Event Detection in Football using Graph Convolutional Networks

TL;DR

This paper explores using Graph Convolutional Networks to automatically detect events in football videos by modeling players and the ball as graphs, capturing temporal context for improved accuracy.

Contribution

It introduces a novel approach to model football tracking data as graphs and applies GCNs for effective event detection in sports videos.

Findings

GCNs effectively model player and ball interactions

Graph pooling captures temporal context around actions

Proposed method improves event detection accuracy

Abstract

The massive growth of data collection in sports has opened numerous avenues for professional teams and media houses to gain insights from this data. The data collected includes per frame player and ball trajectories, and event annotations such as passes, fouls, cards, goals, etc. Graph Convolutional Networks (GCNs) have recently been employed to process this highly unstructured tracking data which can be otherwise difficult to model because of lack of clarity on how to order players in a sequence and how to handle missing objects of interest. In this thesis, we focus on the goal of automatic event detection from football videos. We show how to model the players and the ball in each frame of the video sequence as a graph, and present the results for graph convolutional layers and pooling methods that can be used to model the temporal context present around each action.