Design and implementation of adaptive architecture for Catmull-Rom image scaling algorithm

REN Xiang-long; TIAN Ze; ZHANG Jun; HAN Li-min; ZHENG Xin-jian; FAN Fei-hu

Chinese

您当前的位置：

首页 >

文章列表页 >

Design and implementation of adaptive architecture for Catmull-Rom image scaling algorithm

更新时间：2026-09-04

- Design and implementation of adaptive architecture for Catmull-Rom image scaling algorithm
- Vol. 36, Issue 8, Pages: 39-44(2019)
- 作者机构：
  
  1. 中国航空工业集团西安航空计算技术研究所,陕西,西安,710068
  2. 集成电路与微系统设计航空科技重点实验室,陕西,西安,710068
- 作者简介：
- 基金信息：
- DOI：
  CLC：
- Published：2019
- 稿件说明：
移动端阅览
任向隆, 田泽, 张骏, 韩立敏, 郑新建, 范飞虎. Catmull-Rom图像缩放算法的自适应结构设计与实现[J]. 微电子学与计算机, 2019, 36(8): 39-44.

REN Xiang-long, TIAN Ze, ZHANG Jun, et al. Design and implementation of adaptive architecture for Catmull-Rom image scaling algorithm[J]. 2019, 36(8): 39-44.
任向隆, 田泽, 张骏, 韩立敏, 郑新建, 范飞虎. Catmull-Rom图像缩放算法的自适应结构设计与实现[J]. 微电子学与计算机, 2019, 36(8): 39-44. DOI：

REN Xiang-long, TIAN Ze, ZHANG Jun, et al. Design and implementation of adaptive architecture for Catmull-Rom image scaling algorithm[J]. 2019, 36(8): 39-44. DOI：

摘要

为解决传统Catmull-Rom缩放结构因行列计算量比例不协调导致行/列插值部件长期停顿而造成的性能低下问题

提出了两种自适应结构.在传统结构的基础上增加三个插值部件

并结合两种自适应策略

分配新增插值部件用于行或列插值

并对处于工作状态的插值部件的数量进行调整

得到两种自适应结构.实验表明:与传统结构相比

结构一各类资源占用为原来的1~2.5倍

而性能提高最大为原来的3.99倍

但仅在缩小时存在性能提升

适用于仅存在缩小的场合(如纹理的MIPMAP); 结构二各类资源占用为原来的1.7~2.5倍

而性能提高最大为原来的3.98倍

在缩小与放大时均存在性能提升

适用于放大缩小同时存在的场合(如图像的缩放).

Abstract

Two adaptive structures are proposed to conquer the low performance caused by long-term pause of the row and column interpolation components in traditional structures of Catmull-Rom

when operations between row and column not suitable. In the two adaptive structures

three interpolators were added on the basis of traditional structure

along with two adaptive strategies which could allocate interpolators between row and column and adjust the number of them at working. The result of experiment is as follows. Compared with the traditional structure

the first structure achieved up to 3.99 times performance improvement

while resources occupy between with 1 to 2.5 times

and the performance improvement achieved only when scaling down

suitable for cases of shrinking only

such as MIPMAP of texture; The second structure achieved up to 3.98 times performance improvement

while resources occupy between with 1.7 to 2.5 times

and the performance improvement achieved when scaling up as well as scaling down

suitable for occasions of scaling up and down

such as image zooming.

关键词

Keywords

references

吕荣国, 蒋林, 杨飞.图像缩放的研究与FPGA设计[J].计算机技术与发展, 2011, 21(12): 205-208. DOI: 205

丁家隆, 杜慧敏, 曹广界, 等.基于最优移位双线性插值的图像缩放旋转硬件加速研究[J].微电子学与计算机, 2016, 33(7): 115-124. DOI: 115

郭莹, 李伦, 王鹏.基于Lanczos核的实时图像插值算法[J].通信学报, 2017, 38(6): 142-147. DOI: 142

王玮.几种最新的图像缩放方法的比较性研究[D].大连: 大连理工大学, 2013.

吴以凯.基于FPGA的视频缩放的设计与实现[D].镇江: 江苏大学, 2017.

王翔.数字图像缩放及图像质量评价关键技术研究[D].杭州: 浙江大学, 2012.

王平, 全吉成, 赵柏宇.基于双线性插值的图像缩放在GPU上的实现[J].微电子学与计算机, 2016, 33(11): 129-132. DOI: 129

武文斌, 高俊雄, 王耘波.基于叠加的图像缩放优化及FPGA实现[J].微电子学与计算机, 2017, 34(11): 128-130. DOI: 128

陈宝国, 李宁.一种基于Sobel算子和混合有理插值的图像缩放方法[J].微电子学与计算机, 2012, 29(2): 150-152. DOI: 150

江巨浪.基于改进Catmull-Rom样条的图像缩放算法[J].计算机技术与发展, 2007, 17(4) :211-217. DOI: 211

冉峰, 李天, 季渊, 等.基于FPGA的图像缩放算法设计[J].光电子技术, 2017, 37(1): 21-26. DOI: 21

莫迪涵, 杜慧敏, 沈绪榜.基于线性插值法图像缩放的设计与FPGA实现[J].西安邮电大学学报, 2013, 18(3):52-55. DOI: 52

魏美荣, 蒋林.一种自适应Catmull-Rom样条图像缩放算法的设计实现[J].微电子学与计算机, 2011, 28(12): 63-67+71. DOI: 63

王中博, 周远远, 黄鲁.基于多相位插值的视频缩放系统FPGA实现[J].微型机与应用, 2016, 35(24): 46-49. DOI: 46

邹学瑜, 刘昌禄, 胡敬营.基于双线性插值算法的缩放IP核设计[J].计算技术与自动化, 2017, 36(3):113-117. DOI: 113

袁扬智, 韦明, 曾献军.2D图像硬件加速引擎的设计优化[J].微电子学与计算机, 2009, 26(4): 241-248. DOI: 241

陈利平.自适应Catmull-Rom样条图像放大[J].计算机辅助设计与图形学学报, 2013, 25(2): 200-207. DOI: 200

Views

下载量

CSCD

Alert me when the article has been cited

提交

Tools

Publicity Resources

Research on assembly action recognition based on MSS-YOLO-MPHands fusion architecture

Design of ultra-low power real-time clock circuits

High gain stability high temperature operational amplifier based on reverse body bias

Steganography model guided by attention mechanism and improved dense convolution

Microservices anomaly detection based on the correlation of monitoring metrics

Related Author

No data

Related Institution

No data

AI问答

Postal code：100079
Tel：（010）53879206 Email：tmw@bjxintong.com.cn
Technical support is provided by Beijing Founder electronics co., LTD 京ICP备09082226号-64 京公网安备11010602201714号
It is recommended to read the content of this site in Chrome&IE9+. Please switch to extreme mode in browser 360.
Cookies We use cookies to help provide and enhance our service and tailor content. By continuing, you agree to the use of cookies.

⁰