隨著多媒體傳播跟籃球運動的普及，使得觀看電視轉播或電視重播運動節目的人數越來越多，但是仍然有許多人沒有太多的時間去一一看完整場球賽的轉播或是錄影，雖然每週都會有精選的十大好球讓球迷們回味精采的動作，但是仍有很多漏網之魚的精彩動作沒有被票選入網。因此我們希望可以發展出一套系統，讓那些對於籃球充滿狂熱卻沒有時間看完整場比賽的人可以看到比賽中精彩的灌籃動作，以及每週都要整理一大堆影片並從中挑出灌籃的人一個快速的工具。本論文分為四大部分。
第一部分是將影片中得分板的位置找出來。首先，先取出影片最常出現的邊點的位置，製作了一個最常出現的梯度圖。接著藉由斷開和閉合的運算，消除並擴大梯度圖。
第二部分是找出得分板上顯示兩隊得分資訊的位置。對於之前所製作的梯度圖中，取出經常變化的像素點位置，因此得到得分板上會變動資訊的位置，接著根據長寬的比來判斷分數區塊的位置。
第三部分我們則須辨識兩隊的得分。在這部分必須對之前所找到的分數區塊的位置再做一次單一數字位元位置的找尋，接著對數字位元進行辨識，略過一分以及三分的得分事件，專注於兩分的得分事件。
第四部分則是判斷灌籃動作的方法。首先針對之前分類好的得分事件，對兩分得分事件，利用我們找尋適合偵測灌籃的拍攝鏡頭的方法，找出符合拍攝鏡頭的影格，然後找出影格中籃框的位置，接著找尋籃框附近有沒有人手膚色的顯示，若滿足這樣條件的臨界值，則判定是灌籃的動作。
這篇論文主要的貢獻在於可以讓喜愛觀看灌籃動作的人能夠節省看完整部片子的時間。並且證明了，在投影到二維影像中使用低階影像處理技術上，利用顏色特徵資訊，用來達到判斷灌籃的高階語意，是一種可行的做法。

Because of the spread of multi-media broadcast and fascinated Basketball sport, people who want to watch live or replay program is more than before but not all of them have time to enjoy the whole game show. Although there are top ten selections from the one week program, there are still some good actions that are not selected.  Therefore, we hope we can construct a system that can pick out the “Slam-Dunk” events from the basketball game videos for those who are addicted to basketball or has a job to pick out the “Slam-Dunk” events from the thousands of videos.
	This thesis can be divided into four parts. At first, we should extract the location of score board. Firstly, we make those which edge pixels have been appeared mostly in the whole video into a gradient map. Though the operations of closing and opening, we eliminate the noises and gather the connected parts. 
	Next, we find the location of score on the scoreboard. According to the gradient map we did it before, we take down the changing pixel within it so that we can get the changing information thought time to time. Then, we select those candidates according to their height-width ratio to find out the locations of scores.
	The third part is score identification. We focus on the region of score location and extract the explicit of score digit. After identifying scores, we only focus on those score events which equal to two. 
	The final part of the thesis is identifying whether the two-point events are slam-dunk or not. We pick up the two-point events. During the events, we use our method to select the right view frame and find the hoop firstly then count the skin pixel near the hoop position in order to find the hands grabbing the hoop. If the skin pixels are greater than our threshold, we claim it as a slam-dunk event. 
	The contribution of this research is we save much time for those who are addicted to slam-dunk actions and those who need to find out them. And the more, we prove that using low level feature in image processing still can reach the high level semantic event.

目錄
第一章	緒論	1
1．1	研究動機	1
1．2	論文組織架構	2
第二章	文獻分析	4
2．1 動作分析	4
2．2影片中事件的偵測	6
2．3 分鏡方式	7
2．4 物件擷取	8
2．5 球類運動影片的分析	9
2．5．1 足球	9
2．5．2 網球和羽球	10
2．5．3 籃球	12
第三章	系統架構	14
3．1簡介	14
3．2得分板的擷取	14
3．2．1 膨脹和侵蝕	14
3．2．2 斷開和閉合	15
3．3得分區塊的擷取	18
3．4分數辨識	20
3．4．1數字位置的擷取	20
3．4．2數字的判斷	23
3．4．2．1細線化	28
3．5拍攝鏡頭分類	32
3．6灌籃的辨識	36
第四章	系統實作	46
4．1開發環境	46
4．2 實驗資料與方法	46
4．3 實驗結果與討論	52
4．3．1 得分板實驗結果之討論	52
4．3．2 分數辨識實驗結果之討論	53
4．3．3辨識灌籃發生實驗結果之討論	54
第五章	結論與未來展望	59
參考文獻	61
附件一 影片A詳細細節	67
附錄二 影片B詳細細節	83
附錄三 英文論文	97
 
圖目錄
圖一 動作分析基本流程圖	4
圖二 網球追蹤系統架構	11
圖三	影片得分板位置	16
圖四	梯度圖	17
圖五	經過閉合的梯度圖	18
圖六	差集和梯度圖合作	18
圖七	得分板區塊內改變的像素位置	19
圖八	經過投影切變處理	20
圖九	範例	21
圖十	再經過水平頭影切片	22
圖十一	再經過垂直投影切片	22
圖十二	正確數字位置的定位	22
圖十三	分數辨識規則架構	24
圖十四	區域成長非期望範例	26
圖十五	區域成長非期望範例	27
圖十六	區域成長非期望範例	27
圖十七	區域成長前處理	27
圖十八	數字細線化的副程式產生結果	29
圖十九	細線化前	29
圖二十	細線化後	30
圖二十一	0的封閉面積範例	31
圖二十二	4的封閉面積範例	31
圖二十三	地面顏色實驗圖	33
圖二十四	近距離梯度圖	34
圖二十五	遠距離梯度圖	34
圖二十六	動作特寫的梯度圖	35
圖二十七	HSI籃框顏色位置	38
圖二十八	HSI籃框顏色位置做閉合、斷開後	38
圖二十九	球場投影點	39
圖三十	HSI地板顏色位置	40
圖三十一	HSI地板顏色位置做閉合、斷開後	40
圖三十二	填補後	42
圖三十三	選取的籃框位置	43
圖三十四	HSI膚色顏色位置	44
圖三十五	HSI膚色顏色位置做閉合、斷開後	44
圖三十六	判斷灌籃區塊	45
圖三十七	系統圖	48
圖三十八	得到梯度圖	48
圖三十九	經過斷開和閉合處理過後	49
圖四十	得分區塊結果	49
圖四十一	經過投影切片後	50
圖四十二	分數辨識中畫面	50
圖四十三	分數辨識的監控	51
圖四十四	分數事件辨識的細節	51
圖四十五	灌籃事件辨識的細節	52
圖四十六	會影響辨識的得分板範例	53

 
表目錄
表一	分數辨識規則	25
表二 影片資訊	46
表三	分數辨識的正確率	54
表四	A影片灌籃測試結果	55
表五	B影片灌籃測試結果	55
表六	A影片灌籃分類整體性正確率	56
表七	A影片灌籃分類局部性正確率	56
表八	B影片灌籃分類整體性正確率	57
表九	 B影片灌籃分類局部性正確率	57

公式目錄
（公式一）	15
（公式二）	15
（公式三）	15
（公式四）	15
（公式五）	16
（公式六）	29
（公式七）	29
（公式八）	32
（公式九）	32
（公式十）	33
（公式十一）	33
（公式十二）	33
（公式十三）	37
（公式十四）	43
（公式十五）	55

[1]	Hsuan-Sheng Chen, Hua-Tsung Chen, Yi-Wen Chen, Suh-Yin Lee,“Human Action Recognition Using Star Skeleton,”     International Multimedia Conference  Proceedings of the  4th ACM international workshop on Video surveillance and sensor networks, Oct., 27,2006, pp. 171-178.
[2]	Shihong Xia, Xianjie Qiu, Zhaoqi Wang, “A Novel Framework for Athlete Training Based on Interactive Motion Editing           Silhouette Analysis,” Virtual Reality Software and Technology Proceedings of the ACM symposium on Virtual reality software and technology, Nov., 7-9, 2005, pp.56-58.
	
[3]	Pedro F. Felzenszwalb, Daniel P. Huttenlocher,“Pictorial Structure for Object Recognition,” International Journal of Computer Vision ,Vol.61, Issue 1, Jan., 2005, pp. 55-79.
[4]	Etievent, E.; Lebourgeois, F.; Jolion, J.-M.; “Assisted Video Sequences Indexing : Motion Analysis Based on Interest Points,” 10th International Conference on Image Analysis and Processing, Sep., 27-29, 1999, pp.1059-1062.
[5]	Yao-Bao Yen, Hui-Huang Hsu, “A Standing Long Jump Evaluation System Based on Silhouette Thinning and Dynamic Bayesian Networks,” http://etds.ncl.edu.tw/theabs/english_site/search_result_eng.jsp?hot_query=Yao-Bao+Yen&field=AU.
[6]	Chen-Yu Chen, Jia-Ching Wang, Jhing-Fa Wang, Yu-Hen Hu, “Event based Segmentation of Sports Video Using Motion Entropy,” IEEE International Symposium on Multimedia 2007,  Dec., 10-12, 2007, pp. 107-111.
[7]	Dongqing Zhang, Shih-Fu Chung, “Event Detection in Baseball Video Using Superimposed Caption Recognition,” Proceedings of the tenth ACM international conference on Multimedia, Dec., 1-6, 2002, pp. 315-318.
[8]	Chung-Lin Huang, Huang-Chia Shih, Ching-Lun Chen, “Shot and Scoring Events Identification of Basketball Videos,” 2006 IEEE International Conference on Multimedia and Expo, Jul., 9-12, 2006, pp. 1885-1888.
[9]	Yifan Zhang, Changsheng Xu, YongRui, Jinqiao Wang, Hanqing Lu, “Semantic Event Extraction from Basketball Games Using Multi-Modal Analysis,” 2007 IEEE International Conference on Multimedia and Expo, Jul, 2-5, 2007, pp. 2190-2193.
[10]	Wu Lifang, Han Xiuli, Cui Hao, Shen Wei,“Shot segmentation and classification in Basketball Videos,” Third International Conference on International Information Hiding and Multimedia Signal Processing, Vol. 2, Nov., 26-28, 2007, pp. 539-542.
[11]	Ekin, A., Tekalp, A.M., “Shot Type Classification by Dominant Color for Sports Video Segmentation and Summarization,” 2003 IEEE International Conference on Acoustics, Speech, and Signal Processing, Apr., 6-10, 2003, Vol. 3, pp. 173-176.
[12]	Lifang Wu, Xun Liu, Lu Yin,“Object recognition in complex backgrounds,” 2004 7th International Conference on Signal Processing Proceedings, Aug. 31- Sep.4, 2004, Vol. 2, pp. 1601-1604.
[13]	Lifang Wu, Xianglong Meng, Xun Liu, Shiju Chen, “A New Method of Object Segmentation in the Basketball Videos,” 18th International Conference on Pattern Recognition, Vol. 1, pp. 319-322.
[14]	Wu Lifang, Shen Wei, Han Xiuli, Meng Xianglong , Liu Chao,“A Method of the Basketball Trajectory Reconstruction,” 2008 9th International Conference on Signal Processing Proceedings, Oct., 26-29, 2008, pp. 1360-1363.
[15]	Chueh-Wei Chang,  Chieh-Min Chang, “A Dynamic Object Searching and Tracking Approach in Sports Video Scenes,” JOURNAL OF NATIONAL TAIPEI UNIVERSITY OF TECHNOLOGY , Vol. 40, Issue 1, Mar., 2007, pp. 59-74. 
[16]	“Camera-based Observation of Football Games for Analyzing Multi-agent Activities”, Fifth international joint conference on Autonomous Agents and Multiagent Systems, May, 8-12, 2006, pp. 42-49. 
[17]	F.Yan, W.Christmas and J.Kittler, “A Tennis Ball Tracking Algorithm for Automatic Annotation of Tennis Match,”2005 The British Machine Vision Conference, Sep., 5-8, 2005, http://www.bmva.ac.uk/bmvc/2005/papers/150/paper150.pdf.
[18]	Guangyi Miao, Guangyu Zhu, Shuqiang Jiang, Qingming Huang, Xu Changsheng, Wen Gao,“A Real Time Score Detection and Recognition Approach for Broadcast Basketball Video,” 2007 IEEE International Conference on Multimedia and Expo, Jul, 2-5, 2007, pp. 1691-1694
[19]	Qixiang Ye, Qingming Huang, Wen Gao, Debin Zhao,“Fast and robust text detection in images and video frames,” http://www.jdl.ac.cn/doc/2005/Fast%20and%20robust%20text%20detection%20in%20images%20and%20video%20frames.pdf.
[20]	Lienhart, R., Wernicke, A., “Localizing and Segmenting Text in Images and Videos”, IEEE TRANSACTIONS ON CIRCUITS AND SYSTEMS FOR VIDEO TECHNOLOGY, Vol. 12, No. 4, Apr.,  2002,pp. 256-268.
[21]	Changsheng Xu, Jinjun Wang, Kongwah Wan, Yiaun Liand Lingyu Duan,“Live sports event detection based on broadcast video and web-casting text” The 14th annual ACM international conference on Multimedia, Oct., 23-27, 2006,pp. 221-230. 
[22]	Rafael C. Gonzalez, Richard E. Woods,“Digital Image Processing,” Addison-Wesley, 1992.