The Lucas-Kanade method is used for sparse optical flow tracking. By sparse, we mean that the number of feature points is relatively low. You can refer to their original paper here: http://cseweb.ucsd.edu/classes/sp02/cse252/lucaskanade81.pdf. We start the process by extracting the feature points. For each feature point, we create 3 x 3 patches with the feature point at the center. The assumption here is that all the points within each patch will have a similar motion. We can adjust the size of this window depending on the problem at hand.
For each feature point in the current frame, we take the surrounding 3 x 3 patch as our reference point. For this patch, we look in its neighborhood in the previous frame to get the ...
