Mean field annealing for motion estimation in medical image sequences

This paper presents an application of mean field annealing (MFA) theory for motion estimation in medical image sequences. More precisely, we present the adaptation of the MFA algorithm to solve the motion estimation problem in NMR (nuclear magnetic resonance) image sequences. The proposed algorithm ensures a satisfying trade-off between precision and computational time, in other words, it ensures a good efficiency in comparison with stochastic algorithms. The results are compared in term of precision and computational time with some basic algorithms, such as the basic block-matching and Horn & Schunck. The results are illustrated on both synthetic images (obtained using the free form deformation principle) and real NMR medical image sequences.