摘要
针对高斯滤波会使图像过度平滑及高低阈值选取的主观性影响传统的Canny边缘检测效果,提出一种基于改进Canny算子的边缘检测方法。该方法采用了改进的中值滤波,且依据图像的幅值梯度直方图特性得到自适应的高低阈值,再结合FPGA(现场可编程门阵列)高速并行处理数据和多级流水的特点,设计了一个基于硬件平台的实时边缘检测系统。实验结果表明,该系统实时性效果好,边缘的提取完整,阈值的选取具有自适应性。
Aiming at the fact that Gaussian filtering will over-smooth the image and the subjectivity of selecting high and low thresholds affects the traditional Canny edge detection effect, an edge detection method based on improved Canny operator is proposed. This method uses an improved median filter, and obtains adaptive high and low thresholds according to the characteristics of the image’s amplitude gradient histogram, and combines the high-speed parallel processing data and multi-stage pipeline characteristics of FPGA(Field Programmable Gate Array) to design A real-time edge detection system based on hardware platform is developed. Experimental results show that the system has good real-time performance, complete edge extraction, and adaptive threshold selection.
作者
崔玉
俞建定
邹洪彬
李乐薇
CUI Yu;YU Jian-ding;ZOU Hong-bin;LI Le-wei(School of Information Science and Engineering,Ningbo University,Ningbo 315211,China)
出处
《无线通信技术》
2021年第4期27-31,36,共6页
Wireless Communication Technology
