How was the hogdescriptor::getDefaultPeopleDetector() trained
I am curious to know how the float detector[] in DefaultPeopleDetector() was trained. With this I mean what database,parameters,SVM were used. If somebody can identify the exact steps that would be very helpful.
Thank you.
yea, and why has the getDaimlerPeopleDetector() a different size, and thus cannot be used ?
Hi berak, i guess the size of the DaimlerPeopleDetector() is 48x96 since the training images from the Daimler Benchmark dataset has this size. The dataset and the paper where it is described can be found here: http://www.gavrila.net/Research/Pedestrian_Detection/Daimler_Pedestrian_Benchmark_D/Daimler_Mono_Ped__Detection_Be/daimler_mono_ped__detection_be.html
thanks, siegfried, sorry, btw, for hijacking the question ;)
to use DaimlerPeopleDetector just set winsize to 48X96
thanks, @Spas.
Has anybody figured it out ?