1
$\begingroup$

I read Dalal and Triggs paper for HOG description and a blog Chris McCormick HOG regarding the same. The blog says that the image needs to be re-sampled at different scales to recognize different person.

My question is: Already we have a window which we place on the image having a size of 64*128 and which slides over the image. Then why re-sampling instead of sliding the whole window over the image which can detect the persons instead. ?

Please rectify if I am wrong, thanks in advance !!

Improve this question
$\endgroup$
1
  • 1
    $\begingroup$ People can have different distances to the camera $\endgroup$
    – Martin Thoma
    May 26, 2016 at 23:28

1 Answer 1

Reset to default
1
$\begingroup$

You are indeed sliding window over the image which has fixed size, but the picture may have different resolution or simply the person in the photo is in some distance from the camera (so the face size in the picture will be related to distance) but your classifier should work anyway, so checking at different sizes is one of the ways to detect people at different depth.

Improve this answer
$\endgroup$

Your Answer

By clicking “Post Your Answer”, you agree to our terms of service and acknowledge that you have read and understand our privacy policy and code of conduct.

Not the answer you're looking for? Browse other questions tagged or ask your own question.