First time here? Check out the FAQ!

Ask Your Question
0

Comparing two HOG descriptors vectors

asked Nov 4 '12

Ben-Uri gravatar image

I am using cv::HOGDescriptor (CPU version) to compute descriptors of two images.

Then I would like to compare each window from the first image to each window of the other window of the other image and store location of the two windows that got the best score (nearest by L2 distance) and the distance between them.

What is the best way to access all window descriptors received by cv::HOGDescriptor::compute(...) method?

(This method is not documented, and fills one vector of floats which I don't understand how to interpreted)

Preview: (hide)

2 answers

Sort by » oldest newest most voted
1

answered Nov 5 '12

sub_o gravatar image

updated Nov 5 '12

Hi Ben-Uri. From what I know the vector should be multiply of 9, which means that it's a flatten version of HoG with 9 bins. Each 9 float in that vector should represent a single cell region (? correct me if I'm wrong).

I'm creating my own HoG using OpenCV's function (besides its own HoG method), and you can find it here: http://code.google.com/p/custom-hog-pedestrian/

Preview: (hide)
0

answered Feb 22 '14

nkint gravatar image

A similar question is asked here:

http://stackoverflow.com/questions/11626140/extracting-hog-features-using-opencv

they just do a hog-to-hog distance accumulating the error.. nothing complicated, just an accumulation error between two float array (the two hog must be of the same size of course)

Preview: (hide)

Question Tools

Stats

Asked: Nov 4 '12

Seen: 7,067 times

Last updated: Feb 22 '14