Inter mode selection for H.264/AVC using time-efficient learning-theoretic algorithms

In this paper we present a novel algorithm to speed up the inter mode decision process for the H.264/AVC encoding. The proposed inter mode decision scheme determines the best coding mode between P16×16 and P8×8 based on learning theoretic classification algorithms to discern between mode classes based on the evaluation of a simple set of features extracted from a motion compensated macroblock. We show that the proposed method can reduce the number of macroblocks for P8×8 mode testing by 80% on average, at the cost of only a small loss of 0.1 dB in compression performance.