Tracking of Kendo Athletes and Quantification for Effective Striking Judgment by Image and Voice Recognition
Project/Area Number |
17K01708
|
Research Category |
Grant-in-Aid for Scientific Research (C)
|
Allocation Type | Multi-year Fund |
Section | 一般 |
Research Field |
Sports science
|
Research Institution | Sendai National College of Technology |
Principal Investigator |
|
Co-Investigator(Kenkyū-buntansha) |
本郷 哲 仙台高等専門学校, 総合工学科, 教授 (80271881)
|
Project Period (FY) |
2017-04-01 – 2021-03-31
|
Project Status |
Completed (Fiscal Year 2020)
|
Budget Amount *help |
¥4,810,000 (Direct Cost: ¥3,700,000、Indirect Cost: ¥1,110,000)
Fiscal Year 2019: ¥650,000 (Direct Cost: ¥500,000、Indirect Cost: ¥150,000)
Fiscal Year 2018: ¥520,000 (Direct Cost: ¥400,000、Indirect Cost: ¥120,000)
Fiscal Year 2017: ¥3,640,000 (Direct Cost: ¥2,800,000、Indirect Cost: ¥840,000)
|
Keywords | モーションキャプチャー / 運動解析・評価 / 音声認識・理解 / 画像・文章・音声等認識 |
Outline of Final Research Achievements |
We analyzed the capture image a kendo athletes from the upper part and the side, and we enabled the measurement of the distance between two athletes, the detection at a moment (first action) of the striking start, distinction of the striking movement, the contact judgment of the bamboo sword to the striking part. We confirmed that it became the elemental technology for them to judge effective striking. In addition, for a substantial spirit evaluation at the time of the effective striking, we analyzed a change at time of the spectrum entropy and devised the extracting method of the point at time to be related to effective striking from a sound. After analyzing the progress of the sound of various striking points, suggestion technique was found to be effective. We were able to show possibility of the quantification of the striking judgment condition effective in synchronizing these images and voice recognition technique.
|
Academic Significance and Societal Importance of the Research Achievements |
平成24年度より中学校の体育授業において「武道」が必修となった.「剣道」の授業やクラブ活動では,担当教員が剣道経験者とは限らないため,剣道経験の有無に関わらず客観的に有効打突の判定を可能とするシステムとしての普及が予想できる. また,競技会における有効打突の判定は3名の熟練審判員の主観に委ねられており,競技数が多くなると審判員の心身に大きな負担がかかるが,客観的に評価するシステムが現時点では存在しない.本システムの判定アルゴリズムに熟練審判員の判定情報を学習させることにより精度が向上し,将来,審判員の負担低減に繋がる技術となる.
|
Report
(5 results)
Research Products
(31 results)