Spatial-temporal feature guided adaptive rate control for screen content videos

In this paper, an adaptive rate control algorithm based on screen content characteristics is proposed. It enhances the coding performance of HEVC Extensions on Screen Content Coding (HEVC-SCC) by leveraging the unique characteristics of screen content videos (SCVs). Firstly, considering the characteristics of the human visual system (HVS) and the particular spatial–temporal characteristics of SCVs, the spatial feature (SF) and temporal feature (TF) factors are extracted by Gabor filter. Then, a spatial–temporal fused feature of SVC is modeled an adaptive \(R-\lambda\) $R-\lambda$ model to guide the rate control of HEVC-SCC. More bitrates are allocated to coding tree units (CTUs) that have higher vision sensitivity, and vice versa. The experimental results demonstrate the effectiveness of the proposed STF_RC. It achieves a quality improvement of 1.70 dB in Low Delay B (LDB) and 2.55 dB in Random Access (RA) configurations. Additionally, it reduces bitrate by 21.75% in LDB and 25.42% in RA compared to the standard platform. Compared to state-of-the-art rate control algorithms for HEVC-SCC, it reduces bitrate mismatch significantly and achieves better performance in both rate-distortion and subjective quality.