void ConvolveSeparable(CImageOf<T> src, CImageOf<T>& dst,
CFloatImage x_kernel, CFloatImage y_kernel,
float scale, float offset,
int decimate, int interpolate)
{
// Allocate the result, if necessary
CShape dShape = src.Shape();
if (decimate > 1)
{
dShape.width = (dShape.width + decimate-1) / decimate;
dShape.height = (dShape.height + decimate-1) / decimate;
}
dst.ReAllocate(dShape, false);
// Allocate the intermediate images
CImageOf<T> tmpImg1(src.Shape());
CImageOf<T> tmpImg2(src.Shape());
// Create a proper vertical convolution kernel
CFloatImage v_kernel(1, y_kernel.Shape().width, 1);
for (int k = 0; k < y_kernel.Shape().width; k++)
v_kernel.Pixel(0, k, 0) = y_kernel.Pixel(k, 0, 0);
v_kernel.origin[1] = y_kernel.origin[0];
// Perform the two convolutions
Convolve(src, tmpImg1, x_kernel, 1.0f, 0.0f);
Convolve(tmpImg1, tmpImg2, v_kernel, scale, offset);
// Downsample or copy
for (int y = 0; y < dShape.height; y++)
{
T* sPtr = &tmpImg2.Pixel(0, y * decimate, 0);
T* dPtr = &dst.Pixel(0, y, 0);
int nB = dShape.nBands;
for (int x = 0; x < dShape.width; x++)
{
for (int b = 0; b < nB; b++)
dPtr[b] = sPtr[b];
sPtr += decimate * nB;
dPtr += nB;
}
}
interpolate++; // to get rid of "unused parameter" warning
}
void ConvolveSeparable(CImageOf<T> src, CImageOf<T>& dst,
CFloatImage x_kernel, CFloatImage y_kernel,
int subsample)
{
// Allocate the result, if necessary
CShape dShape = src.Shape();
if (subsample > 1)
{
dShape.width = (dShape.width + subsample-1) / subsample;
dShape.height = (dShape.height + subsample-1) / subsample;
}
dst.ReAllocate(dShape, false);
// Allocate the intermediate images
CImageOf<T> tmpImg1(src.Shape());
CImageOf<T> tmpImg2(src.Shape());
// Create a proper vertical convolution kernel
CFloatImage v_kernel(1, y_kernel.Shape().width, 1);
for (int k = 0; k < y_kernel.Shape().width; k++)
v_kernel.Pixel(0, k, 0) = y_kernel.Pixel(k, 0, 0);
v_kernel.origin[1] = y_kernel.origin[0];
// Perform the two convolutions
Convolve(src, tmpImg1, x_kernel);
Convolve(tmpImg1, tmpImg2, v_kernel);
// Downsample or copy
for (int y = 0; y < dShape.height; y++)
{
T* sPtr = &tmpImg2.Pixel(0, y * subsample, 0);
T* dPtr = &dst.Pixel(0, y, 0);
int nB = dShape.nBands;
for (int x = 0; x < dShape.width; x++)
{
for (int b = 0; b < nB; b++)
dPtr[b] = sPtr[b];
sPtr += subsample * nB;
dPtr += nB;
}
}
}
void drawMatching(const ImgG& img1, const Mat_d& keyPts1, const ImgG& img2,
const Mat_d& keyPts2, const Matching& matches, ImgRGB& outImg,
double scale, unsigned char* flag) {
cv::Mat tmpImg1(img1.rows, img1.cols, CV_8UC1, img1.data);
cv::Mat tmpImg2(img2.rows, img2.cols, CV_8UC1, img2.data);
KpVec tmpKeyPts1, tmpKeyPts2;
mat2KpVec(keyPts1, tmpKeyPts1);
mat2KpVec(keyPts2, tmpKeyPts2);
DMatchVec tmpMatches;
myMatch2CvMatch(matches, tmpMatches);
cv::Mat cvImg;
drawMatching(tmpImg1, tmpKeyPts1, tmpImg2, tmpKeyPts2, tmpMatches, cvImg,
scale, flag);
cvImg2ImgRGB(cvImg, outImg);
}
void ConvolveSeparable(CImageOf<T> src, CImageOf<T>& dst,
CFloatImage x_kernel, CFloatImage y_kernel,
float scale, float offset,
int decimate, int interpolate)
{
// Allocate the result, if necessary
CShape dShape = src.Shape();
if (decimate > 1)
{
dShape.width = (dShape.width + decimate-1) / decimate;
dShape.height = (dShape.height + decimate-1) / decimate;
}
dst.ReAllocate(dShape, false);
// Allocate the intermediate images
CImageOf<T> tmpImg1(src.Shape());
//CImageOf<T> tmpImgCUDA(src.Shape());
CImageOf<T> tmpImg2(src.Shape());
// Create a proper vertical convolution kernel
CFloatImage v_kernel(1, y_kernel.Shape().width, 1);
for (int k = 0; k < y_kernel.Shape().width; k++)
v_kernel.Pixel(0, k, 0) = y_kernel.Pixel(k, 0, 0);
v_kernel.origin[1] = y_kernel.origin[0];
#ifdef RUN_ON_GPU
// Modifications for integrating CUDA kernels
BinomialFilterType type;
profilingTimer->startTimer();
// CUDA Convolve
switch (x_kernel.Shape().width)
{
case 3:
type = BINOMIAL6126;
break;
case 5:
type = BINOMIAL14641;
break;
default:
// Unsupported kernel case
throw CError("Convolution kernel Unknown");
assert(false);
}
// Skip copy if decimation is not required
if (decimate != 1) CudaConvolveXY(src, tmpImg2, type);
else CudaConvolveXY(src, dst, type);
printf("\nGPU convolution time = %f ms\n", profilingTimer->stopAndGetTimerValue());
#else
profilingTimer->startTimer();
//VerifyComputedData(&tmpImg2.Pixel(0, 0, 0), &tmpImgCUDA.Pixel(0, 0, 0), 7003904);
// Perform the two convolutions
Convolve(src, tmpImg1, x_kernel, 1.0f, 0.0f);
Convolve(tmpImg1, tmpImg2, v_kernel, scale, offset);
printf("\nCPU Convolution time = %f ms\n", profilingTimer->stopAndGetTimerValue());
#endif
profilingTimer->startTimer();
// Downsample or copy
// Skip decimate and recopy if not required
#ifdef RUN_ON_GPU
if (decimate != 1)
{
#endif
for (int y = 0; y < dShape.height; y++)
{
T* sPtr = &tmpImg2.Pixel(0, y * decimate, 0);
T* dPtr = &dst.Pixel(0, y, 0);
int nB = dShape.nBands;
for (int x = 0; x < dShape.width; x++)
{
for (int b = 0; b < nB; b++)
dPtr[b] = sPtr[b];
sPtr += decimate * nB;
dPtr += nB;
}
}
#ifdef RUN_ON_GPU
}
#endif
printf("\nDecimate/Recopy took = %f ms\n", profilingTimer->stopAndGetTimerValue());
}
