Skip navigation

DSpace

機構典藏 DSpace 系統致力於保存各式數位資料(如:文字、圖片、PDF)並使其易於取用。

點此認識 DSpace
DSpace logo
English
中文
  • 瀏覽論文
    • 校院系所
    • 出版年
    • 作者
    • 標題
    • 關鍵字
    • 指導教授
  • 搜尋 TDR
  • 授權 Q&A
    • 我的頁面
    • 接受 E-mail 通知
    • 編輯個人資料
  1. NTU Theses and Dissertations Repository
  2. 電機資訊學院
  3. 資訊工程學系
請用此 Handle URI 來引用此文件: http://tdr.lib.ntu.edu.tw/jspui/handle/123456789/70880
完整後設資料紀錄
DC 欄位值語言
dc.contributor.advisor莊永裕(Yung-Yu Chuang)
dc.contributor.authorYu-Ching Wangen
dc.contributor.author王于青zh_TW
dc.date.accessioned2021-06-17T04:42:11Z-
dc.date.available2018-08-10
dc.date.copyright2018-08-10
dc.date.issued2018
dc.date.submitted2018-08-05
dc.identifier.citationReference
1 S. Baker and I. Matthews. Lucas-Kanade 20 years on: a unifying framework. In International Journal of Computer Vision, volume 56, pages 221–255, 2004.
2 G. Bertasius, A. Chan, and J. Shi. Egocentric basketball motion planning from a single first-person image. In CVPR, 2018.
3 G. Bertasius, S. X. Yu, H. S. Park, and J. Shi. Am I a baller? basketball skill assessment using first-person cameras. In CVPR, 2016.
4 J.-Y. Bouguet. Pyramidal implementation of the lucas kanade feature tracker description of the algorithm. 2000.
5 P. Carr, Y. Sheikh, and I. Matthews. Point-less calibration: Camera parameters from gradient-based alignment to edge images. In IEEE Workshop on the Applications of Computer Vision, page 377–384, 2012.
6 H.-T. Chen, M.-C. Tien, Y.-W. Chen, W.-J. Tsai, and S.-Y. Lee. Physics-based ball tracking and 3d trajectory reconstruction with applications to shooting location estimation in basketball video. In J. Visual Communication and Image Representation, volume 20, pages 204–216, 2009.
7 J. Chen, F. Zhu, and J. J. Little. A two-point method for PTZ camera calibration in sports. In CVPR, 2018.
8 L.-C. Chen, G. Papandreou, I. Kokkinos, K. Murphy, and A. L. Yuille. Deeplab: semantic image segmentation with deep convolutional nets, atrous convolution, and fully connected CRFs. In CVPR, 2016.
9 E. Cheshire, M.-C. Hu, and M.-H. Chang. Player tracking and analysis of basketball plays. 2015.
10 A. Cioppa, A. Deli`ege, and M. V. Droogenbroeck. A bottom-up approach based on semantics for the interpretation of the main camera stream in soccer games. In CVPR, 2018.
11 D. Farin, J. Han, and P. H. N. de With. Fast camera calibration for the analysis of sport sequences. In IEEE International Conference on Multimedia and Expo, page 482–485, 2005.
12 D. Farin, J. Han, and P. H. N. de With. Fast camera calibration for the analysis of sport sequences. In IEEE International Conference on Multimedia and Expo, pages 4 pp.–, 2005.
13 D. Farin, S. Krabbe, P. H. N. de With, and W. E elsberg. Robust camera calibration for sport videos using court models. In Storage and Retrieval Methods and Applications for Multimedia, volume 5307, page 80–91, 2004.
14 T.-S. Fu, H.-T. Chen, C.-L. Chou, W.-J. Tsai, and S.-Y. Lee. Screen-strategy analysis in broadcast basketball video using player tracking. In Visual Communications and Image Processing, pages 1–4, 2011.
15 R. Girshick, I. Radosavovic, G. Gkioxari, P. Doll´ar, and K. He. Detectron. 2018. https://github.com/facebookresearch/detectron.
16 J. Han, D. Farin, and P. H. N. de With. Generic 3-D modeling for content analysis of court-net sports sequences. In Advances in Multimedia Modeling, volume 4352, 2007.
17 J. Han, D. Farin, and P. H. N. de With. A real-time augmented-reality system for sports broadcast video enhancement. In International Conference on Multimedia, page 337–340, 2007.
18 J.-B. Hayet, J. Piater, and J. Verly. Robust incremental rectification of sports video sequences. In BMVC, 2004.
19 R. Hess and A. Fern. Improved video registration using non-distinctive local image features. In CVPR, 2007.
20 N. Homayounfar, S. Fidler, and R. Urtasun. Sports field localization via deep structured models. In CVPR, pages 4012–4020, 2017.
21 M.-C. Hu, M.-H. Chang, J.-L. Wu, and L. Chi. Robust camera calibration and player tracking in broadcast basketball video. In IEEE Transactions on Multimedia, volume 13, page 266–279, 2011.
22 W.-L. Lu, J.-A. Ting, J. J. Little, and K. P. Murphy. Learning to track and identify players from broadcast sports videos. In IEEE Trans. Pattern Anal. Mach. Intell., volume 35, pages 1704–1716, 2013.
23 A. Maksai, X. Wang, and P. Fua. What players do with the ball: A physically constrained interaction modeling. In CVPR, 2015.
24 J. Puwein, R. Ziegler, L. Ballan, and M. Pollefeys. PTZ camera network calibration from moving people in sports broadcasts. In IEEE Winter Conference on Applications of Computer Vision, page 25–32, 2012.
25 V. Ramanathan, J. Huang, S. Abu-El-Haija, A. N. Gorban, K. Murphy, and L. Fei-Fei. Detecting events and key actors in multi-person videos. In CVPR, 2015.
26 J. L. Schonberger, H. Hardmeier, T. Sattler, and M. Pollefeys. Comparative evaluation of hand-crafted and learned local features. In CVPR, 2017.
27 H. B. Shitrit, J. Berclaz, F. Fleuret, , and P. Fua. Tracking multiple people under global appearance constraints. In International Conference on Computer Vision, 2011.
28 S. Su, J. Pyo Hong, J. Shi, and H. Soo Park. Predicting behaviors of basketball players from first person videos. In CVPR, pages 1206–1215, 2017.
29 L. Sun and G. Liu. Field lines and players detection and recognition in soccer video. In IEEE International Conference on Acoustics, Speech and Signal Processing, pages 1237–1240, 2009.
30 L.-g. Tian and F.-s.Wang. Design and application of basketball tactics analysis based on the database and data mining technology. In ICCSEE, 2013.
31 A. Vedaldi and B. Fulkerson. VLFeat: An open and portable library of computer vision algorithms. 2008. http://www.vlfeat.org/.
32 P.-C. Wen, W.-C. Cheng, Y.-S. Wang, H.-K. Chu, N. C. Tang, and H.-Y. M. Liao. Court reconstruction for camera calibration in broadcast basketball videos. In IEEE Transactions on Visualization and Computer Graphics, volume 22, pages 1517–1526, 2016.
33 X. Yu, N. Jiang, L.-F. Cheong, H. W. Leong, and X. Yan. Automatic camera calibration of broadcast tennis video with applications to 3D virtual content insertion and ball detection and tracking. In Comput. Vis. Image Underst., volume 113, page 643–652, 2009.
34 S. Zheng, Y. Yue, and J. Hobbs. Generating long-term trajectories using deep hierarchical networks. In NIPS, 2016.
35 X. Zhou, L. Xie, Q. Huang, S. J. Cox, and Y. Zhang. Tennis ball tracking using a twolayered data association approach. In IEEE Transactions on Multimedia, volume 17, pages 145–156, 2015.
dc.identifier.urihttp://tdr.lib.ntu.edu.tw/jspui/handle/123456789/70880-
dc.description.abstract本篇論文提出了從籃球影片的單一影像中,提取出有效的場地語意資訊,並進一步將任意相機視角的球場,自動定位到俯視球場模型的單應矩陣估計方法。
先前使用語意資訊分析的方法,會需要事先假定球場與球場線的顏色,或是需要使用者手動標記出參考影像的球場定位資訊,來進行進一步語意分析。而使用相機校正的方法,則需要限制相機的位置與移動方式,並會受到影像追蹤器表現的影響。相較於這些方法,我們首先開發了可以讓使用者快速標記影像定位參數的工具,來產生大量的場地語意資訊。我們使用生成的訓練資料,透過現有的深度影像分割網路,訓練出穩定的籃球場地語意提取模型。
此外,目前在球場定位表現最好的方法,使用了馬可夫隨機場來解決球場定位問題,將場地語意資訊轉換成線段能量,與球場水平和垂直方向上兩消失點的射線,計算之間的最小能量,以得到最終的單應矩陣估計值。
對此,我們則提出了兩階段的方法,在階段一結合了傳統方法與深度球場分割模型來得到初始球場對應點的估計值,並在階段二將球場定位問題轉換成影像對齊問題,利用現有的線性優化器,與階段一得到較好的初始值,估計出最終球場定位結果。
在考慮整段影片的時間關聯性後,我們成功產生出在時間上有較好連貫性的球場定位結果,並改進了缺少場地語意資訊與單應矩陣對應點影像的定位成果。
zh_TW
dc.description.abstractThis thesis introduces a homography estimation technique that efficiently extracts semantic features and automatically localizes basketball court from a single image of broadcast videos.
Unlike previous methods that require color presumptions or manual keyframe annotations of the field surface and court lines to extract possible court features, or add position and motion constraints on cameras to achieve reliable camera calibration, we develop a fast homography annotation tool to generate large amounts of court annotations, and train deep segmentation models that can efficiently extract semantic court features from general NBA basketball courts.
Also, compared to the state-of-the-art method that formulates the court localization problem as a branch and bound inference in a Markov random field where an energy function is defined in terms of semantic cues, we propose a two-stage method that uses deep semantic features to estimate initial homography points, and we formulate the court localization problem as an image alignment problem, which can be solved by existing linear optimizers with our good initial transformation matrices.
By taking temporal correlations into consideration, we successfully localize video sequences with satisfactory temporal coherence, and we even achieve acceptable performance for images that are lack of semantic homography correspondences.
en
dc.description.provenanceMade available in DSpace on 2021-06-17T04:42:11Z (GMT). No. of bitstreams: 1
ntu-107-R05922004-1.pdf: 77109012 bytes, checksum: 457f7c9635a9cd893c2c763cc480ecbe (MD5)
Previous issue date: 2018
en
dc.description.tableofcontents致謝 i
摘要 ii
Abstract iii
List of Figures vi
List of Tables viii
Chapter 1 Introduction 1
Chapter 2 Related Work 5
2.1 Semantic Feature Detection 6
2.2 Camera Calibration 7
Chapter 3 Methodology 9
3.1 Annotation Tool 10
3.2 Segmentation Dataset Generation 12
3.3 Deep Segmentation Models 14
3.4 Court Localization 17
3.4.1 Preprocessing of segmentation images 18
3.4.2 Stage 1: initial homography points estimation 19
3.4.3 Stage 2: homography regression by image alignment algorithm 21
Chapter 4 Experimental Results 25
4.1 Criteria for Measurements 25
4.2 Quantitative Comparison 26
4.2.1 Localization rate 26
4.2.2 Effectiveness of semantic maps 27
4.2.3 Comparison to homography regressors 28
4.3 Visualization 31
Chapter 5 Discussion 33
Chapter 6 Conclusion 35
Bibliography 37
dc.language.isoen
dc.subject球場定位zh_TW
dc.subject相機校正zh_TW
dc.subject球場分割zh_TW
dc.subject球場對齊zh_TW
dc.subject籃球zh_TW
dc.subjectcamera calibrationen
dc.subjectcourt localizationen
dc.subjectcourt segmentationen
dc.subjectcourt alignmenten
dc.subjectbasketballen
dc.title使用影像分割與單應性矩陣對齊之影片籃球場定位zh_TW
dc.titleBasketball Court Localization for Videos by Image Segmentation and Homography Alignmenten
dc.typeThesis
dc.date.schoolyear106-2
dc.description.degree碩士
dc.contributor.oralexamcommittee朱宏國(Hung-Kuo Chu),朱威達(Wei-Ta Chu)
dc.subject.keyword球場定位,相機校正,球場分割,球場對齊,籃球,zh_TW
dc.subject.keywordcourt localization,camera calibration,court segmentation,court alignment,basketball,en
dc.relation.page40
dc.identifier.doi10.6342/NTU201802502
dc.rights.note有償授權
dc.date.accepted2018-08-06
dc.contributor.author-college電機資訊學院zh_TW
dc.contributor.author-dept資訊工程學研究所zh_TW
顯示於系所單位:資訊工程學系

文件中的檔案:
檔案 大小格式 
ntu-107-1.pdf
  未授權公開取用
75.3 MBAdobe PDF
顯示文件簡單紀錄


系統中的文件,除了特別指名其著作權條款之外,均受到著作權保護,並且保留所有的權利。

社群連結
聯絡資訊
10617臺北市大安區羅斯福路四段1號
No.1 Sec.4, Roosevelt Rd., Taipei, Taiwan, R.O.C. 106
Tel: (02)33662353
Email: ntuetds@ntu.edu.tw
意見箱
相關連結
館藏目錄
國內圖書館整合查詢 MetaCat
臺大學術典藏 NTU Scholars
臺大圖書館數位典藏館
本站聲明
© NTU Library All Rights Reserved