臺灣博碩士論文加值系統

由於盜版電影的猖獗， 電影業者每年損失上百億美元， 而這些盜
版電影的來源， 則多半是經由手持攝錄影機在劇院內偷拍而來。因
此，過去幾年都在不斷地研究防止盜錄的方法， 而其中之一最有效的
方法就是透過特殊的方法找出盜錄者， 並將其繩之於法。本論文採用
過去的相機校準方法並且提出一套修正的方法， 如此一來， 便可透
過校準的相機， 找出盜錄者的位置。此外，因3D電影畫面重疊的特
性， 電影業者認為3D電影難以盜錄， 但我們將在此論文提出3D電影
的盜錄方法， 並針對此情況，提出有效的定位方法來找出盜錄者。最
後我們建立了一個新的資料庫， 並利用它做了一系列的驗證及實驗來
證明本論文方法的有效性。

Most copyright infringement or piracy in cinemas is committed by recording the theatre screen with handheld camcorders. As a result of piracy, the worldwide motion picture industry lost almost 18.2 billion U.S. dollars annually. Therefore, efforts have been put forth to prevent illicit videotaping using hidden cameras. One of the most effective ways to cease piracy is to directly locate the pirate and hand them to law enforcement officials. Hence,
in this thesis, we solved it by relating this piracy locating problem to the traditional camera calibration problems. Via the traditional camera calibration method and our revised method using constraints especially for cinemas, the pirate location can be estimated. Moreover, by pointing out a potential crisis that even 3D films are recordable, we specifically solve the piracy locating problem for 3D films. Finally, to show the effectiveness of the new methods as well as to compare it with previous ones, we run a series of simulations and experiments based on real positions acquired from our database, which is especially built for this research.

致謝ii
中文摘要iii
Abstract iv
1 Introduction 1
2 Related Works 5
2.1 Locating Piracy via Movie Soundtrack . . . . . . . . . 5
2.2 Locating Piracy via Movie Scene . . . . 6
2.2.1 Watermarking Scheme . . . . . . . . 6
2.2.2 Non-Watermarking Scheme . . . . . . . . . 6
3 Preliminaries 8
3.1 Camera Model . . . . . . . . . . . . . . . . . . 8
3.1.1 Intrinsic Parameters . . . . . . . . . . . . . . . 9
3.1.2 Extrinsic Parameters . . . . . . . . . . . . . . . 9
3.2 2D Homography . . . . . . . . . . . . . . . . . . . 11
4 Piracy Locating 13
4.1 Camera Calibration with One View . . . . . . . . 13
4.1.1 Orthonormal Constraint from R . . . . . . . . . 14
4.1.2 Parallelogram Constraint from Movie Scene . . . . 15
4.2 Camera Calibration with Two Views . . .. . . 18
4.2.1 Separating Two Views . . . . . . . . . . . . . . 18
4.2.2 Combining Two Views . . . . . . . . . . . . . . 18
4.3 Scenario for Piracy Locating . . . . . . . . . . 21
5 Evaluation and Discussion 23
5.1 Establishment of Dataset . . . . . . . . . . 23
5.1.1 Environment . . . . ... . . . . . . . . . . 23
5.1.2 Equipment . . . . . . . . . . . . . . . . . 24
5.1.3 Content . . . . . . . . . . . . . . . . 25
5.2 Evaluation on Simulated Data . . . . . . . . . . . . 25
5.2.1 Effectiveness . . . . . . . . . . . . . . . . . . . 25
5.2.2 Limitation . . . . . . . . . . . . . . . 27
5.3 Experiment on Real Data . . . . . . . . . . . . . . . . . . . 28
6 Conclusions 40
Bibliography 42

[1] http://www.mpaa.org/.
[2] http://www.thebusinessofentertainment.com/index.html.
[3] J. Bloom and C. Polyzois. Watermarking to track motion picture theft. In Signals,
Systems and Computers, 2004. Conference Record of the Thirty-Eighth Asilomar
Conference on, volume 1, pages 363–367 Vol.1, 2004.
[4] P. Bourdon, S. Thiebaud, J.-J. Sacr’e, and D. Doyen. A metamerism-based method to
prevent camcorder movie piracy in digital theaters. In Multimedia and Expo (ICME),
2010 IEEE International Conference on, pages 468–473, 2010.
[5] C.-Y. Chiu, C.-S. Chen, and L.-F. Chien. A framework for handling spatiotemporal
variations in video copy detection. Circuits and Systems for Video Technology, IEEE
Transactions on, 18(3):412–417, 2008.
[6] C.-Y. Chiu, H.-M. Wang, and C.-S. Chen. Fast min-hashing indexing and robust
spatio-temporal matching for detecting video copies. ACM Trans. Multimedia Comput.
Commun. Appl., 6(2):10:1–10:23, Mar. 2010.
[7] B. Chupeau, A. Massoudi, and F. Lefebvre. In-theater piracy: finding where the
pirate was. pages 68190T–68190T–10, 2008.
[8] P. Dong, J. Brankov, N. Galatsanos, Y. Yang, and F. Davoine. Digital watermarking
robust to geometric distortions. Image Processing, IEEE Transactions on,
14(12):2140–2150, 2005.
[9] M. Epstein and D. A. Stanton. Method and device for preventing piracy of video
material from theater screens, US Patent US6529600, March 2003.
[10] J. A. Fancher, D. H. Sitrick, and G. P. Sitrick. Movie film security system utilizing
infrared patterns, US Patent US6559883, May 2003.
[11] M. A. Fischler and R. C. Bolles. Random sample consensus: A paradigm for model
fitting with applications to image analysis and automated cartography. Communications
of the ACM, 24(6):381–395, 1981.
[12] A. Garboan, M. Mitrea, and F. Preteux. Cinematography sequences tracking by
means of fingerprinting techniques. annals of telecommunications - annales des
telecommunications, 68(3-4):187–199, 2013.
[13] J. Haitsma and T. Kalker. A watermarking scheme for digital cinema. In Image
Processing, 2001. Proceedings. 2001 International Conference on, volume 2, pages
487–489 vol.2, 2001.
[14] A. Hampapur, K. Hyun, and R. M. Bolle. Comparison of sequence matching techniques
for video copy detection. pages 194–201, 2001.
[15] M. A. Isnardi, J. Lubin, and M. Tinker. Camcorder jamming techniques using high
frame rate displays, US Patent US20090129746, May 2009.
[16] I. Karybali and K. Berberidis. Efficient spatial image watermarking via new perceptual
masking and blind detection schemes. Information Forensics and Security,
IEEE Transactions on, 1(2):256–274, 2006.
[17] N. Lazic and P. Aarabi. Communication over an acoustic channel using data hiding
techniques. Multimedia, IEEE Transactions on, 8(5):918–924, 2006.
[18] M.-J. Lee, K.-S. Kim, and H.-K. Lee. Digital cinema watermarking for estimating
the position of the pirate. Multimedia, IEEE Transactions on, 12(7):605–621, 2010.
[19] M.-J. Lee, K.-S. Kim, H.-Y. Lee, T.-W. Oh, Y.-H. Suh, and H.-K. Lee. Robust
watermark detection against d-a/a-d conversion for digital cinema using local autocorrelation
function. In Image Processing, 2008. ICIP 2008. 15th IEEE International
Conference on, pages 425–428, 2008.
[20] D. G. Lowe. Distinctive image features from scale-invariant keypoints. Int. J. Comput.
Vision, 60(2):91–110, Nov. 2004.
[21] Y. Nakashima, R. Tachibana, and N. Babaguchi. Maximum-likelihood estimation of
recording position based on audio watermarking. In Intelligent Information Hiding
and Multimedia Signal Processing, 2007. IIHMSP 2007. Third International Conference
on, volume 2, pages 255–258, 2007.
[22] Y. Nakashima, R. Tachibana, and N. Babaguchi. Watermarked movie soundtrack
finds the position of the camcorder in a theater. Multimedia, IEEE Transactions on,
11(3):443–454, 2009.
[23] J. O’Ruanaidh and T. Pun. Rotation, scale and translation invariant digital image
watermarking. In Image Processing, 1997. Proceedings., International Conference
on, volume 1, pages 536–539 vol.1, 1997.
[24] S. Pereira and T. Pun. Robust template matching for affine resistant image watermarks.
Image Processing, IEEE Transactions on, 9(6):1123–1129, 2000.
[25] R. Roopalakshmi and G. R. M. Reddy. A novel spatio-temporal registration framework
for video copy localization based on multimodal features. Signal Processing,
93(8):2339 – 2351, 2013. !ce:title¿Indexing of Large-Scale Multimedia Signals!/
ce:title¿.
[26] D. Wu, X. Zhou, and X. Niu. A novel image hash algorithm resistant to print–scan.
Signal Processing, 89(12):2415 – 2424, 2009. !ce:title¿Special Section: Visual Information
Analysis for Security!/ce:title¿.
[27] T. Yamada, S. Gohshi, and I. Echizen. Ir hiding: A method to prevent video reshooting
by exploiting differences between human perceptions and recording device characteristics. In H.-J. Kim, Y. Shi, and M. Barni, editors, Digital Watermarking,
volume 6526 of Lecture Notes in Computer Science, pages 280–292. Springer Berlin
Heidelberg, 2011.
[28] Z. Zhang, C. Cao, R. Zhang, and J. Zou. Video copy detection based on speeded up
robust features and locality sensitive hashing. In Automation and Logistics (ICAL),
2010 IEEE International Conference on, pages 13–18, 2010.