利用鱼眼照片恢复景物的深度信息

通过照片获取深度信息的技术已经研究多年，也产生了各种算法，但这些算法或者需要一张以上的照片来计算，或者运算量比较大。此外，它们的共同点是：各种方法采用的照片是用普通镜头拍摄的。笔者给出一种新的方法：利用一张鱼眼镜头照片和少量的辅助手段来获取深度信息。建立了一种简便而又准确的辅助手段，从而可以构造景物的三维框架，最终可以实现在景物内的任意位置向任意方向进行虚拟浏览。

3D Model Reconstruction by Using Fish-eye Picture

Tremendous papers have been published for 3D object reconstruction from 2D pictures. However, most of these techniques need two pictures or a large scale of calculation, and these methods are based on the pictures taken by camera with normal lens. In this paper, an algorithm based on fish-eye picture is studied. By using this algorithm, the depth of an image can be acquired and the 3D model of the image can be reconstructed by only one picture and some assistant operation.