| Title | Forecasting Hand Gestures for Human-Drone Interaction |
| Publication Type | Conference Paper |
| Year of Publication | 2018 |
| Authors | Lee, Jangwon, Tan, Haodan, Crandall, David, Šabanović, Selma |
| Conference Name | Companion of the 2018 ACM/IEEE International Conference on Human-Robot Interaction |
| Publisher | ACM |
| Conference Location | New York, NY, USA |
| ISBN Number | 978-1-4503-5615-2 |
| Keywords | Automated Response Actions, composability, convolutional neural network, early recognition, gesture recognition, human-drone-interaction, pubcrawl, Resiliency |
| Abstract | Computer vision techniques that can anticipate people>>s actions ahead of time could create more responsive and natural human-robot interaction systems. In this paper, we present a new human gesture forecasting framework for human-drone interaction. Our primary motivation is that despite growing interest in early recognition, little work has tried to understand how people experience these early recognition-based systems, and our human-drone forecasting framework will serve as a basis for conducting this human subjects research in future studies. We also introduce a new dataset with 22 videos of two human-drone interaction scenarios, and use it to test our gesture forecasting approach. Finally, we suggest follow-up procedures to investigate people>>s experience in interacting with these early recognition-enabled systems. |
| URL | http://doi.acm.org/10.1145/3173386.3176967 |
| DOI | 10.1145/3173386.3176967 |
| Citation Key | lee_forecasting_2018 |
Forecasting Hand Gestures for Human-Drone Interaction