HHO-LSSVM算法在匹配地面点云孔洞修补中的应用研究  

Application of HHO-LSSVM algorithm in patching cloud holes at matching ground points

作　　者：张炎 刘立龙 何广焕 梁月吉 于松超 ZHANG Yan;LIU Lilong;HE Guanghuan;LIANG Yueji;YU Songchao(College of Geomatics and Geoinformation,Guilin University of Technology,Guilin 541006,China;Guangxi Key Laboratory of Spatial Information and Geomatics,Guilin 541006,China;College of Municipal and Transportation,Guangxi Polytechnic of Construction,Nanning 530007,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]广西空间信息与测绘重点实验室,广西桂林541006 [3]广西建设职业技术学院市政与交通学院,广西南宁530007

出　　处：《海洋测绘》2022年第6期65-69,共5页Hydrographic Surveying and Charting

基　　金：国家自然科学基金(42064002);广西自然科学基金(2020GXNSFBA297160,2021GXNSFBA220046)。

摘　　要：针对无人机匹配点云经地面点滤波后会存在较多孔洞的问题,提出利用哈里斯鹰算法(harris hawks optimization,HHO)优化最小二乘支持向量机(least squares support vector machine,LSSVM)来进行地面点云孔洞修补。首先利用八叉树结构法对滤波后点云数据进行地面特征点提取,其次采用哈里斯鹰算法对最小二乘支持向量机中的核参数和正则化参数进行优化,并利用组合算法构建匹配地面点云孔洞修补模型。实验结果表明,与单一最小二乘支持向量机相比,组合模型的孔洞修补精度提高了22.3%,其稳定性也得到增强,具备一定的时效性及现实性。Aiming at the problem that there will be more holes in the UAV matching point cloud after ground point filtering,this paper proposes to use the Harris Hawks Optimization(HHO)to optimize the Least Squares Support Vector Machine(LSSVM)to repair the ground point cloud holes.Firstly,the ground feature point extraction is performed on the filtered point cloud data by the octopus structure method,and secondly,the kernel parameters and regularization parameters in the Least Squares Support Vector Machine are optimized by Harris Hawks Optimization,and the matching ground point cloud hole repair model is constructed by using the combined algorithm.Experimental results show that compared with the single least squares support vector machine,the hole repair accuracy of the combined model is improved by 22.3%,and its stability is also enhanced,which has certain timeliness and realism.

关 键 词：摄影测量 点云孔洞修补 八叉树结构 最小二乘支持向量机 参数优化 哈里斯鹰算法 

分 类 号：P231[天文地球—摄影测量与遥感]