近年來虛擬實境的發展越來越成熟,在現實生活中的應用也越來越多元。本次論文是透過支援Google’s Project Tango的智慧型手機,使用其兩種相機-RGB攝影機、深度攝影機-結合Google’s Project Tango之技術,可以做到的3D即時建模功能,將3D即時建模之場景物件與現實場景物件做虛實整合。本次研究將以深度攝影機捕捉到的場景物件之點雲(Point Clouds)平均深度數據,透過平均深度數據之變化量,來判斷在現實場景裡是否有3D動態物件。當平均深度數據變化量超出所設定門檻值時,則可偵測出3D動態物件,以此作為3D掃描速度調整及VR畫面更新之依據。本論文進行詳細實驗分析及驗證,實驗結果完整分析在虛實整合之物理上誤差。
In recent years, the development of virtual reality has become more mature, and its application in real life has become more diverse. This these is based on an AR smartphone that supports Google’s Project Tango with its two cameras - RGB camera and depth camera, to sense 3D real world. In this study, the average depth data of Point Clouds on the real 3D objects captured by the depth camera is used to determine whether there are 3D dynamic objects in the real scene. When the average depth data change exceeds the threshold of the average depth data, a 3D dynamic object can be detected. This threshold is also adopted to adjust 3D scanning speed and to update VR representation. We conduct detailed experimental analysis and verification, and completely analyze the physical error of the virtual and real integration in this thesis.