學術產出-Theses
Article View/Open
Publication Export
-
題名 基於多視角幾何萃取精確影像對應之研究
Accurate image matching based on multiple view geometry作者 謝明龍
Hsieh, Ming Lung貢獻者 何瑁鎧
Hor, Maw Kae
謝明龍
Hsieh, Ming Lung關鍵詞 多視角影像
對應點匹配
補綴面
點雲
三維模型重建
multi-view images
corresponding point matching
patch
point cloud
3D model reconstruction日期 2010 上傳時間 4-Sep-2013 17:09:06 (UTC+8) 摘要 近年來諸多學者專家致力於從多視角影像獲取精確的點雲資訊，並藉由點雲資訊進行三維模型重建等研究，然而透過多視角影像求取三維資訊的精確度仍然有待提升，其中萃取影像對應與重建三維資訊方法，是多視角影像重建三維資訊的關鍵核心，決定點雲資訊的形成方式與成效。本論文中，我們提出了一套新的方法，由多視角影像之間的幾何關係出發，萃取多視角影像對應與重建三維點，可以有效地改善對應點與三維點的精確度。首先，在萃取多視角影像對應的部份，我們以相互支持轉換、動態高斯濾波法與綜合性相似度評估函數，改善補綴面為基礎的比對方法，提高相似度測量值的辨識力與可信度，可從多視角影像中獲得精確的對應點。其次，在重建三維點的部份，我們使用K均值分群演算法與線性內插法發掘潛在的三維點，讓求出的三維點更貼近三維空間真實物體表面，能在多視角影像中獲得更精確的三維點。實驗結果顯示，採用本研究所提出的方法進行改善後，在對應點精確度的提升上有很好的成效，所獲得的點雲資訊存在數萬個精確的三維點，而且僅有少數的離群點。
Recently, many researchers pay attentions in obtaining accurate point cloud data from multi-view images and use these data in 3D model reconstruction. However, this accuracy still needs to be improved. Among these researches, the methods in extracting the corresponding points as well as computing the 3D point information are the most critical ones. These methods practically affect the final results of the point cloud data and the 3D models so constructed.In this thesis, we propose new approaches, based on multi-view geometry, to improve the accuracy of corresponding points and 3D points. Mutual support transformation, dynamic Gaussian filtering, and similarity evaluation function were used to improve the patch-based matching methods in multi-view image correspondence. Using these mechanisms, the discrimination ability and reliability of the similarity function and, hence, the accuracy of the extracted corresponding points can be greatly improved. We also used K-mean algorithms and linear interpolations to find the better 3D point candidates. The 3D point so computed will be much closer to the surface of the actual 3D object. Thus, this mechanism will produce highly accurate 3D points. Experimental results show that our mechanism can improve the accuracy of corresponding points as well as the 3D point cloud data. We successfully generated accurate point cloud data that contains tens of thousands 3D points, and, moreover, only has a few outliers.參考文獻 [1]李唐宇，"結合多元資料重建三維房屋模型"，中央大學土木工程學所碩士論文，民國96年。[2]吳坤信，"從多視角已校正影像改善三維粗略模型"，政治大學資訊科學所碩士論文，民國98年。[3]林立哲，"融合光達點雲以及航照影像於三維房屋模型之變遷偵測"，中央大學土木工程學所碩士論文，民國99年。[4]莊子毅，"以三維直線特徵進行地面光達點雲套合"，臺灣大學土木工程學所碩士論文，民國95年。[5]詹凱軒，"利用地面光達資料自動重建建物模型之研究"，政治大學資訊科學所碩士論文，民國96年。[6]蔡瑞陽，"從多視角萃取密集影像對應"，政治大學資訊科學所碩士論文，民國98年。[7]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"，政治大學資訊科學所碩士論文，民國98年。[8]鄭邦寧，"使用空載光達點雲求定數值地表高程模型之小波法"，成功大學測量及空間資訊學所碩士論文，民國96年。[9]Sameer Agarwal, Yasutaka Furukawa, Noah Snavely, Brian Curless, Steven M. Seitz and Richard Szeliski, "Reconstructing Rome," Computer, IEEE Computer Society Press, vol. 43, pp. 40-47, 2010.[10]Derek Bradley, Tamy Boubekeur and Wolfgang Heidrich, "Accurate Multi-View Reconstruction Using Robust Binocular Stereo and Surface Meshing," IEEE Conference on Computer Vision and Pattern Recognition, pp. 1-8, 2008.[11]Neill D.F. Campbell, George Vogiatzis, Carlos Hernández and Roberto Cipolla, "Automatic 3D Object Segmentation in Multiple Views Using Volumetric Graph-Cuts," Image and Vision Computing, vol. 28, pp. 14-25, 2008.[12]Neill D.F. Campbell, George Vogiatzis, Carlos Hernández and Roberto Cipolla, "Using Multiple Hypotheses to Improve Depth-Maps for Multi-View Stereo," European Conference on Computer Vision, vol. 5302, pp. 766-779, 2008.[13]Yasutaka Furukawa, Brian Curless, Steven M. Seitz and Richard Szeliski, "Towards Internet-scale Multi-view Stereo," IEEE Conference on Computer Vision and Pattern Recognition, pp. 1434-1441, 2010.[14]Yasutaka Furukawa and Jean Ponce, "Accurate, Dense, and Robust Multi-View Stereopsis," IEEE Conference on Computer Vision and Pattern Recognition, pp. 1-8, 2007.[15]Yasutaka Furukawa and Jean Ponce, "Accurate Camera Calibration from Multi-view Stereo and Bundle Adjustment," IEEE Conference on Computer Vision and Pattern Recognition, pp. 1-8, 2008.[16]Michael Goesele, Noah Snavely, Brian Curless, Hugues Hoppe and Steven M. Seitz, "Multi-View Stereo for Community Photo Collections," IEEE International Conference on Computer Vision, pp. 1-8, 2007.[17]C. Harris and M. Stephens, "A Combined Corner and Edge Detector," Proceedings of the 4th Alvey Vision Conference, vol. 15, pp. 147-151, 1988.[18]R. Hartley and A. Zisserman, Multiple View Geometry in Computer Vision, Second Edition, Cambridge University Press, 2003.[19]Vu Hoang Hiep, Renaud Keriven, Patrick Labatut and Jean-Philippe Pons, "Towards High-resolution Large-scale Multi-view Stereo," IEEE Conference on Computer Vision and Pattern Recognition, pp. 1430-1437, 2009.[20]Jianguo Li, Eric Li, Yurong Chen, Lin Xu and Yimin Zhang, "Bundled Depth-map Merging for Multi-view Stereo," IEEE Conference on Computer Vision and Pattern Recognition, pp. 2769-2776, 2010.[21]David G. Lowe, "Distinctive Image Features from Scale-invariant Keypoints," International Journal of Computer Vision, vol. 60 , pp. 91-110, 2004.[22]J. B. MacQueen, "Some Methods for Classification and Analysis of Multivariate Observations," Proceedings of 5-th Berkeley Symposium on Mathematical Statistics and Probability, Berkeley, University of California Press, vol. 1, pp. 281-297, 1967.[23]Steve M. Seitz, Brian Curless, James Diebel, Daniel Scharstein and Richard Szeliski, "A Comparison and Evaluation of Multi-View Stereo Reconstruction Algorithms," IEEE Conference on Computer Vision and Pattern Recognition, pp. 519-528, 2006.[24]Noah Snavely, Steven M. Seitz and Richard Szeliski, "Photo Tourism: Exploring Image Collections in 3D," ACM Transactions on Graphics, vol. 25, pp. 835-846, 2006.[25]Noah Snavely, Steven M. Seitz and Richard Szeliski, "Modeling the World from Internet Photo Collections," International Journal of Computer Vision, vol. 80, pp. 189-210, 2008.[26]Peng Song, Xiaojun Wu and Michael Yu Wang, "Volumetric Stereo and Silhouette Fusion for Image-based Modeling," The Visual Computer Journal, vol. 26, pp. 1435-1450, 2010.[27]C. Strecha, W. von Hansen, L. Van Gool, P. Fua and U. Thoennessen, "On Benchmarking Camera Calibration and Multi-View Stereo for High Resolution Imagery," IEEE Conference on Computer Vision and Pattern Recognition, pp. 1-8, 2008.[28]http://cvlab.epfl.ch/~strecha/multiview/denseMVS.html[29]http://graphics.stanford.edu/projects/gantry/[30]http://meshlab.sourceforge.net/[31]http://phototour.cs.washington.edu/bundler/[32]http://vision.middlebury.edu/mview/[33]http://www.vision.caltech.edu/bouguetj/calib_doc/ 描述 碩士
國立政治大學
資訊科學學系
98753034
99資料來源 http://thesis.lib.nccu.edu.tw/record/#G0098753034 資料類型 thesis dc.contributor.advisor 何瑁鎧 zh_TW dc.contributor.advisor Hor, Maw Kae en_US dc.contributor.author (Authors) 謝明龍 zh_TW dc.contributor.author (Authors) Hsieh, Ming Lung en_US dc.creator (作者) 謝明龍 zh_TW dc.creator (作者) Hsieh, Ming Lung en_US dc.date (日期) 2010 en_US dc.date.accessioned 4-Sep-2013 17:09:06 (UTC+8) - dc.date.available 4-Sep-2013 17:09:06 (UTC+8) - dc.date.issued (上傳時間) 4-Sep-2013 17:09:06 (UTC+8) - dc.identifier (Other Identifiers) G0098753034 en_US dc.identifier.uri (URI) http://nccur.lib.nccu.edu.tw/handle/140.119/60255 - 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) 98753034 zh_TW dc.description (描述) 99 zh_TW dc.description.abstract (摘要) 近年來諸多學者專家致力於從多視角影像獲取精確的點雲資訊，並藉由點雲資訊進行三維模型重建等研究，然而透過多視角影像求取三維資訊的精確度仍然有待提升，其中萃取影像對應與重建三維資訊方法，是多視角影像重建三維資訊的關鍵核心，決定點雲資訊的形成方式與成效。本論文中，我們提出了一套新的方法，由多視角影像之間的幾何關係出發，萃取多視角影像對應與重建三維點，可以有效地改善對應點與三維點的精確度。首先，在萃取多視角影像對應的部份，我們以相互支持轉換、動態高斯濾波法與綜合性相似度評估函數，改善補綴面為基礎的比對方法，提高相似度測量值的辨識力與可信度，可從多視角影像中獲得精確的對應點。其次，在重建三維點的部份，我們使用K均值分群演算法與線性內插法發掘潛在的三維點，讓求出的三維點更貼近三維空間真實物體表面，能在多視角影像中獲得更精確的三維點。實驗結果顯示，採用本研究所提出的方法進行改善後，在對應點精確度的提升上有很好的成效，所獲得的點雲資訊存在數萬個精確的三維點，而且僅有少數的離群點。 zh_TW dc.description.abstract (摘要) Recently, many researchers pay attentions in obtaining accurate point cloud data from multi-view images and use these data in 3D model reconstruction. However, this accuracy still needs to be improved. Among these researches, the methods in extracting the corresponding points as well as computing the 3D point information are the most critical ones. These methods practically affect the final results of the point cloud data and the 3D models so constructed.In this thesis, we propose new approaches, based on multi-view geometry, to improve the accuracy of corresponding points and 3D points. Mutual support transformation, dynamic Gaussian filtering, and similarity evaluation function were used to improve the patch-based matching methods in multi-view image correspondence. Using these mechanisms, the discrimination ability and reliability of the similarity function and, hence, the accuracy of the extracted corresponding points can be greatly improved. We also used K-mean algorithms and linear interpolations to find the better 3D point candidates. The 3D point so computed will be much closer to the surface of the actual 3D object. Thus, this mechanism will produce highly accurate 3D points. Experimental results show that our mechanism can improve the accuracy of corresponding points as well as the 3D point cloud data. We successfully generated accurate point cloud data that contains tens of thousands 3D points, and, moreover, only has a few outliers. en_US dc.description.tableofcontents 第1章 緒論 11.1 研究動機與目的 11.2 問題描述 81.3 系統架構與流程 101.4 論文貢獻 121.5 章節架構 13第2章 相關研究 142.1 文獻探討 142.2 比對方法 212.3 相機參數 282.4 直接線性轉換 32第3章 萃取多視角影像對應與重建三維點方法 333.1 相互支持轉換 343.2 動態高斯濾波法 353.3 綜合性相似度評估函數 373.4 K均值分群演算法與線性內插法 38第4章 建立實驗環境與取得相機參數 414.1 建立實驗環境 414.2 取得相機參數 44第5章 實驗結果 505.1 不同比對方法的相似度測量實驗 505.2 萃取精確影像對應與重建三維點實驗 55第6章 結論 606.1 研究成果 606.2 未來發展 61參考文獻 62附件A 相似度測量實驗數據表 66附件B 暴龍實驗結果圖集 69B.1暴龍多視角影像圖集 69B.2暴龍特徵點影像圖集 72B.3暴龍點雲影像圖集 74附件C 翼龍實驗結果圖集 76C.1翼龍多視角影像圖集 76C.2翼龍特徵點影像圖集 78C.3翼龍點雲影像圖集 80 zh_TW dc.format.extent 6311530 bytes - dc.format.mimetype application/pdf - dc.language.iso en_US - dc.source.uri (資料來源) http://thesis.lib.nccu.edu.tw/record/#G0098753034 en_US dc.subject (關鍵詞) 多視角影像 zh_TW dc.subject (關鍵詞) 對應點匹配 zh_TW dc.subject (關鍵詞) 補綴面 zh_TW dc.subject (關鍵詞) 點雲 zh_TW dc.subject (關鍵詞) 三維模型重建 zh_TW dc.subject (關鍵詞) multi-view images en_US dc.subject (關鍵詞) corresponding point matching en_US dc.subject (關鍵詞) patch en_US dc.subject (關鍵詞) point cloud en_US dc.subject (關鍵詞) 3D model reconstruction en_US dc.title (題名) 基於多視角幾何萃取精確影像對應之研究 zh_TW dc.title (題名) Accurate image matching based on multiple view geometry en_US dc.type (資料類型) thesis en dc.relation.reference (參考文獻) [1]李唐宇，"結合多元資料重建三維房屋模型"，中央大學土木工程學所碩士論文，民國96年。[2]吳坤信，"從多視角已校正影像改善三維粗略模型"，政治大學資訊科學所碩士論文，民國98年。[3]林立哲，"融合光達點雲以及航照影像於三維房屋模型之變遷偵測"，中央大學土木工程學所碩士論文，民國99年。[4]莊子毅，"以三維直線特徵進行地面光達點雲套合"，臺灣大學土木工程學所碩士論文，民國95年。[5]詹凱軒，"利用地面光達資料自動重建建物模型之研究"，政治大學資訊科學所碩士論文，民國96年。[6]蔡瑞陽，"從多視角萃取密集影像對應"，政治大學資訊科學所碩士論文，民國98年。[7]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"，政治大學資訊科學所碩士論文，民國98年。[8]鄭邦寧，"使用空載光達點雲求定數值地表高程模型之小波法"，成功大學測量及空間資訊學所碩士論文，民國96年。[9]Sameer Agarwal, Yasutaka Furukawa, Noah Snavely, Brian Curless, Steven M. Seitz and Richard Szeliski, "Reconstructing Rome," Computer, IEEE Computer Society Press, vol. 43, pp. 40-47, 2010.[10]Derek Bradley, Tamy Boubekeur and Wolfgang Heidrich, "Accurate Multi-View Reconstruction Using Robust Binocular Stereo and Surface Meshing," IEEE Conference on Computer Vision and Pattern Recognition, pp. 1-8, 2008.[11]Neill D.F. Campbell, George Vogiatzis, Carlos Hernández and Roberto Cipolla, "Automatic 3D Object Segmentation in Multiple Views Using Volumetric Graph-Cuts," Image and Vision Computing, vol. 28, pp. 14-25, 2008.[12]Neill D.F. Campbell, George Vogiatzis, Carlos Hernández and Roberto Cipolla, "Using Multiple Hypotheses to Improve Depth-Maps for Multi-View Stereo," European Conference on Computer Vision, vol. 5302, pp. 766-779, 2008.[13]Yasutaka Furukawa, Brian Curless, Steven M. Seitz and Richard Szeliski, "Towards Internet-scale Multi-view Stereo," IEEE Conference on Computer Vision and Pattern Recognition, pp. 1434-1441, 2010.[14]Yasutaka Furukawa and Jean Ponce, "Accurate, Dense, and Robust Multi-View Stereopsis," IEEE Conference on Computer Vision and Pattern Recognition, pp. 1-8, 2007.[15]Yasutaka Furukawa and Jean Ponce, "Accurate Camera Calibration from Multi-view Stereo and Bundle Adjustment," IEEE Conference on Computer Vision and Pattern Recognition, pp. 1-8, 2008.[16]Michael Goesele, Noah Snavely, Brian Curless, Hugues Hoppe and Steven M. Seitz, "Multi-View Stereo for Community Photo Collections," IEEE International Conference on Computer Vision, pp. 1-8, 2007.[17]C. Harris and M. Stephens, "A Combined Corner and Edge Detector," Proceedings of the 4th Alvey Vision Conference, vol. 15, pp. 147-151, 1988.[18]R. Hartley and A. Zisserman, Multiple View Geometry in Computer Vision, Second Edition, Cambridge University Press, 2003.[19]Vu Hoang Hiep, Renaud Keriven, Patrick Labatut and Jean-Philippe Pons, "Towards High-resolution Large-scale Multi-view Stereo," IEEE Conference on Computer Vision and Pattern Recognition, pp. 1430-1437, 2009.[20]Jianguo Li, Eric Li, Yurong Chen, Lin Xu and Yimin Zhang, "Bundled Depth-map Merging for Multi-view Stereo," IEEE Conference on Computer Vision and Pattern Recognition, pp. 2769-2776, 2010.[21]David G. Lowe, "Distinctive Image Features from Scale-invariant Keypoints," International Journal of Computer Vision, vol. 60 , pp. 91-110, 2004.[22]J. B. MacQueen, "Some Methods for Classification and Analysis of Multivariate Observations," Proceedings of 5-th Berkeley Symposium on Mathematical Statistics and Probability, Berkeley, University of California Press, vol. 1, pp. 281-297, 1967.[23]Steve M. Seitz, Brian Curless, James Diebel, Daniel Scharstein and Richard Szeliski, "A Comparison and Evaluation of Multi-View Stereo Reconstruction Algorithms," IEEE Conference on Computer Vision and Pattern Recognition, pp. 519-528, 2006.[24]Noah Snavely, Steven M. Seitz and Richard Szeliski, "Photo Tourism: Exploring Image Collections in 3D," ACM Transactions on Graphics, vol. 25, pp. 835-846, 2006.[25]Noah Snavely, Steven M. Seitz and Richard Szeliski, "Modeling the World from Internet Photo Collections," International Journal of Computer Vision, vol. 80, pp. 189-210, 2008.[26]Peng Song, Xiaojun Wu and Michael Yu Wang, "Volumetric Stereo and Silhouette Fusion for Image-based Modeling," The Visual Computer Journal, vol. 26, pp. 1435-1450, 2010.[27]C. Strecha, W. von Hansen, L. Van Gool, P. Fua and U. Thoennessen, "On Benchmarking Camera Calibration and Multi-View Stereo for High Resolution Imagery," IEEE Conference on Computer Vision and Pattern Recognition, pp. 1-8, 2008.[28]http://cvlab.epfl.ch/~strecha/multiview/denseMVS.html[29]http://graphics.stanford.edu/projects/gantry/[30]http://meshlab.sourceforge.net/[31]http://phototour.cs.washington.edu/bundler/[32]http://vision.middlebury.edu/mview/[33]http://www.vision.caltech.edu/bouguetj/calib_doc/ zh_TW
