羽毛球是所有運動中球速最快的運動，並在電腦視覺領域中給予了各種艱難的挑戰與任務，像是球員身分辨識、球場標線辨識、羽毛球軌跡追蹤、球員揮拍動作分類辨識等等。在這篇論文當中，我們提出了一個新的影片裁切方法提取在羽毛球單打比賽影片中羽毛球球員的每一個揮拍擊球瞬間的前後幀畫面，這些逐拍的影片片段隨後由兩種現有的模型進行處理：一種用於人體姿勢評估以獲取球員的關節點，另一種用於偵測出羽毛球在每個畫面中的位置。接著，我們提出了一個以注意力機制為基礎的深度學習模型（BST: Badminton Stroke-type Transformer）辨識球員的擊球類型，該模型根據上述得到的關節點、羽毛球軌跡、球員在球場上的位置資訊來當作是輸入。實驗結果表明我們的方法在目前最大的公開羽毛球影片資料集（ShuttleSet）上超越了先前的最好的方法，並且顯現出「有效地」利用球的軌跡對球拍運動動作辨識來說可能是一個趨勢。程式碼已公布在 https://github.com/Va6lue/BST-Badminton-Stroke-type-Transformer。

Badminton, known for having the fastest ball speeds among all sports, presents significant challenges to the field of computer vision, including player identification, court line detection, shuttlecock trajectory tracking, and player stroke-type classification. In this thesis, we introduce a novel video segmentation strategy to extract frames of each player’s racket swing in a badminton broadcast match. These segmented frames are then processed by two existing models: one for Human Pose Estimation to obtain player skeletal joints, and the other for shuttlecock trajectory detection to extract shuttlecock trajectories. Leveraging these joints, trajectories, and player positions as inputs, we propose Badminton Stroke-type Transformer (BST) to classify player stroke-types in singles. To the best of our knowledge, experimental results demonstrate that our method outperforms the previous state-of-the-art on the largest publicly available badminton video dataset, ShuttleSet, which shows that effectively leveraging ball trajectory is likely to be a trend for racket sports action recognition. The code is publicly available at https://github.com/Va6lue/BST-Badminton-Stroke-type-Transformer.