比较好的论述文章 :
http://blog.csdn.net/abcjennifer/article/details/7639681
http://www.vlfeat.org/api/sift.html
1、高斯金字塔的创建 尺度连续性 冗余金字塔
2、原作者推荐 第0个octave中的第0层 delta = 1.6 输入图像一般经过抗混叠滤波 认为 delta = 0.5
3、方向参数的确定,如何设置窗的大小。
The magnitude and direction calculations for the gradient are done for every pixel in a neighboring region around the keypoint in the Gaussian-blurred image L. An orientation histogram with 36 bins is formed, with each bin covering 10 degrees. Each sample in the neighboring window added to a histogram bin is weighted by its gradient magnitude and by a Gaussian-weighted circular window with a that is 1.5 times that of the scale of the keypoint.
高斯窗 1.5*delta
区域 3*1.5*delta
4、一张老被错误描述的图形
其实这张图只是描述了2*2*8 = 32 个描述符特征
5、Vl-sift 对特征抽取的描述
6、特征点窗口大小如何计算?
从5中可以知道 binsize = m*delta
因此窗口矩形尺寸为 m*delta*(d,d)
由于需要考虑旋转的影响 m*delta* sqrt(2)*(d,d)
考虑插值 m*delta* sqrt(2)*(d+1,d+1)
半径+0.5取整 m*delta* sqrt(2)*(d+1,d+1) /2+ 0.5