论文标题
棒球游戏重建的跟踪系统
A Tracking System For Baseball Game Reconstruction
论文作者
论文摘要
棒球比赛通常被认为是个人之间进行的许多比赛。例如，投手与击球手之间的决斗被认为是驱动这项运动的发动机。投手使用各种策略来对击球手获得竞争优势，后者尽最大努力弄清球轨迹并及时做出反应。在这项工作中，我们提出了一个系统，该系统可以详细地捕获投手，击球手和球的运动，并讨论如何处理此信息以计算有趣统计数据的几种方法。我们在大型视频数据库中证明了我们的方法与以前的系统相当的结果，而仅在视频材料上操作。此外，还合并了最先进的AI技术，以增加为球员，教练，团队和球迷提供的信息的数量。
The baseball game is often seen as many contests that are performed between individuals. The duel between the pitcher and the batter, for example, is considered the engine that drives the sport. The pitchers use a variety of strategies to gain competitive advantage against the batter, who does his best to figure out the ball trajectory and react in time for a hit. In this work, we propose a system that captures the movements of the pitcher, the batter, and the ball in a high level of detail, and discuss several ways how this information may be processed to compute interesting statistics. We demonstrate on a large database of videos that our methods achieve comparable results as previous systems, while operating solely on video material. In addition, state-of-the-art AI techniques are incorporated to augment the amount of information that is made available for players, coaches, teams, and fans.
