선박에서 증강현실 위치 정합 활용을 위한 기계학습 기반의 마커 복원 방법 연구

초록

The interior of the ship is very complex and the equipment is equipped with pipes, valves, sup ports, etc. In order to utilize augmented reality in such an environment, it is more appropriate to use markers rather than markerless, which creates a model based on the characteristics of the target equipment. However, it is difficult to apply the marker because a lot of corrosion or dam age to the marker may occur in the ship. Therefore, in this study, when a marker is damaged, it is intended to restore the marker using GAN among machine learning techniques. At this time, the model was built using the Pix2Pix, Cycle GAN, and Disco GAN algorithms widely used for images among GAN algorithms. Finally, an efficient marker restoration algorithm was verified by qualitatively and quantitatively comparing the model results.

키워드