NBA球幕防守的认识与分析Recognizing and Analyzing Ball Screen Defense in the NBA |
|
课程网址: | https://videolectures.net/videos/kdd2016_brooks_screen_defense |
主讲教师: | Joel Brooks |
开课单位: | KDD 2016研讨会 |
开课时间: | 2016-10-12 |
课程语种: | 英语 |
中文简介: | 随着NBA进入进攻阶段,决定如何防守球屏是NBA教练组面临的最关键的决定之一。在本次演讲中,我们将介绍一种工具的构建和应用,该工具用于自动识别常见的防守反击。使用SportVU球员跟踪数据和监督机器学习技术,我们学习了一个分类器,该分类器根据球屏的防守方式对其进行标记。应用五个NBA赛季的数据,我们的分类器识别出总共超过30万个屏幕的屏幕防御。这些标记的数据能够对防御策略进行新颖的分析。我们呈现了团队和球员层面的观察结果和趋势。我们的工作是朝着构建教练辅助工具迈出的一步,该工具用于分析比赛中最重要的动作之一。 |
课程简介: | As the NBA’s go-to offensive play, determining how to defend the ball screen is among the most critical decisions faced by NBA coaching staffs. In this talk, we present the construction and application of a tool for automatically recognizing common defensive counters to ball screens. Using SportVU player tracking data and supervised machine learning techniques, we learn a classifier that labels ball screens according to how they were defended. Applied to data from five NBA seasons, our classifier identified the screen defense of over 300,000 screens in total. These labeled data enable novel analyses of defensive strategies. We present observations and trends at both the team and player levels. Our work is a step towards the construction of a coaching assistance tool for analyzing one of the game’s most important actions. |
关 键 词: | 球幕防守; 自动识别; 机器学习技术 |
课程来源: | 视频讲座网 |
数据采集: | 2025-01-07:liyq |
最后编审: | 2025-01-07:liyq |
阅读次数: | 9 |