臺灣博碩士論文加值系統

在球類運動分析中，多數研究著重於足球或籃球等，相較之下排球的分析研究偏少，本研究特別針對排球球員的運動軌跡，偵測其運動中跳躍的部分，可以提供此球員正確的移動軌跡，以及跳躍的資訊。本篇論文提出兩種跳躍軌跡分析方法，分別以軌跡垂直分量及消失點的特性，判斷球員移動軌跡中跳躍的部份。細部來說，我們利用背景模型切割前景區域，偵測出影像中欲追蹤之球員頭部位置，再藉由平面投影轉換，建構出球員在頂視平面上的軌跡，最後利用軌跡與消失點的特性，判斷軌跡中屬於跳躍的部分。而從實驗結果來看，軌跡中球員跳躍的部分都可有效的被偵測出來，並在移除跳躍軌跡後，呈現完整的球員移動軌跡。

In volleyball games, the analysis of players’ moving and jumping trajectories bring much tactical information. In this paper, we analyze volleyball videos to extract players’ trajectories and to identify the jumping parts of the extracted trajectories. The jumping parts can be determined via (i) vertical component analysis of trajectories and (ii) vanishing point-based collinear analysis of trajectories. Specifically, we first use background subtraction to segment foreground athletes and detect their head positions in an image sequence. The head positions are then transformed to top-view coordinates via homography transformation and form athletes’ trajectories. Finally, the method (i) and (ii) are applied to differentiate the moving and jumping parts of the trajectories. In our experiments, all the jumping parts of the trajectories are detected correctly, with moving trajectories of the athletes being displayed.

摘 要 I
Abstract II
目 錄 III
圖目錄 IV
表目錄 VI
第一章 緒論 1
1.1 研究目的與動機 1
1.2 相關研究 2
1.3 想法與貢獻 3
1.4 論文架構 4
第二章 相關幾何原理 5
2.1 平面投影轉換 5
2.2 消失點 7
第三章 頭部偵測 9
3.1 背景模型 9
3.2 前景物件之輪廓最高點 10
3.3 頭部位置檢測及修正 12
3.3.1 髮色與膚色提取 12
3.3.2 頭部位置異常之修正 13
第四章 跳躍分析 17
4.1 跳躍偵測 18
4.1.1 垂直軌跡檢測 19
4.1.2 與消失點延伸線的一致性 24
4.2 跳躍高度估測 26
4.3 頭部尺寸不變性之分析 27
第五章 實驗結果 31
5.1 平面投影轉換 31
5.2 頭部偵測 32
5.3 跳躍分析 35
第六章 結論與未來工作 44
參考文獻 45

[1] M. Li, S. Yang, and X.-W. Li, “A Head Detection Method Based on Curvature Scale Space,” IEEE Intelligent Information Technology Application Workshops, pp. 390-393, 2009.
[2] S. Birchfield, “Elliptical Head Tracking Using Intensity Gradients and Color Histograms,” IEEE Conference on Computer Vision and Pattern Recognition, pp. 232-237, 1998.
[3] Z. Zhang, H. Gunes, and M. Piccardi, “An Accurate Algorithm for Head Detection Based on XYZ and HSV Hair and Skin color Models,” IEEE International Conference on Image Processing, pp. 1644-1647, 2008.
[4] Y. Ishii, H. Hongo, K. Yamamoto, and Y. Niwa, “Face and Head Detection for a Real-Time Surveillance System,” IEEE International Conference on Pattern Recognition, Vol. 3, pp. 298-301, 2004
[5] T. Matsuyama, and N. Ukita, “Stable Multi-Target Tracking in Real-Time Surveillance Video,” Proceedings of the IEEE, Vol. 90, No. 7, pp. 1136-1150, 2002.
[6] P. J. Figueroa, N J. Leite, and R. Barros, “Tracking Soccer Players Aiming Their Kinematical Motion Analysis,” Computer Vision and Image Understanding, Vol. 101, No. 2, pp. 122-135, 2006.
[7] A. Alahi, Y. Boursier, L. Jacques, and P. Vandergheynst, “Sport Players Detection and Tracking with a Mixed Network of Planar and Omnidirectional Cameras,” IEEE International Conference on Distributed Smart Cameras, pp. 1-8, 2009.
[8] C. J. Needham, and R. D. Boyle, “Tracking Multiple Sports Players Through Occlusion, Congestion and Scale,” Research Report Series - University of Leeds School of Computer Studies LU SCS RR, 2001.
[9] M. Thomas, C. Koch, M. Tilp, and B. Horst, “Visual Tracking of Athletes in Beach Volleyball Using a Single Camera,” International Journal of Computer Science in Sport, Vol. 6, pp. 21-34, 2007.
[10] J.Liu, X.-F. Tong, W.-L. Li, T. Wang, Y.-M. Zhang, and H.-Q. Wang, “Automatic Player Detection, Labeling and Tracking in Broadcast Soccer Video,” Pattern Recognition Letters, Vol. 30, No. 2, pp. 103-113, 2009
[11] S.-M. Chang, “An Study on Image-based Crowd Detection and Estimation,” NCTU, 2009