2015 Fiscal Year Final Research Report
Non-contact and Non-invasive 3D Motion Sensing without a burden on an operator or an athlete
Project/Area Number |
26750260
|
Research Category |
Grant-in-Aid for Young Scientists (B)
|
Allocation Type | Multi-year Fund |
Research Field |
Sports science
|
Research Institution | Iwate University |
Principal Investigator |
|
Project Period (FY) |
2014-04-01 – 2016-03-31
|
Keywords | コンピュータビジョン / パターン認識 / スポーツバイオメカニクス / ヒューマンセンシング |
Outline of Final Research Achievements |
Until now, we have succeeded in the feature tracking, such as a head, which do not use any marker. However, the system is not evaluated and the motion is not analyzed in real environment of outdoor. Moreover, it is processing in 2D space. In this research, a lot of special cameras, markers, a special suit, etc. are not used. Furthermore, one of the purpose is establishment as the basic technology for a advanced and practical motion analysis system in 3D space without environmental restrictions. the system was evaluated in real environment the 1st year. The 3D posture estimation technique from 2D skeleton by the naive Bayes classification based on Bayes' theorem and clustering technology was proposed in 2nd. Moreover, the database with annotated data is made.
|
Free Research Field |
コンピュータビジョン
|