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.
Abstract (translated)
体育数据收集的大规模增长已经为职业球队和媒体机构提供了许多从这些数据中获取见解的途径。收集的数据包括每帧球员和球的轨迹,以及事件注释,例如传球、犯规、卡牌、进球等。最近,Graph Convolutional Networks (GCNs) 被用于处理这种高度非结构化跟踪数据,由于其缺乏清晰的序列安排和失踪物体的处理问题,这些数据可能难以建模。在本文中,我们专注于从足球视频中提取自动事件检测的目标。我们展示了如何将视频序列中的每个帧中的球员和球建模为图,并呈现了可用于建模每个行动的图卷积层和聚合方法的结果。
URL
https://arxiv.org/abs/2301.10052
