我刚开始使用 SSE 优化我的代码,用于一个计算机视觉项目,旨在检测图像中的肤色。以下是我的函数。该函数接受一张彩色图像,并查看每个像素并返回一个概率映射。注释掉的代码是我的原始 C++ 实现,其余部分是 SSE 版本。我对它们都进行了定时,奇怪的是发现 SSE 比我的原始 C++ 代码更快。有关发生了什么或如何进一步优化函数的任何建议吗?
void EvalSkinProb(const Mat& cvmColorImg, Mat& cvmProb)
{
std::clock_t ts = std::clock();
Mat cvmHSV = Mat::zeros(cvmColorImg.rows, cvmColorImg.cols, CV_8UC3);
cvtColor(cvmColorImg, cvmHSV, CV_BGR2HSV);
std::clock_t te1 = std::clock();
float fFG, fBG;
double dp;
__declspec(align(16)) int frgb[4] = {0};
__declspec(align(16)) int fBase[4] = {g_iLowHue, g_iLowSat, g_iLowVal, 0};
__declspec(align(16)) int fIndx[4] = {0};
__m128i* pSrc1 = (__m128i*) frgb;
__m128i* pSrc2 = (__m128i*) fBase;
__m128i* pDest = (__m128i*) fIndx;
__m128i m1;
for (int y = 0; y < cvmColorImg.rows; y++)
{
for (int x = 0; x < cvmColorImg.cols; x++)
{
cv::Vec3b hsv = cvmHSV.at<cv::Vec3b>(y, x);
frgb[0] = hsv[0];hsv[1] = hsv[1];hsv[2] =hsv[2];
m1 = _mm_sub_epi32(*pSrc1, *pSrc2);
*pDest = _mm_srli_epi32(m1, g_iSValPerbinBit);
// c++ code
//fIndx[0] = ((hsv[0]-g_iLowHue)>>g_iSValPerbinBit);
//fIndx[1] = ((hsv[1]-g_iLowSat)>>g_iSValPerbinBit);
//fIndx[2] = ((hsv[2]-g_iLowVal)>>g_iSValPerbinBit);
fFG = m_cvmSkinHist.at<float>(fIndx[0], fIndx[1], fIndx[2]);
fBG = m_cvmBGHist.at<float>(fIndx[0], fIndx[1], fIndx[2]);
dp = (double)fFG/(fBG+fFG);
cvmProb.at<double>(y, x) = dp;
}
}
std::clock_t te2 = std::clock();
double dSecs1 = (double)(te1-ts)/(CLOCKS_PER_SEC);
double dSecs2 = (double)(te2-te1)/(CLOCKS_PER_SEC);
}