Adaptive and recursive based spatio-temporal filtering for video denoising with RWT transformation

Video noise reduction technology can be used not only to filter out the noise in video, it also enhances the visual quality, performance of the subsequent processing tasks such as compression, target recognition and tracking as well as frame interpolation. The methodology presents video denoising technique where spatially adaptive noise filtering is combined with temporal filtering. In this paper we follow two filtering approach i.e. adaptive spatial filtering and recursive temporal filtering. Initially in adaptive spatial filtering, RWT is applied on every frame. These coefficients are used to modify trained coefficients stored in knowledge base using adaptive spatial filter. On the other hand, motion estimation is performed and the estimated results are used to guide the temporal filtering on current noisy frame. So, after above processing, there are two denoised frames, one comes from recursive temporal filtering and another comes from adaptive spatial filtering. Finally, by weighting the two denoised frames, a satisfactory result can be obtained. Later all the de-noised frames are combined to get the denoised video.