政大機構典藏-National Chengchi University Institutional Repository(NCCUR):Item 140.119/38546
English  |  正體中文  |  简体中文  |  Post-Print筆數 : 27 |  全文筆數/總筆數 : 114014/145046 (79%)
造訪人次 : 52062230      線上人數 : 766
RC Version 6.0 © Powered By DSPACE, MIT. Enhanced by NTU Library IR team.
搜尋範圍 查詢小技巧:
  • 您可在西文檢索詞彙前後加上"雙引號",以獲取較精準的檢索結果
  • 若欲以作者姓名搜尋,建議至進階搜尋限定作者欄位,可獲得較完整資料
  • 進階搜尋
    政大機構典藏 > 資訊學院 > 資訊科學系 > 學位論文 >  Item 140.119/38546
    請使用永久網址來引用或連結此文件: https://nccur.lib.nccu.edu.tw/handle/140.119/38546


    題名: 從多視角已校正影像改善三維粗略模型
    Refinement of 3D rough models from calibrated multi-view images
    作者: 吳坤信
    貢獻者: 何瑁鎧
    吳坤信
    關鍵詞: 極線轉換
    多視角
    日期: 2008
    上傳時間: 2010-04-09 13:27:47 (UTC+8)
    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。
    參考文獻: [1].Baumgart, B.G., “A polyhedron representation for computer vision“, In AFIPS Nation Computer Conference, 1975.
    [2].Derpanis, K.G., “The Harris Corner Detector”, In CVPR 2003.
    [3].Franco, J.S. and E. Boyer, “Exact Polyhedral Visual Hulls” ,In BMVC 03, Vol. I, pp. 329-338, September 2003.
    [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.
    [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.
    [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.
    [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.
    [8].Laurentini, A., “The visual hull concept for silhouette based image understanding”, PAMI, 16(2):150–162, February 1994.(8)
    [9].Matusik, W., C. Buehler, R. Raskar, S.J. Gortler, and L. McMillan, “Image-Based Visual Hulls”, In SIGGRAPH 2000.
    [10].Milne, P, F. Nicolls, and G.. Jager, “Visual hull surface Estimation”, PRASA2004, pp. 13-18, Grabouw, Cape Town, 2004.
    [11].Jui-Yang Tsai, “Generation of Dense Image Matching Using Epipolar Geometry”, International Display Manufacturing Conference & 3D Systems and Applications, 2009.
    [12].Jui-Yang Tsai, “Generation of Dense Image Matching Using Epipolar Geometry”, 3D systems and Applications, 2009.
    [13].Kun-Shin Wu, “Refinement of 3D Models Reconstructed from Visual Hull”, Conference on Computer Vision, Graphics and Image Processing, 2009
    [14].Kun-Shin Wu, “Refinement of 3D Models Reconstructed from Visual Hull”, 3D systems and Applications , 2009
    [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.
    [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。
    [17].http://en.wikipedia.org/wiki/Visual_hull
    [18].http://www.vision.caltech.edu/bouguetj/calib_doc/
    描述: 碩士
    國立政治大學
    資訊科學學系
    96753031
    97
    資料來源: http://thesis.lib.nccu.edu.tw/record/#G0096753031
    資料類型: thesis
    顯示於類別:[資訊科學系] 學位論文

    文件中的檔案:

    檔案 描述 大小格式瀏覽次數
    303101.pdf94KbAdobe PDF2788檢視/開啟
    303102.pdf107KbAdobe PDF2738檢視/開啟
    303103.pdf111KbAdobe PDF2836檢視/開啟
    303104.pdf108KbAdobe PDF2746檢視/開啟
    303105.pdf118KbAdobe PDF2948檢視/開啟
    303106.pdf90KbAdobe PDF2720檢視/開啟
    303107.pdf430KbAdobe PDF2957檢視/開啟
    303108.pdf406KbAdobe PDF21165檢視/開啟
    303109.pdf382KbAdobe PDF25625檢視/開啟
    303110.pdf561KbAdobe PDF21385檢視/開啟
    303111.pdf1407KbAdobe PDF2843檢視/開啟
    303112.pdf132KbAdobe PDF2857檢視/開啟
    303113.pdf97KbAdobe PDF2722檢視/開啟


    在政大典藏中所有的資料項目都受到原著作權保護.


    社群 sharing

    著作權政策宣告 Copyright Announcement
    1.本網站之數位內容為國立政治大學所收錄之機構典藏,無償提供學術研究與公眾教育等公益性使用,惟仍請適度,合理使用本網站之內容,以尊重著作權人之權益。商業上之利用,則請先取得著作權人之授權。
    The digital content of this website is part of National Chengchi University Institutional Repository. It provides free access to academic research and public education for non-commercial use. Please utilize it in a proper and reasonable manner and respect the rights of copyright owners. For commercial use, please obtain authorization from the copyright owner in advance.

    2.本網站之製作,已盡力防止侵害著作權人之權益,如仍發現本網站之數位內容有侵害著作權人權益情事者,請權利人通知本網站維護人員(nccur@nccu.edu.tw),維護人員將立即採取移除該數位著作等補救措施。
    NCCU Institutional Repository is made to protect the interests of copyright owners. If you believe that any material on the website infringes copyright, please contact our staff(nccur@nccu.edu.tw). We will remove the work from the repository and investigate your claim.
    DSpace Software Copyright © 2002-2004  MIT &  Hewlett-Packard  /   Enhanced by   NTU Library IR team Copyright ©   - 回饋