An empirical evaluation of factors influencing camera calibration accuracy using three publicly available techniques

详细信息    查看全文

• 作者：Wei Sun and Jeremy R. Cooperstock
• 关键词：Camera calibration ; Camera parameters ; Coordinate transformations ; Distortion models ; Accuracy evaluation
• 刊名：Machine Vision and Applications
• 出版年：2006
• 出版时间：April 2006
• 年：2006
• 卷：17
• 期：1
• 页码：51-67
• 全文大小：1,215 KB

文摘

This paper presents an empirical study investigating the effects of training dataquantity, measurement error, pixel coordinate noise, and the choice of camera model, oncamera calibration accuracy, based on three publicly available techniques, developed byTsai, Heikkilä and Zhang. Results are first provided for asimulated camera system and then verified through carefully controlled experiments using real-world measurements. Our aims are to provide suggestions to researchers who require an immediate solution for camera calibration and a warning of the practical difficulties one may encounter in a real environment. In addition, we offer some insight into the factors to keep in mind when selecting a calibration technique. Finally, we hope that this paper can serve as an introduction to the field for those newly embarking upon calibration-related research.