- What is the criteria used to determine that a point is a corner in the Harris detector?
- What is your intuition behind what makes the Harris corner detector effective?
- Which is the main advantage of the Harris detector over the Moravec detector?
- How is the fast detector different from the Harris corner detector?
What is the criteria used to determine that a point is a corner in the Harris detector?
A corner is a point whose local neighborhood stands in two dominant and different edge directions. In other words, a corner can be interpreted as the junction of two edges, where an edge is a sudden change in image brightness.
What is your intuition behind what makes the Harris corner detector effective?
The basic intuition behind the Harris Detector is that sliding a small window over the image causes graident change in different directions. This can be used to detect corners as shifting the window in any direction will result in a large change.
Which is the main advantage of the Harris detector over the Moravec detector?
Moravec only considered shifts in discrete 45 degree angles whereas Harris considered all directions. Harris detector has proved to be more accurate in distinguishing between edges and corners.
How is the fast detector different from the Harris corner detector?
The Harris algorithm uses more hardware resources than the FAST algorithm but can detect corners that the FAST algorithm might not find.