Video Augmentation for Enhanced Skill Learning in Karate Using Homography Transformation and Stacked Hourglass Networks | Chapter 5 | Scientific Research, New Technologies and Applications Vol. 6

 

This paper describes an image processing method that can facilitate skill learning in karate using recorded karate competition videos. The proposed method superimposes a partially filmed karate competition court in the input video image onto an overall model of a karate court via a homography transform. This method utilizes the Stacked Hourglass Network, a deep neural network proposed for estimating human poses, to estimate the corresponding points needed for the homography transform. 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. The evaluation of the proposed method by a university karate club showed that it was useful for skill learning.

 

Author(s) Details

 

Kazumoto Tanaka
Kindai University, Japan.

 

Please see the book here:- https://doi.org/10.9734/bpi/srnta/v6/2773

Video Transformation for the Facilitation of Skill Learning in Sport | Chapter 9 | Advances and Challenges in Science and Technology Vol. 2

 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