Improving scalable video adaptation in a knowledge-based framework

In a knowledge-based content adaptation framework, video adaptation can be performed in a series of steps, named conversions. The high-level decision phase in such a framework occasionally encounters several feasible parameter values of a specific conversion. This paper proposes to transfer further decisions to a low-level phase that decides which parameters maximise the quality of the adaptation. Particularly when more than one solution are available, an innovative quality measure is used for selecting the best values for the parameters among the set of values that fulfil the adaptation constraints in the case of scalable video.