When searching for interesting feature points in images, corners come out as an interesting solution. They are indeed local features that can be easily localized in an image, and in addition, they should abound in scenes of man-made objects (where they are produced by walls, doors, windows, tables, and so on).
这里主要是基于Harris feature detector的实现。
To define the notion of corners in images, the Harris feature detector looks at the average directional change in intensity in a small window around a putative interest point…. This average intensity change can then be computed in all possible directions, which leads to the definition of a corner as a point for which the average change is high in more than one direction.
这里首先介绍了经典的Harris feature detector的实现，接着针对feature point clustering问题给出了两种解决的办法，分别是non-maxima suppression，通过dilate操作来实现；还有GFTT（good-features-to-track），通过设置两个interest points 之间的最小距离来解决。