Sports Events Classification Using Convolutional Neural Networks

Abstract

Analysis of different sports data to get valuable insight has become immensely important now-a-days. Profuse application of Artificial Intelligence in different sectors has become a very popular trend as well. However, application of AI in sports analytics is still a new research domain left for exploration. With a view to applying AI in sports analytics, we have deployed Inception V3 and MobileNet which are Google's most popular Convolutional Neural Networks to successfully recognize 5 different sports events from a huge image dataset of these events. We also developed a Convolutional Neural Network model which name is SP-Net and we trained our proposed model with these 5 different sports events. SP-Net correctly predicted the class almost all images during the period of testing and gives a high performance. In terms of performance our proposed model SP Net surpass Inception v3 and MobileNet both of these models. Besides, Inception v3 and MobileNet also achieved a very high performance in terms of accuracy, precision, recall and f-measure while applied on the target dataset for successful classification.