Adaptive interpolation for heterogeneous multidimensional signals fusion

we propose an adaptive parameterized interpolator to solve the problem of heterogeneous multidimensional signals fusion. This interpolator is based on the automatic switching between several interpolating functions at each point of the signal. We propose a set of interpolating functions for the case of arbitrary signal dimension. Besides, we describe a procedure for the optimization of the adaptive interpolator according to the criterion of the minimum energy of post-interpolation residues. We perform the optimization of the adaptive interpolator for a multidimensional signal of reduced resolution. Then we use the found optimal parameter value to interpolate the signal of the required resolution. We perform the computational experiments in natural multidimensional signals to investigate the proposed adaptive interpolator. This interpolator can significantly (up to 26%) increase the efficiency of heterogeneous signals fusion.