2016-04-27 22:44:16 -0600 | received badge | ● Enthusiast |
2016-04-23 22:15:20 -0600 | asked a question | Python OpenCV Kalman Filter, How to set the initial position ? I tried setting statePre, and statePost variables to desired initial position but it has no effect. The initial position is always (0,0). Thank you |
2016-01-01 22:56:11 -0600 | answered a question | cuda 7.5 integration with opencv 3 https://diluka7.wordpress.com/2016/01... See if this helps. |
2015-03-26 01:50:57 -0600 | asked a question | Image resize vs Image pyramid for generating ROI for pedestrian detection 0 down vote favorite For a OpenCV driving assistance application I want to generate ROI(Region of Interest) s as candidates for faster HoG(Histogram of Gradients) + SVM classification of pedestrians. I'm running this on GPU. I do not want to use detectMultiscale function as it scan all over the image (including sky), since it's unnecessary waste of clock cycles for this application. Since the features are not scalable, which of the following functions I should use for resizing the images for generating the ROIs? 1) gpu::resize(const GpuMat& src, GpuMat& dst, Size dsize, double fx=0, double fy=0, int interpolation=INTER_LINEAR, Stream& stream=Stream::Null()) 2) Image pyramids cv2.pyrUp(), cv2.pyrDown() Also I couldn't find image pyramids in OpenCV GPU library(2.4.9). Can anyone please suggest which method I should follow? Thank you. |