OpenCV Cuda Example source code

#include < stdio.h >  
#include < opencv2\opencv.hpp >
#include < opencv2\gpu\gpu.hpp >
 
#ifdef _DEBUG  
#pragma comment(lib, "opencv_core246d.lib")   
#pragma comment(lib, "opencv_imgproc246d.lib")   //MAT processing  
//#pragma comment(lib, "opencv_objdetect246d.lib")   
#pragma comment(lib, "opencv_gpu246d.lib")  
//#pragma comment(lib, "opencv_features2d246d.lib")  
#pragma comment(lib, "opencv_highgui246d.lib")   
//#pragma comment(lib, "opencv_ml246d.lib")  
#else  
#pragma comment(lib, "opencv_core246.lib")  
#pragma comment(lib, "opencv_imgproc246.lib")  
//#pragma comment(lib, "opencv_objdetect246.lib")  
#pragma comment(lib, "opencv_gpu246.lib")  
//#pragma comment(lib, "opencv_features2d246.lib")  
#pragma comment(lib, "opencv_highgui246.lib")  
//#pragma comment(lib, "opencv_ml246.lib")  
#endif  

using namespace cv;  


void main()  
{  
 unsigned long AAtime=0, BBtime=0;
 
 Mat img;
 Mat outimg, outimg2;
 img = imread("Tulips.jpg",0); 
 gpu::GpuMat d_src, d_dst;
 
 d_src.upload(img);
 AAtime = getTickCount(); 
 gpu::Canny(d_src, d_dst, 35, 200, 3); 
 BBtime = getTickCount();

 printf("cuda %.5lf \n",  (BBtime - AAtime)/getTickFrequency() );
 d_dst.download(outimg);


 AAtime = getTickCount();
 Canny(img, outimg2, 35, 200, 3);
 BBtime = getTickCount();
 printf("cpu %.5lf \n",  (BBtime - AAtime)/getTickFrequency() );


 

 namedWindow("t");  
 imshow("t",outimg2); 
 namedWindow("t2");  
 imshow("t2",outimg);  
 
 cvWaitKey(0);  
 

} 

////

cuda processing takes 0.00578 sec.

and non-cuda processing takes 0.01707 sec.

In this case, cuda is faster 2times than non-cuda, but cuda will be seen higher speed.