摘要
基于多级分类和模块化设计思想设计一套基于机器视觉的冷轧带钢表面缺陷检测系统.该系统硬件采用自行研制的高速线阵CCD图像采集器及配套的高速光纤图像采集卡、高速FPGA图像处理卡和多核处理器;软件采用RTAI-Linux实时操作系统及并行处理策略,确保了系统的实时性.图像分割并行处理实验表明,四核处理器的处理速度是单核处理器的3.2倍,显著提高了系统的处理性能.
The cold rolling strip surface defect detection system based on machine vision was designed with multi-classification and modularization idea.For realizing real-time characteristics of system,high-speed linear CCD camera and relational high-speed fiber image collection card,high-speed FPGA image processing card designed by ourselves were adopted in hardware;RTAI-Linux operation system and parallel processing method were adopted in software.Image segmentation parallelization experiment result indicates that the processing speed of quad-core processor is 3.2 times faster than that of single core;and the system's performance is improved effectively.
出处
《吉林大学学报(理学版)》
CAS
CSCD
北大核心
2011年第5期911-917,共7页
Journal of Jilin University:Science Edition
基金
国家高技术研究发展计划863项目基金(批准号:2007AA041501)
国家重大科技专项基金(批准号:2009ZX04004-062)
哈尔滨工业大学科研创新基金(批准号:HIT.NSRIF.2009023)
关键词
表面缺陷
图像处理
模块化
并行处理
surface defect
image process
modularization
parallel processing