ABSTRACT
The final goal is to make a "tankendo machine" that is easy to use, safe, fun, and can provide a mechanical competitor for humans. First, deep learning technology was used to install an image processing system that could detect the start (initial motion) of striking and thrusting motions by humans and quickly predict the type of technique used.
References
- K.Hoshino and C.Cheng: "Development of a swordsmanship machine enabling the inner and outer muscles to be safely trained while having fun," Proc. 3rd Intl. Conf. on Biomedical and Bioinformatics Engineering, pp.59--62, 2016. http://dx.doi.org/10.1145/3022702.3022711Google Scholar
- Nippon Budo Kyokai: "Budo: The Martial Ways of Japan," ed. Alexander Bennet, Nippon Budokan Foundation, 2009Google Scholar
- K.Hoshino: The Method for Analyzing the Motions of Martial Arts. Patent Application No. 2018--27366, Filling date: Feb 19, 2018. (in Japanese)Google Scholar
- M.Nakamura and K.Hoshino: "Tankendo motion estimation system with robustness against differences in color and size between users' clothes using 4-color markers with elastic belts," Proc. International Conference on Biomedical and Bioinformatics Engineering (ICBBE 2018), pp.110--117, 2018. http://dx.doi.org/10.1145/3301879.3301890Google Scholar
Digital Library
- K.Hoshino and S.Shimanoe: Face Protector, the Device, and Method for Recording the Motions. Patent Application No. 2018--248113, Filling date: Dec 28, 2018. (in Japanese)Google Scholar
- S.Shimanoe and K.Hoshino: "A wearable imaging system for recording the game tactics in martial arts using swords," Proc. 2019 IEEE 1st Global Conference on Life Sciences and Technologies (LifeTech 2019), pp.139--140, 2019Google Scholar
Cross Ref
- M.Nakamura and K.Hoshino: "Experimental Discussion about the Influence of the proficiency in Tankendo on the Foot Posture," Humanities & Social Sciences Reviews, 7, 5, pp 296--305, 2019. https://doi.org/10.18510/hssr.2019.7535Google Scholar
Cross Ref
Index Terms
Predicting the Types of Striking and Thrusting Motions by using Deep Learning





Comments