Fast mode selection with sub-sampled based block matching algorithm and architecture design for H.264/AVC fast intra prediction

In this paper, we propose a regular fast algorithm, which is called Block Matching Algorithm (BMA), to predict the best direction mode except for the DC mode for fast intra mode decision. The edge detective technique predicts luma-4×4, luma16×16, and chroma-8×8 modes directly. We partition the intra prediction procedure into two steps. At the first step, we use the pre-processing mode selection algorithms to find the primary mode which is selected for fast prediction. At the second step, the selected fewer high-potential candidate modes are applied to calculate the RD cost for the mode decision. Simulation results show that the proposed BMA method reduces the encoding time by 75%, and requires bit-rate increase about 2% and peak signal-to-noise ratio (PSNR) decrease about 0.07 dB in QCIF and CIF sequences, compared with the H.264/AVC JM 14.2 software. The methods achieve less PSNR degradation and bit-rate increase than the previous methods with more encoding time reduction. By implementing with TSMC 0.18μm CMOS standard cell library, the proposed sub-sampled BMA based processor achieves the full-HD 1920×1080 real-time encoding with 104MHz operational frequency.