1
I think this part in article is starting point of the confusion :
See how the $I(x+u, y+v)$ changed into a totally different form
$I(x,y)+ uI_x + vI_y)$?
The author should have write a bit more detailed notation as:
$I(x,y)+ uI_x(x,y) + vI_y(x,y)$
i.e. pointing out that these are element-wise spatial derivatives (like Sobel) not matrix derivatives ( ...
1
Check out Szeliski's book:
http://szeliski.org/Book/drafts/SzeliskiBook_20100903_draft.pdf
There is also an old book on feature detection:
http://www.amazon.com/Feature-Extraction-Processing-Computer-Edition/dp/0123965497
You can read the sections that you care about. Also, I think it is always a good idea to read about scale space theory if you are to ...
1
I think the first smoothing, by $\sigma_D$, is only done to get more stable derivatives whereas in the second step the convolution by a Gaussian with $\sigma_I$ is done to establish the 'scale-space' in which the operator is applied.
Ignoring $\sigma_D$, this looks like this in Matlab:
dx = [-1 0 1; -1 0 1; -1 0 1]; % Simple mask for derivative
Ix = ...
Only top voted, non community-wiki answers of a minimum length are eligible
Related Tags
harris × 7local-features × 4
corners × 4
detection × 3
computer-vision × 2
image-processing × 1
fft × 1
dft × 1
window-functions × 1
linear-algebra × 1
sift × 1