Much like this paper on cell detection, I have a vision task in which I'd like to output the pixel coordinates of object centers. The number of objects can vary. Effectively I'd like to learn a boolean mask with the same shape of the image which has true values wherever an object center is located. In my application, the objects are all the same.
I'm having trouble performing a literature search on this problem. What can I call this type of regression? Given an image, I would like to develop the boolean mask of object centers with the same shape as the image.
If it helps, images are large (1680x720) which complicates approaches.