我想对大图像应用 sobel 过滤器。
我正在使用 OpenMP 进行并行处理以优化计算时间。
在用于并行优化之后,我注意到它需要的时间比预期的要长。这是代码:
#include<iostream>
#include<cmath>
#include<opencv2/imgproc/imgproc.hpp>
#include<opencv2/highgui/highgui.hpp>
using namespace std;
using namespace cv;
// Computes the x component of the gradient vector
// at a given point in a image.
// returns gradient in the x direction
int xGradient(Mat image, int x, int y)
{
return image.at<uchar>(y-1, x-1) +
2*image.at<uchar>(y, x-1) +
image.at<uchar>(y+1, x-1) -
image.at<uchar>(y-1, x+1) -
2*image.at<uchar>(y, x+1) -
image.at<uchar>(y+1, x+1);
}
// Computes the y component of the gradient vector
// at a given point in a image
// returns gradient in the y direction
int yGradient(Mat image, int x, int y)
{
return image.at<uchar>(y-1, x-1) +
2*image.at<uchar>(y-1, x) +
image.at<uchar>(y-1, x+1) -
image.at<uchar>(y+1, x-1) -
2*image.at<uchar>(y+1, x) -
image.at<uchar>(y+1, x+1);
}
int main()
{
const clock_t begin_time = clock();
Mat src, dst;
int gx, gy, sum;
// Load an image
src = imread("/home/cgross/Downloads/pano.jpg", 0);
dst = src.clone();
if( !src.data )
{ return -1; }
#pragma omp parallel for private(gx, gy, sum) shared(dst)
for(int y = 0; y < src.rows; y++)
for(int x = 0; x < src.cols; x++)
dst.at<uchar>(y,x) = 0.0;
#pragma omp parallel for private(gx, gy, sum) shared(dst)
for(int y = 1; y < src.rows - 1; y++){
for(int x = 1; x < src.cols - 1; x++){
gx = xGradient(src, x, y);
gy = yGradient(src, x, y);
sum = abs(gx) + abs(gy);
sum = sum > 255 ? 255:sum;
sum = sum < 0 ? 0 : sum;
dst.at<uchar>(y,x) = sum;
}
}
namedWindow("final", WINDOW_NORMAL);
imshow("final", dst);
namedWindow("initial", WINDOW_NORMAL);
imshow("initial", src);
std::cout << float( clock () - begin_time ) / CLOCKS_PER_SEC<<endl;
waitKey();
return 0;
}
如果我注释掉编译指示(禁用 OpenMP),计算会更快(10 秒),我看不出问题出在哪里。