你可以使用
cv::parallel_for_
和
cv::ParallelLoopBody
,来使用OpenCV并发API:
class ParallelBGRtoGrayOR : public ParallelLoopBody
{
const Mat3b src;
mutable Mat1b dst;
public:
ParallelBGRtoGrayOR(const Mat3b& _src, Mat1b& _dst) : ParallelLoopBody(), src(_src), dst(_dst) {}
virtual void operator()(const Range& range) const
{
int rows = range.end - range.start;
int cols = src.cols;
int len = rows * cols;
const uchar* yS = src.ptr<uchar>(range.start);
uchar* yD = dst.ptr<uchar>(range.start);
for (int i = 0; i < len; ++i, yD++, yS += 3)
{
*yD = yS[0] | yS[1] | yS[2];
}
}
};
void cvtBgrToGray_OR_Miki(const Mat3b& src, Mat1b& dst)
{
dst.create(src.rows, src.cols);
parallel_for_(Range(0, src.rows), ParallelBGRtoGrayOR(src, dst), -1);
}
测试
使用您和@akarsakov的方法进行测试,我得到了(以毫秒为单位的时间):
Size: akarsakov Humam Helfawi Miki OpenCV (not same operation)
[10 x 10] 0.00109963 0.0711094 2.60722 0.0934685
[100 x 100] 0.0106298 0.0373874 0.0461844 0.0395867
[1000 x 1000] 1.1799 3.30622 0.747382 1.61646
[1280 x 720] 1.07324 2.91585 0.520858 0.9893
[1920 x 1080] 2.31252 6.87818 1.11502 1.94011
[4096 x 3112] 14.3454 42.0125 6.79644 12.0754
[10000 x 10000] 115.575 321.145 61.1544 93.8846
注意事项
@akarsakov的方法(在原始数据上智能工作)通常是更好的方法,因为它非常快速且易于编写。只有在大型图像(至少在我的电脑上)上使用ParallelLoopBody
才有一些优势。
我假设源图像是连续的。实际应该进行这个检查。
测试代码
您可以使用此代码在您的计算机上评估结果:
#include <opencv2/opencv.hpp>
#include <iostream>
using namespace std;
using namespace cv;
class ParallelBGRtoGrayOR : public ParallelLoopBody
{
const Mat3b src;
mutable Mat1b dst;
public:
ParallelBGRtoGrayOR(const Mat3b& _src, Mat1b& _dst) : ParallelLoopBody(), src(_src), dst(_dst) {}
virtual void operator()(const Range& range) const
{
int rows = range.end - range.start;
int cols = src.cols;
int len = rows * cols;
const uchar* yS = src.ptr<uchar>(range.start);
uchar* yD = dst.ptr<uchar>(range.start);
for (int i = 0; i < len; ++i, yD++, yS += 3)
{
*yD = yS[0] | yS[1] | yS[2];
}
}
};
void cvtBgrToGray_OR_Miki(const Mat3b& src, Mat1b& dst)
{
dst.create(src.rows, src.cols);
parallel_for_(Range(0, src.rows), ParallelBGRtoGrayOR(src, dst), -1);
}
void cvtBgrToGray_OR_akarsakov(const Mat3b& src, Mat1b& dst)
{
int rows = src.rows, cols = src.cols;
dst.create(src.size());
if (src.isContinuous() && dst.isContinuous())
{
cols = rows * cols;
rows = 1;
}
for (int row = 0; row < rows; row++)
{
const uchar* src_ptr = src.ptr<uchar>(row);
uchar* dst_ptr = dst.ptr<uchar>(row);
for (int col = 0; col < cols; col++)
{
dst_ptr[col] = src_ptr[0] | src_ptr[1] | src_ptr[2];
src_ptr += 3;
}
}
}
void cvtBgrToGray_OR_Humam_Helfawi(const Mat3b& src, Mat1b& dst)
{
cv::Mat channels[3];
cv::split(src, channels);
dst = channels[0] | channels[1] | channels[2];
}
int main()
{
vector<Size> sizes{ Size(10, 10), Size(100, 100), Size(1000, 1000), Size(1280, 720), Size(1920, 1080), Size(4096, 3112), Size(10000, 10000) };
cout << "Size: \t\takarsakov \tHumam Helfawi \tMiki \tOpenCV (not same operation)" << endl;
for (int is = 0; is < sizes.size(); ++is)
{
Size sz = sizes[is];
cout << sz << "\t";
Mat3b img(sz);
randu(img, Scalar(0, 0, 0), Scalar(255, 255, 255));
Mat1b gray_akarsakov;
Mat1b gray_Miki;
Mat1b gray_Humam;
Mat1b grayOpenCV;
double tic = double(getTickCount());
cvtBgrToGray_OR_akarsakov(img, gray_akarsakov);
double toc = (double(getTickCount()) - tic) * 1000. / getTickFrequency();
cout << toc << " \t";
tic = double(getTickCount());
cvtBgrToGray_OR_Humam_Helfawi(img, gray_Humam);
toc = (double(getTickCount()) - tic) * 1000. / getTickFrequency();
cout << toc << " \t";
tic = double(getTickCount());
cvtBgrToGray_OR_Miki(img, gray_Miki);
toc = (double(getTickCount()) - tic) * 1000. / getTickFrequency();
cout << toc << " \t";
tic = double(getTickCount());
cvtColor(img, grayOpenCV, COLOR_BGR2GRAY);
toc = (double(getTickCount()) - tic) * 1000. / getTickFrequency();
cout << toc << endl;
}
getchar();
return 0;
}
diff
的声明是什么? - John Zwinck