This study was attended on an video image conversion method that can simplify skill learning in sport utilizing recorded competition videos. The projected method for the ability learning targeting far eastern discipline or sport competition are detailed in this paper. The method resides of two stages. The first stage compensates for partially photographed karate contest field in the input video concept by generating a complete field image by way of a deep neural network (DNN) located image-generator. The alternator was developed established a pix2pix framework to perform this concept transformation. The second stage utilizes the gain image of the engine converting energy and the players’ stick models to convert the output figure into a front view image. The transfered video is valuable for observing not only the players’ motions, but too the entire flow of the contest. The evaluation experiment showed that the molded video promotes ease of attention. By the proposed plan, it becomes possible to together observe players' activity skills and the overall strategies on the field such as formations, thereby reveal new possibilities for broadcast-based sports learning.
Author(s) Details:
Kazumoto Tanaka,
Faculty
of Engineering, Kindai University, Higashi-Hiroshima, Japan.
Please see the link here: https://stm.bookpi.org/ACST-V2/article/view/11934
No comments:
Post a Comment