This forum is disabled, please visit https://forum.opencv.org
| 2015-11-10 08:35:02 -0600 | received badge | ● Enthusiast |
| 2015-11-07 16:27:54 -0600 | commented answer | Would like to use different scales with HOG people detection The problem was that the found locations were for the down-scaled image. I think most people would need found locations for the input image as you mentioned. |
| 2015-11-07 13:16:42 -0600 | answered a question | Would like to use different scales with HOG people detection This works good. There is a problem with the resulting found_locations vector of rectangles though, but for my purposes it's fine. |
| 2015-10-29 00:06:43 -0600 | asked a question | Would like to use different scales with HOG people detection I think the default scaling for OpenCV's HOG implementation is 1.05 raised to some power, where that power is a value from 1 to nlevels(which is 64) . I'd like to skip the lower scales (1.05^1 - 1.05^13) and start at 1.05^14. I know I can enter 1.05^14 into detectMultiScale as the value for scale0, but then HOG would use powers of 1.05^14 rather than 1.05. How can I use the HOG implementation such that I use scales 1.05^14 - 1.05^54, thereby skipping the lower scales? Thanks, --jkutchk |