线段描述子与光束法平差融合下破损建筑场景点云重建  

Reconstruction of point clouds in damaged building scenes using the fusion of line segment descriptors and beam adjustment

在线阅读下载全文

作  者:梁锜 郭沁 范蒙[1,2] LIANG Qi;GUO Qin;FAN Meng(School of Design,Inner Mongolia Normal University,Hohhot 010020,China;Design and Social Innovation Key Research Base of Humanities and Social Sciences in Inner Mongolia Universities,Hohhot 010020,China)

机构地区:[1]内蒙古师范大学设计学院,呼和浩特010020 [2]设计与社会创新内蒙古高校人文社科重点研究基地,呼和浩特010020

出  处:《激光杂志》2025年第3期120-126,共7页Laser Journal

基  金:内蒙古自治区自然科学基金项目(No.2021BS05009);内蒙古自治区自然科学基金项目:基于绿色设计理念的博览建筑展示空间模块化与数字化构建研究(No.2022MS05009);内蒙古师范大学基本科研业务费项目(No.2022JBTD014)。

摘  要:准确捕捉建筑物的几何形状和结构信息,对破损建筑场景的点云重建至关重要。针对破损建筑场景点云重建完整度低的问题,提出线段描述子与光束法平差融合下破损建筑场景点云重建方法。采用Mask-RCNN方法检测破损建筑场景目标,对获取的点云平面实施二维投影。采用主成分分析方法估计全部点云法向量,引入区域增长方法对全部点云数据聚类和分割处理,拟合破损建筑场景图像中的各平面,得到点云平面。利用二维线段检测方法获取破损建筑平面的线段特征,将二维线段投影到三维空间内获取三维线段,生成破损建筑场景对应的线段描述子。对所获取的线段描述子实施光束法平差优化处理,实现破损建筑场景的点云重建。实验结果表明,所提方法能够有效重建破损建筑场景点云,点云重建的相对误差最小值仅为0.117。Accurately capturing the geometric shape and structural information of buildings is crucial for point cloud reconstruction of damaged building scenes.Aiming at the problem of low completeness in point cloud reconstruction of damaged building scenes,a point cloud reconstruction method for damaged building scenes is proposed by integrating line segment descriptors and beam adjustment.Using the Mask RCNN method to detect damaged building scene targets and implementing two-dimensional projection on the obtained point cloud plane.Using principal component analysis method to estimate all point cloud normal vectors,introducing region growth method to cluster and segment all point cloud data,fitting each plane in the damaged building scene image,and obtaining the point cloud plane.Using the two-dimensional line segment detection method to obtain the line segment features of the damaged building plane,projecting the two-dimensional line segment into the three-dimensional space to obtain the three-dimensional line segment,and generating the line segment descriptor corresponding to the damaged building scene.Implement beam adjustment optimization on the obtained line segment descriptors to achieve point cloud reconstruction of damaged building scenes.The experimental results show that the proposed method can effectively reconstruct the point cloud of damaged building scenes,and the minimum relative error of point cloud reconstruction is only 0.117.

关 键 词:线段描述子 破损建筑场景 点云重建 Mask-RCNN 

分 类 号:TN209[电子电信—物理电子学]

 

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