基于FPGA的实时钢轨图像采集与预处理  

Real-time Steel Rail Image Acquisition and Preprocessing Based on FPGA

作　　者：马俊[1] 李春茂[1] 郭鑫[2] 

机构地区：[1]西南交通大学电气工程学院,四川成都610031 [2]西南交通大学,牵引动力国家重点实验室,四川成都610031

出　　处：《仪表技术与传感器》2015年第6期111-113,120,共4页Instrument Technique and Sensor

摘　　要：提出利用电荷耦合元件(CCD)和现场可编程门阵列(FPGA)实现钢轨图像实时采集与预处理,以解决人工检测钢轨效率低、实时性低等问题。在Quartus II中编写钢轨图像采集模块、读写模块、视频图形阵列(VGA)模块等,采用快速中值滤波和索贝尔(Sobel)边缘检测算法,实时显示预处理后的钢轨图像。试验结果表明FPGA能够实时采集钢轨图像,并快速检测出钢轨边缘轮廓,有效去除噪声干扰,实现钢轨图像的预处理。The charge-coupled device（ CCD） and field programmable gate array（ FPGA） were used to realize the real-time acquisition and preprocessing of steel rail image in this paper to solve the problems of inefficient and real-time＇s requirements by manual detection. The image acquisition module,reading and writing module and video graphics array（ VGA） module were written in Quartus II. Fast median filtering algorithm and Sobel edge detection algorithm were adopted to preprocess steel rail image,and real-time rail image was displayed after preprocessing The experiment results show that FPGA has very high real- time performance in terms of steel rail image acquisition,it can effectively remove the noise and quickly detect the steel rail＇s contour,thus realizing the steel rail image＇s preprocessing.

关 键 词：电荷耦合元件 现场可编程门阵列 钢轨图像 实时采集 预处理 视频图形阵列 

分 类 号：TP391.4[自动化与计算机技术—计算机应用技术]