臺灣博碩士論文加值系統

本論文中，提出一個透過擴增實境技術與結合視訊即時影像處理所開發的體感互動式平台。隨著數位多媒體相關產品的技術提升與普及，數位相機、智慧型手機等數位攝影裝置與日常生活漸漸密不可分。多數人常常在旅遊時，拍回一大堆數位相片，卻發現拍攝效果不好，為了產生具有紀念價值的照片，必須要藉由影像處理人員與專業工具進行編修。一般使用者在對相片進行處理或事後製的修圖動作，如果使用人工的方式調整，往往過於繁雜，需要較多的時間卻又效果不佳。
本研究主要目的是開發一套基於白平衡調整技術與體感互動之即時影像合成系統，用以解決上述問題。透過Webcam視訊擷取影格，進行即時處理，相關的影格處理動作包含(1)使用虛擬攝影棚背景相減的方式完整把人物從影像中擷取出來，取代虛擬的3D物體，(2)針對人物影像進行邊緣平滑與雜訊去除，(3)將人物影像序列即時嵌入播放的影像或是預合成的圖片中，(4) 利用影像色溫的即時調整技術，讓合成影像顯示更加自然的效果，(5)結合手勢的動作偵測，進行遊戲或是介面控制。透過手部位置互動更換場景，將人物與虛擬場景進行合成，達到互動效果。
本研究所完成的即時影像合成系統，可以讓使用者隨意選擇不同的景點背景圖，進行照片合成的動作，另外本研究同時延伸此方法，將自己的動作投影到其他視訊影格中，產生合成的視訊，在本論文中我們已經開發完成視訊合成的雛型系統。此研發成果應用在體操、舞蹈與肢體運動的教育用途上，可幫助使用者進行自我訓練與輔助動作的學習。

In this study, we proposed an interactive platform which is combined augmented reality and real-time video processing technique. With the enhancement and popularity of the digital multimedia products, digital cameras, smart phones and other digital photography devices gradually become popularized in daily life. While traveling, most of the people like to shoot a lot of photos. However, some of those commemorative photos were not satisfied by people since the disadvantaged circumstances such as lighting effect. In general, these unsatisfactory photos can be edited using professional image processing tools. But the picture editing process would be too complicated, time consuming and ineffective
The purpose of this study is to develop a somatosensory interaction and real-time image synthesis system based on which balance adjustment to solve the above problem. The related techniques of the designed system include (1) a virtual studio background subtraction method to extract the characters from the captures images, (2) image edge smoothing and noise removal, (3) embedding the extracted character image sequence into background image to create pre-synthesized picture, (4) color adjustments of image according to color temperature information, so that the composite image can show a more natural effect,(5) combined with gestures, motion detection, game or interface control.
The developed real-time video synthesis system can allow the user free to choose the different scenic spots in the background. We also extended this method to project the segmented character image onto the other video frames, to produce synthetic video. The experimental results can be applied in gymnastics, dance and body movement, educational purposes, to help users self-training and supporting action learning.

摘要 I
ABSTRACT II
誌謝 IV
目錄 V
表目錄 VI
圖目錄 VII
第一章 緒論 1
1.1 研究背景 1
1.2 研究動機 2
1.3 研究目的 3
1.4 論文架構 5
第二章 文獻探討 6
2.1 AR技術介紹 6
2.2 前景影像切割 9
2.3 影像色彩調整與相關技術 10
2.3.1 CIE色彩空間 10
2.3.2 HSV色彩空間 12
2.4 色溫相關技術比較 14
2.5 影像合成系統比較 16
第三章 研究方法 19
3.1 前景影像處理 21
3.1.1 背景相減法 22
3.1.2 前景物件提取 24
3.1.3 前景物件輪廓平滑化 29
3.2 手部動作偵測 31
3.3 基於影像色溫調校影像技術 32
3.4 合成影像拼接技術 40
第四章 實驗結果 41
4.1 參考圖影像自動調整影像色彩 42
4.2 系統效能評估 46
4.3 AR系統實驗結果 48
第五章 結論與未來工作 52
參考文獻 53

[1]Mobile AR Content Downloads to Top 400 Million, Juniper Research Jan. 2010.
http://news.softpedia.com/news/Mobile-AR-Content-Downloads-to-Top-400-Million-by-2014-131196.shtml
[2]Special Reports 10 Emerging Techologies http://www.technologyreview.com/special/emerging/
[3]Z. Feng, B. Henry, B. Mark. "Trends in Augmented Reality Tracking, Interaction and Display:A Review of Ten Years of ISMAR".IEEE International Symposium on Mixed and Augmented Reality, 193-202, 2008.
[4]J. P. Rolland, L. Davis and Y. Baillot."A survey of tracking technology for virtual environments, In Fundamentals of Wearable Computers and Augmented Reality". 1st ed, W. Barfield and T. Caudell,Eds. Mahwah, NJ: CRC, pp. 67-112, 2001.
[5]M. Pressigout and E. Marchand. "Hybrid tracking algorithms for planar and non-planar structures subject to illumination changes". In ISMAR ‘06, pp. 52-55, 2006.
[6]X. Zhang; Fronz, S.; Navab, N. "Visual marker detection and decoding in AR systems: a comparative study".In ISMAR, pp. 97 – 106, 2002.
[7]N. Navab, E. Cubillo, B. Bascle, J. Lockau, K. D.Kamsties, and M. Neuberger. "CyliCon: a software platform for the creation and update of virtual factories". In Proc.of the 7th IEEE Int’l.Conference on Emerging Technologies and Factory Automation,pages 459–463, Barcelona, Spain, 1999.
[8]Andreas Dunser, Eva Hornecker ."Lessons from an AR book study" TEI''07, 15-17, Baton Rouge, LA, USA Chapter 4, Feb 2007.
[9]Park, S. You and U. Neumann. "Natural feature tracking for extendible robust augmented realities". In IWAR ‘98, 1998.
[10]張兆翔. "An Efficient Augmented Reality Architecture by Binary Tree and Optical Flow". 國立高雄第一科技大學資管系碩士論文 July 2009.
[11]S.O.Lee, S.C. Ahn, J.I. Hwang, H.G. Kim. "A Vision-Based Mobile Augmented Reality System for Baseball Games".Virtual and Mixed Reality, Part I, HCII 2011, LNCS 6773, pp. 61–68, 2011.
[12]Shao-Yi Chien, Shyh-Yih Ma, and Liang-Gee Chen.(2002). "Efficient Moving Object Segmentation Algorithm Using Background Registration Technique".IEEE transaction on circuits and system for video technology, VOL. 12, NO. 7, JULY 2002.
[13]David Harwood,Larry S. Davis,"Real-Time Surveillance of People and Their Activities",IEEE tramsaction on pattern analysis and machine intelligence, VOL. 22, NO. 8, AUGUST 2000
[14]Kyungnam Kim, Thanarat H. Chalidabhongse, David Harwood, LarryDavis,"Real-time foreground–background segmentation using codebookmodel",Real-Time Imaging 11 (2005) 172–185
[15]Hsien-Che Lee (2005). "Introduction to Color Imaging Science". Cambridge University Press. p. 450.
[16]K. Wnukowicz, W. Skarbek. "Color temperature estimation algorithm for digital images properties and converge". Opto-electronics Review, vol.11, no. 3, pp. 193-196, 2003.
[17]Michael Stokes(Hewlett-Packard), Matthew Anderson (Microsoft), SrinivasanChandrasekar (Microsoft), Ricardo Motta (Hewlett-Packard). "A Standard Default Color Space for the Internet-sRGB". page1-17.Version 1.10, November 5, 1996.
[18]Mary Nielsen and Michael Stokes ."The Creation of the sRGB ICC Profile ." Hewlett-Packard Company Boise, Idaho/USA
[19]Sural, S.; Gang Qian; Pramanik, S." Segmentation and histogram generation using the HSV color space for image retrieval ",IEEE Image Processing 2002 International Conference on Page(s): II-589-II-592 vol.2
[20]Cheng-Lun Chen, Shao-HuaLin,"Intelligent color temperature estimation using fuzzy neural network with application to automatic white balance",Expert Systems with Applications 38 (2011) 7718–7728
[21]Edoardo Provenzi, Carlo Gatta, Massimo Fierro, and Alessandro Rizzi,"A Spatially Variant White-Patch and Gray-World Method for Color Image Enhancement Driven by Local Contrast",IEEE Transactions on pattern analysis and machine intelligence, VOL. 30, NO. 10, OCTOBER 2008
[22]Brainard, D. A., &Wandell, B. A. (1986). " Analysis of the Retinex theory of color vision". Journal of the Optical Society of America A, 3, 1651–1661.
[23]McCann, John J., McKee, Suzanne P., & Taylor, Thomas H. (1976). "Quantitativestudies in Retinex theory". Vision Research, 16, 445–458.
[24]Finlayson, G. D. (1996). "Color in perspective". IEEE Transactions on Pattern Analysisand Machine Intelligence, 18, 1034–1038.
[25]Finlayson, G. D., &Hordley, S. (2000). " Improving Gamut mapping color constancy".IEEE Transactions on Image Processing, 9(10), 1774–1783.
[26]Tominaga, S., &Wandell, B. A. (1990). "Component estimation of surface spectralreflectance". Journal of the Optical Society of America A, 7, 312–317.
[27]Lee, H.-C. (1986). "Method for computing the scene-illuminant chromaticity fromspecular highlights". Journal of the Optical Society of America A, 3, 1699–1964.
[28]嚴崇仁、李同益,"多媒體影像合成",行政院國家科學委員會2007.
http://web1.nsc.gov.tw/ct.aspx?xItem=8461&ctNode=40&mp=1
[29]諸葛慧，色溫調整影像合成技術之研究，國立臺灣師範大學碩士論文，2005.
[30]A.D. Cheok, "Art and Technology of Entertainment Computing and Communication,-Chapter 3: Interactive Theater Experience with 3D Live Captured Actors and Spatial Sound". Springer-Verlag London Limited, 2010.
[31]Yong Kui Liu, BorutŽalik,"An efficient chain code with Huffman coding",Pattern Recognition 38 (2005) 553 – 557.
[32]H.K. Lam; Au, O.S.; C.W. Wong. " Automatic white balancing using standarddeviation of RGB components”. Circuits and Systems". ISCAS ''04. Proceedings of the2004 International Symposium on Volume 3, 23-26 May 2004 Page(s):III - 921-4Vol.3, 2004