A Novel Surface Reconstruction Method for Noisy Cloud Points Based on Support Vector Machine

作者：Da Li Yu

来源：Advanced Materials Research, 2014, 950: 139-144.

DOI：10.4028/www.scientific.net/amr.950.139

<jats:p>This study proposes a novel suface reconstruction method. Surface reconstruction based on Support Vector Machine (SVM) is a hot topic in the field of 3D surface construction. But it is difficult to apply this method to noisy cloud points and its running time is very long. In this paper, firstly, Fuzzy c-means (FCM) is used to delete the large-scale noise, and then a feature-preserved non-uniform simplification method for cloud points is presented, which simplifies the data set to remove the redundancy while keeping down the features of the model. Finally, the surface is reconstructed from the simplified data using SVM. Both theoretical analysis and experimental results show that after the simplification, the performance of method for surface reconstruction based on SVM is improved greatly as well as the details of the surface are preserved well.</jats:p>

• 出版日期2014-6
• 单位南昌航空大学