This paper introduces a new RAID 6 expanding method HCS, which is facing the circumstance of big data. HCS expands H-Code manner RAID 6. Two key techniques are used to avoid parity blocks’ recalculating.The first one...This paper introduces a new RAID 6 expanding method HCS, which is facing the circumstance of big data. HCS expands H-Code manner RAID 6. Two key techniques are used to avoid parity blocks’ recalculating.The first one is anti-diagonal data blocks’ selection, and the other one is horizontal data migration. These two techniques ensure the data blocks are retained in the same verification zone, that is horizontal verification zone and anti-diagonal verification zone. Experimental results showed that, compared with SDM, which is also a fast expansion method, HCS can reduce 3.6% expansion time and promote 4.62% performance under four traces.展开更多
The typeⅡ codes have been studied widely in applications since their appearance. With analysis of the algebraic structure of finite field of order 4 （i.e., GF（4））, some necessary and sufficient conditions that a ...The typeⅡ codes have been studied widely in applications since their appearance. With analysis of the algebraic structure of finite field of order 4 （i.e., GF（4））, some necessary and sufficient conditions that a generalized H-code （i.e., GH-code） is a type Ⅱ code over GF（4） are given in this article, and an efficient and simple method to generate type Ⅱ codes from GH-codes over GF（4） is shown. The conclusions further extend the coding theory of type Ⅱ.展开更多
近年来,面向机器视觉视频的研究和应用越来越广泛,这对此类视频的存储和传输都提出了巨大的挑战。视频编码标准如多功能视频编码(Versatile Video Coding,VVC)能实现高效的全分辨率压缩与重建,但是对机器视觉任务而言,这种压缩方法是有...近年来,面向机器视觉视频的研究和应用越来越广泛,这对此类视频的存储和传输都提出了巨大的挑战。视频编码标准如多功能视频编码(Versatile Video Coding,VVC)能实现高效的全分辨率压缩与重建,但是对机器视觉任务而言,这种压缩方法是有冗余的。因此,提出了一种在VVC编码过程中结合显著性检测的视频编码方法用于机器任务,用实例分割网络掩膜基于区域的卷积神经网络(Mask Region-based Convolutional Neural Network,Mask R-CNN)获得包含对象的二进制掩膜,并依此判定是否为感兴趣区域,指导VVC编码过程中编码树单元(Coding Tree Unit,CTU)的量化参数的偏移。实验证明,与VVC基线方法相比,所提方法可以在相似的检测精度下节省一定的比特率。展开更多
随着数据量的不断增加,原有存储系统已不能满足海量数据存储的要求。RAID(redundant arrays of independent disks)存储系统因具有良好的数据可靠性、磁盘独立性和可扩展性,成为应用范围最广的存储系统。新型存储技术存在研究迟缓、推...随着数据量的不断增加,原有存储系统已不能满足海量数据存储的要求。RAID(redundant arrays of independent disks)存储系统因具有良好的数据可靠性、磁盘独立性和可扩展性,成为应用范围最广的存储系统。新型存储技术存在研究迟缓、推广率低的问题,使得在原有RAID存储系统中添加新的磁盘,成为存储海量数据最为便捷,最为有效,成本最低的方式。RAID发展至今,根据对数据存储的不同需求,衍生出了不同层级的RAID存储系统。RAID-6存储系统由数据盘与2个校验盘构成,相较于其他RAID存储系统,具有更好的数据容错功能,更高的数据恢复能力。因此,提出一种基于H-Code针对RAID-6存储系统的扩容算法HS6。该算法在扩容过程中体现了最小化数据迁移量和快速扩容等特性,与传统的Round-Robin和Semi-RR扩容算法相比,该算法减少了73.2%~88.6%的数据迁移量,缩短了30.6%~ 62.9%的总扩容时间。展开更多
近年来随着视频编码技术的发展以及高清视频需求的快速增长,国际运动图像专家组ISO-IEC/MPEG和国际电信联盟的视频编码专家组ITU-T/VCEG于2010年成立了视频编码联合工作组JCT-VC,开始针对高分辨率视频应用制定新一代视频编码标准,即高...近年来随着视频编码技术的发展以及高清视频需求的快速增长,国际运动图像专家组ISO-IEC/MPEG和国际电信联盟的视频编码专家组ITU-T/VCEG于2010年成立了视频编码联合工作组JCT-VC,开始针对高分辨率视频应用制定新一代视频编码标准,即高效视频编码HEVC(High Efficiency Video Coding),2012年底形成了国际标准草案,并开发了相应的测试模型HM,进行性能评估和算法测试.该文将对标准制定过程中涉及到的关键技术进行详细介绍,主要包括:基于四叉树结构的编码块组织形式、先进的运动矢量预测和合并方法、多方向的帧内预测模式、基于DCT的分像素插值技术和内容自适应的算术编码技术等,最后对相关编码工具的编码效率、计算复杂度进行了分析,并且指出了未来的研究方向.展开更多
文摘This paper introduces a new RAID 6 expanding method HCS, which is facing the circumstance of big data. HCS expands H-Code manner RAID 6. Two key techniques are used to avoid parity blocks’ recalculating.The first one is anti-diagonal data blocks’ selection, and the other one is horizontal data migration. These two techniques ensure the data blocks are retained in the same verification zone, that is horizontal verification zone and anti-diagonal verification zone. Experimental results showed that, compared with SDM, which is also a fast expansion method, HCS can reduce 3.6% expansion time and promote 4.62% performance under four traces.
基金the National Natural Science Foundation of China (60743007)Fujian Province Young Talent Program (2006F3044)+2 种基金Province Natural Science Foundation of Fujian (JA04169)Province Education Department Foundation of Fujian (JB05331)Beijing Municipal Commission of Education Disciplines and Graduate Education Projects (XK100130648)
文摘The typeⅡ codes have been studied widely in applications since their appearance. With analysis of the algebraic structure of finite field of order 4 （i.e., GF（4））, some necessary and sufficient conditions that a generalized H-code （i.e., GH-code） is a type Ⅱ code over GF（4） are given in this article, and an efficient and simple method to generate type Ⅱ codes from GH-codes over GF（4） is shown. The conclusions further extend the coding theory of type Ⅱ.
文摘近年来,面向机器视觉视频的研究和应用越来越广泛,这对此类视频的存储和传输都提出了巨大的挑战。视频编码标准如多功能视频编码(Versatile Video Coding,VVC)能实现高效的全分辨率压缩与重建,但是对机器视觉任务而言,这种压缩方法是有冗余的。因此,提出了一种在VVC编码过程中结合显著性检测的视频编码方法用于机器任务,用实例分割网络掩膜基于区域的卷积神经网络(Mask Region-based Convolutional Neural Network,Mask R-CNN)获得包含对象的二进制掩膜,并依此判定是否为感兴趣区域,指导VVC编码过程中编码树单元(Coding Tree Unit,CTU)的量化参数的偏移。实验证明,与VVC基线方法相比,所提方法可以在相似的检测精度下节省一定的比特率。
文摘近年来随着视频编码技术的发展以及高清视频需求的快速增长,国际运动图像专家组ISO-IEC/MPEG和国际电信联盟的视频编码专家组ITU-T/VCEG于2010年成立了视频编码联合工作组JCT-VC,开始针对高分辨率视频应用制定新一代视频编码标准,即高效视频编码HEVC(High Efficiency Video Coding),2012年底形成了国际标准草案,并开发了相应的测试模型HM,进行性能评估和算法测试.该文将对标准制定过程中涉及到的关键技术进行详细介绍,主要包括:基于四叉树结构的编码块组织形式、先进的运动矢量预测和合并方法、多方向的帧内预测模式、基于DCT的分像素插值技术和内容自适应的算术编码技术等,最后对相关编码工具的编码效率、计算复杂度进行了分析,并且指出了未来的研究方向.
