A motion-compensated spatio-temporal filter for image sequences with signal-dependent noise

摘要: A novel spatio-temporal filter is described for monochrome image sequences with either signal-independent or signal-dependent noise by considering both spatial and temporal correlations. With the assumptions of separability stationarity, it shown that motion-compensated groups frames can be decorrelated using Karhunen-Loeve transform. Practical filters work well on a variety are developed first applying Hadamard transform along direction. Subsequently, parametric adaptive Wiener applied to each resulting approximately transformed images. These images classified into one average remaining set residual images, which provide interesting useful interpretations type sequence. The performance evaluated different types in database. procedure advanced processing sequence adapted generalization multispectral this possibility currently under detailed investigation.