Good features to track
	Recall Lucas-Kanade equation:
	When is this solvable? • ATA should be invertible • ATA should not be too small due to noise – eigenvalues l1 and l2 of ATA should not be too small • ATA should be well-conditioned –   l1/ l2 should not be too large (l1 = larger eigenvalue) These conditions are satisfied when min(l1, l2) > c