請用此 Handle URI 來引用此文件:
http://tdr.lib.ntu.edu.tw/jspui/handle/123456789/52536
完整後設資料紀錄
DC 欄位 | 值 | 語言 |
---|---|---|
dc.contributor.advisor | 莊永裕 | |
dc.contributor.author | Ying-Hsuang Wang | en |
dc.contributor.author | 王映萱 | zh_TW |
dc.date.accessioned | 2021-06-15T16:17:49Z | - |
dc.date.available | 2020-08-25 | |
dc.date.copyright | 2015-08-25 | |
dc.date.issued | 2015 | |
dc.date.submitted | 2015-08-17 | |
dc.identifier.citation | [1] Middlebury multi-view stereo datasets. http://vision.middlebury.edu/mview/data/
[2] Image reference from http://www.dailypronews.com/android-kalman-filter-accele rometer.html [3] Snavely, Noah, Steven M. Seitz, and Richard Szeliski. 'Photo tourism: exploring photo collections in 3D.' ACM transactions on graphics (TOG). Vol. 25. No. 3. ACM, 2006. [4] Lee, Wonwoo, Woontack Woo, and Edmond Boyer. 'Identifying foreground from multiple images.' Computer Vision–ACCV 2007. Springer Berlin Heidelberg, 2007. 580-589. [5] Achanta, Radhakrishna, et al. Slic superpixels. No. EPFL-REPORT-149300. 2010. [6] Boykov, Yuri, and Vladimir Kolmogorov. 'An experimental comparison of min-cut/max-flow algorithms for energy minimization in vision.' Pattern Analysis and Machine Intelligence, IEEE Transactions on 26.9 (2004): 1124-1137. [7] Rother, Carsten, Vladimir Kolmogorov, and Andrew Blake. 'Grabcut: Interactive foreground extraction using iterated graph cuts.' ACM Transactions on Graphics (TOG) 23.3 (2004): 309-314. [8] Blake, Andrew, et al. 'Interactive image segmentation using an adaptive GMMRF model.' Computer Vision-ECCV 2004. Springer Berlin Heidelberg, 2004. 428-441. [9] Boykov, Yuri, and Vladimir Kolmogorov. 'An experimental comparison of min-cut/max-flow algorithms for energy minimization in vision.' Pattern Analysis and Machine Intelligence, IEEE Transactions on 26.9 (2004): 1124-1137. [10] Campbell, Neill DF, et al. 'Automatic object segmentation from calibrated images.' Visual Media Production (CVMP), 2011 Conference for. IEEE, 2011. [11] Kohli, Pushmeet, and Philip HS Torr. 'Efficiently solving dynamic markov random fields using graph cuts.' Computer Vision, 2005. ICCV 2005. Tenth IEEE International Conference on. Vol. 2. IEEE, 2005. [12] Furukawa, Yasutaka, and Jean Ponce. 'Carved visual hulls for image-based modeling.' Computer Vision–ECCV 2006. Springer Berlin Heidelberg, 2006. 564-577. [13] Strecha, Christoph, et al. 'On benchmarking camera calibration and multi-view stereo for high resolution imagery.' Computer Vision and Pattern Recognition, 2008. CVPR 2008. IEEE Conference on. IEEE, 2008. [14] Furukawa, Yasutaka, and Jean Ponce. 'Accurate, dense, and robust multiview stereopsis.' Pattern Analysis and Machine Intelligence, IEEE Transactions on32.8 (2010): 1362-1376. [15] Kazhdan, Michael, Matthew Bolitho, and Hugues Hoppe. 'Poisson surface reconstruction.' Proceedings of the fourth Eurographics symposium on Geometry processing. Vol. 7. 2006. [16] A produt of Autodesk. http://www.123dapp.com/ | |
dc.identifier.uri | http://tdr.lib.ntu.edu.tw/jspui/handle/123456789/52536 | - |
dc.description.abstract | 隨著3D列印技術越來越流行,對於3D模型的需求也將與日俱增。然而模型的取得並不容易,建立真實世界中物體的3D模型通常需要有經驗和背景的專家花費許多時間才得以完成。
本篇論文提出了一套方法使得3D模型的製作可以脫離經驗與知識的限制,讓一般使用者也能輕鬆製作3D模型。首先我們開發了一個行動裝置上的應用軟體來引導使用者對於目標物體拍攝足以建構模型的照片。接著為了避免在重建過程中將背景一起重建,我們提出了一個全自動的物體分割方法來分離前景背景,並以分割結果製作視覺外殼(visual hull)來當成最終的模型。此方法基於馬可夫隨機場(Markov random field)的架構,將物體/背景的色彩模型、極幾何(epipolar geometry)限制、不同影像間特徵點的匹配等條件結合成單一的能量函式,並使用圖割(graph cut)演算法來最小化此函式以得到分割結果。利用此分割結果製作視覺外殼(visual hull)並投影回各張影像可確保物體輪廓能符合空間一致性,再根據目前的輪廓更新物體的色彩模型。重複使用圖割演算法和更新色彩模型的步驟直到結果收斂為止。 對於沒有紋理的物體,一般多視角立體重建(multi-view stereo)的方法通常會失敗,而我們的方法則能克服這種限制。同時結合色彩與空間的限制,能使得前景背景色彩分布重疊的區域得以分離,而這是傳統只使用色彩為條件的分割方法所不能做到的。 | zh_TW |
dc.description.abstract | As 3D printing technique becomes more popular, the requirements of 3D models also increase. However, even for an experienced expert, making a 3D model from real world object takes a long time, and needless to say, it’s not an easy task for people without any background knowledge.
In this thesis, we propose an approach that allows arbitrary users to create their own 3D models without any experience and background knowledge. First, we develop a guidance application on mobile device which guides users to take sufficient images from the target object. Second, in order to avoid the background being reconstructed as part of the 3D models, we design an automatic object segmentation method to separate foreground and background in multi-view image. Third, we use the segmentation masks to make a visual hull as our final output. The key behind our approach is a MRF framework that combines foreground/background appearance model, epipolar geometry constraints, and feature matching constraints into a single energy function. Therefore, we can use graph cut algorithm to efficiently minimize this function and get the segmentation result. We create a visual hull of the object from the segmentation masks, and then back-projecting it to all the images to make the silhouettes consistent in all view. The consistent silhouettes are used to update our foreground appearance model. We iteratively apply graph cut step and the update step until the segmentation converges. Our method is able to reconstruct a texture-less object, which remains a challenge for most of MVS algorithm. In addition, by taking color and spatial constraints into concern, our approach can separate foreground and background that are overlapping in color space, which is difficult for the traditional object segmentation method. | en |
dc.description.provenance | Made available in DSpace on 2021-06-15T16:17:49Z (GMT). No. of bitstreams: 1 ntu-104-R02922005-1.pdf: 14610930 bytes, checksum: efea2f3af7cbd325aea695cdbdad9934 (MD5) Previous issue date: 2015 | en |
dc.description.tableofcontents | 口試委員會審定書 #
誌謝 i 中文摘要 ii ABSTRACT iii 目錄 iv 附圖目錄 vi 附表目錄 viii 第一章 緒論 1 1.1 前言 1 1.2 研究動機 1 1.3 研究目標 3 1.4 論文架構 4 第二章 方法流程 5 第三章 引導拍攝應用程式 7 3.1 問題分析 7 3.2 開發平台 8 3.3 實作方法 8 3.3.1 加速度計(Accelerometer) 8 3.3.2 陀螺儀(Gyroscope) 9 3.3.3 擴展卡爾曼濾波器(Extended Kalman Filter) 9 3.3.4 取樣點設計 10 3.4 使用說明 11 3.4.1 使用流程 11 3.4.2 注意事項 11 3.5 拍攝成果 13 第四章 自動物體分割 14 4.1 問題分析 14 4.2 演算法流程 14 4.3 色彩模型 16 4.4 標記條件 17 4.5 馬可夫能量項 18 4.5.1 一元項 18 4.5.2 同一張影像內部的二元項 19 4.5.3 橫跨不同影像間的二元項 20 4.6 圖與圖割 26 4.7 視覺外殼 27 第五章 實驗結果 28 5.1 實驗設置 28 5.2 實驗結果 29 5.2.1 網路資料 30 5.2.2 拍攝應用程式資料 32 5.2.3 拍攝圈數多寡比較 37 5.2.4 與 PMVS 的結果做比 38 5.2.5 與 123D catch 的結果做比較 41 第六章 結論 44 6.1 方法限制 44 6.2 未來方向 45 6.3 結論 46 參考文獻 47 | |
dc.language.iso | zh-TW | |
dc.title | 利用自動物體分割從多視角影像建立3D 模型 | zh_TW |
dc.title | 3D Reconstruction by Automatic Object Segmentation from
Multi-view image | en |
dc.type | Thesis | |
dc.date.schoolyear | 103-2 | |
dc.description.degree | 碩士 | |
dc.contributor.oralexamcommittee | 朱宏國,紀明德,姚智原 | |
dc.subject.keyword | 3D模型,物體分割,多視角影像,自動化, | zh_TW |
dc.subject.keyword | 3D model,object segmentation,multi-view image,automatic, | en |
dc.relation.page | 48 | |
dc.rights.note | 有償授權 | |
dc.date.accepted | 2015-08-17 | |
dc.contributor.author-college | 電機資訊學院 | zh_TW |
dc.contributor.author-dept | 資訊工程學研究所 | zh_TW |
顯示於系所單位: | 資訊工程學系 |
文件中的檔案:
檔案 | 大小 | 格式 | |
---|---|---|---|
ntu-104-1.pdf 目前未授權公開取用 | 14.27 MB | Adobe PDF |
系統中的文件,除了特別指名其著作權條款之外,均受到著作權保護,並且保留所有的權利。