籃球傳球是進攻組織中的重要環節，亦為助攻判定、傳球路徑分析及戰術評估之基礎。本研究旨在建立一套基於單一轉播鏡頭之籃球傳球自動辨識系統，整合YOLOv8物件偵測、OpenCV影像處理及BoT-SORT多目標追蹤技術，並針對籃球、球員、持球者、傳球與投籃五種類別進行標註與辨識。
為降低僅依賴持球者轉換進行傳球判定所造成之限制，本研究提出兩層式判定架構。第一層以模型直接偵測傳球動作作為主要判定依據，並結合投籃動作偵測，以排除視覺特徵相似之非傳球動作；當直接偵測證據不足時，第二層則透過持球者轉換資訊進行交叉確認。研究資料集共包含1,720個標註影格及16,150個標籤，涵蓋8個不同球場與7組球隊對戰組合。經比較不同規模之YOLOv8模型後，本研究選用YOLOv8m作為最終模型，主要考量其在偵測準確度與推論速度之間具有較佳平衡。
研究結果顯示，本系統於兩組測試情境下之平均精確率為78.30%、平均召回率為79.22%，平均F1-score為0.7783。消融分析結果亦顯示，本研究所提出之完整架構，其辨識效能優於僅依賴持球者轉換或僅依賴傳球動作偵測之單一路徑策略。整體而言，本研究證實透過整合物件偵測、多目標追蹤及多線索判定機制，可在單一轉播鏡頭條件下有效辨識籃球傳球事件，並為後續助攻分析、傳球路徑建構及籃球戰術數據化提供可行基礎。

Basketball passing is fundamental to offensive organization and is an essential basis for assist identification, passing-path analysis, and tactical evaluation. This study developed an automated basketball pass recognition system using a single broadcast camera. The system integrated YOLOv8 object detection, OpenCV video processing, and BoT-SORT multi-object tracking, for annotating five categories: basketball, player, ball handler, pass, and shoot.To reduce the limitations of relying only on ball-handler transitions, a two-layer decision framework was proposed. The first layer used direct pass detection as the primary cue and employed shoot detection to exclude visually similar actions. When direct evidence was insufficient, the second layer used ball-handler transitions for cross-validation. The dataset contained 1,720 annotated frames and 16,150 labels collected from eight courts and seven team matchups. YOLOv8m was selected because it provided a favorable balance between detection accuracy and inference speed. Across two test scenarios, the system achieved an average precision of 78.30%, recall of 79.22%, and F1-score of 0.7783. Ablation results showed that the complete framework outperformed both transition-only and passonly strategies.

Aharon, N., Orfaig, R., & Bobrovsky, B.-Z. (2022). BoT-SORT: Robust associations multi-pedestrian tracking. arXiv preprint arXiv:2206.14651.
Bernardo, A., & Della Valle, E. (2024). Learning to Detect Soccer Pass at the Edge: A Comparison Between Edge and Cloud-Based Streaming Machine Learning Approaches. 2024 IEEE International Workshop on Sport, Technology and Research (STAR),
Bewley, A., Ge, Z., Ott, L., Ramos, F., & Upcroft, B. (2016). Simple online and realtime tracking. 2016 IEEE international conference on image processing (ICIP),
Bochkovskiy, A., Wang, C.-Y., & Liao, H.-Y. M. (2020). Yolov4: Optimal speed and accuracy of object detection. arXiv preprint arXiv:2004.10934.
Cai, Z., & Vasconcelos, N. (2018). Cascade r-cnn: Delving into high quality object detection. Proceedings of the IEEE conference on computer vision and pattern recognition,
Cheng, Y.-P., Tsai, T.-H., Tsai, T.-C., Chiu, Y.-H., Chu, H.-K., & Hu, M.-C. (2023). OmniScorer: Real-Time Shot Spot Analysis for Court View Basketball Videos. Proceedings of the 5th ACM International Conference on Multimedia in Asia,
Cheng, Y., Liang, X., Xu, Y., & Kuang, X. (2022). Artificial intelligence technology in basketball training action recognition. Frontiers in Neurorobotics, 16, 819784.
Cossich, V. R., Carlgren, D., Holash, R. J., & Katz, L. (2023). Technological breakthroughs in sport: Current practice and future potential of artificial intelligence, virtual reality, augmented reality, and modern data visualization in performance analysis. Applied Sciences, 13(23), 12965.
Farhadi, A., & Redmon, J. (2018). Yolov3: An incremental improvement. Computer vision and pattern recognition,
Garcia, D. R., Yu, X., & Saniie, J. (2024). Basketball Video Analysis for Automated Game Data Acquisition Deep Learning. 2024 IEEE International Conference on Electro Information Technology (eIT),
Giancola, S., Amine, M., Dghaily, T., & Ghanem, B. (2018). Soccernet: A scalable dataset for action spotting in soccer videos. Proceedings of the IEEE conference on computer vision and pattern recognition workshops,
Giancola, S., Cioppa, A., Ghanem, B., & Van Droogenbroeck, M. (2024). Deep learning for action spotting in association football videos. arXiv preprint arXiv:2410.01304.
Horton, M., Gudmundsson, J., Chawla, S., & Estephan, J. (2015). Automated classification of passing in football. Pacific-Asia conference on knowledge discovery and data mining,
Host, K., Ivasic-Kos, M., & Pobar, M. (2020). Tracking Handball Players with the DeepSORT Algorithm. ICPRAM,
Jegham, N., Koh, C. Y., Abdelatti, M., & Hendawi, A. (2024). Yolo evolution: A comprehensive benchmark and architectural review of yolov12, yolo11, and their previous versions. arXiv preprint arXiv:2411.00201.
Kalman, R. E. (1960). A new approach to linear filtering and prediction problems.
Kaur, J., & Singh, W. (2022). Tools, techniques, datasets and application areas for object detection in an image: a review. Multimedia Tools and Applications, 81(27), 38297-38351.
Khanam, R., & Hussain, M. (2024). Yolov11: An overview of the key architectural enhancements. arXiv preprint arXiv:2410.17725.
Khanam, R., & Hussain, M. (2025). A Review of YOLOv12: Attention-Based Enhancements vs. Previous Versions. arXiv preprint arXiv:2504.11995.
Kuhn, H. W. (1955). The Hungarian method for the assignment problem. Naval research logistics quarterly, 2(1‐2), 83-97.
Li, B., & Xu, X. (2021). Application of artificial intelligence in basketball sport. Journal of Education, Health and Sport, 11(7), 54-67.
Li, C., Li, L., Jiang, H., Weng, K., Geng, Y., Li, L., Ke, Z., Li, Q., Cheng, M., & Nie, W. (2022). YOLOv6: A single-stage object detection framework for industrial applications. arXiv preprint arXiv:2209.02976.
Lin, T.-Y., Maire, M., Belongie, S., Hays, J., Perona, P., Ramanan, D., Dollár, P., & Zitnick, C. L. (2014). Microsoft coco: Common objects in context. European conference on computer vision,
Nunes, H., Iglesias, X., Daza, G., Irurtia, A., Caparrós, T., & Anguera, M. T. (2016). Influencia del pick and roll en el juego de ataque en baloncesto de alto nivel. Cuadernos de psicología del deporte, 16(1), 129-142.
Padilla, R., Passos, W. L., Dias, T. L., Netto, S. L., & Da Silva, E. A. (2021). A comparative analysis of object detection metrics with a companion open-source toolkit. Electronics, 10(3), 279.
Redmon, J. (2016). You only look once: Unified, real-time object detection. Proceedings of the IEEE conference on computer vision and pattern recognition,
Redmon, J., & Farhadi, A. (2017). YOLO9000: better, faster, stronger. Proceedings of the IEEE conference on computer vision and pattern recognition,
Rezatofighi, H., Tsoi, N., Gwak, J., Sadeghian, A., Reid, I., & Savarese, S. (2019). Generalized intersection over union: A metric and a loss for bounding box regression. Proceedings of the IEEE/CVF conference on computer vision and pattern recognition,
Sorano, D., Carrara, F., Cintia, P., Falchi, F., & Pappalardo, L. (2020). Automatic pass annotation from soccer video streams based on object detection and lstm. Joint European Conference on Machine Learning and Knowledge Discovery in Databases,
Terven, J., Córdova-Esparza, D.-M., & Romero-González, J.-A. (2023). A comprehensive review of yolo architectures in computer vision: From yolov1 to yolov8 and yolo-nas. Machine Learning and Knowledge Extraction, 5(4), 1680-1716.
Wang, A., Chen, H., Liu, L., Chen, K., Lin, Z., & Han, J. (2024). Yolov10: Real-time end-to-end object detection. Advances in Neural Information Processing Systems, 37, 107984-108011.
Wang, C.-Y., Bochkovskiy, A., & Liao, H.-Y. M. (2023). YOLOv7: Trainable bag-of-freebies sets new state-of-the-art for real-time object detectors. Proceedings of the IEEE/CVF conference on computer vision and pattern recognition,
Wang, C.-Y., Yeh, I.-H., & Mark Liao, H.-Y. (2024). Yolov9: Learning what you want to learn using programmable gradient information. European conference on computer vision,
Wojke, N., Bewley, A., & Paulus, D. (2017). Simple online and realtime tracking with a deep association metric. 2017 IEEE international conference on image processing (ICIP),
Xu, H., Baniya, A. A., Well, S., Bouadjenek, M. R., Dazeley, R., & Aryal, S. (2025). Action Spotting and Precise Event Detection in Sports: Datasets, Methods, and Challenges. arXiv preprint arXiv:2505.03991.
Yoon, Y., Hwang, H., Choi, Y., Joo, M., Oh, H., Park, I., Lee, K.-H., & Hwang, J.-H. (2019). Analyzing basketball movements and pass relationships using realtime object tracking techniques based on deep learning. IEEE Access, 7, 56564-56576.
Zhang, Y., Sun, P., Jiang, Y., Yu, D., Weng, F., Yuan, Z., Luo, P., Liu, W., & Wang, X. (2022). Bytetrack: Multi-object tracking by associating every detection box. European conference on computer vision,
Zhou, D., Keogh, J. W., Ma, Y., Tong, R. K., Khan, A. R., & Jennings, N. R. (2025). Artificial intelligence in sport: A narrative review of applications, challenges and future trends. Journal of Sports Sciences, 1-16.
Zhu, X., Su, W., Lu, L., Li, B., Wang, X., & Dai, J. (2020). Deformable detr: Deformable transformers for end-to-end object detection. arXiv preprint arXiv:2010.04159.
林欣穎, 蔡旻諺, 林政宏, & 張家豪. (2022). 應用人工智慧及機器學習進行籃球投籃命中辨識. 淡江體育學刊(5), 1-14.
連堃玹. (2024). 基於深度學習對籃球轉播影像之球場校正及球員追蹤. 臺灣師範大學資訊工程學系學位論文, 1-49.
藍于青, & 劉有德. (2019). 籃球得分動作在時間與空間的應用. 中正體育學刊, 32-47.