首页> 外文会议>Asian Conference on Computer Vision(ACCV 2004) vol.1; 20040127-30; Jeju(KR) >DISTORTION CORRECTION OF FISHEYE LENSES USING A NON-PARAMETRIC IMAGING MODEL
【24h】

DISTORTION CORRECTION OF FISHEYE LENSES USING A NON-PARAMETRIC IMAGING MODEL

机译:基于非参数成像模型的鱼眼镜头畸变校正

获取原文
获取原文并翻译 | 示例

摘要

Fisheye lenses are often used to enlarge the field of view of a conventional camera. But the images taken with a camera with fisheye lenses have severe distortions. This paper presents a new non-parametric imaging modeling method to transform the distorted images into the quasi-perspective images. The non-parametric model is a mapping from the rays captured by the camera to their corresponding image points. The non-parametric model of the fisheye camera can be conveniently obtained using the inner surface of a hemispherical calibration pattern. The key distinct characteristic between the parametric method and the non-parametric method is that: the parametric distortion model does not often fit the real distortions in the imaging system well, and the non-parametric model can fit the imaging system better if there are more control points on the hemispherical pattern. Our experimental results show that the fisheye images are corrected satisfactorily using the non-parametric model via a simple look-up table.
机译:鱼眼镜头通常用于扩大传统相机的视野。但是带鱼眼镜头的相机拍摄的图像会出现严重的失真。本文提出了一种新的非参数成像建模方法,可以将畸变图像转换为准透视图像。非参数模型是从相机捕获的光线到其相应图像点的映射。鱼眼镜头的非参数模型可以使用半球形校准图案的内表面方便地获得。参数化方法与非参数化方法之间的关键区别特征在于:参数化失真模型通常无法很好地拟合成像系统中的真实失真,并且如果有更多的话,非参数化模型可以更好地拟合成像系统。半球图案上的控制点。我们的实验结果表明,使用非参数模型通过简单的查找表可以令人满意地校正鱼眼图像。

著录项

相似文献

  • 外文文献
  • 中文文献
  • 专利
获取原文

客服邮箱:kefu@zhangqiaokeyan.com

京公网安备:11010802029741号 ICP备案号:京ICP备15016152号-6 六维联合信息科技 (北京) 有限公司©版权所有
  • 客服微信

  • 服务号