这篇博客概述了Aalto大学计算机视觉课程的主要内容，包括相机模型、图像处理和模型估计。介绍了理想与实际相机投影矩阵的区别，讨论了平滑滤波器如Box和Gaussian滤波器的作用。此外，还详细讲解了特征检测如Harris角点检测器、SIFT描述符以及尺度空间Blob检测器。最后，提到了模型估计中的RANSAC算法及其优缺点。
Chapter 1 Camera model
Basic geometry in homogenous coordinates
Line is given by cross product of two points.
Intersection of two lines is given by cross product of the lines.
More 3D-3D and 2D-2D transformations
Perspective transformation:
There based on the assumptions:
- Camera at world origin image plane
- Camera aligned with world coordinates
- Ideal pinhole camera
Actual situation:
Intrinsic parameters:
Camera projection matrix
Chapter 2 Image Processing
Box filter:
Replaces each pixel with an average of its neighborhood
Achieves smoothing effect (remov
最低0.47元/天 解锁文章
扫一扫
2万+
被折叠的 条评论
为什么被折叠?
到【灌水乐园】发言
