首页 文章

带有CUDA和CImg库的RGB2GRAY

提问于
浏览 次
-1

我需要做一个RGB2GRAY图像处理算法 . 我只需要一些帮助来完成全局函数或如何访问* d_src指针 . 这是我的代码，非常感谢您的帮助 .

#include "cuda_runtime.h"
#include "device_launch_parameters.h"

#include "CImg.h"
#include <iostream>

using namespace std;
using namespace cimg_library;

__global__ void rgb2gray(unsigned char * d_src, unsigned char * d_dst, int width, int height){

    int pos_x = blockIdx.x * blockDim.x + threadIdx.x;
    int pos_y = blockIdx.y * blockDim.y + threadIdx.y;

    if (pos_x >= width || pos_y >= height)
        return;

}


int main(){
    //Load image
    CImg<unsigned char> src("lena.jpg");
    int width = src.width();
    int height = src.height();
    unsigned long sizee = src.size();

    int sze = width * height;

    cout << sze << endl;

    //create pointer to image
    unsigned char *h_src = src.data();

    CImg<unsigned char> dst(width, height, 1, 1);
    unsigned char *h_dst = dst.data();

    unsigned char *d_src;
    unsigned char *d_dst;

    cout << sizee << endl;

    cudaMalloc((void**)&d_src, sizee);
    cudaMalloc((void**)&d_dst, width*height*sizeof(int));

    cudaMemcpy(d_src, h_src, sizee, cudaMemcpyHostToDevice);

    //launch the kernel
    rgb2gray << <(width/16,height/16,1), (16, 16, 1) >> >(d_src, d_dst, width, height);

    //force the printf()s to flush
    cudaDeviceSynchronize();
    // copy back the result array to the CPU
    cudaMemcpy(h_dst, d_dst, width*height, cudaMemcpyDeviceToHost);

    cudaFree(d_src);
    cudaFree(d_dst);


    CImgDisplay main_disp(dst, "After Processing");
    while (!main_disp.is_closed())
        main_disp.wait();


    return 0;
}
image-processing cuda cimg

1 回答

  • 1

    首先，由于 dst 对象由 unsigned char 组成，因此按如下方式分配 d_dst ;

    cudaMalloc((void**)&d_dst, width*height*sizeof(unsigned char));

    接下来，考虑到 width 或 height 不是 16 的倍数时的情况，网格必须覆盖每个像素 . 使用以下内核配置启动内核 .

    dim3 blkDim (16, 16, 1);
dim3 grdDim ((width + 15)/16, (height + 15)/16, 1);
rgb2gray<<<grdDim, blkDim>>>(d_src, d_dst, width, height);

    最后，你的内核应该是这样的 . 请注意，RGB通道在 d_src 中分割 .

    int pos_x = blockIdx.x * blockDim.x + threadIdx.x;
int pos_y = blockIdx.y * blockDim.y + threadIdx.y;

if (pos_x >= width || pos_y >= height)
    return;

unsigned char r = d_src[pos_y * width + pos_x];
unsigned char g = d_src[(height + pos_y) * width + pos_x];
unsigned char b = d_src[(height * 2 + pos_y) * width + pos_x];

unsigned int _gray = (unsigned int)((float)(r + g + b) / 3.0f + 0.5);
unsigned char gray = _gray > 255 ? 255 : _gray;

d_dst[pos_y * width + pos_x] = gray;

    你可以看到完整的代码here .

    回复于

相关问题