Geographical image data efficiently help people with wayfinding when in an unfamiliar environment. However, since the display modes of geographical image data such as 2D and 3D virtual reality could not meet with users' needs anymore, the new technique augmented reality (AR) has then become a better and effective solution to graphics Augmented reality is a kind of 3D display technique by computer vision, in which 3D virtual objects are combined with 3D real environment interactively, dynamically, and in real-time. It will bring more advantages especially to the display of building spatial data. The research aims to find out more spatial information by seeing-through buildings when we stay outside it. The approach is firstly to use a single camera to capture building features with serial images, and secondly to do building recognition and tracking between reference images and serial images by Speeded-Up Robust Features (SURF) algorithm. Thirdly, the relationship of points correspondence between serial images are then applied to estimate camera parameters via computer vision technique. Finally, the 3D model map of buildings can augment to building images according to the camera parameters.
| Identifer | oai:union.ndltd.org:NSYSU/oai:NSYSU:etd-0908110-110729 |
| Date | 08 September 2010 |
| Creators | Yang, Yi-Jang |
| Contributors | Chien-Hsu Chen, Chung-Nan Lee, Tian-Yuan Shih, Shiahn-Wern Shyue, Liang-Hui Li |
| Publisher | NSYSU |
| Source Sets | NSYSU Electronic Thesis and Dissertation Archive |
| Language | Cholon |
| Detected Language | English |
| Type | text |
| Format | application/pdf |
| Source | http://etd.lib.nsysu.edu.tw/ETD-db/ETD-search/view_etd?URN=etd-0908110-110729 |
| Rights | restricted, Copyright information available at source archive |
Page generated in 0.0018 seconds