完整後設資料紀錄
DC 欄位語言
dc.contributor.author林奕成en_US
dc.contributor.authorLIN I-CHENen_US
dc.date.accessioned2014-12-13T10:41:15Z-
dc.date.available2014-12-13T10:41:15Z-
dc.date.issued2012en_US
dc.identifier.govdocNSC101-2221-E009-154zh_TW
dc.identifier.urihttp://hdl.handle.net/11536/98322-
dc.identifier.urihttps://www.grb.gov.tw/search/planDetail?id=2647411&docId=399629en_US
dc.description.abstract本計晝提出分析影像中建築物的結構,以應用於場景物件移除、影像修補與快速三 維建模。當輸入一張街景影像,我們將推估可能得平行與垂直等多種隱含特徵,並以 此擷取出可能的建築物牆面多邊形。這些近似的三維平面將可消除影像修補技術會發 生的透視投影扭曲的情況。當再進一步利用影像分割修正多邊形輪廓與定位其轉向與 深度,我們的系統將讓使用者快速地建立街道建築物的三維模型。 此技術將再擴展到雙眼立體影像上。雙眼影像的視差可提供給我們更豐富的資訊進 行場景的修補與分割。本研究將以兩年的時間進行,透過影像結構的分析,我們的系 統預計將產生更合理與擬真的場景影像修補、更快速的建構建築物三維模型。此結合 影像與三維模型之技術更可使用於擴增實境等應用。zh_TW
dc.description.abstractIn this project, we propose exploring the architectural structures in an image for scene completion and rapid facade modeling. Given an input image, we plan to analyze the implicit orthogonal structures with other cues to extract architectural polygons. With the preliminary polygons, our proposed completion method can fulfill the regions of removed obstacles, and preserves the architectural structures. After refining the borders and evaluating the polygon orientation, we can reconstruct the facades of buildings. Besides, we also plan to take advantage of motion parallax in stereoscopic images to improve the scene completion. The proposed system can provide more reasonable structural image completion, rapid scene prototyping for street images, or references for object interactions in augmented reality.en_US
dc.description.sponsorship行政院國家科學委員會zh_TW
dc.language.isozh_TWen_US
dc.subject影像修補zh_TW
dc.subject影像式三維建模zh_TW
dc.subject場景分析zh_TW
dc.subjectimage completionen_US
dc.subjectimage-based modelingen_US
dc.subjectscene analysisen_US
dc.title由影像建築結構建立三維模型與場景修補之研究zh_TW
dc.titleFacade Modeling and Scene Completion through Image Structure Analysisen_US
dc.typePlanen_US
dc.contributor.department國立交通大學資訊工程學系(所)zh_TW
顯示於類別:研究計畫