| 基于LiDAR点云的建筑物分割深度学习模型研究 |
| |
| 引用本文： | 胡传文,卢世杰,杨文敬,朱小勇. 基于LiDAR点云的建筑物分割深度学习模型研究[J]. 测绘通报, 2021, 0(12): 88-93. DOI: 10.13474/j.cnki.11-2246.2021.379 |
| |
| 作者姓名： | 胡传文 卢世杰 杨文敬 朱小勇 |
| |
| 作者单位： | 1. 浙江省测绘科学技术研究院, 浙江 杭州 311100;2. 武汉大学测绘遥感信息工程国家重点实验室, 湖北 武汉 430079 |
| |
| 摘 要： | 本文针对深度神经网络算法应用于机载激光点云进行大规模建筑物提取的问题,分别选取PointNet++和PointCNN两个网络模型进行了改进和对比。对于PointCNN,通过参数调整,使其更适合大场景信息提取。对于PointNet++,为了增加更多特征,加快大场景下网络模型的训练效率,在网络体系结构中添加了一种新的特征提取层——K-means层。另外,通过在测试数据集上的训练和验证发现,本文基于深度学习方法的分类较好地克服了点云的无序特性,能够更好地利用点之间的空间相关性,改进后两种模型的精度均达96%以上,在建筑物提取的时间效率和效果上优于原始模型。
|
| 关 键 词： | PointNet++ PointCNN 激光雷达 点云 建筑 K均值 |
| 收稿时间： | 2021-09-02 |
| 修稿时间： | 2021-10-20 |
Deep learning architecture for building extraction using LiDAR point clouds |
| |
| HU Chuanwen,LU Shijie,YANG Wenjing,ZHU Xiaoyong. Deep learning architecture for building extraction using LiDAR point clouds[J]. Bulletin of Surveying and Mapping, 2021, 0(12): 88-93. DOI: 10.13474/j.cnki.11-2246.2021.379 |
| |
| Authors: | HU Chuanwen LU Shijie YANG Wenjing ZHU Xiaoyong |
| |
| Affiliation: | 1. Zhejiang Academy of Surveying and Mapping, Hangzhou 311100, China;2. State Key Laboratory of Information Engineering in Surveying, Mapping and Remote Sensing, Wuhan University, Wuhan 430079, China |
| |
| Abstract: | Aiming at the problem of applying deep neural network algorithm to LiDAR point cloud for large-scale building extraction, PointCNN and PointNet++ models are selected for modification and comparison in this paper. For PointCNN, the parameters are adjusted to make it more suitable for large scenes. For PointNet++, in order to add more features and speed up the training efficiency of network model in large scenes, a K-means layer is added after the sampling layer. Finally, through training and verification on the test data set, it is found that the deep learning methods can well solve the disordered characteristics of point cloud and make better use of the spatial correlation between points. The accuracy of the improved models is more than 96% and they are also better than the original models in time consumption and extraction effect. |
| |
| Keywords: | PointNet++ PointCNN LiDAR point clouds building K-means |
| 本文献已被 万方数据 等数据库收录！ |
| 点击此处可从《测绘通报》浏览原始摘要信息 |
|
点击此处可从《测绘通报》下载全文 |
|
