Video Enhancement by Noise Repression and Contrast Adjustment

Bo Yang


Abstract

This work focuses on how to improve video quality by repressing mixture of Gaussian noise and impulse noise as well as adjusting video contrast. We introduce a new adaptive spatio-temporal connective (ASTC) noise filter and an adaptive piecewise mapping function (APMF). We first introduce a novel local image statistic to identify impulse noise pixels, and then incorporate it into the classical bilateral filter to form ASTC, aiming to reduce the mixture of Gaussian and impulse noises in spatial and temporal directions. After noise removal, we adjust the video contrast with APMF based on the statistical information of frame segmentation results. The experiment results demonstrate that, for diverse low-quality videos corrupted by mixed noise, underexposure, overexposure, or any mixture of the above, the proposed system can automatically produce satisfactory results.


Maintained by Dian Gong