Frame level rate control based on support vector machine in HEVC

This paper proposes a frame level rate control scheme for HEVC based on support vector machine. Firstly, textual features of frames are extracted from video sequence. According to different complexities of textual features, support vector machine is chosen as a classifier for video classification. Secondly, a frame level rate control scheme is proposed to achieve higher coding efficiency based on classification results. According to the experiment results, the proposed algorithm achieves better coding performance than the original rate control scheme JCTVC-K0103 in HEVC.