基于Steger算法的弯管图像中心线检测方法  

Pipe Image Centerline Detection Method based on Steger Algorithm

作　　者：杨宏 夏仁波[2] 赵亮[2] YANG Hong;XIA Ren-bo;ZHAO Liang(Clamping Tool Factory, Chengdu Aircraft Industrial (Group) Co., Ltd., Chengdu 610000, China;Shenyang Institute of Automation,Chinese Academy of Sciences,Shenyang 110000,China)

机构地区：[1]成都飞机工业集团有限责任公司钣钳加工厂,成都610000 [2]中国科学院沈阳自动化研究所,沈阳110000

出　　处：《组合机床与自动化加工技术》2020年第5期106-108,共3页Modular Machine Tool & Automatic Manufacturing Technique

摘　　要：在基于多视几何的弯管三维测量方法中,为了重构弯管三维模型,需要精确稳定的提取弯管图像中心线,文章研究了常用的弯管图像中心线检测方法的不足,结合张量投票算法与Steger算法,提出一种亚像素级的弯管图像中心线检测算法。通过实验验证该算法能够克服光照不均匀带来的影响,提取弯管中心线的精度在0.5像素以内。In order to reconstruct the three-dimensional model of the pipe by the method based on multi-view geometry,it is necessary to accurately and stably extract the centerline of the pipe image.The paper studied the shortcomings of commonly used centerline detection methods for pipe images.Combined with tensor voting algorithm and Steger algorithm,the paper proposed a sub-pixel-level curved tube image centerline detection algorithm.The experiment proved that the algorithm could overcome the influence of uneven illumination,and the accuracy is within 0.5 pixels.

关 键 词：中心线 张量投票 Steger 亚像素 

分 类 号：TH162[机械工程—机械制造及自动化] TG506[金属学及工艺—金属切削加工及机床]