I am trying to apply watershed segmentation of a given input image which can be seen below.
I first start by applying a filling function, so that the small inner black dots get removed. This result can be seen below.
Based on an object detector ( which I trained seperately, and of which the centers coincide with a given blob) I plot a marker set, as seen below. For this is use simple circles.
Do note that there is a very small marker at the top left corner, which is placed there to ensure that the background is also a blob that is being created. Now I use the following functionality.
watershed(color_watershed, markers);
// Show the watershed result
// Generate random colors
std::vector<cv::Vec3b> colors;
for (int i = 0; i < centers.size(); i++)
{
int b = theRNG().uniform(0, 255);
int g = theRNG().uniform(0, 255);
int r = theRNG().uniform(0, 255);
colors.push_back(cv::Vec3b((uchar)b, (uchar)g, (uchar)r));
}
// Create the result image
Mat dst = cv::Mat::zeros(markers.size(), CV_8UC3);
// Fill labeled objects with random colors
for (int i = 0; i < markers.rows; i++)
{
for (int j = 0; j < markers.cols; j++)
{
int index = markers.at<int>(i,j);
if (index > 0 && index <= centers.size())
dst.at<Vec3b>(i,j) = colors[index-1];
else
dst.at<Vec3b>(i,j) = Vec3b(0,0,0);
}
}
But for some reason the output stays completely black, instead of colored blobs as I would have been expecting from the many tutorials out there ... which I did not expect. Anyone has an idea on what is going wrong?
