學術產出-Theses

Article View/Open

Publication Export

Google ScholarTM

政大圖書館

Citation Infomation

  • No doi shows Citation Infomation
題名 從多視角影像萃取密集影像對應
Dense image matching from multi-view images
作者 蔡瑞陽
Tsai, Jui Yang
貢獻者 何瑁鎧
Hor, Maw Kae
蔡瑞陽
Tsai, Jui Yang
關鍵詞 影像對應
多視角影像
極線轉換
三維建模
image processing
multi-view images
epipolar transfer
three-dimension model reconstruction
日期 2009
上傳時間 9-May-2016 15:29:12 (UTC+8)
摘要 在三維模型的建構上,對應點的選取和改善佔有相當重要的地位。對應點的準確性影響整個建模的成效。本論文中我們提出了新的方法,透過極線轉換法(epipolar transfer)在多視角影像中做可見影像過濾和對應點改善。首先,我們以Furukawa所提出的方法,建構三維補綴面並加以做旋轉和位移,或是單純在二維影像移動對應點兩種方式選取初始對應點。然後再以本研究所提出的極線轉換法找到適當位置的對應點。接下來我們將每個三維點的可見影像(visible image)再次透過極線轉換法去檢查可見影像上的對應點位置是否適當,利用門檻值將不合適的對應點過濾掉。進一步針對對應點位置的改善和篩選,期望透過極線幾何法來找到位置最準確的對應點位置。最後比較實驗成果,觀察到以本研究所提出的方法做改善後,對應點準確度提高近百分之十五。
In the construction of three-dimensional models, the selection and refinement of the correspondences plays a very important rule. The accuracy of the correspondences affects modeling results. In this paper, we proposed a new approach, that is filtering the visible images and improving the corresponding points in multi-view images by epipolar transfer method. First of all, we use Furukawa proposed method to construct three-dimensional patches and making rotation and displacement, or simply move the corresponding points in two-dimensional images are two ways to select the initial corresponding points. And then to use epipolar transfer method in this study to find the appropriate location of the corresponding points. Next we will check the corresponding points on the each 3D point’s visible image again through the polar transformation method , and we use the threshold value to filter out the corresponding points. Further the location of the corresponding points for the improvement and screening, hoped that through the epipolar geometry method to find the most accurate corresponding points’ location. Experimental results are compared to observe the improvements that the method proposed in this study, the corresponding point accuracy by nearly 15 percent.
第一章 緒論 1
     1.1 研究動機和目的 1
     1.2 問題描述 2
     1.3 系統架構與流程說明 3
     1.4 本論文的貢獻 4
     1.5 論文章節架構 5
     第二章 相關研究 7
     第三章 背景知識 13
     3.1 極線幾何 13
     3.2 投影幾何及三維座標 14
     3.3 零平均正規化相關匹配法 15
     3.4 多視角影像 16
     3.5 極線轉換 17
     3.6 色彩模型 18
     第四章 選取對應點 20
     4.1 以三維補綴面選取對應點 22
     4.1.1 特徵點選取 23
     4.1.2 建構初始三維補綴面 24
     4.1.3 三維補綴面之最佳化 25
     4.2 在平面上移動選取對應點 28
     第五章 對應點的過濾且改善 30
     5.1 極線轉換 30
     5.1.1 選取較合理的對應點 30
     5.1.2 對應點之過濾和改善 34
     5.2 相互支持限制法 38
     5.3 順序限制 39
     5.4 擴展和過濾 39
     第六章 實驗成果 43
     6.1 稀疏對應點之選取 44
     6.2 對應點之過濾和改善 48
     6.2 平面物體之測試 53
     6.3 使用不同色彩模型之比較 57
     6.4 擴展及建模 58
     第七章 結論 60
     7.1 結論 60
     7.2 未來研究 60
     參考文獻 62
參考文獻 [1] Furukawa, Y. and J. Ponce, “Accurate, Dense, and Robust Multi-View Stereopsis”, IEEE Conference on Computer Vision and Pattern Recognition, 1-8 2007.
     [2] Furukawa, Y. and J. Ponce, “Accurate Camera Calibration from Multi-View Stereo and Bundle Adjustment”, IEEE Conference on Computer Vision and Pattern Recognition, 1-8 2008.
     [3] Yebin Liu, X. Cao, Q. Dai and W. Xu, “Continuous Depth Estimation for Multi-view Stereo”, IEEE Computer Vision and Pattern Recognition, CVPR`09, June 2009.
     [4] Lowe, David G., “Distinctive Image Features from Scale-Invariant Keypoints”, International Journal of Computer Vision Vol. 60, No.2, 91–110, 2004.
     [5] Lhuillier M. and L. Quan, “Match Propagation for Image-based Modeling and Rendering”, IEEE Transactions on Pattern Analysis and Machine Intelligence, Vol.24, No.8, 1140-1146, 2002.
     [6] Yuille A. and T. Poggio, “A Generalized Ordering Constraint for Stereo Correspondence”, AI Memo 777, AI Lab, MIT, 1984.
     [7] C.-Y. Tang, H.-L. Chou, Y.-L. Wu and Y.-H. Ding, “Robust Fundamental Matrix Estimation Using Coplanar Constraints”, International Journal of Pattern Recognition and Artificial Intelligence, Vol. 24, No. 4, 2008.
     [8] Seitz S.M., B. Curless, J. Diebel, D. Scharstein, and R. Szeliski, “A Comparison and Evaluation of Multi-View Stereo Reconstruction Algorithms”, IEEE Conference on Computer Vision and Pattern Recognition, Vol. 1, 519-528 2006.
     [9] R. Hartley and A. Zisserman, “Multiple View Geometry in Computer Vision”, Cambridge University Press, 2003.
     [10] Jeng-Jiun T., “Robust Refinement Methods for Camera Calibration and 3D Reconstruction from Multiple Images”, Journal of Visual Communication and Image Representation, 2009.
     [11] Jui-Yang T., “Generation of Dense Image Matching Using Epipolar Geometry”, International Display Manufacturing Conference & 3D Systems and Applications, 2009.
     [12] Kun-Shin W., “Refinement of 3D Models Reconstructed from Visual Hull”, Conference on Computer Vision, Graphics and Image Processing, 2009.
     [13] 蔡政君, 使用光束調整法與多張影像做相機校正與三維模型重建, 國立政治大學資訊科學所碩士論文, 民國98年。
     [14] 洪莘逸, 使用多視角影像合成新視點影像, 華梵大學資訊管理所碩士論文, 民國96年。
     [15] 詹凱軒, 由地面光達資料自動重建建物模型之研究, 國立政治大學資訊科學所碩士論文, 民國96年。
描述 碩士
國立政治大學
資訊科學學系
96753015
資料來源 http://thesis.lib.nccu.edu.tw/record/#G0096753015
資料類型 thesis
dc.contributor.advisor 何瑁鎧zh_TW
dc.contributor.advisor Hor, Maw Kaeen_US
dc.contributor.author (Authors) 蔡瑞陽zh_TW
dc.contributor.author (Authors) Tsai, Jui Yangen_US
dc.creator (作者) 蔡瑞陽zh_TW
dc.creator (作者) Tsai, Jui Yangen_US
dc.date (日期) 2009en_US
dc.date.accessioned 9-May-2016 15:29:12 (UTC+8)-
dc.date.available 9-May-2016 15:29:12 (UTC+8)-
dc.date.issued (上傳時間) 9-May-2016 15:29:12 (UTC+8)-
dc.identifier (Other Identifiers) G0096753015en_US
dc.identifier.uri (URI) http://nccur.lib.nccu.edu.tw/handle/140.119/95269-
dc.description (描述) 碩士zh_TW
dc.description (描述) 國立政治大學zh_TW
dc.description (描述) 資訊科學學系zh_TW
dc.description (描述) 96753015zh_TW
dc.description.abstract (摘要) 在三維模型的建構上,對應點的選取和改善佔有相當重要的地位。對應點的準確性影響整個建模的成效。本論文中我們提出了新的方法,透過極線轉換法(epipolar transfer)在多視角影像中做可見影像過濾和對應點改善。首先,我們以Furukawa所提出的方法,建構三維補綴面並加以做旋轉和位移,或是單純在二維影像移動對應點兩種方式選取初始對應點。然後再以本研究所提出的極線轉換法找到適當位置的對應點。接下來我們將每個三維點的可見影像(visible image)再次透過極線轉換法去檢查可見影像上的對應點位置是否適當,利用門檻值將不合適的對應點過濾掉。進一步針對對應點位置的改善和篩選,期望透過極線幾何法來找到位置最準確的對應點位置。最後比較實驗成果,觀察到以本研究所提出的方法做改善後,對應點準確度提高近百分之十五。zh_TW
dc.description.abstract (摘要) In the construction of three-dimensional models, the selection and refinement of the correspondences plays a very important rule. The accuracy of the correspondences affects modeling results. In this paper, we proposed a new approach, that is filtering the visible images and improving the corresponding points in multi-view images by epipolar transfer method. First of all, we use Furukawa proposed method to construct three-dimensional patches and making rotation and displacement, or simply move the corresponding points in two-dimensional images are two ways to select the initial corresponding points. And then to use epipolar transfer method in this study to find the appropriate location of the corresponding points. Next we will check the corresponding points on the each 3D point’s visible image again through the polar transformation method , and we use the threshold value to filter out the corresponding points. Further the location of the corresponding points for the improvement and screening, hoped that through the epipolar geometry method to find the most accurate corresponding points’ location. Experimental results are compared to observe the improvements that the method proposed in this study, the corresponding point accuracy by nearly 15 percent.en_US
dc.description.abstract (摘要) 第一章 緒論 1
     1.1 研究動機和目的 1
     1.2 問題描述 2
     1.3 系統架構與流程說明 3
     1.4 本論文的貢獻 4
     1.5 論文章節架構 5
     第二章 相關研究 7
     第三章 背景知識 13
     3.1 極線幾何 13
     3.2 投影幾何及三維座標 14
     3.3 零平均正規化相關匹配法 15
     3.4 多視角影像 16
     3.5 極線轉換 17
     3.6 色彩模型 18
     第四章 選取對應點 20
     4.1 以三維補綴面選取對應點 22
     4.1.1 特徵點選取 23
     4.1.2 建構初始三維補綴面 24
     4.1.3 三維補綴面之最佳化 25
     4.2 在平面上移動選取對應點 28
     第五章 對應點的過濾且改善 30
     5.1 極線轉換 30
     5.1.1 選取較合理的對應點 30
     5.1.2 對應點之過濾和改善 34
     5.2 相互支持限制法 38
     5.3 順序限制 39
     5.4 擴展和過濾 39
     第六章 實驗成果 43
     6.1 稀疏對應點之選取 44
     6.2 對應點之過濾和改善 48
     6.2 平面物體之測試 53
     6.3 使用不同色彩模型之比較 57
     6.4 擴展及建模 58
     第七章 結論 60
     7.1 結論 60
     7.2 未來研究 60
     參考文獻 62
-
dc.description.tableofcontents 第一章 緒論 1
     1.1 研究動機和目的 1
     1.2 問題描述 2
     1.3 系統架構與流程說明 3
     1.4 本論文的貢獻 4
     1.5 論文章節架構 5
     第二章 相關研究 7
     第三章 背景知識 13
     3.1 極線幾何 13
     3.2 投影幾何及三維座標 14
     3.3 零平均正規化相關匹配法 15
     3.4 多視角影像 16
     3.5 極線轉換 17
     3.6 色彩模型 18
     第四章 選取對應點 20
     4.1 以三維補綴面選取對應點 22
     4.1.1 特徵點選取 23
     4.1.2 建構初始三維補綴面 24
     4.1.3 三維補綴面之最佳化 25
     4.2 在平面上移動選取對應點 28
     第五章 對應點的過濾且改善 30
     5.1 極線轉換 30
     5.1.1 選取較合理的對應點 30
     5.1.2 對應點之過濾和改善 34
     5.2 相互支持限制法 38
     5.3 順序限制 39
     5.4 擴展和過濾 39
     第六章 實驗成果 43
     6.1 稀疏對應點之選取 44
     6.2 對應點之過濾和改善 48
     6.2 平面物體之測試 53
     6.3 使用不同色彩模型之比較 57
     6.4 擴展及建模 58
     第七章 結論 60
     7.1 結論 60
     7.2 未來研究 60
     參考文獻 62
zh_TW
dc.source.uri (資料來源) http://thesis.lib.nccu.edu.tw/record/#G0096753015en_US
dc.subject (關鍵詞) 影像對應zh_TW
dc.subject (關鍵詞) 多視角影像zh_TW
dc.subject (關鍵詞) 極線轉換zh_TW
dc.subject (關鍵詞) 三維建模zh_TW
dc.subject (關鍵詞) image processingen_US
dc.subject (關鍵詞) multi-view imagesen_US
dc.subject (關鍵詞) epipolar transferen_US
dc.subject (關鍵詞) three-dimension model reconstructionen_US
dc.title (題名) 從多視角影像萃取密集影像對應zh_TW
dc.title (題名) Dense image matching from multi-view imagesen_US
dc.type (資料類型) thesisen_US
dc.relation.reference (參考文獻) [1] Furukawa, Y. and J. Ponce, “Accurate, Dense, and Robust Multi-View Stereopsis”, IEEE Conference on Computer Vision and Pattern Recognition, 1-8 2007.
     [2] Furukawa, Y. and J. Ponce, “Accurate Camera Calibration from Multi-View Stereo and Bundle Adjustment”, IEEE Conference on Computer Vision and Pattern Recognition, 1-8 2008.
     [3] Yebin Liu, X. Cao, Q. Dai and W. Xu, “Continuous Depth Estimation for Multi-view Stereo”, IEEE Computer Vision and Pattern Recognition, CVPR`09, June 2009.
     [4] Lowe, David G., “Distinctive Image Features from Scale-Invariant Keypoints”, International Journal of Computer Vision Vol. 60, No.2, 91–110, 2004.
     [5] Lhuillier M. and L. Quan, “Match Propagation for Image-based Modeling and Rendering”, IEEE Transactions on Pattern Analysis and Machine Intelligence, Vol.24, No.8, 1140-1146, 2002.
     [6] Yuille A. and T. Poggio, “A Generalized Ordering Constraint for Stereo Correspondence”, AI Memo 777, AI Lab, MIT, 1984.
     [7] C.-Y. Tang, H.-L. Chou, Y.-L. Wu and Y.-H. Ding, “Robust Fundamental Matrix Estimation Using Coplanar Constraints”, International Journal of Pattern Recognition and Artificial Intelligence, Vol. 24, No. 4, 2008.
     [8] Seitz S.M., B. Curless, J. Diebel, D. Scharstein, and R. Szeliski, “A Comparison and Evaluation of Multi-View Stereo Reconstruction Algorithms”, IEEE Conference on Computer Vision and Pattern Recognition, Vol. 1, 519-528 2006.
     [9] R. Hartley and A. Zisserman, “Multiple View Geometry in Computer Vision”, Cambridge University Press, 2003.
     [10] Jeng-Jiun T., “Robust Refinement Methods for Camera Calibration and 3D Reconstruction from Multiple Images”, Journal of Visual Communication and Image Representation, 2009.
     [11] Jui-Yang T., “Generation of Dense Image Matching Using Epipolar Geometry”, International Display Manufacturing Conference & 3D Systems and Applications, 2009.
     [12] Kun-Shin W., “Refinement of 3D Models Reconstructed from Visual Hull”, Conference on Computer Vision, Graphics and Image Processing, 2009.
     [13] 蔡政君, 使用光束調整法與多張影像做相機校正與三維模型重建, 國立政治大學資訊科學所碩士論文, 民國98年。
     [14] 洪莘逸, 使用多視角影像合成新視點影像, 華梵大學資訊管理所碩士論文, 民國96年。
     [15] 詹凱軒, 由地面光達資料自動重建建物模型之研究, 國立政治大學資訊科學所碩士論文, 民國96年。
zh_TW