void cv::blendLinear( InputArray _src1, InputArray _src2, InputArray _weights1, InputArray _weights2, OutputArray _dst )
{
int type = _src1.type(), depth = CV_MAT_DEPTH(type);
Size size = _src1.size();
CV_Assert(depth == CV_8U || depth == CV_32F);
CV_Assert(size == _src2.size() && size == _weights1.size() && size == _weights2.size());
CV_Assert(type == _src2.type() && _weights1.type() == CV_32FC1 && _weights2.type() == CV_32FC1);
_dst.create(size, type);
CV_OCL_RUN(_dst.isUMat(),
ocl_blendLinear(_src1, _src2, _weights1, _weights2, _dst))
Mat src1 = _src1.getMat(), src2 = _src2.getMat(), weights1 = _weights1.getMat(),
weights2 = _weights2.getMat(), dst = _dst.getMat();
if (depth == CV_8U)
{
BlendLinearInvoker<uchar> invoker(src1, src2, weights1, weights2, dst);
parallel_for_(Range(0, src1.rows), invoker, dst.total()/(double)(1<<16));
}
else if (depth == CV_32F)
{
BlendLinearInvoker<float> invoker(src1, src2, weights1, weights2, dst);
parallel_for_(Range(0, src1.rows), invoker, dst.total()/(double)(1<<16));
}
}
void repeat(InputArray _src, int ny, int nx, OutputArray _dst)
{
CV_Assert( _src.dims() <= 2 );
CV_Assert( ny > 0 && nx > 0 );
Size ssize = _src.size();
_dst.create(ssize.height*ny, ssize.width*nx, _src.type());
CV_OCL_RUN(_dst.isUMat(),
ocl_repeat(_src, ny, nx, _dst))
Mat src = _src.getMat(), dst = _dst.getMat();
Size dsize = dst.size();
int esz = (int)src.elemSize();
int x, y;
ssize.width *= esz; dsize.width *= esz;
for( y = 0; y < ssize.height; y++ )
{
for( x = 0; x < dsize.width; x += ssize.width )
memcpy( dst.data + y*dst.step + x, src.data + y*src.step, ssize.width );
}
for( ; y < dsize.height; y++ )
memcpy( dst.data + y*dst.step, dst.data + (y - ssize.height)*dst.step, dsize.width );
}
void forward(InputArrayOfArrays inputs_arr, OutputArrayOfArrays outputs_arr, OutputArrayOfArrays internals_arr)
{
CV_TRACE_FUNCTION();
CV_TRACE_ARG_VALUE(name, "name", name.c_str());
CV_OCL_RUN((preferableTarget == DNN_TARGET_OPENCL) &&
OCL_PERFORMANCE_CHECK(ocl::Device::getDefault().isIntel()),
forward_ocl(inputs_arr, outputs_arr, internals_arr))
Layer::forward_fallback(inputs_arr, outputs_arr, internals_arr);
}
void flip( InputArray _src, OutputArray _dst, int flip_mode )
{
CV_Assert( _src.dims() <= 2 );
CV_OCL_RUN( _dst.isUMat(), ocl_flip(_src,_dst, flip_mode))
Mat src = _src.getMat();
_dst.create( src.size(), src.type() );
Mat dst = _dst.getMat();
size_t esz = src.elemSize();
if( flip_mode <= 0 )
flipVert( src.data, src.step, dst.data, dst.step, src.size(), esz );
else
flipHoriz( src.data, src.step, dst.data, dst.step, src.size(), esz );
if( flip_mode < 0 )
flipHoriz( dst.data, dst.step, dst.data, dst.step, dst.size(), esz );
}
void cv::fastNlMeansDenoisingColored( InputArray _src, OutputArray _dst,
float h, float hForColorComponents,
int templateWindowSize, int searchWindowSize)
{
int type = _src.type(), depth = CV_MAT_DEPTH(type), cn = CV_MAT_CN(type);
if (type != CV_8UC3 && type != CV_8UC4)
{
CV_Error(Error::StsBadArg, "Type of input image should be CV_8UC3!");
return;
}
CV_OCL_RUN(_src.dims() <= 2 && (_dst.isUMat() || _src.isUMat()),
ocl_fastNlMeansDenoisingColored(_src, _dst, h, hForColorComponents,
templateWindowSize, searchWindowSize))
Mat src = _src.getMat();
_dst.create(src.size(), type);
Mat dst = _dst.getMat();
Mat src_lab;
cvtColor(src, src_lab, COLOR_LBGR2Lab);
Mat l(src.size(), CV_8U);
Mat ab(src.size(), CV_8UC2);
Mat l_ab[] = { l, ab };
int from_to[] = { 0,0, 1,1, 2,2 };
mixChannels(&src_lab, 1, l_ab, 2, from_to, 3);
fastNlMeansDenoising(l, l, h, templateWindowSize, searchWindowSize);
fastNlMeansDenoising(ab, ab, hForColorComponents, templateWindowSize, searchWindowSize);
Mat l_ab_denoised[] = { l, ab };
Mat dst_lab(src.size(), CV_MAKE_TYPE(depth, 3));
mixChannels(l_ab_denoised, 2, &dst_lab, 1, from_to, 3);
cvtColor(dst_lab, dst, COLOR_Lab2LBGR, cn);
}
void cv::fastNlMeansDenoising( InputArray _src, OutputArray _dst, float h,
int templateWindowSize, int searchWindowSize)
{
CV_OCL_RUN(_src.dims() <= 2 && (_src.isUMat() || _dst.isUMat()),
ocl_fastNlMeansDenoising(_src, _dst, h, templateWindowSize, searchWindowSize))
Mat src = _src.getMat();
_dst.create(src.size(), src.type());
Mat dst = _dst.getMat();
#ifdef HAVE_TEGRA_OPTIMIZATION
if(tegra::fastNlMeansDenoising(src, dst, h, templateWindowSize, searchWindowSize))
return;
#endif
switch (src.type()) {
case CV_8U:
parallel_for_(cv::Range(0, src.rows),
FastNlMeansDenoisingInvoker<uchar>(
src, dst, templateWindowSize, searchWindowSize, h));
break;
case CV_8UC2:
parallel_for_(cv::Range(0, src.rows),
FastNlMeansDenoisingInvoker<cv::Vec2b>(
src, dst, templateWindowSize, searchWindowSize, h));
break;
case CV_8UC3:
parallel_for_(cv::Range(0, src.rows),
FastNlMeansDenoisingInvoker<cv::Vec3b>(
src, dst, templateWindowSize, searchWindowSize, h));
break;
default:
CV_Error(Error::StsBadArg,
"Unsupported image format! Only CV_8UC1, CV_8UC2 and CV_8UC3 are supported");
}
}
void cv::updateMotionHistory( InputArray _silhouette, InputOutputArray _mhi,
double timestamp, double duration )
{
CV_Assert( _silhouette.type() == CV_8UC1 && _mhi.type() == CV_32FC1 );
CV_Assert( _silhouette.sameSize(_mhi) );
float ts = (float)timestamp;
float delbound = (float)(timestamp - duration);
CV_OCL_RUN(_mhi.isUMat() && _mhi.dims() <= 2,
ocl_updateMotionHistory(_silhouette, _mhi, ts, delbound))
Mat silh = _silhouette.getMat(), mhi = _mhi.getMat();
Size size = silh.size();
if( silh.isContinuous() && mhi.isContinuous() )
{
size.width *= size.height;
size.height = 1;
}
#if CV_SSE2
volatile bool useSIMD = cv::checkHardwareSupport(CV_CPU_SSE2);
#endif
for(int y = 0; y < size.height; y++ )
{
const uchar* silhData = silh.ptr<uchar>(y);
float* mhiData = mhi.ptr<float>(y);
int x = 0;
#if CV_SSE2
if( useSIMD )
{
__m128 ts4 = _mm_set1_ps(ts), db4 = _mm_set1_ps(delbound);
for( ; x <= size.width - 8; x += 8 )
{
__m128i z = _mm_setzero_si128();
__m128i s = _mm_unpacklo_epi8(_mm_loadl_epi64((const __m128i*)(silhData + x)), z);
__m128 s0 = _mm_cvtepi32_ps(_mm_unpacklo_epi16(s, z)), s1 = _mm_cvtepi32_ps(_mm_unpackhi_epi16(s, z));
__m128 v0 = _mm_loadu_ps(mhiData + x), v1 = _mm_loadu_ps(mhiData + x + 4);
__m128 fz = _mm_setzero_ps();
v0 = _mm_and_ps(v0, _mm_cmpge_ps(v0, db4));
v1 = _mm_and_ps(v1, _mm_cmpge_ps(v1, db4));
__m128 m0 = _mm_and_ps(_mm_xor_ps(v0, ts4), _mm_cmpneq_ps(s0, fz));
__m128 m1 = _mm_and_ps(_mm_xor_ps(v1, ts4), _mm_cmpneq_ps(s1, fz));
v0 = _mm_xor_ps(v0, m0);
v1 = _mm_xor_ps(v1, m1);
_mm_storeu_ps(mhiData + x, v0);
_mm_storeu_ps(mhiData + x + 4, v1);
}
}
#endif
for( ; x < size.width; x++ )
{
float val = mhiData[x];
val = silhData[x] ? ts : val < delbound ? 0 : val;
mhiData[x] = val;
}
}
}