Deep Learning of Player Trajectory Representations for Team Activity Analysis
Deep Learning of Player Trajectory Representations for Team Activity Analysis
复制标题
用于团队活动分析的球员轨迹表示的深度学习
DOI：
--
复制
发表时间：
2018
期刊：
影响因子：
--
通讯作者：
Simon Fraser
中科院分区：
文献类型：
--
作者：
Nazanin Mehrasa;Yatao Zhong;Frederick Tung;L. Bornn;Greg Mori;Simon Fraser
团队运动，如冰球和篮球，涉及复杂的球员互动。运动员之间如何相互作用的建模是运动分析领域的研究者面临的一个巨大挑战。这种类型的分析最常见的数据来源是球员轨迹跟踪数据，它编码了有关球员运动，动作和意图的重要信息。在个人层面上，每个球员都表现出一种独特的轨迹风格，可以将他与其他球员区分开来。在团队层面上，一组球员轨迹形成了独特的动态，将团队与其他团队区分开来。我们相信玩家和团队都拥有隐藏在轨迹数据中的特定时空模式，我们提出了一个通用的深度学习模型，可以从玩家轨迹中学习强大的表示。我们展示了我们的方法在事件识别和团队分类上的有效性。
Team sports such as ice hockey and basketball involve complex player interactions. Modeling how players interact with each other presents a great challenge to researchers in the ield of sports analysis. The most common source of data available for this type of analysis is player trajectory tracking data, which encode vital information about themotion, action, and intention of players. At an individual level, each player exhibits a characteristic trajectory style that can distinguish him from other players. At a team level, a set of player trajectories forms unique dynamics that differentiate the team from others. We believe both players and teams possess their own particular spatio-temporal patterns hidden in the trajectory data and we propose a generic deep learning model that learns powerful representations from player trajectories. We show the effectiveness of our approach on event recognition and team classi ication.