| Budget Amount *help |
¥16,120,000 (Direct Cost: ¥12,400,000、Indirect Cost: ¥3,720,000)
Fiscal Year 2019: ¥2,340,000 (Direct Cost: ¥1,800,000、Indirect Cost: ¥540,000)
Fiscal Year 2018: ¥3,120,000 (Direct Cost: ¥2,400,000、Indirect Cost: ¥720,000)
Fiscal Year 2017: ¥4,030,000 (Direct Cost: ¥3,100,000、Indirect Cost: ¥930,000)
Fiscal Year 2016: ¥6,630,000 (Direct Cost: ¥5,100,000、Indirect Cost: ¥1,530,000)
|
|---|
| Outline of Final Research Achievements |
Unlike projection mapping on a static object, projection on a fast moving object causes a delay in projection. Previous research has proposed a method to predict the position of an object using a Kalman filter, but this method does not deal with projections onto objects with three-dimensional shapes. In this study, we attempted to solve the above delay by learning the object's motion using deep learning, simultaneously predicting the object's position and 3D posture in about 0.5 seconds, and projecting the object. As a result of the experiment, we were able to improve the projection accuracy compared to the case of no prediction and Kalman filter prediction only.
|
