Home | History | Annotate | Download | only in cuda
      1 /*M///////////////////////////////////////////////////////////////////////////////////////
      2 //
      3 //  IMPORTANT: READ BEFORE DOWNLOADING, COPYING, INSTALLING OR USING.
      4 //
      5 //  By downloading, copying, installing or using the software you agree to this license.
      6 //  If you do not agree to this license, do not download, install,
      7 //  copy or use the software.
      8 //
      9 //
     10 //                           License Agreement
     11 //                For Open Source Computer Vision Library
     12 //
     13 // Copyright (C) 2000-2008, Intel Corporation, all rights reserved.
     14 // Copyright (C) 2009, Willow Garage Inc., all rights reserved.
     15 // Third party copyrights are property of their respective owners.
     16 //
     17 // Redistribution and use in source and binary forms, with or without modification,
     18 // are permitted provided that the following conditions are met:
     19 //
     20 //   * Redistribution's of source code must retain the above copyright notice,
     21 //     this list of conditions and the following disclaimer.
     22 //
     23 //   * Redistribution's in binary form must reproduce the above copyright notice,
     24 //     this list of conditions and the following disclaimer in the documentation
     25 //     and/or other materials provided with the distribution.
     26 //
     27 //   * The name of the copyright holders may not be used to endorse or promote products
     28 //     derived from this software without specific prior written permission.
     29 //
     30 // This software is provided by the copyright holders and contributors "as is" and
     31 // any express or implied warranties, including, but not limited to, the implied
     32 // warranties of merchantability and fitness for a particular purpose are disclaimed.
     33 // In no event shall the Intel Corporation or contributors be liable for any direct,
     34 // indirect, incidental, special, exemplary, or consequential damages
     35 // (including, but not limited to, procurement of substitute goods or services;
     36 // loss of use, data, or profits; or business interruption) however caused
     37 // and on any theory of liability, whether in contract, strict liability,
     38 // or tort (including negligence or otherwise) arising in any way out of
     39 // the use of this software, even if advised of the possibility of such damage.
     40 //
     41 //M*/
     42 
     43 #include "opencv2/opencv_modules.hpp"
     44 
     45 #ifndef HAVE_OPENCV_CUDEV
     46 
     47 #error "opencv_cudev is required"
     48 
     49 #else
     50 
     51 #include "opencv2/cudaarithm.hpp"
     52 #include "opencv2/cudev.hpp"
     53 #include "opencv2/core/private.cuda.hpp"
     54 
     55 using namespace cv;
     56 using namespace cv::cuda;
     57 using namespace cv::cudev;
     58 
     59 //////////////////////////////////////////////////////////////////////////////
     60 // mulSpectrums
     61 
     62 namespace
     63 {
     64     __device__ __forceinline__ float real(const float2& val)
     65     {
     66         return val.x;
     67     }
     68 
     69     __device__ __forceinline__ float imag(const float2& val)
     70     {
     71         return val.y;
     72     }
     73 
     74     __device__ __forceinline__ float2 cmul(const float2& a, const float2& b)
     75     {
     76         return make_float2((real(a) * real(b)) - (imag(a) * imag(b)),
     77                            (real(a) * imag(b)) + (imag(a) * real(b)));
     78     }
     79 
     80     __device__ __forceinline__ float2 conj(const float2& a)
     81     {
     82         return make_float2(real(a), -imag(a));
     83     }
     84 
     85     struct comlex_mul : binary_function<float2, float2, float2>
     86     {
     87         __device__ __forceinline__ float2 operator ()(const float2& a, const float2& b) const
     88         {
     89             return cmul(a, b);
     90         }
     91     };
     92 
     93     struct comlex_mul_conj : binary_function<float2, float2, float2>
     94     {
     95         __device__ __forceinline__ float2 operator ()(const float2& a, const float2& b) const
     96         {
     97             return cmul(a, conj(b));
     98         }
     99     };
    100 
    101     struct comlex_mul_scale : binary_function<float2, float2, float2>
    102     {
    103         float scale;
    104 
    105         __device__ __forceinline__ float2 operator ()(const float2& a, const float2& b) const
    106         {
    107             return scale * cmul(a, b);
    108         }
    109     };
    110 
    111     struct comlex_mul_conj_scale : binary_function<float2, float2, float2>
    112     {
    113         float scale;
    114 
    115         __device__ __forceinline__ float2 operator ()(const float2& a, const float2& b) const
    116         {
    117             return scale * cmul(a, conj(b));
    118         }
    119     };
    120 }
    121 
    122 void cv::cuda::mulSpectrums(InputArray _src1, InputArray _src2, OutputArray _dst, int flags, bool conjB, Stream& stream)
    123 {
    124     (void) flags;
    125 
    126     GpuMat src1 = getInputMat(_src1, stream);
    127     GpuMat src2 = getInputMat(_src2, stream);
    128 
    129     CV_Assert( src1.type() == src2.type() && src1.type() == CV_32FC2 );
    130     CV_Assert( src1.size() == src2.size() );
    131 
    132     GpuMat dst = getOutputMat(_dst, src1.size(), CV_32FC2, stream);
    133 
    134     if (conjB)
    135         gridTransformBinary(globPtr<float2>(src1), globPtr<float2>(src2), globPtr<float2>(dst), comlex_mul_conj(), stream);
    136     else
    137         gridTransformBinary(globPtr<float2>(src1), globPtr<float2>(src2), globPtr<float2>(dst), comlex_mul(), stream);
    138 
    139     syncOutput(dst, _dst, stream);
    140 }
    141 
    142 void cv::cuda::mulAndScaleSpectrums(InputArray _src1, InputArray _src2, OutputArray _dst, int flags, float scale, bool conjB, Stream& stream)
    143 {
    144     (void) flags;
    145 
    146     GpuMat src1 = getInputMat(_src1, stream);
    147     GpuMat src2 = getInputMat(_src2, stream);
    148 
    149     CV_Assert( src1.type() == src2.type() && src1.type() == CV_32FC2);
    150     CV_Assert( src1.size() == src2.size() );
    151 
    152     GpuMat dst = getOutputMat(_dst, src1.size(), CV_32FC2, stream);
    153 
    154     if (conjB)
    155     {
    156         comlex_mul_conj_scale op;
    157         op.scale = scale;
    158         gridTransformBinary(globPtr<float2>(src1), globPtr<float2>(src2), globPtr<float2>(dst), op, stream);
    159     }
    160     else
    161     {
    162         comlex_mul_scale op;
    163         op.scale = scale;
    164         gridTransformBinary(globPtr<float2>(src1), globPtr<float2>(src2), globPtr<float2>(dst), op, stream);
    165     }
    166 
    167     syncOutput(dst, _dst, stream);
    168 }
    169 
    170 #endif
    171