HOG latent SVM obj detection doesn't seem to work (Bug #2107)

Rob Schlacter wrote:

am trying to use latent SVM trained with person.xml [of PASCAL VOC]. i've tried several images and there are major problems with it:

plz see attached image - it draws several bounding boxes all over the place although there is only one person in the image - these bbs are mostly outside the person bb - i.e. too many false positives to say it is even detecting anything - might as well randomly draw bounding boxes :(

the person is not detected accurately - i.e the bb doesn't cover or covers only part of the person many times - tried with many many images from UCB, PASCAL, INRIA, etc.

lastly, it takes forever to simply process one image - i.e in the order of 1-2 MINUTES on a Macbook Pro - anything so slow is totally not usable.

bottomline - it doesn't seem to work - i've checked most documentation/paper/etc. including Felzenschwalb...'s site, but no idea what is wrong with opencv implementation - does anyone know?

BTW, the paper states somewhere that it should converge [output result] in just 2 or 3 seconds on a standard desktop - so the implementation seems to be way off both in performance, not to mention accuracy - read somewhere it is implemented by U. of Nishni - but no doc anywhere or any pointers

sorry to sound so negative - spent a few hours on it and is very frustrating!!! thanks if someone responsible can look into it and respond.

Hi, Can you send part of code that you use for init Vector Machine and person.xml by email ([email protected]), it seems you doing something wrong because i`m use same thing and its works good in video stream, with some mistakes in simple way of using, but such no like you have...

Yes, I think so.