IEEE Transactions on Pattern Analysis and Machine Intelligence
| Hi-index | 0.00 |
Control point assessment (CPA) is motivated by the question of whether it is possible to computationally assess the quality of optical flow estimates at various points throughout the image without knowing the true flow field. Surprisingly the answer is yes and is determined by the norm of the least squares operator associated with the optical flow equation. The method isolates points in the image corresponding to maximum reliability. These points in turn can be used as control points for registration without actually computing the optical flow and indeed only require a single frame for computation. In this paper we present several extensions of the basic CPA algorithm. The paper also discuss how LS operator norm information can be coupled with anisotropic diffusion to produce smoothed images without corner degradation.