| 基于点云数据的山区建筑物屋顶轮廓线提取研究 |
| |
| 作者姓名： | 刘涛 刘正才 |
| |
| 作者单位： | 湘潭大学土木工程与力学学院 ,湖南 湘潭 ,411105 |
| |
| 基金项目： | 国家自然科学基金(61672447)。 |
| |
| 摘 要： | 山区建筑物由于地势起伏大、周边植被茂盛等特点使得传统屋顶轮廓线提取算法应用效果较差。根据研究区域的地理特征,对轮廓线提取算法进行了改进,即以点云数据的曲率值为影响因子来评价离散程度,对离散程度高的数据选取曲率的最小值为种子点,对离散程度低的数据选取曲率的平均值为种子点。该方法与传统轮廓线提取算法相比,提高了屋顶轮廓线提取结果的精确度和连续性。
|
| 关 键 词： | 山区建筑物 点云数据 屋顶轮廓线提取 种子点提取 高散程度 |
Research on Roof Contour Extraction of Mountain Buildings Based on Point Cloud Data |
| |
| Authors: | LIU Tao LIU Zhengcai |
| |
| Institution: | (School of Civil Engineering and Mechanics,Xiangtan University,Xiangtan 411105,China) |
| |
| Abstract: | The application effect of traditional roof contour extraction algorithm is poor,due to the characteristics of mountainous buildings,such as large relief and lush surrounding vegetation,In this paper,the improvement of contour extraction algorithm is studied,according to the geographical characteristics of the study area,that is,the curvature value of point cloud data is taken as the influence factor to evaluate the degree of dispersion.The minimum value of curvature is selected as the seed point for the data with high degree of dispersion,and the average value of curvature is selected as the seed point for the data with low degree of dispersion.Compared with the traditional contour extraction algorithm,this method improves the accuracy and continuity of roof contour extraction results. |
| |
| Keywords: | mountain buildings point cloud data roofcontour extraction seed point extraction degree of dispersion |
| 本文献已被 CNKI 维普 万方数据 等数据库收录！ |
|
