一种复杂地形场景点云的WOA-CSF自适应性滤波方法
A WOA-CSF adaptive filtering method for complex terrain scene point clouds
戚鑫鑫 1王磊 1储栋 1池深深1
作者信息
- 1. 安徽理工大学空间信息与测绘工程学院,安徽淮南 232001;安徽理工大学矿山采动灾害空天地协同监测与预警安徽普通高校重点实验室,安徽淮南 232001;安徽理工大学矿区环境与灾害协同监测煤炭行业工程研究中心,安徽淮南 232001
- 折叠
摘要
为解决布料模拟滤波算法(CSF)自适应性不高的问题,提出了一种基于鲸鱼优化算法(WOA)和自适应参数调整的改进CSF算法(WOA-CSF).本文首先构造以误分类点云误差率最小为标准的适应度评价函数,然后采用WOA算法对CSF算法的四个参数进行自适应寻优,构建了 WOA-CSF滤波算法,最后开展了 WOA-CSF算法与CSF算法滤波实验的对比研究.实验结果表明:WOA-CSF算法在城市、乡镇、村庄和山区等四种复杂环境下平均Kappa系数从68.33％提升到81.54％,平均总误差率从10.54％下降到6.62％,平均Ⅰ类误差率从25.87％下降到6.77％,在复杂场景下较好地滤除非地面点的同时,又极大程度上保留了地形特征.
Abstract
In order to solve the problem of poor adaptivity of the cloth simulation filtering(CSF)algorithm,an improved CSF algorithm(WOA-CSF)based on the whale optimization algorithm(WO A)and adaptive parameter tuning is pro-posed.In this paper,a fitness evaluation function based on the minimum error rate of misclassified point clouds as the criterion is constructed,then the WO A algorithm is used to adaptively optimize the four parameters of the CSF algo-rithm,and the WOA-CSF filtering algorithm is constructed,and finally the comparative study of the filtering experi-ments of the WOA-CSF algorithm and the CSF algorithm is carried out.The experimental results show that the average Kappa coefficient of WOA-CSF algorithm in four complex environments such as cities,towns,villages and mountainous areas improves from 68.33％to 81.54％,the average total error rate decreases from 10.54％to 6.62％,and the average class Ⅰ error rate decreases from 25.87％to 6.77％.In the complex scene,the non-ground points are well filtered while the terrain features are retained to a great extent.
关键词
复杂地形场景/布料模拟滤波/鲸鱼优化算法/点云滤波/智能优化Key words
complex terrain scenes/cloth simulation filtering/whale optimization algorithm/point cloud filtering/intelli-gent optimization引用本文复制引用
基金项目
国家自然科学基金(52074010)
安徽省优秀青年科学基金(2108085Y20)
出版年
2024
NETL
NSTL
万方数据