Fast CU size decision based on temporal homogeneity detection

High-Efficiency Video Coding (HEVC) is the latest video coding standard of the Joint Collaborative Team on Video Coding (JCT-VC). HEVC noticeably improves compression performance when comparing with previous standards such as H264, providing a major leap forward in video compression technology. However this improvement is achieved increasing the complexity of the encoding process. In this paper an optimized CU size decision algorithm is proposed in order to reduce HEVC computational cost by means of temporal homogeneity classification, which is directly applied to the input image using a GPU.