Computing radial average of the autocorrelation of a binary image

edit

if you just want to extract the pixel coordinates of the non-zero pixels, then you can use the findNonZero() (for some reason I cannot find it in the documentation) function:

cv::Mat binaryImage; // input, binary image
cv::Mat locations;   // output, locations of non-zero pixels 
cv::findNonZero(binaryImage, locations);

and then access the coordinates by:

Point coordinate = locations.at<Point>(i);

Otherwise, you will have to do it by yourself through looping the binary image and pushing the x, y point values of the non-zero pixels into a vector<point> structure. You can find many examples how to do that if you search into the web.

edit ------------------------------------------------------------------------------------------------

it seems that passing coordinates straight forward to a vector<point> structure is also supported from the findNonZero() function, so you can just use:

cv::Mat binaryImage; // input, binary image
vector<Point> locations;   // output, locations of non-zero pixels 
cv::findNonZero(binaryImage, locations);