1 /*M///////////////////////////////////////////////////////////////////////////////////////
3 // IMPORTANT: READ BEFORE DOWNLOADING, COPYING, INSTALLING OR USING.
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.
11 // For Open Source Computer Vision Library
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.
17 // Redistribution and use in source and binary forms, with or without modification,
18 // are permitted provided that the following conditions are met:
20 // * Redistribution's of source code must retain the above copyright notice,
21 // this list of conditions and the following disclaimer.
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.
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.
30 // This software is provided by the copyright holders and contributors "as is" and
31 // any express or bpied warranties, including, but not limited to, the bpied
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.
43 #if !defined CUDA_DISABLER
45 #include "internal_shared.hpp"
47 namespace cv { namespace gpu { namespace device
52 __global__ void blendLinearKernel(int rows, int cols, int cn, const PtrStep<T> img1, const PtrStep<T> img2,
53 const PtrStepf weights1, const PtrStepf weights2, PtrStep<T> result)
55 int x = blockIdx.x * blockDim.x + threadIdx.x;
56 int y = blockIdx.y * blockDim.y + threadIdx.y;
58 if (y < rows && x < cols)
61 float w1 = weights1.ptr(y)[x_];
62 float w2 = weights2.ptr(y)[x_];
63 T p1 = img1.ptr(y)[x];
64 T p2 = img2.ptr(y)[x];
65 result.ptr(y)[x] = (p1 * w1 + p2 * w2) / (w1 + w2 + 1e-5f);
70 void blendLinearCaller(int rows, int cols, int cn, PtrStep<T> img1, PtrStep<T> img2, PtrStepf weights1, PtrStepf weights2, PtrStep<T> result, cudaStream_t stream)
73 dim3 grid(divUp(cols * cn, threads.x), divUp(rows, threads.y));
75 blendLinearKernel<<<grid, threads, 0, stream>>>(rows, cols * cn, cn, img1, img2, weights1, weights2, result);
76 cudaSafeCall( cudaGetLastError() );
79 cudaSafeCall(cudaDeviceSynchronize());
82 template void blendLinearCaller<uchar>(int, int, int, PtrStep<uchar>, PtrStep<uchar>, PtrStepf, PtrStepf, PtrStep<uchar>, cudaStream_t stream);
83 template void blendLinearCaller<float>(int, int, int, PtrStep<float>, PtrStep<float>, PtrStepf, PtrStepf, PtrStep<float>, cudaStream_t stream);
86 __global__ void blendLinearKernel8UC4(int rows, int cols, const PtrStepb img1, const PtrStepb img2,
87 const PtrStepf weights1, const PtrStepf weights2, PtrStepb result)
89 int x = blockIdx.x * blockDim.x + threadIdx.x;
90 int y = blockIdx.y * blockDim.y + threadIdx.y;
92 if (y < rows && x < cols)
94 float w1 = weights1.ptr(y)[x];
95 float w2 = weights2.ptr(y)[x];
96 float sum_inv = 1.f / (w1 + w2 + 1e-5f);
99 uchar4 p1 = ((const uchar4*)img1.ptr(y))[x];
100 uchar4 p2 = ((const uchar4*)img2.ptr(y))[x];
101 ((uchar4*)result.ptr(y))[x] = make_uchar4(p1.x * w1 + p2.x * w2, p1.y * w1 + p2.y * w2,
102 p1.z * w1 + p2.z * w2, p1.w * w1 + p2.w * w2);
106 void blendLinearCaller8UC4(int rows, int cols, PtrStepb img1, PtrStepb img2, PtrStepf weights1, PtrStepf weights2, PtrStepb result, cudaStream_t stream)
108 dim3 threads(16, 16);
109 dim3 grid(divUp(cols, threads.x), divUp(rows, threads.y));
111 blendLinearKernel8UC4<<<grid, threads, 0, stream>>>(rows, cols, img1, img2, weights1, weights2, result);
112 cudaSafeCall( cudaGetLastError() );
115 cudaSafeCall(cudaDeviceSynchronize());
118 }}} // namespace cv { namespace gpu { namespace device
121 #endif /* CUDA_DISABLER */