A CNN Implementation of the Horn & Schunck Motion Estimation Method

In this paper the parallel implementation of the Horn and Schunck motion estimation method in image sequences is presented, by using cellular neural networks (CNN). One of the drawbacks of the classical motion estimation algorithms is the computational time. The goal of the CNN implementation of the Horn & Schunck method is to increase the efficiency of the well-known classical implementation of this method, which is one of the most used algorithms among the motion estimation techniques. The aim is to obtain a smaller computation time and to include such an algorithm in motion compensation algorithms implemented using CNN, in order to obtain homogeneous algorithms for real-time applications in artificial vision or medical imaging