A multiresolution approach for video texture registration

Electro-optical imagery can have uniform characteristics that prevent it from being registered by conventional edge-based methods. Such uniform characteristics, if they have periodicity, can be exploited using multi-resolution texture extraction techniques. We first use a multi-resolution Markov model to represent electro-optical textures and apply an autoregressive statistical approach to find correspondence between two images. We then demonstrate how this approach reduces the computational complexity of registering of two successive frames of video