find optical flow for each pixel opencv

Question

I use the following functions as a base of my tracking algorithm.

//1. detect the features what i mean, this function extract the only good features,

cv::goodFeaturesToTrack(gray_prev, // the image 
features,   // the output detected features
max_count,  // the maximum number of features 
qlevel,     // quality level
minDist);   // min distance between two features

// 2. track features

cv::calcOpticalFlowPyrLK(
gray_prev, gray, // 2 consecutive images
points_prev, // input point positions in first im
points_cur, // output point positions in the 2nd
status,    // tracking success
err);      // tracking error

cv::calcOpticalFlowPyrLK takes vector of points from the previous image as input, and returns appropriate points on the next image. Suppose I want to calculate the opical flow for each pixle instead of good features

in the other meaning, start to calculate the optical flow from(1,1 ) to (m,n)

Answer 1

cv::calcOpticalFlowPyrLK does sparse OF, ie from feature points, if you want it for each pixel, use

calcOpticalFlowFarneback .

Computes a dense optical flow (using the Gunnar Farneback’s algorithm).