Research Sports Video Analysis

Form analysis by unsupervised classification of tennis videos using posture estimation

In this research, we propose a method to classify pose information obtained by estimating joint position of players from tennis game images by classification by unsupervised classification method, considering even a series of actions of form. By extracting features and comparing the results it is possible to compare what features are present in each class's form and what is different from other forms.

Form analysis by unsupervised classification of tennis videos using posture estimation