dc.contributor.advisor | 何瑁鎧 | zh_TW |
dc.contributor.author (Authors) | 吳坤信 | zh_TW |
dc.creator (作者) | 吳坤信 | zh_TW |
dc.date (日期) | 2008 | en_US |
dc.date.accessioned | 9-Apr-2010 13:27:47 (UTC+8) | - |
dc.date.available | 9-Apr-2010 13:27:47 (UTC+8) | - |
dc.date.issued (上傳時間) | 9-Apr-2010 13:27:47 (UTC+8) | - |
dc.identifier (Other Identifiers) | G0096753031 | en_US |
dc.identifier.uri (URI) | http://nccur.lib.nccu.edu.tw/handle/140.119/38546 | - |
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) | 96753031 | zh_TW |
dc.description (描述) | 97 | zh_TW |
dc.description.abstract (摘要) | 由多視角已校正相片重建出的三維空間模型精確度不佳,近年來甚多學者專家致力於提升改善建模的精確度。在本論文中,我們提出了新的方法,透過多視角相片結合極線轉換可以改善對應點的準確度,並且有效的排除光源的影響,以提升模型整體的精確度。 我們首先利用多視角已校正影像建立粗略3D模型,並轉出模型初始三維點座標。接著將三維座標點投影回可視相片,並使用色彩分布值和多視角極線轉換去改善可視相片中的對應點。 其次利用多視角幾何創造出更多資訊,來能幫助提升對應點的正確性。接著調整法向量角度,使自動化的貼圖更精確。最後結合貼圖使3D模型更加逼真。 在我們的實驗顯示發現對應點經過改善後較未改善前對應點的正確性高出約10%,3D模型的細節也更符合實際物體的形狀。敷貼上多視角拍攝的相片後3D模型也更加逼真。 | zh_TW |
dc.description.tableofcontents | 第一章 緒論 1.1 前言 1.2 研究動機與目的 1.3 問題描述 1.4 本論文貢獻 1.5 論文章節架構第二章 相關研究 2.1 視覺外廓法 2.2 多視角立體映像法 2.3 多視角深度圖建模法第三章 背景知識 3.1 相機校正 3.2 視覺外廓 3.3 極線幾何與投影幾何 3.4 色彩分布圖值第四章 三維空間模型改善 4.1 系統架構與流程圖 4.2 三維座標及法向量轉出 4.3 三維空間模型改善 4.4 V集合 4.5 三維座標點投影 4.6 投影點修正 4.7 極線轉換 4.8 多視角調整法 4.9 法向量改善 4.10 相片敷貼第五章 實驗結果 5.1 建模資料 5.2 投影點修正實驗 5.3 極線轉換實驗 5.4 改善三維空間模型結果 5.5 隨機取樣 5.6 對應點改善情形 5.7 相片敷貼結果第六章 結論 6.1 結論 6.2 未來發展參考文獻 | zh_TW |
dc.format.extent | 96778 bytes | - |
dc.format.extent | 109718 bytes | - |
dc.format.extent | 114271 bytes | - |
dc.format.extent | 110637 bytes | - |
dc.format.extent | 120851 bytes | - |
dc.format.extent | 92847 bytes | - |
dc.format.extent | 440665 bytes | - |
dc.format.extent | 416329 bytes | - |
dc.format.extent | 392076 bytes | - |
dc.format.extent | 574993 bytes | - |
dc.format.extent | 1441115 bytes | - |
dc.format.extent | 135843 bytes | - |
dc.format.extent | 100066 bytes | - |
dc.format.mimetype | application/pdf | - |
dc.format.mimetype | application/pdf | - |
dc.format.mimetype | application/pdf | - |
dc.format.mimetype | application/pdf | - |
dc.format.mimetype | application/pdf | - |
dc.format.mimetype | application/pdf | - |
dc.format.mimetype | application/pdf | - |
dc.format.mimetype | application/pdf | - |
dc.format.mimetype | application/pdf | - |
dc.format.mimetype | application/pdf | - |
dc.format.mimetype | application/pdf | - |
dc.format.mimetype | application/pdf | - |
dc.format.mimetype | application/pdf | - |
dc.language.iso | en_US | - |
dc.source.uri (資料來源) | http://thesis.lib.nccu.edu.tw/record/#G0096753031 | en_US |
dc.subject (關鍵詞) | 極線轉換 | zh_TW |
dc.subject (關鍵詞) | 多視角 | zh_TW |
dc.title (題名) | 從多視角已校正影像改善三維粗略模型 | zh_TW |
dc.title (題名) | Refinement of 3D rough models from calibrated multi-view images | en_US |
dc.type (資料類型) | thesis | en |
dc.relation.reference (參考文獻) | [1].Baumgart, B.G., “A polyhedron representation for computer vision“, In AFIPS Nation Computer Conference, 1975. | zh_TW |
dc.relation.reference (參考文獻) | [2].Derpanis, K.G., “The Harris Corner Detector”, In CVPR 2003. | zh_TW |
dc.relation.reference (參考文獻) | [3].Franco, J.S. and E. Boyer, “Exact Polyhedral Visual Hulls” ,In BMVC 03, Vol. I, pp. 329-338, September 2003. | zh_TW |
dc.relation.reference (參考文獻) | [4].Furukawa, Y and J. Ponce, “Accurate, Dense, and Robust Multi-View Stereopsis”, IEEE Conference on Computer Vision and Pattern Recongition, pp.1-8, 2007. | zh_TW |
dc.relation.reference (參考文獻) | [5].Furukawa, Y and J. Ponce, “Accurat Camera Calibration from Multi-View Stereo and Bundle Adjustment”, IEEE Conference on Computer Vision and Pattern Recongition, pp.1-8, 2008. | zh_TW |
dc.relation.reference (參考文獻) | [6].Hwang, Y., J. Kim, and I. Kweon, “Silhouette extraction for visual hull reconstruction“, MVA2005 IAPR Conference on Machine Vision Applications, pp. 39-42, May 16-18 2005. | zh_TW |
dc.relation.reference (參考文獻) | [7].Laurentini, A., “How Far 3D Shapes Can Be Understood from 2D Silhouettes”, IEEE Transactions on pattern analysis and machine intelligence, Volume 17, Number 2, pp.188-195, Feb 1995. | zh_TW |
dc.relation.reference (參考文獻) | [8].Laurentini, A., “The visual hull concept for silhouette based image understanding”, PAMI, 16(2):150–162, February 1994.(8) | zh_TW |
dc.relation.reference (參考文獻) | [9].Matusik, W., C. Buehler, R. Raskar, S.J. Gortler, and L. McMillan, “Image-Based Visual Hulls”, In SIGGRAPH 2000. | zh_TW |
dc.relation.reference (參考文獻) | [10].Milne, P, F. Nicolls, and G.. Jager, “Visual hull surface Estimation”, PRASA2004, pp. 13-18, Grabouw, Cape Town, 2004. | zh_TW |
dc.relation.reference (參考文獻) | [11].Jui-Yang Tsai, “Generation of Dense Image Matching Using Epipolar Geometry”, International Display Manufacturing Conference & 3D Systems and Applications, 2009. | zh_TW |
dc.relation.reference (參考文獻) | [12].Jui-Yang Tsai, “Generation of Dense Image Matching Using Epipolar Geometry”, 3D systems and Applications, 2009. | zh_TW |
dc.relation.reference (參考文獻) | [13].Kun-Shin Wu, “Refinement of 3D Models Reconstructed from Visual Hull”, Conference on Computer Vision, Graphics and Image Processing, 2009 | zh_TW |
dc.relation.reference (參考文獻) | [14].Kun-Shin Wu, “Refinement of 3D Models Reconstructed from Visual Hull”, 3D systems and Applications , 2009 | zh_TW |
dc.relation.reference (參考文獻) | [15].Yebin Liu, Xun Cao, Qionghai Dai and Wenli Xu, “Continuous Depth Estimation for Multi-view Stereo“, IEEE international Conference on Computer Vision and Pattern Recognition, 2009. | zh_TW |
dc.relation.reference (參考文獻) | [16].丁彥弘,從未校正影像序列做三維建築物重建,碩士論文,華梵大學資管系,西元2005年。 | zh_TW |
dc.relation.reference (參考文獻) | [17].http://en.wikipedia.org/wiki/Visual_hull | zh_TW |
dc.relation.reference (參考文獻) | [18].http://www.vision.caltech.edu/bouguetj/calib_doc/ | zh_TW |