Video Augmentation Method for the Facilitation of Skill Learning in Karate

This paper describes an image processing method that can facilitate skill learning in karate using recorded karate competition videos. The proposed method compensates for a partially filmed karate court in the input video image by generating a complete court image via a network-based generator. To evaluate our method, a player-focused video was augmented with complete competition field information. The augmented video would be useful for observing both players' actions as well as the player positioning within the entire competition court. In particular, a complete court image generator was developed based on a generative adversarial network (GAN) framework to perform this video augmentation.