Issue No. 10 - Oct. (2013 vol. 19)
DOI Bookmark: http://doi.ieeecomputersociety.org/10.1109/TVCG.2013.74
Yong-Jin Liu , Dept. of Comput. Sci. & Technol., Tsinghua Univ., Beijing, China
Jun-Bin Zhang , Dept. of Comput. Sci. & Technol., Tsinghua Univ., Beijing, China
Ji-Chun Hou , Dept. of Comput. Sci. & Technol., Tsinghua Univ., Beijing, China
Ji-Cheng Ren , Beijing Zhongke Fulong Comput. Technol. Co., Ltd., Beijing, China
Wei-Qing Tang , Beijing Zhongke Fulong Comput. Technol. Co., Ltd., Beijing, China
The huge number of points scanned from pipeline plants make the plant reconstruction very difficult. Traditional cylinder detection methods cannot be applied directly due to the high computational complexity. In this paper, we explore the structural characteristics of point cloud in pipeline plants and define a structure feature. Based on the structure feature, we propose a hierarchical structure detection and decomposition method that reduces the difficult pipeline-plant reconstruction problem in R3 into a set of simple circle detection problems in R2. Experiments with industrial applications are presented, which demonstrate the efficiency of the proposed structure detection method.
Pipelines, Transforms, Histograms, Solid modeling, Noise, Computational modeling, Fuel storage
Yong-Jin Liu, Jun-Bin Zhang, Ji-Chun Hou, Ji-Cheng Ren and Wei-Qing Tang, "Cylinder Detection in Large-Scale Point Cloud of Pipeline Plant," in IEEE Transactions on Visualization & Computer Graphics, vol. 19, no. 10, pp. 1700-1707, 2013.