期刊文献+

基于机器视觉的柴油机缸套尺寸测量 被引量:20

Dimension Measurement of Diesel Cylinder Liner Based on Machine Vision
下载PDF
导出
摘要 为满足柴油机对缸套尺寸的高精度需求,提出了一种基于RANSAC(随机抽样一致性)拟合缸套亚像素轮廓的内外径尺寸检测方法。根据生产线上工业相机获取的CCD图像结构和灰度的信息特征,该测量方法先采用双边滤波和形态学梯度算法对图像预处理,去除噪声提高对比度;然后在用大律算法(QTSU)和Canny边缘检测算子获取图像边缘的像素级坐标;通过双线性插值算法对像素级坐标进行亚像素的重新定位,获取边缘亚像素坐标;最后采用RANSAC拟合算法对缸套内外径进行尺寸测量。通过仿真与实际尺寸对比,该方法具有更好的定位精度和抗噪性,相比最小二乘法RANSAC检测更可靠。 In order to meet the high precision requirements of cylinder liner size for diesel engine, a method of measuring inner and outer diameter size based on RANSAC(Random Sampling Consensus) fitting sub-pixel contour of cylinder liner was proposed. According to the information characteristics of CCD image structure and gray scale obtained by industrial camera on the production line, the bilateral filtering and Morphological gradient algorithm are firstly adopted to preprocess the image, remove noise and improve contrast. Then the pixel coordinates of image edges are obtained by using the large law algorithm(QTSU) and Canny edge detection operator. By means of bilinear interpolation algorithm, sub-pixel coordinates are repositioned at pixel level to obtain edge sub-pixel coordinates. Finally, RANSAC fitting method was used to measure the inner and outer diameter of cylinder liner. Compared with the real size, this method has better positioning accuracy and anti-noise, and is more reliable than the least square method for RANSAC detection.
作者 任永强 涂德江 韩暑 REN Yong-qiang;TU De-jiang;HAN Shu(School of Mechanical Engineering,Hefei University of Technology,Hefei 230009,China)
出处 《组合机床与自动化加工技术》 北大核心 2020年第9期151-153,共3页 Modular Machine Tool & Automatic Manufacturing Technique
关键词 边缘检测 亚像素 随机抽样一致性 双边滤波 edge detection sub-pixel random sampling consensus bilateral filtering
  • 引文网络
  • 相关文献

参考文献7

二级参考文献54

共引文献146

同被引文献213

引证文献20

二级引证文献78

;
使用帮助 返回顶部