C# Bitmap图像处理加速的实现

private void Gray_Tradition()
{
    for(int i = 0; i < bitmap.Width; i++)
    {
        for(int j = 0; j < bitmap.Height; j++)
        {
            Color color = bitmap.GetPixel(i, j);
            int RGB = (color.R + color.G + color.B) / 3;
            bitmap.SetPixel(i, j, Color.FromArgb(255, RGB, RGB, RGB));
        }
    }
}

private void Gray_BitmapData()
{
    int width = bitmap.Width, height = bitmap.Height;//图片的宽度和高度
    //在内存中以读写模式锁定Bitmap
    BitmapData bitmapData = bitmap.LockBits(
    new Rectangle(0, 0, width, height),
    ImageLockMode.ReadWrite,
    PixelFormat.Format24bppRgb);
    //图片像素点数组的长度，由于一个像素点占了3个字节，所以要乘上3
    int size = width * height * 3;
    //缓冲区数组
    byte[] srcArray = new byte[size];
    //获取第一个像素的地址
    IntPtr ptr = bitmapData.Scan0;
    //把像素值复制到缓冲区
    Marshal.Copy(ptr, srcArray, 0, size);
    int p;
    for (int i = 0; i < width; i++)
    {
        for (int j = 0; j < height; j++)
        {
            //定位像素点位置
            p = j * width * 3 + i * 3;
            //计算灰度值
            byte color = (byte)((srcArray[p] + srcArray[p + 1] + srcArray[p + 2]) / 3);
            srcArray[p] = srcArray[p + 1] = srcArray[p + 2] = color;
        }
    }
    //从缓冲区复制回BitmapData
    Marshal.Copy(srcArray, 0, ptr, size);
    //从内存中解锁
    bitmap.UnlockBits(bitmapData);
}

private void onTest()
{
    double t1, t2;
    Stopwatch watch = new Stopwatch();
    watch.Start();
    Gray_BitmapData();
    watch.Stop();
    t1 = watch.Elapsed.TotalMilliseconds;
    watch.Reset();
    watch.Start();
    Gray_Tradition();
    watch.Stop();
    t2 = watch.Elapsed.TotalMilliseconds;
    MessageBox.Show("BitmapData=" + (long)t1 + "\nTradition=" + (long)t2);
}

#include "cuda_runtime.h"
#include "device_launch_parameters.h"
 
#include <stdio.h>
#include <Windows.h>
 
__global__ void DoInKernel(byte* o, int num)
{
    int i = blockIdx.x * blockDim.x + threadIdx.x;
    if (i >= num) return;
    byte* ori = o + i * 3;
    ori[0] = ori[1] = ori[2] = (ori[0] + ori[1] + ori[2]) / 3;
}
 
extern "C" _declspec(dllexport) void Gray(byte * oriArray, int num) {
    int size = num * 3 * sizeof(byte);
    byte* dev_ori;
    //在GPU上分配内存
    cudaMalloc((void**)&dev_ori, size);
    //把数组复制到显存
    cudaMemcpy(dev_ori, oriArray, size, cudaMemcpyHostToDevice);
    //计算
    DoInKernel << <num / 1024 + 1, 1024 >> > (dev_ori, num);
    //从显存复制到内存
    cudaMemcpy(oriArray, dev_ori, size, cudaMemcpyDeviceToHost);
    //释放
    cudaFree(dev_ori);
}

[DllImport("CUDA.dll", EntryPoint = "Gray", CallingConvention = CallingConvention.Cdecl)]
public static extern void Gray(IntPtr ori, int num);

private void Gray_GPU()
{
    int width = bitmap.Width, height = bitmap.Height;//图片的宽度和高度
    //在内存中以读写模式锁定Bitmap
    BitmapData bitmapData = bitmap.LockBits(
    new Rectangle(0, 0, width, height),
    ImageLockMode.ReadWrite,
    PixelFormat.Format24bppRgb);
    //图片像素点数组的长度，由于一个像素点占了3个字节，所以要乘上3
    int size = width * height * 3;
    //获取第一个像素的地址
    IntPtr ptr = bitmapData.Scan0;
    Gray(ptr, width * height);
    //从内存中解锁
    bitmap.UnlockBits(bitmapData);
    pictureBox1.Refresh();
}