基于传输触发架构的IIR型高斯滤波实现

杨莫洋; 蒋剑飞; 王琴

Chinese

您当前的位置：

首页 >

文章列表页 >

基于传输触发架构的IIR型高斯滤波实现

更新时间：2026-09-04

- 基于传输触发架构的IIR型高斯滤波实现
- Implementation of IIR gaussian filter based on transport triggered architecture
- 微电子学与计算机 2020年37卷第7期页码：21-24
- 作者机构：
  
  上海交通大学电子信息与电气工程学院,上海,200240
- 作者简介：
- 基金信息：
  
  天津市自然科学基金 15JCQNJC00100
- DOI：
  中图分类号：
- 纸质出版：2020
- 稿件说明：
移动端阅览
杨莫洋, 蒋剑飞, 王琴. 基于传输触发架构的IIR型高斯滤波实现[J]. 微电子学与计算机, 2020, 37(7): 21-24, 30.

YANG Mo-yang, JIANG Jian-fei, WANG Qin. Implementation of IIR gaussian filter based on transport triggered architecture[J]. 2020, 37(7): 21-24.
杨莫洋, 蒋剑飞, 王琴. 基于传输触发架构的IIR型高斯滤波实现[J]. 微电子学与计算机, 2020, 37(7): 21-24, 30. DOI：

YANG Mo-yang, JIANG Jian-fei, WANG Qin. Implementation of IIR gaussian filter based on transport triggered architecture[J]. 2020, 37(7): 21-24. DOI：

摘要

为了满足嵌入式领域需求，针对无限冲激响应(IIR)高斯滤波器，提出了一种定点化策略，能够有效地替代浮点数实现版本.为了进一步提高滤波速度，设计了一款传输触发架构(TTA)处理器，并针对该算法特点，定制特殊功能单元，优化存储结构.实验结果表明，对于大小为640×480的24位真彩图像，IIR型高斯滤波的TTA实现速度是通用DSP的4.12倍.

Abstract

In order to meet the needs of the embedded field

a fixed-point strategy is proposed for the infinite impulse response Gaussian filter

which can effectively replace the floating-point implementation version. In order to further improve the speed of filtering

a Transport Triggered Architecture processor is designed

and special function units are customized for the characteristics of the algorithm

and the storage structure is optimized. The experimental results show that for a 24-bit true color image with a size of 640×480

the Transport Triggered Architecture implementation speed of the IIR Gaussian filter is 4.12 times that of the general-purpose DSP.

关键词

Keywords

references

YOUNG I T, VLIET L J V. Recursive implementation of the Gaussian filter[J]. Signal Processing, 1995, 44(2):139-151. DOI: 139

CANNY J. A Computational Approach To Edge Detection[J]. IEEE Transactions on Pattern Analysis and Machine Intelligence, 1986, PAMI-8(6):679-698. DOI: 679

ESKO O, PEKKA J, HUERTA P, et al. Customized Exposed Datapath Soft-Core Design Flow with Compiler Support[C]// International Conference on Field Programmable Logic and Applications. Milano, Italy: IEEE Computer Society, 2010: 217-222.

RAMESH B, BHARDWAJ A, RICHARDSON J, et al. Optimization and evaluation of image- and signal-processing kernels on the TI C6678 multi-core DSP[C]// High Performance Extreme Computing Conference. Waltham, MA USA: IEEE, 2015: 1-6.

LAMPERT C H, WIRJADI O. Anisotropic Gaussian Filtering using Fixed Point Arithmetic[C]// 2006 International Conference on Image Processing. Atlanta, Georgia, USA: IEEE, 2007: 1565-1568.

TAN S, DALE J L, JOHNSTON A. Performance of three recursive algorithms for fast space-variant Gaussian filtering[J]. Real-Time Imaging, 2003, 9(3):215-228. DOI: 215

Chichester CORPORAAL H. Microprocessor Architectures - from VLIW to TTA[M]. Chichester :John Wiley % Sons, 1997:101-125. DOI: 101

浏览量

下载量

CSCD

文章被引用时，请邮件提醒。

提交

工具集

关联资源

基于区块链的AI生成内容溯源框架设计研究

AlN/GaN混合缓冲层双异质结p-GaN HEMT直流特性仿真

基于反向体偏置的高增益稳定性高温运放设计

基于改进RT-DETR的航拍小目标检测算法

基于监控指标关联性的微服务异常检测