2014-04-29 11:00:38 -0600 | commented answer | DaimlerPeopleDetector with smaller images all right the problem came from some other implementation mistake, blurring the image did the trick, thanks! |
2014-04-29 10:59:47 -0600 | received badge | ● Scholar (source) |
2014-04-29 06:36:24 -0600 | commented answer | DaimlerPeopleDetector with smaller images I used a Gaussian Blur with kernel of size 3, 5, 7, but still no hit... Are you using another smoothing method ? |
2014-04-29 04:48:10 -0600 | commented answer | DaimlerPeopleDetector with smaller images I can't make it work... I edited the question to add sample images |
2014-04-29 04:47:19 -0600 | received badge | ● Student (source) |
2014-04-29 04:45:25 -0600 | received badge | ● Editor (source) |
2014-04-29 02:49:52 -0600 | asked a question | DaimlerPeopleDetector with smaller images Hi, Is it possible to get the HOG DaimlerPeopleDetector work with smaller images? I am just upscaling the image before passing it to detectMultiScale. The idea behind that is that the gradients look roughly the same even with some upscaling? Edit: I can't make it work with sample images like the ones below, even with a hit threshold as low as 0.1...
Some code: Thanks for any help |