Im使用C ++ openCV程序实现第一原理HDL(Verilog)图像对象检测的算法开发。我终于设法使HDL版本达到精明的检测点。为了验证两者,两者都需要具有相同的输出。我发现它们之间的细微差别是由openCV读取的颜色到灰度转换偏向绿色造成的。在openCV C ++方法中,平滑的图像总体上更亮。通过查看rgb2gray方法,似乎openCV使用了一个偏差,即(R X + G Y + B * Z)/ 3,而在HDL中,我一直在使用(R + G + B)/ 3完成高斯,Sobel和Canny滤波器。人类可视化是次要的,并且不以非整数相乘是不希望的。
是否有用于转换的标准线性灰度转换或替代现有方法的方法?...
int main()
{
int thold = 15;
clock_t start;
double duration;
const int sobelX[3][3] = { {-1, 0, 1}, {-2, 0, 2}, {-1, 0, 1} }; //Where origionally floats in python
const int sobelY[3][3] = { {-1, -2, -1}, {0, 0, 0}, {1, 2, 1} }; //Where origionally floats in python
const int kernel[5][5] = { {1,6,12,6,1},
{6,42,79,42,6},
{12,79,148,79,12},
{6,42,79,42,6},
{1,6,12,6,1} };// 1/732
// Above normalised kernal for smoothing, see origional python script for method
start = std::clock();
int height, width, intPixel, tSx, tSy, tS, dirE, dirEE, maxDir, curPoint, contDirection, cannyImgPix, nd, tl, tm, tr, mr, br, bm, bl, ml = 0;
int contNum = 128;
int contPixCount = 0;
int curContNum = 0;
int contPlace = 0;
int oldContPlace = 0;
int g = 0;
bool maxPoint;
struct pixel {
int number;
int h;
int w;
};
std::vector<pixel> contourList;
//double floatPixel = 0.0;
int kernalCumulator = 0;
const int mp = 3;
// Scalar color(0, 0, 255);
// duration = ((clock()) - start) / (double)CLOCKS_PER_SEC;
// start = clock();
// cout << "Start image in" << duration << '\n';
// Mat dst;
Mat rawImg = imread("C:\\Users\\&&&\\Documents\\pycode\\paddedGS.png",0);
printf("%d",rawImg.type());
// Mat rawImg = imread("C:\\Users\\&&&\\Documents\\openCV_Master\\openCVexample\\openCVexample\\brace200.jpg ", 0);
height = rawImg.rows;
width = rawImg.cols;
cout << "Height of image " << height << '\n';
cout << "Width of image " << width << '\n';
Mat filteredImg = Mat::zeros(height, width, CV_8U);
printf("%d", filteredImg.type());
Mat sobelImg = Mat::zeros(height, width, CV_8U);
Mat directionImg = Mat::zeros(height, width, CV_8U);
Mat cannyImg = Mat::zeros(height, width, CV_8U);
Mat contourImg = Mat::zeros(height, width, CV_16U);
// rawImg.convertTo(rawImg, CV_8UC1);
duration = ((clock()) - start) / (double)CLOCKS_PER_SEC;
start = clock();
cout << "Start image in" << duration << '\n';
// Loop to threshold already grayscaled image
/*
for (int h = 0; h < (height); h++)
{
for (int w = 0; w < (width); w++)
{
g = (int)rawImg.at<uchar>(h, w,0);
cout << g << "g";
g+= (int)rawImg.at<uchar>(h, w, 1);
cout << g << "g";
g+= (int)rawImg.at<uchar>(h, w, 2);
cout << g << "g";
g = g/3;
rawGImg.at<uchar>(h,w) = g;
}
}
*/
// imshow("thresholded Image", rawImg);
// waitKey();
// Loop to smooth using Gausian 5 x 5 kernal
// imshow("raw Image", rawImg);
for (int h = 3; h < (height - 3); h++)
{
for (int w = 3; w < (width - 3); w++)
{
if (rawImg.at<uchar>(h, w) >=6 )//Thresholding included
{
for (int xk = 0; xk < 5; xk++)
{
for (int yk = 0; yk < 5; yk++)
{
intPixel = rawImg.at<uchar>((h + (xk - mp)), (w + (yk - mp)));
kernalCumulator += intPixel*(kernel[xk][yk]);//Mutiplier required as rounding is making number go above 255, better solution?
}
}
}
else
kernalCumulator = 0;
kernalCumulator = kernalCumulator / 732;
if (kernalCumulator < 0 || kernalCumulator > 255)
{
// cout << "kernal Value: " << kernalCumulator;
// cout << " intPixel:" << intPixel << '\n';
}
filteredImg.at<uchar>(h, w) = (uchar)kernalCumulator;
kernalCumulator = 0;
}
}
我们的视觉不能线性地感知亮度,因此对于通常的应用而言,使用某种模仿人类感知的变换是有意义的。
对于您的应用程序,您有2个选择:要么在HDL中使用类似的转换(这可能不容易,要么不期望),或者为OpenCV使用自定义的rgb进行灰度转换,以使用您使用的相同转换。
这是一个简短的代码段(更像伪代码,您必须弄清楚细节),类似于:
cv::Mat linearRgbToGray(const cv::Mat &color) {
cv::Mat gray(color.size(), CV_8UC1);
for (int i = 0; i < color.rows; i++)
for (int j = 0; j < color.cols; j++)
gray.at(i, j) = (color.at(i, j)[0] + color.at(i, j)[1] + color.at(i, j)[2]) / 3;
}