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：	黃雅涵 Huang, Ya-Han
論文名稱：	基於多尺度影像切割與迭代式修正之強健立體匹配 Robust Stereo Matching Using Multiscale Segmentation and Iterative Refinement
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：	2019
畢業學年度：	107
語文別：	英文
論文頁數：	64
中文關鍵詞：	立體匹配技術、十字適應性區域、影像切割、適應性權重、基於深度影像生成技術、深度修正
外文關鍵詞：	stereo matching, cross-based region, image segmentation, ASW, DIBR, depth refinement
相關次數：	點閱：51 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3D裸眼技術的快速發展，人們希望能夠透過3D裸眼技術達到更舒適且真實的視覺體驗。避免傳送複雜的多視角影像，3D訊息可改用較有效率的單視角影像加上景深圖方式描述，景深圖可表示每一像速到觀賞者的距離。因此，利用雙視角產生深度資訊的技術成為相當重要的議題。在電腦視覺研究中，雙視角的立體匹配演算法是非常重要的議題，其目的即為獲得最精確且符合立體視覺的深度圖。一般而言，較為平滑或是圖形不連續的區域通常會在深度計算中導致錯誤的匹配而造成深度圖的誤差。在本論文中，我們提出基於多尺度影像切割的方法，來計算代價合併中的適應性權重，以改善只利用顏色與位置差異性的權重估計。另外，為了獲得更精確的深度圖，我們最後使用迭代式的深度修正來提升深度圖的正確性與品質。在深度修正的過程中，我們使用十字適應性區域結合邊緣偵測來修正初始的深度圖。本篇論文的實驗結果顯示出比起其他立體匹配演算法能得到更精準與高品質的深度圖。

With the rapid development of 3D display technologies, people are inclined to enjoy more comfortable and realistic fine vision through naked-eyes 3D displays. Instead of transmitting complex multiple views, the 3D video information can be effectively represent by a color texture frame with its corresponding depth map, which describes the pixel distance from the camera center. Stereo matching is one of the most important topics in binocular stereo computer vision and aims at reconstructing precise depth map. Generally, smooth, occluded and discontinuous regions are the main challenges that might easily produce errors in stereo matching. In this thesis, we first propose a stereo matching algorithm, which uses multiscale segmentation information to calculate the adaptive support weight in cost aggregation instead of color similarity and spatial proximity only. In order to generate high accuracy disparity map, iterative refinement is further proposed to correct the raw disparity map. In depth refinement step, we utilized the cross-based support region by referring texture image to correct the error disparity and adopted the iterative procedure to further improve the performance. The experimental results show that the proposed method can obtain higher accurate depth map compared with the conventional methods.

摘 要........I
Abstract........II
Contents........IV
List of Tables........VII
List of Figures........VIII
Chapter 1  Introduction........1
1 Research Background........1
1.1 Introduction of Stereopsis........2
1.2 Applications in Various Aspects for Computer Vision........3
2 Motivations........6
3 Thesis Organization........6
Chapter 2  Related Works........8
1 Concept of Stereo Matching........8
1.1 Literature Review........10
2 Fundamental of Local Stereo Matching........11
2.1 Matching Cost Computation........12
2.2 Cost Aggregation........15
2.2.1 Weight Calculation........15
2.2.2 Cost Aggregation........18
2.3 Disparity Decision........18
2.4 Disparity Refinement........19
3 SLIC Superpixels........22
Chapter 3  The Proposed Stereo Matching System with Iterative Depth Refinement........25
1 Overview of the Proposed System........25
2 Modified Local Stereo Matching Method........27
2.1 Plane Decision and Cost Computation........27
2.2 Multiscale Segmentation-based Cost Aggregation........31
2.2.1 Multiscale Segmentation-based ASW........32
2.2.2 Cost Aggregation........34
2.3 Two-level WTA Strategy........34
3 Iterative Depth Map Refinement........35
3.1 Mismatched Region Filling........37
3.2 Occlusion Region Filling........38
3.2.1 Non-Border Occlusion Filling........39
3.2.2 Border Occlusion Filling........40
Chapter 4  Experimental Results........43
1 Performance Evaluation of the Proposed Algorithm........43
2 Results of the Proposed System........47
2.1 Performance of Estimated Depth Map........47
2.2 Comparisons with Other Approaches........49
2.2.1 Error Evaluation of Estimated Depth Map........49
2.2.2 Performance of DIBR........54
Chapter 5  Conclusions........59
Chapter 6  Future Work........60
References........61

                                    

[1]I. P. Howard and B. J. Rogers. (1995, Nov. 30), Binocular vision and stereopsis (1st ed.) [Online]. 2. Available DOI: 10.1093/acprof:oso/9780195084764.001.0001.
[2]S. C. Chan, H. Shum and K. Ng, "Image-Based Rendering and Synthesis," in IEEE Signal Processing Magazine, vol. 24, no. 6, pp. 22-33, Nov. 2007.
[3]W. Luo, A. G. Schwing and R. Urtasun, "Efficient Deep Learning for Stereo Matching," 2016 IEEE Conference on Computer Vision and Pattern Recognition (CVPR), Las Vegas, NV, 2016, pp. 5695-5703.
[4]E. Zappa, P. Mazzoleni, Y. Hai, "Stereoscopy based 3D face recognition system", Proc. Comput. Sci., vol. 1, no. 1, pp. 2529-2538, 2010.
[5]Jian Sun, Nan-Ning Zheng and Heung-Yeung Shum, "Stereo matching using belief propagation," in IEEE Transactions on Pattern Analysis and Machine Intelligence, vol. 25, no. 7, pp. 787-800, July 2003.
[6]Y. Boykov, O. Veksler and R. Zabih, "Fast approximate energy minimization via graph cuts," in IEEE Transactions on Pattern Analysis and Machine Intelligence, vol. 23, no. 11, pp. 1222-1239, Nov. 2001.
[7]X. Sun, X. Mei, S. Jiao, M. Zhou and H. Wang, "Stereo Matching with Reliable Disparity Propagation," 2011 International Conference on 3D Imaging, Modeling, Processing, Visualization and Transmission, Hangzhou, 2011, pp. 132-139.
[8]Sing Bing Kang, R. Szeliski and Jinxiang Chai, "Handling occlusions in dense multi-view stereo," Proceedings of the 2001 IEEE Computer Society Conference on Computer Vision and Pattern Recognition. CVPR 2001, Kauai, HI, USA, 2001, pp. I-I.
[9]O. Veksler, "Fast variable window for stereo correspondence using integral images," 2003 IEEE Computer Society Conference on Computer Vision and Pattern Recognition, 2003. Proceedings., Madison, WI, USA, 2003, pp. I-I.
[10]Kuk-Jin Yoon and In So Kweon, "Adaptive support-weight approach for correspondence search," in IEEE Transactions on Pattern Analysis and Machine Intelligence, vol. 28, no. 4, pp. 650-656, April 2006.
[11]K. Zhang, J. Lu and G. Lafruit, "Cross-Based Local Stereo Matching Using Orthogonal Integral Images," in IEEE Transactions on Circuits and Systems for Video Technology, vol. 19, no. 7, pp. 1073-1079, July 2009.
[12]F. Tombari, S. Mattoccia, L. Di Stefano, "Segmentation-based adaptive support for accurate stereo correspondence" in Lecture Notes in Computer Science, Berlin, Germany:Springer, vol. 4872, pp. 427-438, Dec. 2007.
[13]D. Chang, S. Wu, H. Hou and L. Chen, "Accurate and fast segment-based cost aggregation algorithm for stereo matching," 2017 IEEE 19th International Workshop on Multimedia Signal Processing (MMSP), Luton, 2017, pp. 1-6.
[14]H. Zhu, J. Yin and D. Yuan, "SVCV: segmentation volume combined with cost volume for stereo matching," in IET Computer Vision, vol. 11, no. 8, pp. 733-743, 12 2017.
[15]Stereo - Middlebury Computer Vision [Online]. Available: http://vision.middlebury.edu/stereo/.
[16]K. L. Lo, “A real-time stereo matching algorithm with iterative aggregation and its VLSI implementation,” M.S. thesis, National Cheng Kung University, Tainan, Taiwan, July 2015.
[17]H. T. Kuo, “VLSI Implementation of Real-Time Stereo Matching and Centralized Texture Depth Packing for 3D Video Broadcasting,” M.S. thesis, National Cheng Kung University, Tainan, Taiwan, July 2017.
[18]C. L. Hsieh, “A Two-View to Multi-View Conversion System and Its VLSI Implementation for 3D Displays,” M. S. Thesis, National Cheng Kung University, Tainan, Taiwan, July 2017.
[19]A. Emlek, M. Peker and K. F. Dilaver, "Variable window size for stereo image matching based on edge information," 2017 International Artificial Intelligence and Data Processing Symposium (IDAP), Malatya, 2017, pp. 1-4.
[20]T. Y. Sun, “Stereo Matching and Depth Refinement on GPU Platform,” M. S.Thesis, National Cheng Kung University, Tainan, Taiwan, July 2018.
[21]R. Achanta, A. Shaji, K. Smith, A. Lucchi, P. Fua and S. Süsstrunk, "SLIC Superpixels Compared to State-of-the-Art Superpixel Methods," in IEEE Transactions on Pattern Analysis and Machine Intelligence, vol. 34, no. 11, pp. 2274-2282, Nov. 2012.
[22]K. J. Hsu, “GPU implementation for centralized texture depth depacking and depth image-based rendering,” M. S. Thesis, National Cheng Kung University, Tainan, Taiwan, July 2017.
[23]M. Bleyer, C. Rother, P. Kohli, D. Scharstein and S. Sinha, "Object stereo — Joint stereo matching and object segmentation," CVPR 2011, Colorado Springs, CO, USA, 2011, pp. 3081-3088.
[24]T. Chen and W. Li, "Stereo matching algorithm based on adaptive weight and local entropy," 2017 9th International Conference on Modelling, Identification and Control (ICMIC), Kunming, 2017, pp. 630-635.

校內：2024-09-01公開
校外：2024-09-01公開

簡易檢索 / 詳目顯示

相關論文