摘要
视觉浇注系统浇包出液口处图像经处理后提取的特征可以为后续浇口杯钢水液位识别和浇包塞杆启动控制提供判断依据。本文对比了单摄像头和垂直双摄像头两种方式获取的图像利用全局阈值分割和形态学算法去噪等预处理后构建出特征参数的情况,通过对比分析双摄像头方式构造的参数可以更好的为液位识别提供依据。
The molten steel volume of ladle is an important parameter for auto-pouring sys- tem based on machine vision. It is the fundamental of judging the level of sprue cup and the stopper rod start-stop time. By comparing the images obtained by single camera and binocu- lar camera, the global threshold image segment algorithm and the morphological image de- noising algorithm are applied to creat the characteristic parameters. Simulation results show that it is a more optimal way of judging sprue cup leve by binocular camera image.
作者
杨慧英
YANG Huiying(Northeastern University, Shenyang 110004, China Shenyang Ligong University, Shenyang 110159, China)
出处
《沈阳理工大学学报》
CAS
2017年第4期24-27,53,共5页
Journal of Shenyang Ligong University
基金
辽宁省教育厅项目(L2015468)
关键词
视觉浇注
图像处理
参数构建
auto pouring by machine vision
image processing
parameter construction