Junji Tajime

High performance and cost effective memory architecture for an HDTV decoder LSI

This paper proposes an efficient memory mapping and a frame memory compression for an HDTV decoder LSI using Direct Rambus/sup TM/ DRAM (DRDRAM). The DRDRAM is employed to achieve the high memory bandwidth required for HDTV decoding at the minimum memory cost. The proposed memory mapping achieves a high memory bandwidth sufficient for HDTV decoding even in the worst case and no costly line buffers are required in the LSI for format conversion. The frame memory compression method reduces the memory cost by half and achieves HDTV decoding with a single 64 Mb DRDRAM chip without loss of memory access efficiency. Simulation results show that SNR degradation is 0.1 to 2 dB in the worst frame and no visible degradation is perceived except for a resolution chart sequence.

Memory compression method considering memory bandwidth for HDTV decoder LSIs

This paper proposes a frame memory compression method for an MPEG-2 Main Profile@High-Level (MP@HL) decoder LSI using Direct RambusTM DRAM (DRDRAM). The compression method is based on two-dimensional adaptive DPCM (2-D ADPCM) and is designed to achieve efficient memory access. HDTV bitstreams are decoded with a single 64 megabit (Mb) DRDRAM without subjective image quality degradation. Computer simulation is performed for ten HDTV bitstreams encoded at 22 Mbps. Simulation results show that, in the worst case, SNR loss compared to the full spec decoder is 0.71 dB for a luminance, 0.27 dB and 0.57 dB for chrominances.

Fast software MPEG-2 video transcoder with optimization of requantization error compensation

A low-complexity software video transcoder with motion compensation (MC) of requantization errors has been developed. For reducing the processing time of the developed transcoder, two novel methods are proposed. One is a sparse block transcoding method that bypasses a transcoding process according to the distribution of the transform coefficients in an input block. This method is valid for about half of all blocks of P pictures. The other is a fast MC method that alternates rounding directions of MC per picture to decrease conditional judgments. The processing time of the fast MC is reduced to three fifths. The transcoder with the proposed methods has been running in real-time on PCs.

A Memory Compression Method for Avoiding Perceivable Distortion Due to Intra-Prediction in H.264 Decoders

This paper analyzes the video-quality degradation mechanism in an H.264 decoder with memory compression and proposes a new DPCM memory compression method which avoids that degradation. When memory compression methods used in MPEG-2 decoders are applied to H.264 decoders, heavy degradation sometimes occurs because H.264 employs directional spatial prediction in intra-coding. The proposed method avoids such degradation by deploying DPCM base points to intra reference pixels in order to protect them from compression distortion. Simulation results show that the proposed method significantly improves video-quality, in the best case by 7.51 dB in PSNR, over that of conventional methods, and subjective quality is also improved.