Ask Your Question

HoG constructor and detectMultiScale parameters effetcs

asked 2014-02-20 05:09:42 -0500

Steve7 gravatar image

Hi I am trying to understand various parameters that HoG uses but it isn't documented properly in the docs (CPU version). There are some explanation on the GPU::HogDescriptor though but I find it difficult to understand as I was new to the whole image processing area but I needed to implement a mini-project using HoG asap.

So my question is, how does these parameters (win_size, block_size, block_stride, hit_threshold, win_stride, padding, group_threshold etc.) affects accuracy, performance, reliability, false positives.

By the way I did try to read the Dalal,Triggs papers but there are too many concepts to understand but too few amount of time. Therefore I was wondering can anyone shed some light on how these parameters affects those attributes. Thanks a lot

edit retag flag offensive close merge delete

1 answer

Sort by ยป oldest newest most voted

answered 2014-02-20 10:03:40 -0500

JohannesZ gravatar image

Hm, seems to be a difficult task. Try to search for the book of Szeliski, there is a section deticated to pedestrian detection. There is also an online-version of the book on the homepage of Szeliszki.

Hope this helps in understanding HOG-Descriptors better :-)

edit flag offensive delete link more

Question Tools


Asked: 2014-02-20 05:09:42 -0500

Seen: 197 times

Last updated: Feb 20 '14