Context based coding of quantized alpha planes for video objects

Abstract

In object based video, each frame is a composition of objects that are coded separately. The composition is performed through the alpha plane that represents the transparency of the object. We present an alternative to MPEG-4 for coding of alpha planes that considers their specific properties. Comparisons in terms of rate and distortion are provided, showing that the proposed coding scheme for still alpha planes is better than the algorithms for I-frames used in MPEG-4.