多方向自适应阈值边缘检测算法及FPGA并行实现  

Multi-Directional Adaptive Threshold Edge Detection Algorithm and FPGA Parallel Implementation

作　　者：陈磊 叶焱[1] CHEN Lei;YE Yan(School of Information Science and Engineering,Ningbo University,Ningbo 315211,China)

机构地区：[1]宁波大学信息科学与工程学院,宁波315211

出　　处：《无线通信技术》2019年第4期21-26,共6页Wireless Communication Technology

基　　金：国家自然科学基金项目(U1809203,61571251,61501272,61801252)。

摘　　要：本文提出一种采用多个方向模板和阈值自适应相结合的sobel边缘检测算法,并且利用FPGA并行流水的特性将该算法在FPGA硬件平台上加速实现。与传统软件技术的方式来做图像处理相比,纯逻辑硬件搭建的图像采集以及图像处理平台在速度上提高了近10倍,解决了由于处理速度慢导致的图像延迟和滞后的问题,加强了其实时性与鲁棒性。This paper proposes a sobel edge detection algorithm combining multiple direction templates and threshold adaptive,and accelerates the algorithm on the FPGA hardware platform by using the characteristics of FPGA parallel pipeline.Compared with the traditional software technology to image processing,the image acquisition and image processing platform built by pure logic hardware has improved the speed by nearly 10 times,and solved the problem of image delay and lag caused by slow processing speed.Its real-time and robustness.

关 键 词：SOBEL边缘检测 多方向 阈值自适应 FPGA 

分 类 号：TP391[自动化与计算机技术—计算机应用技术]