问利用NVIDIA库将YUV420(I420)图像转换为BGR时，如何确定YUV420的步长(行大小)

EN

int rSrcStep[3] = { COLS, COLS / 2, COLS / 2 };
int nDstStep = COLS * 3;

#include <stdint.h>
#include <stdio.h>
#include "nppi.h"

#define COLS 192
#define ROWS 108

uint8_t Y[COLS * ROWS];       //Y color channel in host memory
uint8_t U[COLS * ROWS / 4];   //U color channel in host memory
uint8_t V[COLS * ROWS / 4];   //V color channel in host memory

uint8_t BGR[COLS * ROWS * 3];   //BGR output image in host memory

int main()
{
    //Read Y, U, V planes to host memory buffers.
    //Build input sample using FFmpeg first:
    //ffmpeg -y -f lavfi -i testsrc=size=192x108:rate=1:duration=1 -pix_fmt yuvj420p -f rawvideo in.yuv420p
    ////////////////////////////////////////////////////////////////////////////
    FILE* f = fopen("in.yuv420p", "rb");
    fread(Y, 1, COLS * ROWS, f);
    fread(U, 1, COLS * ROWS / 4, f);
    fread(V, 1, COLS * ROWS / 4, f);
    fclose(f);
    ////////////////////////////////////////////////////////////////////////////

    //Allocate device memory, and copy Y,U,V from host to device.
    ////////////////////////////////////////////////////////////////////////////
    Npp8u* gpuY, * gpuU, * gpuV, * gpuBGR;
    cudaMalloc(&gpuY, COLS * ROWS);
    cudaMalloc(&gpuU, COLS * ROWS / 4);
    cudaMalloc(&gpuV, COLS * ROWS / 4);
    cudaMalloc(&gpuBGR, COLS * ROWS * 3);
    cudaMemcpy(gpuY, Y, COLS * ROWS, cudaMemcpyHostToDevice);
    cudaMemcpy(gpuU, U, COLS * ROWS / 4, cudaMemcpyHostToDevice);
    cudaMemcpy(gpuV, V, COLS * ROWS / 4, cudaMemcpyHostToDevice);
    ////////////////////////////////////////////////////////////////////////////


    //Execute nppiYUV420ToBGR_8u_P3C3R
    ////////////////////////////////////////////////////////////////////////////
    const Npp8u* const pSrc[3] = { gpuY, gpuU, gpuV };
    int rSrcStep[3] = { COLS, COLS / 2, COLS / 2 };
    int nDstStep = COLS * 3;
    NppiSize oSizeROI = { COLS, ROWS };

    NppStatus sts = nppiYUV420ToBGR_8u_P3C3R(pSrc,      //const Npp8u* const pSrc[3], 
                                             rSrcStep,  //int rSrcStep[3], 
                                             gpuBGR,    //Npp8u *pDst, 
                                             nDstStep,  //int nDstStep, 
                                             oSizeROI); //NppiSize oSizeROI);

    if (sts != NPP_SUCCESS) 
    {
        printf("Error: nppiResize_8u_C3R status = %d\n", (int)sts);
    }
    ////////////////////////////////////////////////////////////////////////////


    // Copy BGR output from device to host, and save BGR output to binary file
    // After saving, use FFmpeg to convert the output image from binary to PNG:
    // ffmpeg -y -f rawvideo -video_size 192x108 -pixel_format bgr24 -i out.bgr out.png
    ////////////////////////////////////////////////////////////////////////////
    cudaMemcpy(BGR, gpuBGR, COLS * ROWS * 3, cudaMemcpyDeviceToHost);
    f = fopen("out.bgr", "wb");
    fwrite(BGR, 1, COLS * ROWS * 3, f);
    fclose(f);
    ////////////////////////////////////////////////////////////////////////////


    cudaFree(&gpuY);
    cudaFree(&gpuU);
    cudaFree(&gpuV);
    cudaFree(&gpuBGR);

    return 0;
}