我想使用此公式Gray=B OR G OR R; pixel-wise operation將BGR cv :: Mat轉換爲灰色。我試過這個：優化Mat通道的獲取OR
cv::Mat diff_channels[3];
cv::split(diff, diff_channels);
diff = diff_channels[0] | diff_channels[1] | diff_channels[2];
這可以通過更好的方法來實現嗎？
另外，如果我想實現Gray=MAX(B,G,R); pixel-wise operation的任何建議？
OpenCV不包含任何合適的內置函數來以這種方式處理單獨的通道。如果你想獲得最高的性能，你可以自己實施這個程序。我建議你這樣的事情：
void calcOrChannels(const cv::Mat& src, cv::Mat& dst)
{
CV_Assert(src.type() == CV_8UC3);
int rows = src.rows, cols = src.cols;
dst.create(src.size(), CV_8UC1);
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]; // std::max(src_ptr[0], std::max(src_ptr[1], src_ptr[2]))
src_ptr += 3;
}
}
}
請注意，您需要在您的硬件測試此功能的性能，因爲它使用SIMD指令並行這OpenCV的實現（或者也許以後Implemeted一個）失去的利益。 但是這個過程使用更少的額外內存和算術操作。我想在大多數系統上（特別是嵌入式）它會工作得更快。它也取決於矩陣的大小。
我的計時系統（核心i7-4790）上：
| Matrix size | OpenCV (ms) | My (ms) |
|:-----------:|------------:|---------|
| 1280*720 | 4 | 1 |
| 1920*1080 | 8 | 2 |
| 4096*3112 | 41 | 17 |
謝謝，但在這種情況下，我不會像優化並行過程一樣優化OpenCV嗎？ –
@HumamHelfawi好問題！我更新了答案。你也可以使用來自OpenCV的並行後端（'cv :: parallel_for'）加速這個函數。如果您遇到問題，請立即告訴我，我會幫助您。 – akarsakov
非常感謝您的基準測試 –
您可以使用cv::ParallelLoopBody與cv::parallel_for_使用OpenCV的併發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];
//*yD = std::max(yS[0], std::max(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);
}
測試
與測試你和@akarsakov方法，我得到了（以毫秒爲單位）：
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
考慮
@akarsakov方法（原始數據智能地工作）一般比較好的方法，因爲它的速度非常快，更容易編寫。使用ParallelLoopBody僅在大圖像時纔有優勢（至少在我的電腦上）。
我假定源圖像是連續的。這項檢查應該在實踐中完成。
#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];
//*yD = std::max(yS[0], std::max(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);
}
// credits to @akarsakov
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];
//dst_ptr[col] = std::max(src_ptr[0], std::max(src_ptr[1], src_ptr[2]));
src_ptr += 3;
}
}
}
// credits to @Humam_Helfawi
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;
}
只是想分享我的成果
Size: akarsakov Humam Helfawi Miki OpenCV (not same operation)
[10 x 10] 0.00733416 1.03216 1.15244 0.044005
[100 x 100] 0.078231 0.0816536 0.185799 0.043516
[1000 x 1000] 7.81039 5.89764 40.7481 3.49253
[1280 x 720] 7.61432 5.31824 8.74916 1.70397
[1920 x 1080] 16.0256 12.8186 9.32367 3.6045
[4096 x 3112] 97.7365 72.6287 49.3452 22.9545
[10000 x 10000] 763.509 575.718 402.729 197.01
編輯：
測試代碼
您可以使用此代碼評估電腦的結果我有一個新的筆記本電腦，並再次在它和舊的測試代碼。看來結果的差異取決於OpenCV的
1.Intel（R）_Core（TM）_i5-3230M_CPU _ @ _ 2.60GHz
Size: akarsakov Humam Helfawi Miki OpenCV (not same operation)
[10 x 10] 0.00276318 0.0627636 0.445661 0.0351318
[100 x 100] 0.0303949 0.0734216 0.0457898 0.0663162
[1000 x 1000] 3.01186 5.30727 2.11699 3.05805
[1280 x 720] 2.59975 4.91806 1.82014 2.69528
[1920 x 1080] 5.97478 11.5406 3.56213 5.52556
[4096 x 3112] 37.3076 64.1728 22.4575 35.0398
[10000 x 10000] 284.249 510.332 175.626 268.652
2.Intel（R）_Core（TM的不同的內置配置）2_Duo_CPU _____ T6500 __ @ _ 2。10GHz
Size: akarsakov Humam Helfawi Miki OpenCV (not same operation)
[10 x 10] 0.00586751 0.107571 24.1966 1.50844
[100 x 100] 0.0704101 0.154511 0.308044 0.119306
[1000 x 1000] 7.00825 11.072 3.44912 5.25778
[1280 x 720] 6.63322 9.88529 3.91999 5.0177
[1920 x 1080] 14.6199 21.8047 7.19357 10.9551
[4096 x 3112] 85.8226 133.165 42.4392 64.2184
[10000 x 10000] 675.604 1050.19 334.334 507.87
'diff'的聲明是什麼？ –
對於最大值，請查看http://stackoverflow.com/a/24688707/2589776。 – herohuyongtao
差異是另一個墊子 –