支持动态搜索区域的运动估计硬件结构设计与优化

doi:10.7523/j.issn.2095-6134.2012.4.012

中国科学院大学学报 ›› 2012, Vol. 29 ›› Issue (4): 512-517.DOI: 10.7523/j.issn.2095-6134.2012.4.012

支持动态搜索区域的运动估计硬件结构设计与优化

陈运必¹, 郭立¹, 李正东², 池凌鸿¹

1. 中国科学技术大学电子科学与技术系, 合肥 230027;
2. 重庆通信学院电子技术教研室, 重庆 400035

收稿日期:2011-03-14 修回日期:2011-06-07 发布日期:2012-07-15
通讯作者: 陈运必
基金资助:
国家自然科学基金(61071173)资助

Architecture design and optimization for motion estimation with dynamic search range

CHEN Yun-Bi¹, GUO Li¹, LI Zheng-Dong², CHI Ling-Hong¹

1. Department of Electronic Science and Technology, University of Science and Technology of China, Hefei 230027, China;
2. Staff room of Electronic and Technology, Chongqing Communication College, Chongqing 400035, China

Received:2011-03-14 Revised:2011-06-07 Published:2012-07-15

摘要/Abstract

摘要： 提出一种支持动态搜索区域的可变块大小运动估计硬件结构, 弥补固定大小搜索区域的不足, 可同时降低外存带宽、计算复杂度和功耗. 使用循环分布式存储结构来支持动态搜索区域的数据存取. 此外, 对耗时的SAD(sum of absolute differences)计算阵列进行均衡的流水线划分和加法逻辑优化. 实现结果表明, 相比同类设计, 该设计以少量的吞吐率损失, 换取面积效率和功耗效率的明显提高.

关键词: 运动估计, 动态搜索区域, 存储带宽, 流水线, 大规模集成电路

Abstract: A VBSME with dynamic search range is proposed to overcome the defects of the engine with fixed search range, and it reduces off-chip bandwidth, computational complexity, and power dissipation. A circularly distributed storage structure is adopted to realize the access to the dynamic search area. Besides, the time-consuming SAD computing array is divided into the balanced and adder-optimized pipelines. The implementation results show that, compared to traditional engines, the proposed engine can achieve significant improvements of the hardware and the power efficiency without much loss of throughput.

Key words: motion estimation, dynamic search range, memory bandwidth, pipeline, VLSI

中图分类号:

TN47

陈运必, 郭立, 李正东, 池凌鸿. 支持动态搜索区域的运动估计硬件结构设计与优化[J]. 中国科学院大学学报, 2012, 29(4): 512-517.

CHEN Yun-Bi, GUO Li, LI Zheng-Dong, CHI Ling-Hong. Architecture design and optimization for motion estimation with dynamic search range[J]. , 2012, 29(4): 512-517.

参考文献

[1] Wiegand T, Sullivan G J, Bjontegaard G, et al. Overview of the H.264/AVC video coding standard[J]. IEEE Trans Circuits Syst Video Technol, 2003, 13(7):560-576.
[2] Wiegand T, Schwarz H, Joch A, et al. Rate-constrained coder control and comparison of video coding standards[J]. IEEE Trans Circuits Syst Video Technol, 2003, 13(7):688-703.
[3] Huang Y W, Hsieh B Y, Chien S Y, et al. Analysis and complexity reduction of multiple reference frames motion estimation in H.264/AVC[J]. IEEE Trans Circuits Syst Video Technol, 2006, 16(4):507-522.
[4] Deng L, Gao W, Hu M Z, et al. An efficient hardware implementation for motion estimation of AVC standard[J]. IEEE Trans Consum Electron, 2005, 51(4):1360-1366.
[5] Li D X, Zheng W, Zhang M. Architecture design for H.264/AVC integer motion estimation with minimum memory bandwidth[J]. IEEE Trans Consum Electron, 2007, 53(3):1053-1060.
[6] Cao W, Hou H, Tong J R, et al. A high-performance reconfigurable VLSI architecture for VBSME in H.264[J]. IEEE Trans Consum Electron, 2008, 54(3):1338-1345.
[7] Ou C M, Le C F, Hwang W J. An efficient VLSI architecture for H.264 variable block size motion estimation[J]. IEEE Trans Consum Electron, 2005, 51(4):1291-1299.
[8] Jung J, Kim J, Kyung C M. A dynamic search range algorithm for stabilized reduction of memory traffic in video encoder[J]. IEEE Trans Circuits Syst Video Technol, 2010, 20(7):1041-1046.
[9] Zhang L, Xie D, Wu D. Improved FFSBM algorithm and its VLSI architecture for AVS video standard[J]. Journal of Computer Science and Technology, 2006, 21(3):378-382.
[10] Tuan J C, Chang T S, Jen C W. On the data reuse and memory bandwidth analysis for full-search block-matching VLSI architecture[J]. IEEE Trans Circuits Syst Video Technol, 2002, 12(1):61-72.
[11] Chen Z X, Song Y, Ikenaga T, et al. A dynamic search range algorithm for variable block size motion estimation in H.264/AVC //Proceedings of the 6th International Conference on Information, Communications & Signal Processing. Singapore: IEEE Communications Society, 2007:1-4.
[12] Chen T C, Chien S Y, Huang Y W, et al. Analysis and architecture design of an HDTV720p 30 frames/s H.264/AVC encoder[J]. IEEE Trans Circuits Syst Video Technol, 2006, 16(6): 673-688.
[13] Chen Y B, Guo L, Li Z D, et al. An efficient parallel architecture for one-bit transform based motion estimation[J]. Journal of Electronics & Information Technology, 2011, 33(3): 717-722(in Chinese). 陈运必, 郭立, 李正东, 等. 高性能并行比特变换运动估计硬件架构设计[J]. 电子与信息学报, 2011, 33(3):717-722.

支持动态搜索区域的运动估计硬件结构设计与优化

Architecture design and optimization for motion estimation with dynamic search range

PDF (PC)

可视化

摘要/Abstract

引用本文

使用本文

参考文献

相关文章 4

编辑推荐

Metrics

本文评价

访问统计

联系我们

[1]	袁竞杰, 张清毅, 马宜科, 宋风龙. 细粒度并行归一化部分失真运动估计[J]. 中国科学院大学学报, 2013, 30(6): 813-818.
[2]	蔡晓宁, 陈仲林, 董戈, 谢珊英. 数字PID控制器的硬件优化设计[J]. 中国科学院大学学报, 2010, 27(5): 690-694.
[3]	王大鹏杨寿保胡云滕达. 2.4GHz MIMO 网状网络中一种固定信道分配方法（英文）[J]. 中国科学院大学学报, 2007, 24(4): 506-515.
[4]	谌安军; 滕升华; 邹谋炎. 一种用于图像序列斑点去除的运动估计修正方法[J]. 中国科学院大学学报, 2006, 23(3): 396-402.