |
| Publication status | Published - 2018 Feb 6 |
| Event | 9th Augmented Human International Conference, AH 2018 - Seoul, Korea, Republic of Duration: 2018 Feb 7 → 2018 Feb 9 |
Other
| Other | 9th Augmented Human International Conference, AH 2018 |
|---|---|
| Country | Korea, Republic of |
| City | Seoul |
| Period | 18/2/7 → 18/2/9 |
Fingerprint
Keywords
- 3D gaze
- 3D segmentation
- Gaze mapping
ASJC Scopus subject areas
- Human-Computer Interaction
- Computer Networks and Communications
- Computer Vision and Pattern Recognition
- Software
Cite this
Object-wise 3d gaze mapping in physicalworkspace. / Hagihara, Kakeru; Taniguchi, Keiichiro; Abibouraguimane, Irshad; Itoh, Yuta; Higuchi, Keita; Otsuka, Jiu; Sugimoto, Maki; Sato, Yoichi.
Proceedings of the 9th Augmented Human International Conference, AH 2018. Vol. Part F134484 Association for Computing Machinery, 2018. a25.Research output: Chapter in Book/Report/Conference proceeding › Conference contribution
}
TY - GEN
T1 - Object-wise 3d gaze mapping in physicalworkspace
AU - Hagihara, Kakeru
AU - Taniguchi, Keiichiro
AU - Abibouraguimane, Irshad
AU - Itoh, Yuta
AU - Higuchi, Keita
AU - Otsuka, Jiu
AU - Sugimoto, Maki
AU - Sato, Yoichi
PY - 2018/2/6
Y1 - 2018/2/6
N2 - skill in human communication. Eye behavior is an important, yet implicit communication cue. In this work, we focus on enabling people to see the users' gaze associated with objects in the 3D space, namely, we present users the history of gaze linked to real 3D objects. Our 3D gaze visualization system automatically segments objects in the workspace and projects user's gaze trajectory onto the objects in 3D for visualizing user's intention. By combining automated object segmentation and head tracking via the firstperson video from a wearable eye tracker, our system can visualize user's gaze behavior more intuitively and efficiently compared to 2D based methods and 3D methods with manual annotation. We performed an evaluation of the system to measure the accuracy of object-wise gaze mapping. In the evaluation, the system achieved 94% accuracy of gaze mapping onto 40, 30, 20, 10-centimeter cubes. We also conducted a case study of through a case study where the user looks at food products, we showed that our system was ableto predict products that the user is interested in.
AB - skill in human communication. Eye behavior is an important, yet implicit communication cue. In this work, we focus on enabling people to see the users' gaze associated with objects in the 3D space, namely, we present users the history of gaze linked to real 3D objects. Our 3D gaze visualization system automatically segments objects in the workspace and projects user's gaze trajectory onto the objects in 3D for visualizing user's intention. By combining automated object segmentation and head tracking via the firstperson video from a wearable eye tracker, our system can visualize user's gaze behavior more intuitively and efficiently compared to 2D based methods and 3D methods with manual annotation. We performed an evaluation of the system to measure the accuracy of object-wise gaze mapping. In the evaluation, the system achieved 94% accuracy of gaze mapping onto 40, 30, 20, 10-centimeter cubes. We also conducted a case study of through a case study where the user looks at food products, we showed that our system was ableto predict products that the user is interested in.
KW - 3D gaze
KW - 3D segmentation
KW - Gaze mapping
UR - http://www.scopus.com/inward/record.url?scp=85044317398&partnerID=8YFLogxK
UR - http://www.scopus.com/inward/citedby.url?scp=85044317398&partnerID=8YFLogxK
U2 - 10.1145/3174910.3174921
DO - 10.1145/3174910.3174921
M3 - Conference contribution
AN - SCOPUS:85044317398
VL - Part F134484
BT - Proceedings of the 9th Augmented Human International Conference, AH 2018
PB - Association for Computing Machinery
ER -