改进的3D-BoNet算法应用于点云实例分割与三维重建  

Application of improved 3D-BoNet to segmentation and 3D reconstruction of point cloud instances

作　　者：郭宝云[1] 姚玉凯 李彩林[1,2] 王悦 孙娜 鲁一慧[3] GUO Baoyun;YAO Yukai;LI Cailin;WANG Yue;SUN Na;LU Yihui(School of Architectural Engineering and Spatial Information,Shandong University of Technology,Zibo 255000,China;Hubei Luojia Laboratory,Wuhan University,Wuhan 430070,China;Shandong Provincial Institute of Land Surveying and mapping,Jinan 250013,China)

机构地区：[1]山东理工大学建筑工程与空间信息学院,山东淄博255000 [2]武汉大学湖北珞珈实验室,湖北武汉430070 [3]山东省国土测绘院,山东济南250013

出　　处：《测绘通报》2024年第6期30-35,共6页Bulletin of Surveying and Mapping

基　　金：山东省自然科学基金(ZR2022MD039);湖北珞珈实验室开放基金(230100026)。

摘　　要：为了更好地利用点云数据重建室内三维模型,本文提出了一种基于3D-BoNet-IAM算法的室内场景三维重建方法。该方法通过改进3D-BoNet算法提高点云数据的实例分割精度。针对点云数据缺失问题,提出了基于平面基元合并优化的拟合平面方法,利用拟合得到的新平面重建建筑表面模型。在S3DIS和ScanNet V2数据集上验证3D-BoNet算法的改进效果。试验结果表明,本文提出的3D-BoNet-IAM算法比原始算法分割精度提高了3.3%;对比本文建模效果与其他建模效果发现,本文方法的建模效果更准确。本文方法能够提高室内点云数据的实例分割精度,同时得到高质量的室内三维模型。In order to better utilize point cloud data to reconstruct indoor 3D models,this paper proposes a 3D reconstruction method for indoor scenes based on 3D-BoNet-IAM algorithm.The method improves the instance segmentation accuracy of the point cloud data by improving the 3D-BoNet algorithm.For the problem of missing point cloud data,a method based on plane primitive merging optimization is proposed to fit the plane,and the new plane obtained from the fitting is used to reconstruct the building surface model.The improved effect of 3D-BoNet algorithm is verified on S3DIS and ScanNet V2 dataset,and it is proved through experiments that the algorithm of 3D-BoNet-IAM proposed in this paper improves the segmentation accuracy by 3.3%compared with the original algorithm;the modeling effect of this paper is compared with other modeling effects,and it is proved through comparisons that this paper s modeling effect is more accurate.The method in this paper can improve the instance segmentation accuracy of indoor point cloud data,and at the same time obtain high-quality indoor 3D models.

关 键 词：点云数据 3D-BoNet-IAM 三维重建 实例分割 平面基元 

分 类 号：P237[天文地球—摄影测量与遥感]