Preliminary analysis of effective assistance timing for iterative visual search tasks using gaze-based visual cognition estimation
Syunsuke Yoshida, Makoto Sei, Akira Utsumi, Hirotake Yamazoe · 2022 IEEE Conference on Virtual Reality and 3D User Interfaces Abstracts and Workshops (VRW) · 2022
In this paper, focusing on whether a person has visually recognized a target (visual cognition, VC) in iterative visual-search tasks, we propose an efficient assistance method based on the VC. In the proposed method, we first estimate the participant's VC of the target in the previous task. We then determine the target for the next task based on the VC and start to guide the participant's attention to the target for the next task at the VC timing. By initiating the guidance from the timing of the previous target's VC, we can guide attention at an earlier time and achieve efficient attention guidance. The preliminary experimental results showed that VC-based assistance improves task performance.