Motion dependent spatiotemporal smoothing for noise reduction in very dim light image sequences

A new method for noise reduction using spatiotemporal smoothing is presented in this paper. The method is devel-oped especially for reducing the noise that arises when ac-quiring video sequences with a camera under very dim light conditions. The work is inspired by research on the vision of nocturnal animals and the adaptive spatial and temporal summation that is prevalent in the visual systems of these animals. From analysis using the so-called structure ten-sor in the three-dimensional spatiotemporal space, motion segmentation and global ego-motion estimation, Gaussian shaped smoothing kernels are oriented mainly in the direc-tion of the motion and in spatially homogeneous directions. In static areas, smoothing along the temporal dimension is favoured for maximum preservation of structure. The technique has been applied to various dim light image se-quences and results of these experiments are presented here