擴增實境技術是在真實視訊影像中加入虛擬物件，並透過追蹤與定位技術，可以與人們產生良好之互動效果。在視覺追蹤應用領域裡，可分為標記與無標記兩類應用。標記識別技術較為成熟，目前擴增實境開發平台以採用標記識別為主；至於無標記則侷限在特定方法之識別追蹤應用領域，例如樂高玩具利用包裝盒上之印刷圖片當作辨識物件。面對無標記擴增實境之應用日趨重要，且必須因應不同物件採用不同特徵之識別追蹤方法來達成無標記擴增實境之應用。而目前擴增實境平台並不提供模組化方式來替換識別追蹤方法，因此本文提出無標記擴增實境實驗平台，以現有擴增實境套件ARtoolKit為基礎，整合OpenCV與OpenGL函式庫，並採用模組化方式來設計視覺追蹤方法，做為驗證無標記擴增實境識別追蹤方法之平台，且透過視窗操作選擇不同視覺追蹤模組來呈現各式追蹤方法，以利分析驗證追蹤效能。-The technique of augmented reality (AR) is to augment 3D virtual objects into real images. Individual can interact with 3D virtual objects using tracking and registration methods. Visual tracking is the most popular tracking approach used in AR system, and markers are simply and generally used for identification and tracking. Moreover, natural feature or marker-less identification and tracking is getting more and more important and can be widely used in numerous applications. Therefore, many natural feature extraction and object tracking schemes are developed to efficiently identify and track natural objects. However, few of platforms are designed to verify different tracking algorithms for AR system. In this thesis, a novel tracking verification platform for AR environment, ARStudio, is proposed. ARStudio is on the basis of ARToolKit, and integrates the library of OpenCV and OpenGL. Furthermore, we modularize each component such as image capture, image transform, visual tracking, imag