透過您的圖書館登入
IP:3.145.74.54
  • 學位論文

二維自由視角立體影像監視系統

Two-dimensional Free View Stereo Video Monitor System

指導教授 : 李維聰

摘要


由於近年來日漸成熟的影像技術,未來影像資訊勢必不只是單純呈現立體影像,而是能與使用者互動,由使用者決定觀看影像角度。因此,本論文將建立一個二維自由視角監視系統,利用多個不同角度的攝影機所拍攝出的影像資料,經過運算,提供使用者即時的自由視角監視功能。 在大多數自由視角系統必須建立一個完整的三維立體模型,建立三維立體模型將會花費龐大運算的時間,因此本計畫捨棄了原始的三維立體建模方式,而提出另一套影像系統,此影像系統是只根據使用者需求,即時計算出使用者所需的角度影像,而不需要建立完整模型後,再提供影像,因此,可節省許多建立模型的時間,達到即時的目的。 本論文的影像系統,第一步驟,將於環境中多個不同角度架設攝影機,對同一個場景,不同角度擷取影像,擷取影像畫面,步驟二,當得到影像後,會分別對每張影像以Harris-SURF特徵點偵測演算法提取特徵點,步驟三,做特徵點匹配,以此來找出不同角度所拍的影像畫面中相同的地方,步驟四,再將影像以特徵點作為頂點,以三角分割演算法,將影像分割成數個三角形。以上步驟一至步驟四會不斷循環,以更新最新影像資訊,直到當使用者提出的要求時,才會以三角分割後的三角形為單位,配合匹配結果透過影像合成計算出觀看者所要求之角度影像,呈現給觀看者。

關鍵字

即時 自由視角 SURF Harris 匹配

並列摘要


Due to the maturing of imaging technology in recent years, future monitoring has become not only simply display 3D images, but also be able to interact with users. In this paper, we present a Two-dimensional free view point monitor system. The images captured by the multiple cameras in the system. After calculation, the system to provide users with real time free view point. Tradition 3D modeling algorithms usually have high accuracy but low performance, speeding up the system is the first problem we face. Instead of reconstructing 3D models, we put our focus on simulating users’ point of view in our new algorithm. Our experimental environment requires multiple cameras focus on one object in different angle. After images are captured by cameras, we’ll find feature points on each image with Harris-SURF corner detector. The third step is matching these corner points, finding relations between different images. The fourth step is triangle meshing. By using feature points as vertex, the images are segmented into several triangles. System repeats step one to four until user has new view point commands.

並列關鍵字

Real-time Free view point SURF Harris Feature Matching

參考文獻


[6]羅一喬,基於影像特徵點之全方位視覺里程計的設計,淡江大學電機工程學系研究所碩士論文,中華民國一百年。
[8]洪志輝,具有影像特徵辨識之視覺系統於人形機器人的設計與實現,淡江大學電機工程學系研究所碩士論文,中華民國九十九年六月。
[5]H. Bay, A. Ess, T. Tuytelaars, and L. Van Gool, “Speeded-Up Robust Features (SURF),” Computer Vision and Image Understanding, vol. 110, pp. 346-359, 2008.
[7]J.S. Beis and D.G. Lowe, “Shape indexing using approximate nearest-neighbor search in high-dimensional spaces,” Computer Vision and Pattern Recognition, pp. 1000-1006, Jun. 1997.
[11]David G. Lowe,” Distinctive Image Features from Scale-Invariant Keypoints,” International Journal of Computer Vision, vol.60, no.2, pp. 91-110,Jan.2004.

被引用紀錄


余方翊(2013)。特徵點穩定與匹配校正應用於自由視角即時監視系統〔碩士論文,淡江大學〕。華藝線上圖書館。https://doi.org/10.6846/TKU.2013.00477

延伸閱讀