一种改进的Sobel图像边缘检测算法及其实现  

An Improved Sobel Image Edge Detection Algorithm and Its Implementation

作　　者：张萍萍 李童 李茹 卢胜男[1] ZHANG Pingping;LI Tong;LI Ru;LU Shengnan(School of computer science,Xi’an Shiyou University,Xi'an 710000,China)

机构地区：[1]西安石油大学计算机学院,陕西西安710000

出　　处：《电视技术》2022年第5期42-45,共4页Video Engineering

基　　金：2020年陕西省大学生创新创业训练计划项目(No.S202010705089)。

摘　　要：Sobel算子原理易懂,计算简单,但传统的Sobel算子只对垂直和水平方向进行检测,应用范围受到限制,且存在边缘定位不准确的问题。对此,对Sobel算子进行改进,将水平和垂直方向模板增加到8个方向(0°,45°,90°,135°,180°,225°,270°,315°),同时,利用现场可编程逻辑门阵列(Field Programmable Gate Array,FPGA)并行流水线处理、处理速度快的优点,采用Verilog HDL语言对改进后的Sobel算子进行仿真,并在FPGA平台上进行实现和测试。实验结果表明,改进后的Sobel算子检测精度明显提高,边缘以及信息提取更加完整精细,满足图像处理的实时性要求。The principle of Sobel operator is easy to understand and the calculation is simple,but the traditional Sobel operator only detects the vertical and horizontal directions,the scope of application is limited,and there is the problem of inaccurate edge positioning.In this regard,the Sobel operator is improved,and the horizontal and vertical templates are increased to 8 directions(0°,45°,90°,135°,180°,225°,270°,315°).At the same time,taking advantage of the parallel pipeline processing and fast processing speed of Field Programmable Gate Array(FPGA),the improved Sobel operator is simulated by Verilog HDL language,and implemented and tested on FPGA platform.The experimental results show that the detection accuracy of the improved Sobel operator is significantly improved,and the edge and information extraction are more complete and fine,which meets the real-time requirements of image processing.

关 键 词：现场可编程逻辑门阵列(FPGA) SOBEL算子 方向模板 VERILOG语言 边缘检测 

分 类 号：TP311.5[自动化与计算机技术—计算机软件与理论]