基于加权组合算法的点云孔洞修补  

Point cloud hole repair based on weighted combination algorithm

作　　者：吕富强 唐诗华 何广焕[1,2] 刘坤之 李灏杨 LYU Fuqiang;TANG Shihua;HE Guanghuan;LIU Kunzhi;LI Haoyang(College of Geomatics and Geoinformation,Guilin University of Technology,Guilin 541006,China;Guangxi Key Laboratory of Spatial Information and Geomatics,Guilin University of Technology,Guilin 541006,China)

机构地区：[1]桂林理工大学测绘地理信息学院,广西桂林541006 [2]桂林理工大学广西空间信息与测绘重点实验室,广西桂林541006

出　　处：《桂林理工大学学报》2024年第2期288-293,共6页Journal of Guilin University of Technology

基　　金：国家自然科学基金项目(41864002);广西自然科学基金项目(2018GXNSFAA281279)。

摘　　要：为了对无人机航测数据中的点云孔洞进行修补,将最小二乘支持向量机算法LS-SVM和遗传算法GA优化的反向传播神经网络算法BP进行线性组合,构建一种加权组合模型,用于散乱点云数据中的孔洞修补。通过两种修补方法的误差进行两者的加权组合,建立出与两种修补方法误差相关的加权组合模型,并将加权组合模型的修补结果与单一使用最小二乘支持向量机、遗传算法优化的BP神经网络两种修补方法的修补结果进行残差和内外符合精度的比较与分析。结果表明:采用加权组合模型得到的点云修补结果内外符合精度较高,且具有更强的稳定性,为无人机获取的点云数据提供了一种有效的孔洞修补方法。In order to repair point cloud holes in UAV aerial survey data,LS-SVM algorithm and BP optimized by GA(BP-GA)are linearly combined to construct a weighted combination model for hole repair in scattered point cloud data.By combining the errors of the two methods,a weighted combination model related to the errors of two repair methods is established,and it will repair the point cloud holes.The residual and internal and external accuracy of the repair results of weighted combination model,LS-SVM and BP-GA are analyzed.Compared with the results of the two single repair methods,the point cloud repair results obtained by the weighted combination model have higher internal and external coincidence accuracy and higher stability,which provides an effective hole repair method for the point cloud data obtained by UAV.

关 键 词：点云孔洞 最小二乘支持向量机 反向传播神经网络算法 加权组合 孔洞修补 

分 类 号：P231[天文地球—摄影测量与遥感]