成功大學博碩士論文系統

簡易檢索 / 詳目顯示

回結果列表

研究生：	洪譽禎 Hung, Yu-Chen
論文名稱：	一種用於多視角影像內插之區域視差向量估計演算法 A Segment-Based Disparity Estimation Algorithm for Multiview Image Interpolation
指導教授：	楊家輝 Yang, Jar-Ferr
學位類別：	碩士 Master
系所名稱：	電機資訊學院 - 電腦與通信工程研究所 Institute of Computer & Communication Engineering
論文出版年：	2010
畢業學年度：	98
語文別：	英文
論文頁數：	73
中文關鍵詞：	虛擬影像生成、視差向量、區域向量估計、影像修補
外文關鍵詞：	Virtual image generation, disparity, segment-based disparity estimation, hole filling
相關次數：	點閱：109 下載：0
分享至:	分享至facebook 分享至twitter

查詢本校圖書館目錄查詢臺灣博碩士論文知識加值系統勘誤回報

隨著電腦視覺與圖學的發展，在產生虛擬影像方面的研究有顯著的進步。虛擬影像的產生技術可應用於自由視角電視。自由視角電視是一項可允許觀賞者選擇其所想要觀賞的視角的創新應用。若由多支視角預先定義的相機所拍攝而得的真實影像是可取得的，則虛擬影像可由擷取到的真實影像所內插而成。本篇論文的目的在於實現一個可內插虛擬影像的系統。在本論文中，首先我們提出了一種區域向量估測的演算法。用於顏色分類的方塊分割法可以避免過度冗長的分類程序及耗時的問題。論文中也會介紹改善視差向量的方法。接下來，三種影像內插的方法也會被詳細的介紹。我們所提出的影像內插的方法還可應用於合成3D 立體影像上。最後，為了得到更好的內插結果，修補影像內插之後所產生的空洞是需要的。

Researches in both computer vision and graphics have made great progress toward virtual image generation. Virtual image generation is applied to FTV which is an innovative application that permits the viewers selecting the desired viewpoints. Supposing the real images captured by multiple cameras at predefined viewpoints are available, the virtual images are able to be generated by interpolating the captured real images. The objective of the thesis is to realize a virtual image generating system.
In the thesis, a segment-based disparity estimation algorithm is proposed first. Block-based segmentation which is not tedious and time-consuming is utilized. The scheme for disparity refinement is also presented. Next, three image interpolation approaches are described in details. 3D stereo images are able to be synthesized using the proposed interpolation method. Finally, hole filling is required for the purpose of obtaining the delicate interpolated images.

摘  要	                                         i
Abstract	                                ii
TABLE OF CONTENTS	                        iv
Introduction	                                 1
1 Motivation	                                 1
2 Organization of the Thesis	                 1
Overview of Multiview Geometry	         2
1 Introduction to 3D Space	                 2
1.1 World Coordinate System	                 2
1.2 3D Stereo Vision	                         3
2 Multiview Camera Geometry	                 3
2.1 Projective Geometry	                 4
2.2 Camera coordinate system	                 4
2.3 Pinhole Camera Model	                 5
2.4 Principal Point Offset	                 6
2.5 Intrinsic Parameter	                 7
2.6 Extrinsic Parameter	                 7
2.7 Projective matrix	                         8
2.8 Epipolor Geometry                  	 9
2.9 Fundamental Matrix	                10
Disparity Estimation Algorithm	        12
1 Overview	                                12
2 Image Enhancement Filters	                12
2.1 Generalized Weighted Smoothing Filter 	13
2.2 High-boost Filter	                        13
2.3 Sharpening Filter	                        14
2.4 Median Filter	                        15
3 Color-Based Segmentation	                15
3.1 Image Pre-process	                        16
3.2 Block-Based Segmentation	                19
3.3 Segment Mergence	                        24
3.4 Division for Large Segments	        27
4 Initial Disparity Estimation	        28
4.1 Image Pre-Process	                        29
4.2 Block-Based Search	                30
4.3 Disparity Inheritance	                32
4.4 Matching Probability	                33
4.5 Disparity Diffusion	                37
5 Disparity Refinement	                40
5.1 Disparity Refinement for Large segLs	40
5.2 Disparity Diffusion for Small segLs	45
6 Summary	                                47
Image View Interpolation Schemes	        48
1 Overview	                                48
2 Proposed Schemes for Image Interpolation	48
2.1 Image Interpolation based on Linear Interpolation in 2D Space	                                48
2.2 Parameter Estimation of Virtual Camera and 2D image Interpolation	                                50
2.3 3D image Interpolation	                55
3 Procedures of Three Interpolation Schemes	57
3.1 Occlusion Issue	                        57
3.2 Procedures of Image Interpolation Using Linear Interpolation	                                60
3.3 Procedures of Image Interpolation Using Interpolated Camera Parameters	                        61
3.4 The 3D Image Interpolation Using Interpolated Camera Parameters	                                62
4 Hole Filling	                        62
5 Summary	                                63
Experimental Results	                        64
1 Experimental Environment Settings	        64
2 Experimental Results	                66
Conclusions and Future Works	                71
1 Conclusions	                                71
2 Future Works	                        71
References	                                73


                                    

[1] L. Zitnick, S.B. Kang, M. Uyttendaele, S. Winder, and R. Szeliski, “High-quality video view interpolation using a layered representation,” ACM Trans. Graph., vol. 23, no. 3, pp. 600–608, 2004.

[2] K.R. Connor and I.D. Reid, “Novel view specification and synthesis,” in Proc. Brit. Mach. Vision Conf., 2002, Cardiff, England, pp. 243–252.

[3] W. Li, J. Zhou, B. Li, I. Sezan, ”Virtual view specification and synthesis for free viewpoint television,” IEEE Trans. Circuits Syst. Video Technol., vol. 19, no. 4, pp. 533-546, Apr 2009.

[4] H. Saito, S. Baba, T. Kanade, “Appearance-based virtual view generation from multicamera videos captured in the 3-D room,” IEEE Trans. on Multimedia, vol. 5, no. 3, pp. 303-316, Sep 2003.

[5] G. Arfken, Mathematical Methods for Physicists. 3rd ed. Orlando, FL: Academic Press, 1985.

[6] R. W. Brockett, “Robotic manipulators and the product of exponentials formula,” in Proc. Int. Symp. Math. Theory Networks Syst., 1983, Blacksburg, VA, pp. 120–127.

[7] J. B. Kuipers, Quaternions and Rotation Sequences: A Primer with Applications to Orbits, Aerospace and Virtual Reality. Princeton, NJ: Princeton Univ. Press, 2002.

[8] N. Bangchang, T. Fujii, and M. Tanimoto, “Experimental system of free viewpoint TeleVision,” in Proc. IST/SPIE Symp. Electron. Imaging, vol. 5006, no. 66, Jan. 2003, pp. 554–563.

[9] M. Tanimoto and T. Fujii, “FTV: Achievements and Challenges,” ISO/IEC JTC1/SC29/WG11 M11259, Oct. 2004.

校內：2015-08-04公開
校外：不公開電子論文尚未授權公開，紙本請查館藏目錄

簡易檢索 / 詳目顯示

相關論文