針對籃球影片的單應性估計與球員追蹤

Abstract

隨著運動迷人口增長,相當多體育視頻已被錄製,並且很多研究集中在自動化檢測視頻中的語意事件,從而開發高效的視頻瀏覽工具給一般觀眾。然而在不同觀點下,專業運動員或教練想了解更高階的語意事件,例如:進攻或防守策略。相較於其它類型的體育視頻,籃球視頻中複雜的場景和不規則的攝相機運動,導致分析戰術在籃球視頻中更具有挑戰性;在本篇論文中,改良了基於球場的攝像機校準技術來應用於籃球視頻中,並且使用單應性將視頻中的座標轉換至球場模型的座標。提出了一種二階段的線段偵測,並使用偵測得到的結果當作單應性估計的輸入,其中球員的軌跡使用均值位移追蹤從視頻中提取,並且根據單應性映射到球場模型的座標。球員在球場座標中的位置訊息,在專業取向中有更多的應用,例如:偵測無人防守的投籃事件、基於軌跡獲取目標的視頻剪輯以及推測戰術。

With the growth of fandom population, a considerable amount of sports videos have been recorded , and a lot of research has focused on automatically detecting semantic events in the recorded video to develop an efficient video browsing tool for a general viewer. However, a professional sportsman or coach wonders about high level semantics in a different perspective, such as the offensive or defensive strategy performed by the players. Analyzing tactics is much more challenging in a basketball video than in other kinds of sports videos due to its complicated scenes and irregular camera movements. In this thesis,we ameliorate the court-based camera calibration technique to be applicable to basketball videos and use homography to convert positions in the video frame to real-world coordinates. We propose a two-stage line detection for basketball courts and then use the result as an input for homography estimation. Player trajectories are extracted from the video by a method based on mean-shift tracking and mapped to the real-world court coordinates according to the homography results. The player position information in the court coordinates can be further analyzed for professional-oriented applications such as detecting wide open events, retrieving target video clips based on trajectories, and inferring tactics.