基于蛇模型的管路三维重建方法  被引量:2

Three Dimensional Reconstruction Method of Pipeline Based on Snake Model

在线阅读下载全文

作  者:刘少丽 张文雄 吴天一 刘检华 王桢杰 胡佳 LIU Shaoli;ZHANG Wenxiong;WU Tianyi;LIU Jianhua;WANG Zhenjie;HU Jia(Laboratory of Digital Manufacturing,School of Mechanical Engineering,Beijing Institute of Technology,Beijing 100081,China)

机构地区:[1]北京理工大学机械与车辆学院,数字化制造研究所,北京100081

出  处:《北京理工大学学报》2021年第7期721-727,共7页Transactions of Beijing Institute of Technology

基  金:国家自然科学基金资助项目(51875044);国防基础科研基金资助项目(JCKY2017204B502)。

摘  要:针对航空航天中大量应用的管路高精度快速测量难题,提出了基于蛇模型的管路三维重建方法.该方法充分利用管路灰度图像边缘特征,借助阈值分割和高斯滤波消除图像噪声,先结合蛇模型获取精准的管路图像边缘,贪心算法进行迭代以保证收敛效率,利用极线约束原理得到二维管路中心线点云,然后根据视觉投影原理,重建管路三维模型,最后使用多目视觉系统拍摄的照片进行结果优化以保证重建精度.结果表明:该方法对管路的测量精度为±0.15 mm,简便高效,无需过多的人工操作.同时,实现了管路圆弧段弯曲半径的测量,满足工业应用需求.Aiming at the difficult problem of high-precision and fast pipeline measurement applied in aerospace,a 3D pipeline reconstruction method was proposed based on snake model.Making full use of the edge features of the gray image of the pipeline and eliminating image noise by means of threshold segmentation and Gaussian filtering,the method was arranged firstly to combine the snake model to obtain accurate pipeline image edges,carry out iteration with the greedy algorithm to ensure convergence efficiency,and use the principle of Epipolar constraint to obtain a two-dimensional pipeline centerline point cloud.And then,a three-dimensional model of pipeline was reconstructed based on the principle of visual projection.Finally,the designed results were optimized to ensure the reconstruction accuracy according to the photos taken by the multi-eye vision system.The results show that the measurement accuracy of the method for pipelines can reach±0.15 mm,the measurement process is simple and efficient without more operators.The new method can measure the bending radius of the pipeline arc section,adapting industrial applications.

关 键 词:蛇模型 图像处理 边缘提取 视觉测量 

分 类 号:TP211.3[自动化与计算机技术—检测技术与自动化装置]

 

参考文献:

正在载入数据...

 

二级参考文献:

正在载入数据...

 

耦合文献:

正在载入数据...

 

引证文献:

正在载入数据...

 

二级引证文献:

正在载入数据...

 

同被引文献:

正在载入数据...

 

相关期刊文献:

正在载入数据...

相关的主题
相关的作者对象
相关的机构对象