基于FPGA的实时彩色图像边缘检测算法的实现  

Real-time FPGA-based implementation of color image edge detection algorithm

作　　者：陈虎[1,2] 凌朝东[1,2] 张浩[1,2] 杨骁[1,2] 汤炜[2] 

机构地区：[1]华侨大学信息科学与工程学院,福建厦门361021 [2]厦门市专用集成电路系统重点实验室,福建厦门361008

出　　处：《液晶与显示》2015年第1期143-150,共8页Chinese Journal of Liquid Crystals and Displays

基　　金：福建省自然科学基金(No.2011J01351);福建省科技计划重点项目(No.2013H0029);泉州市科技计划项目(No.2013Z33)

摘　　要：针对传统的基于灰度图像的边缘检测算法抗噪能力弱、对方向敏感、获取边缘细节信息较粗等不足,本文通过分析彩色图像的特点,提出一种改进的Sobel算子与快速中值滤波相结合的彩色图像边缘检测算法,通过扩展边缘检测算子的方向模板,提高Sobel算子对纹理复杂图像的适应能力及抵抗噪声的能力。该改进算法在Altera DE2-70FPGA硬件开发平台上,应用Verilog HDL语言与Quartus II中的可编程宏功能模块实现。实验结果表明,该算法的处理只占用了约2%的系统硬件资源,资源占用相对合理,且图像边缘定位准确,抗噪能力强,能够实时有效地提取出彩色图像的边缘。Traditional grayscale-based image edge detection algorithms generally suffer from the disadvantages in weak anti-noise ability,sensitivity to direction and coarse edge details.Based on the analysis of statistics and characteristics of color images,this paper presents a modified algorithm for color image edge detection that combines the Sobel operator and a fast median filtering.By expanding the direction templates of the edge detection operator,the modified algorithm can improve the abilities to adapt the complex texture images and resist strong noises.The modified algorithm is implemented on the Altera DE2-70 FPGA hardware development platform by programming with the Verilog HDL language and the Megafunctions of Quartus II.The experimental results show that the processing of the modified algorithm reasonably takes up only about 2% of system hardware resources to accurately locate the image edges and efficiently extract the edges of color images in real time under strong noises.

关 键 词：边缘检测 中值滤波 SOBEL算子 现场可编程门阵列 宏模块 

分 类 号：TN911.73[电子电信—通信与信息系统]