amir_pro's profile - activity

overview network karma followed questions activity

2016-07-05 00:33:03 -0600	received badge	● Enthusiast
2016-07-04 22:14:25 -0600	commented answer	why cv::cuda::createMedianFilter function is slower than cv::medianBlur? Thanks a lot. Did you implement cuda median filter that use OpenCV Mat?
2016-07-04 13:58:17 -0600	commented answer	why cv::cuda::createMedianFilter function is slower than cv::medianBlur? Thanks for your answer. Why perform at least one iteration of each function before entering the timing loop? and why do 1000 iterations of each inside the loop?
2016-07-04 07:06:58 -0600	commented answer	Can't compile .cu file when including opencv.hpp `"opencv2/core/devmem2d.hpp"` , This file does not exist in OpenCV3.1.0 What's the solution for this question in OpenCV3.1.0?
2016-07-04 06:23:28 -0600	received badge	● Editor
2016-07-04 06:22:33 -0600	answered a question	Can't compile .cu file when including opencv.hpp `"opencv2/core/devmem2d.hpp"` , This file does not exist in OpenCV3.1.0 What's the solution for this question in OpenCV3.1.0?
2016-07-04 05:14:25 -0600	asked a question	why cv::cuda::createMedianFilter function is slower than cv::medianBlur? As you know, `Ptr<Filter> cv::cuda::createMedianFilter (int srcType, int windowSize, int partition=128)` function added to OpenCV3.1.0. I'm trying to do a median filter on 8 bit large images (6000*6000) with custom window size(up to 21). I compare cv::medianBlur and cv::cuda::createMedianFilter and results was `windowSize cv::medianBlur cv::cuda::createMedianFilter 3 0.071 sec 3.637 sec 5 0.285 sec 3.679 sec 11 2.641 sec 3.652 sec 19 2.566 sec 3.719 sec` 1) why cuda::createMedianFilter is slower than cv::medianBlur? 2) How can i write a kernel code to implement median filter that use opencv Mat with custom kernel size?
2016-02-27 05:52:58 -0600	asked a question	What is the largest amount of memory for gpu::matchTemplate? I use OpenCV2.4.11 + CUDA 7.5 + GeForece GTX 750 Ti. Source image for gpu::matchTemplate is large. I've done a comparison between GpuMat different sizes and i found best GpuMat size for gpu::matchtemplate in all six matching algorithm (CV_TM_SQDIFF .. CV_TM_CCOEFF_NORMED) and that is 90006000 (rowscols). I have two question: 1) How can i use of gpu::matchtemplate on largest images? 2) How to work gpu::MatchTemplateBuf?
2016-02-27 05:52:57 -0600	commented question	how to calculate real object width and height with known distance ? first, you can read about stereo camera calibration. i think if you can find depth first, then you can find the width and height.
2016-02-27 05:52:57 -0600	commented question	OpenCV is built with CUDA but gpu::getCudaEnableDeviceCount() returns 0 whats your GPU? "NVIDIA GPU arch" and "NVIDIA PTX archs" depends on your GPU.