Full metadata record
DC FieldValueLanguage
dc.contributor.author顏志翰en_US
dc.contributor.authorZhi-Han Yenen_US
dc.contributor.author林奕成en_US
dc.contributor.authorI-Chen Linen_US
dc.date.accessioned2014-12-12T01:19:12Z-
dc.date.available2014-12-12T01:19:12Z-
dc.date.issued2008en_US
dc.identifier.urihttp://140.113.39.130/cdrfb3/record/nctu/#GT009555561en_US
dc.identifier.urihttp://hdl.handle.net/11536/39512-
dc.description.abstract本論文提出一個能從影像序列中還原物體表面演算法,以應用在三維顯示器中。針對單一方向光源環境,我們能還原多材質和非剛體物體表面。還原真實物體表面一直是很難的課題,shape-from-shading和multiple-view是最常使用的技術。但是shape-from-shading只能處理單一材質且表面連續的物體,multiple-view則無法保留較細微的表面,同時也需要耗時的配對對應點。因此, 我們結合 shape-from-shading 和 non-rigid structure-from-motion的技術來重建更細微完整的表面。zh_TW
dc.description.abstractIn this thesis, we propose a method to reconstruct real object in a video sequence which can be used for the 3D display. Under a single directional lighting condition, the target object can be multi-material、non-rigid. Shape recovery of real object from a video sequence is a difficult subject. Shape-from-shading and multiple-view technique are the most common methods. Shape-from-shading can only deal with single-material smooth objects. The multiple-view technique acquires the point clouds without the surface detail and needs time-consuming correspondence matching. For these reasons, we combine shape-from-shading and non-rigid structure-from-motion techniques to reconstruct more detailed surfaces.en_US
dc.language.isozh_TWen_US
dc.subjectshape from shadingzh_TW
dc.subjectnon-rigid structure from motionzh_TW
dc.subject多材質zh_TW
dc.subjectshape from shadingen_US
dc.subjectnon-rigid structure from motionen_US
dc.subjectmulti-materialen_US
dc.title無校正影片中多材質物體深度之重建zh_TW
dc.titlemage-based Depth Reconstruction of Multi-material Objects from Uncalibrated Videoen_US
dc.typeThesisen_US
dc.contributor.department資訊科學與工程研究所zh_TW
Appears in Collections:Thesis


Files in This Item:

  1. 556101.pdf

If it is a zip file, please download the file and unzip it, then open index.html in a browser to view the full text content.