解释ARM霓虹灯图像采样

Question

我试图写一个更好的版本的cv::resize()的OpenCV，我来了一个交叉的代码，在这里:https://github.com/rmaz/NEON-Image-Downscaling/blob/master/ImageResize/BDPViewController.m代码是下行采样的图像2，但我不能得到的算法。我想先把这个算法转换成C语言，然后为了学习的目的对它进行修改。是否也容易将其转换为任意大小的downsample ?

函数是:

static void inline resizeRow(uint32_t *dst, uint32_t *src, uint32_t pixelsPerRow)
{
    const uint32_t * rowB = src + pixelsPerRow;
    // force the number of pixels per row to a multiple of 8
    pixelsPerRow = 8 * (pixelsPerRow / 8);
    __asm__ volatile("Lresizeloop: n" // start loop
                     "vld1.32 {d0-d3}, [%1]! n" // load 8 pixels from the top row
                     "vld1.32 {d4-d7}, [%2]! n" // load 8 pixels from the bottom row
                     "vhadd.u8 q0, q0, q2 n" // average the pixels vertically
                     "vhadd.u8 q1, q1, q3 n"
                     "vtrn.32 q0, q2 n" // transpose to put the horizontally adjacent pixels in different registers
                     "vtrn.32 q1, q3 n"
                     "vhadd.u8 q0, q0, q2 n" // average the pixels horizontally
                     "vhadd.u8 q1, q1, q3 n"
                     "vtrn.32 d0, d1 n" // fill the registers with pixels
                     "vtrn.32 d2, d3 n"
                     "vswp d1, d2 n"
                     "vst1.64 {d0-d1}, [%0]! n" // store the result
                     "subs %3, %3, #8 n" // subtract 8 from the pixel count
                     "bne Lresizeloop n" // repeat until the row is complete
: "=r"(dst), "=r"(src), "=r"(rowB), "=r"(pixelsPerRow)
: "0"(dst), "1"(src), "2"(rowB), "3"(pixelsPerRow)
: "q0", "q1", "q2", "q3", "cc"
);
}
To call it:
 // downscale the image in place
    for (size_t rowIndex = 0; rowIndex < height; rowIndex+=2)
    {
        void *sourceRow = (uint8_t *)buffer + rowIndex * bytesPerRow;
        void *destRow = (uint8_t *)buffer + (rowIndex / 2) * bytesPerRow;
        resizeRow(destRow, sourceRow, width);
    }

Answer 1

算法非常简单。它从当前行读取8个像素，从下一行读取8个像素。然后使用vhadd(减半-add)指令垂直平均8个像素。然后它调换像素的位置，使水平相邻的像素对现在在单独的寄存器中(垂直排列)。然后再做另一组减半——将这些加起来取平均值。然后将结果再次转换，将它们放在原始位置并写入目的地。该算法可以重写以处理不同的积分大小的缩放，但按照所写的，它只能进行2x2到1的平均化简。下面是等价的C代码:

static void inline resizeRow(uint32_t *dst, uint32_t *src, uint32_t pixelsPerRow)
{
    uint8_t * pSrc8 = (uint8_t *)src;
    uint8_t * pDest8 = (uint8_t *)dst;
    int stride = pixelsPerRow * sizeof(uint32_t);
    int x;
    int r, g, b, a;
    for (x=0; x<pixelsPerRow; x++)
    {
       r = pSrc8[0] + pSrc8[4] + pSrc8[stride+0] + pSrc8[stride+4];
       g = pSrc8[1] + pSrc8[5] + pSrc8[stride+1] + pSrc8[stride+5];
       b = pSrc8[2] + pSrc8[6] + pSrc8[stride+2] + pSrc8[stride+6];
       a = pSrc8[3] + pSrc8[7] + pSrc8[stride+3] + pSrc8[stride+7];
       pDest8[0] = (uint8_t)((r + 2)/4); // average with rounding
       pDest8[1] = (uint8_t)((g + 2)/4);
       pDest8[2] = (uint8_t)((b + 2)/4);
       pDest8[3] = (uint8_t)((a + 2)/4);
       pSrc8 += 8; // skip forward 2 source pixels
       pDest8 += 4; // skip forward 1 destination pixel
    }