Run under jupyter-lab
.jpg)
OpenSfM
feature_type
- KAZE[EECV]風
- AKAZE[Accelerated-KAZE KAZE的加速版]
- SIFT
- DoG[Difference of Gaussian]
- SURF[Speeded up robust features]
- Use Box-Filter[盒子滤波器] instead of DoG
- Change the size of Box-Filter, to build scala space.
- 方向定位,haar小波
- Integral image[积分图]
- 递归计算
-
$$
I(x,y)=i(x,y)+I(x-1,y)+I(x,y-1)+I(x-1,y-1)
$$
- 算好之后达到快速计算任意图形区域积分的目的

-
$$
I_{\square_{ABCD}} = I(C)+I(A)-I(B)-I(D)
$$
- Hessian矩阵
- HAHOG
- ORB
Reference
- SURF is faster than SIFT?
- The Difference between of SIFT and SURF
- KAZE