This paper presents a method for position estimation of superimposing information based on user's gaze position and players' positions in soccer videos.
First, candidate regions for superimposing information are calculated by generating a likelihood map based on the detection results of objects such as players and soccer goals.
Next, our method estimates the placement of the objects as information in the candidate regions based on the user's gaze position and players' positions in soccer videos.
Experimental results show that the proposed method realizes accurate superimposing information estimation.