碩士 / 國立交通大學 / 多媒體工程研究所 / 103 / Recently, fish-eye cameras are used in many applications such as around vehicle monitoring system and parking guidance. A fish-eye camera can support very large field of view, up to 180 degrees or more, and is very suitable for above applications for large areas. However, an image captured by fish-eye camera impaired with severe radial distortion. Distorted images are very unnatural for human to perceive. Therefore, it is an important issue to eliminate the radial distortion of a fish-eye image. In this thesis, a novel fish-eye camera calibration method based on an off-the-shelf laser level is proposed, which estimates the principal point and measures the data for correcting radial distortion by using the relationship between laser lines projected by a laser level and imaging geometry of a camera. Finally, the geometric relation between a fish-eye image and perspective projection can be applied to de-warp the fish-eye image.
| Identifer | oai:union.ndltd.org:TW/103NCTU5641028 |
| Date | January 2015 |
| Creators | 邱裕翔 |
| Contributors | 莊仁輝 |
| Source Sets | National Digital Library of Theses and Dissertations in Taiwan |
| Language | zh-TW |
| Detected Language | English |
| Type | 學位論文 ; thesis |
| Format | 27 |
Page generated in 0.0193 seconds