OpenCV+CUDA学习6---Laplace算法

#include "cuda_runtime.h"
#include "device_launch_parameters.h"
#include 
#include 
#include 
#include 
using namespace std;
using namespace cv;
//========================Sobel算子边缘检测核函数========================
__global__ void laplaceInCuda(unsigned char* dataIn, unsigned char* dataOut, int  imgHeight, int imgWidth)
{
    //==========1,1,1=============
    //==========1,-8,1============
    //========= 1,1,1=============
    //===============找寻线程的唯一ID=================
    int yIndex = threadIdx.y + blockIdx.y * blockDim.y; //=====row====
    int xIndex = threadIdx.x + blockIdx.x * blockDim.x; //=====col====
    int index = yIndex * imgWidth + xIndex;
    float G = 0.f;
    if (xIndex > 0 && xIndex < imgWidth - 1 && yIndex > 0 && yIndex < imgHeight - 1) {
        G = dataIn[(yIndex - 1) * imgWidth + xIndex - 1] * 1 + dataIn[(yIndex - 1) *  imgWidth + xIndex] * 1 + dataIn[(yIndex - 1) * imgWidth + xIndex + 1] * 1
            + dataIn[(yIndex)*imgWidth + xIndex - 1] * 1 - 8 * dataIn[yIndex * imgWidth +  xIndex] + dataIn[(yIndex)*imgWidth + xIndex + 1] * 1
            + dataIn[(yIndex + 1) * imgWidth + xIndex - 1] * 1 + dataIn[(yIndex + 1) *  imgWidth + xIndex] * 1 + dataIn[(yIndex + 1) * imgWidth + xIndex + 1] * 1;
        dataOut[index] = G;
    }
}
int main()
{
    //==================加载图像==================
    Mat grayImg = imread("H:\opencv_project\opencv_cuda学习\image\hist_02.jpg", 0);
    int imgHeight = grayImg.rows;
    int imgWidth = grayImg.cols;
    Mat laplaceImg;
    //==============opencv实现laplace图像卷积==========
    cv::Mat kernel = (Mat_(3, 3) <<
        1, 1, 1,
        1, -8, 1,
        1, 1, 1);
    filter2D(grayImg, laplaceImg, CV_32F, kernel);
    laplaceImg.convertTo(laplaceImg,CV_8U);
    cv::namedWindow("laplace-opencv",cv::WINDOW_NORMAL);
    cv::imshow("laplace-opencv",laplaceImg);
    
    //===============CUDA实现后的传回的图像=============
    Mat dstImg(imgHeight, imgWidth, CV_8UC1, Scalar(0));
    //==================创建GPU内存===================
    unsigned char* d_in;
    unsigned char* d_out;
    cudaMalloc((void**)&d_in, imgHeight * imgWidth * sizeof(unsigned char));
    cudaMalloc((void**)&d_out, imgHeight * imgWidth * sizeof(unsigned char));
    //================将高斯滤波后的图像从CPU传入GPU=================
    cudaMemcpy(d_in, grayImg.data, imgHeight * imgWidth * sizeof(unsigned char),  cudaMemcpyHostToDevice);
    dim3 threadsPerBlock(32, 32);
    dim3 blocksPerGrid((imgWidth + threadsPerBlock.x - 1) / threadsPerBlock.x, (imgHeight  + threadsPerBlock.y - 1) / threadsPerBlock.y);
    //========================调用核函数=======================
    laplaceInCuda << > > (d_in, d_out, imgHeight,  imgWidth);
    //=======================将图像传回GPU=====================
    cudaMemcpy(dstImg.data, d_out, imgHeight * imgWidth * sizeof(unsigned char),  cudaMemcpyDeviceToHost);
    //=========================释放GPU内存====================
    cudaFree(d_in);
    cudaFree(d_out);
    cv::namedWindow("cuda-sobel", cv::WINDOW_NORMAL);
    cv::imshow("cuda-sobel", dstImg);
    cv::waitKey(0);
    return 0;
}