Event detection in soccer matches through audio classification using transfer learning

Abstract

Addressing the complexities of generating sports summaries through machine learning, our research aims to bridge the gap in audio-based event detection, particularly in soccer games. We introduce an extended ResNet-50 deep learning approach for soccer audio, emphasizing key moments from large soccer content archives through the use of transfer learning. The proposed model accurately classifies soccer audio segments into two categories: i) events, representing crucial in-game occurrences and ii) no events, denoting less impactful moments. The model involves complete audio preprocessing, the implementation of proposed model using transfer learning and the classification of events. The model’s reliability is validated using the dataset soccer action dataset compilation (SADC), involves dataset creation by football fans. Comparative analysis with pre-trained models such as VGG19, DesNet121, and EfficientNetB7 demonstrates the superior performance of the extended ResNet-50 based approach. Results across different epochs reveal consistently high accuracy, precision, recall, and F1-score, emphasizing the proposed model's effectiveness in event detection through audio classification. The paper concludes that the proposed model offers a robust solution for detecting an event from audio of soccer sports providing valuable insights for fans, analysts, and content creators to identify interested moments from soccer game with low failure.