Egocentric Video Multi-viewer for Analyzing Skilled Behaviors based on Gaze Object
Yuki Umezawa, Takatsugu Hirayama, Yu Enokibori, Kenji Mase · 2018
In many intellectual tasks, efficient succession of human physical and sensory skills is a long-standing issue. In order to analyze skilled behaviors, a useful approach is to compare same task scenes among workers or days and to understand these differences. In this paper, we propose an egocentric scene classification method based on objects which the worker turned the gaze to and a multi-viewer for egocentric videos comparison. We have experimented on proposed classification method with videos of painting watercolor.