Our thesis work is based on revealing minor informative variations in a video which are hard to perceive, that can be further exaggerated to extract hidden variations of color and motions in a video. In our thesis we apply di erent techniques of a video decomposition like Laplacian, Steerable and Gaussian pyramids to observe the improvement in performance of the videos. We start with a standard input video to decompose it in di erent spatial pool of frequencies, the temporal ltering process is applied to the frames to extract hidden signals. The resultant signals from the temporal processing are then ampli ed by a given factor to reveal hidden information in the videos. These ampli ed signals are added back to the original signals and then a pyramid is collapsed to generate an output video. Performance of Gaussian and Steerable pyramids for video decomposition is evaluated over Eulerian motion magni cation. The output videos from all pyramids decomposition is computationally analyzed and compared with each other through SSIM and PSNR graphs. The video processing time is used to compare decomposition methods. It is observed that Eulerian motion magni cation with Steerable pyramid decomposition has potential of revealing hidden motions more than Laplacian and Gaussian pyramids, precisely in monitoring and diagnostic applications. Steerable pyramid decomposition method performs better than the other methods when input video is noisy.

A standard video has been taken as input and magni ed to amplify the small motion in it which was invisible to human eye. This method processes pixels at speci c positions in a video where it has got low frequencies and ampli es them to see small changes in video work improvements in Eulerian motion magni cation and color ampli cation by using Gaussian and Steerable pyramids for video decomposition were investigated. To observe small changes in a video and to extract subtle changes Steerable and Gaussian pyramids were used. The effects on di erent videos with di erent formats and noise environments when subjected to this system were observed. Proposed model was found to be better in performance then contemporary Eulerian magni cation using Laplacian pyramid in some cases. Magni cation using Steerable pyramid showed better results than Laplacian, as seen from PSNR, SSIM graphs and comparison.