基于Hough变换与CV模型的微细铣刀边界提取  

The Micro-milling Tool Boundary Extraction Based on Hough Transformation and CV Model

作　　者：凌志豪 朱锟鹏[2] LING Zhi-hao;ZHU Kun-peng(School of Information Science and Technology,University of Science and Technology of China,Hefei 230026,China;Institute of Advanced Manufacturing Technology,Hefei Institutes of Physical Science,Chinese Academy of Sciences,Changzhou Jiangsu 213164,China)

机构地区：[1]中国科学技术大学信息科学技术学院,合肥230026 [2]中国科学院合肥物质科学研究院先进制造技术研究所,江苏常州213164

出　　处：《组合机床与自动化加工技术》2021年第11期48-52,57,共6页Modular Machine Tool & Automatic Manufacturing Technique

基　　金：国家重点研发计划项目(2018YFB1703200);安徽省自然科学基金资助项目(1808085ME119)。

摘　　要：基于机器视觉的方法是刀具监测的重要途径之一,具有无损、直观反映刀具状态的优点,但采集高质量的监测图像比较困难。在微细加工中,由于主轴转速快,刀具尺寸细小,刀具在图像中的角度与位置具有任意性,在线监测的难度较大。针对微细铣削加工中,光照分布不均匀的在位图像捕捉系统获取的位置与角度任意的刀具图像,研究了一种精确提取刀具图像中感兴趣区域(Region of Interest,ROI)的算法。利用Hough变换以及法向量实现刀具的中心点快速定位,并解决刀具的旋转不变性。通过Chan-Vese(CV)主动轮廓模型与Hough直线检测相结合,恢复刀具的边界轮廓。实验结果显示,文中的方法提取的刀具能够更准确地反映真实的刀具轮廓,并能将任意角度的刀具旋转到统一的角度。Machine vision-based method is one of the important ways of tool monitoring,which has the advantages of non-destructive and intuitive reflection of tool condition,but it is difficult to capture monitoring high-quality images.The micro-machining is characterized by an ultra-high spindle speed and a very small tool size,which make the online detection of tool difficult.To solve these,an algorithm for accurately extracting Region of interest(ROI)in tool images is studied for tool images at any position and angle obtained by the in-place image capture system with the uneven light distribution.The Hough transformation and the normal vector enable the center point of tool to be positioned quickly and solve the rotational variability.The boundary profile of the tool is restored by combining the Chan-Vese(CV)active contour model with Hough linear detection.The experimental results show that the tool extracted by this method can more accurately reflect the true profile and this approach can rotate the tool from any angle to a uniform angle.

关 键 词：HOUGH变换 主动轮廓模型 微细铣刀 

分 类 号：TH16[机械工程—机械制造及自动化] TG714[金属学及工艺—刀具与模具]