A Research Structure of Big Data Analysis and Application for Table Tennis Match Tactics Based on Computer Vision

In recent years, many deep learning techniques have been widely applied in sports events. Therefore, the research based on the collection of big data and applied to the analysis of the overall playing tactics of table tennis is competitive. This study proposes a structure to support this idea, which includes the match video collection raw database, video processing, action classification machine learning model, knowledge database and big data analysis website. Under the above structure, this research focuses on using machine learning model to automatically classify the types of serve motions. The table tennis motion dataset is created by professional players. They cut and label the competition video to complete the database. Then, use these data to train a 3-dimension convolutional neural network (3D-CNN). This experiment selected three common types of serve motions to classify. After training the model, with the validation dataset, the accuracy can reach 89.5%. This result shows that machine learning models have sufficient accuracy to recognize motion categories in table tennis serve motions. Therefore, the proposed method will also be extended to all kinds of motion classification to accomplish efficient and accurate table tennis player competition record. Finally, hoping this model structure can be applied to the variety of sports.