CAJ | 학술논문

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。
제출이용전하우합원건(CCD)화현장가편정문진렬(FPGA)실현강궤도상실시채집여예처리，이해결인공검측강궤효솔저、실시성저등문제。재Quartus II중편사강궤도상채집모괴、독사모괴、시빈도형진렬( VGA)모괴등，채용쾌속중치려파화색패이( Sobel)변연검측산법，실시현시예처리후적강궤도상。시험결과표명FPGA능구실시채집강궤도상，병쾌속검측출강궤변연륜곽，유효거제조성간우，실현강궤도상적예처리。
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 re-al-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.