Reinforcement Learning for HEVC/H.265 Intra-Frame Rate Control

• Main Authors: Hu, Jun-Hao, 胡俊顥
• Other Authors: Peng, Wen-Hsiao
• Format: Others
• Language: en_US
• Published: 2018
• Online Access: http://ndltd.ncl.edu.tw/handle/t942e8

碩士 === 國立交通大學 === 多媒體工程研究所 === 107 === Reinforcement learning has proven effective for solving decision making problems. However, its application to modern video codecs has yet to be seen. This thesis presents an early attempt to introduce reinforcement learning to HEVC/H.265 intra-frame rate control. The task is to determine the λ value in the rate-distortion optimization for every coding tree unit in a frame, with the objective being to minimize the frame-level distortion subject to a rate constraint. We draw an analogy between the rate control problem and the reinforcement learning problem, by considering the texture complexity of coding tree units and bit balance as the environment state, the λ value as an action that an agent needs to take, and the negative distortion of the coding tree unit as an immediate reward. We train a neural network based on DDPF algorithm to be our agent, which observes the state to evaluate the reward for each possible action. The experimental results show that the proposed model can already perform more accurate and state bit rate control than the rate control algorithm in HM-16.15.