去块滤波算法是高效视频编码标准(high-efficiency video coding,HEVC)的重要组成部分,专用硬件实现的去块滤波电路结构难以满足不断革新的算法需求,可重构计算兼具计算高效性和编程灵活性成为研究热点。基于指令流与数据流混合驱动可...去块滤波算法是高效视频编码标准(high-efficiency video coding,HEVC)的重要组成部分,专用硬件实现的去块滤波电路结构难以满足不断革新的算法需求,可重构计算兼具计算高效性和编程灵活性成为研究热点。基于指令流与数据流混合驱动可重构视频阵列处理器(reconfigurable video array processor,RVAP),提出一种可重构的HEVC编码去块滤波电路的并行化实现方法,依据数据流图分析实现去块滤波算法的最大化并行,提高计算效率;通过强/弱滤波方式的灵活切换,提高计算资源利用率。实验结果表明,所提方法在满足算法灵活切换和计算速度要求的同时,硬件资源减少了47.6%,时钟频率达167 MHz。展开更多
In this article, a design for the adaptive deblocking filter is proposed. To understand the real-time performance, a FILTER unit that can process eight pixels beside an edge simultaneously is applied in this design to...In this article, a design for the adaptive deblocking filter is proposed. To understand the real-time performance, a FILTER unit that can process eight pixels beside an edge simultaneously is applied in this design to increase filtering efficiency, and local memory is used to store all temporary data generated by the FILTER to reduce access to system bus. The filter makes every 4×4 sample block pipelined through the process units and achieves an efficiency of 80% for both the FILTER unit and the bus access unit. It can fulfill filtering process for a crystallographic information file （CIF, 352×288） format picture in 95 k clock cycles. The proposed design is part of a H.264/AVC decoder system-on-chip （SOC）, which is fabricated in 0.18 μm complementary metal oxide semiconductor （CMOS） process. The filter module consists of 60 k gates and 25.7 kb static random access memory （SRAM） and it can filter a macro-block in 240 clock cycles.展开更多
Audio Video coding Standard （AVS） is established by the AVS Working Group of China. The main goal of AVS part 7 is to provide high compression performance with relatively low complexity for mobility applications. Th...Audio Video coding Standard （AVS） is established by the AVS Working Group of China. The main goal of AVS part 7 is to provide high compression performance with relatively low complexity for mobility applications. There are 3 main low-complexity tools： deblocking filter, context-based adaptive 2D-VLC and direct intra prediction. These tools are presented and analyzed respectively. Finally, we compare the performance and the decoding speed of AVS part 7 and H.264 baseline profile. The analysis and results indicate that AVS part 7 achieves similar performance with lower cost.展开更多
文摘去块滤波算法是高效视频编码标准(high-efficiency video coding,HEVC)的重要组成部分,专用硬件实现的去块滤波电路结构难以满足不断革新的算法需求,可重构计算兼具计算高效性和编程灵活性成为研究热点。基于指令流与数据流混合驱动可重构视频阵列处理器(reconfigurable video array processor,RVAP),提出一种可重构的HEVC编码去块滤波电路的并行化实现方法,依据数据流图分析实现去块滤波算法的最大化并行,提高计算效率;通过强/弱滤波方式的灵活切换,提高计算资源利用率。实验结果表明,所提方法在满足算法灵活切换和计算速度要求的同时,硬件资源减少了47.6%,时钟频率达167 MHz。
基金supported by the National Natural Science Foundation of China (60372021)the Hi-Tech Research and Development Program of China (2003AA1Z1100).
文摘In this article, a design for the adaptive deblocking filter is proposed. To understand the real-time performance, a FILTER unit that can process eight pixels beside an edge simultaneously is applied in this design to increase filtering efficiency, and local memory is used to store all temporary data generated by the FILTER to reduce access to system bus. The filter makes every 4×4 sample block pipelined through the process units and achieves an efficiency of 80% for both the FILTER unit and the bus access unit. It can fulfill filtering process for a crystallographic information file （CIF, 352×288） format picture in 95 k clock cycles. The proposed design is part of a H.264/AVC decoder system-on-chip （SOC）, which is fabricated in 0.18 μm complementary metal oxide semiconductor （CMOS） process. The filter module consists of 60 k gates and 25.7 kb static random access memory （SRAM） and it can filter a macro-block in 240 clock cycles.
基金Supported by the National Natural Science Foundation of China under Grant Nos. 60333020 and 90207005.
文摘Audio Video coding Standard （AVS） is established by the AVS Working Group of China. The main goal of AVS part 7 is to provide high compression performance with relatively low complexity for mobility applications. There are 3 main low-complexity tools： deblocking filter, context-based adaptive 2D-VLC and direct intra prediction. These tools are presented and analyzed respectively. Finally, we compare the performance and the decoding speed of AVS part 7 and H.264 baseline profile. The analysis and results indicate that AVS part 7 achieves similar performance with lower cost.
