DEM Extraction from ALS Point Clouds in Forest Areas via Graph Convolution Network
It is difficult to extract a digital elevation model (DEM) from an airborne laser scanning (ALS) point cloud in a forest area because of the irregular and uneven distribution of ground and vegetation points. Machine learning, especially deep learning methods, has shown powerful feature extraction in...
Main Authors: | , , , |
---|---|
Format: | Article |
Language: | English |
Published: |
MDPI AG
2020-01-01
|
Series: | Remote Sensing |
Subjects: | |
Online Access: | https://www.mdpi.com/2072-4292/12/1/178 |
id |
doaj-a222723f1bde41e3bf228b80b83e79ff |
---|---|
record_format |
Article |
spelling |
doaj-a222723f1bde41e3bf228b80b83e79ff2020-11-25T01:35:49ZengMDPI AGRemote Sensing2072-42922020-01-0112117810.3390/rs12010178rs12010178DEM Extraction from ALS Point Clouds in Forest Areas via Graph Convolution NetworkJinming Zhang0Xiangyun Hu1Hengming Dai2ShenRun Qu3School of Remote Sensing and Information Engineering, 129 Luoyu Roud, Wuhan University, Wuhan 430079, ChinaSchool of Remote Sensing and Information Engineering, 129 Luoyu Roud, Wuhan University, Wuhan 430079, ChinaSchool of Remote Sensing and Information Engineering, 129 Luoyu Roud, Wuhan University, Wuhan 430079, ChinaInstitute of Land Resource Surveying and Mapping of Guangdong Province, 28 North Wuxianqiao Street, Guangzhou 510500, ChinaIt is difficult to extract a digital elevation model (DEM) from an airborne laser scanning (ALS) point cloud in a forest area because of the irregular and uneven distribution of ground and vegetation points. Machine learning, especially deep learning methods, has shown powerful feature extraction in accomplishing point cloud classification. However, most of the existing deep learning frameworks, such as PointNet, dynamic graph convolutional neural network (DGCNN), and SparseConvNet, cannot consider the particularity of ALS point clouds. For large-scene laser point clouds, the current data preprocessing methods are mostly based on random sampling, which is not suitable for DEM extraction tasks. In this study, we propose a novel data sampling algorithm for the data preparation of patch-based training and classification named T-Sampling. T-Sampling uses the set of the lowest points in a certain area as basic points with other points added to supplement it, which can guarantee the integrity of the terrain in the sampling area. In the learning part, we propose a new convolution model based on terrain named Tin-EdgeConv that fully considers the spatial relationship between ground and non-ground points when constructing a directed graph. We design a new network based on Tin-EdgeConv to extract local features and use PointNet architecture to extract global context information. Finally, we combine this information effectively with a designed attention fusion module. These aspects are important in achieving high classification accuracy. We evaluate the proposed method by using large-scale data from forest areas. Results show that our method is more accurate than existing algorithms.https://www.mdpi.com/2072-4292/12/1/178alsdigital elevation modeldeep learninglidargraphsampling |
collection |
DOAJ |
language |
English |
format |
Article |
sources |
DOAJ |
author |
Jinming Zhang Xiangyun Hu Hengming Dai ShenRun Qu |
spellingShingle |
Jinming Zhang Xiangyun Hu Hengming Dai ShenRun Qu DEM Extraction from ALS Point Clouds in Forest Areas via Graph Convolution Network Remote Sensing als digital elevation model deep learning lidar graph sampling |
author_facet |
Jinming Zhang Xiangyun Hu Hengming Dai ShenRun Qu |
author_sort |
Jinming Zhang |
title |
DEM Extraction from ALS Point Clouds in Forest Areas via Graph Convolution Network |
title_short |
DEM Extraction from ALS Point Clouds in Forest Areas via Graph Convolution Network |
title_full |
DEM Extraction from ALS Point Clouds in Forest Areas via Graph Convolution Network |
title_fullStr |
DEM Extraction from ALS Point Clouds in Forest Areas via Graph Convolution Network |
title_full_unstemmed |
DEM Extraction from ALS Point Clouds in Forest Areas via Graph Convolution Network |
title_sort |
dem extraction from als point clouds in forest areas via graph convolution network |
publisher |
MDPI AG |
series |
Remote Sensing |
issn |
2072-4292 |
publishDate |
2020-01-01 |
description |
It is difficult to extract a digital elevation model (DEM) from an airborne laser scanning (ALS) point cloud in a forest area because of the irregular and uneven distribution of ground and vegetation points. Machine learning, especially deep learning methods, has shown powerful feature extraction in accomplishing point cloud classification. However, most of the existing deep learning frameworks, such as PointNet, dynamic graph convolutional neural network (DGCNN), and SparseConvNet, cannot consider the particularity of ALS point clouds. For large-scene laser point clouds, the current data preprocessing methods are mostly based on random sampling, which is not suitable for DEM extraction tasks. In this study, we propose a novel data sampling algorithm for the data preparation of patch-based training and classification named T-Sampling. T-Sampling uses the set of the lowest points in a certain area as basic points with other points added to supplement it, which can guarantee the integrity of the terrain in the sampling area. In the learning part, we propose a new convolution model based on terrain named Tin-EdgeConv that fully considers the spatial relationship between ground and non-ground points when constructing a directed graph. We design a new network based on Tin-EdgeConv to extract local features and use PointNet architecture to extract global context information. Finally, we combine this information effectively with a designed attention fusion module. These aspects are important in achieving high classification accuracy. We evaluate the proposed method by using large-scale data from forest areas. Results show that our method is more accurate than existing algorithms. |
topic |
als digital elevation model deep learning lidar graph sampling |
url |
https://www.mdpi.com/2072-4292/12/1/178 |
work_keys_str_mv |
AT jinmingzhang demextractionfromalspointcloudsinforestareasviagraphconvolutionnetwork AT xiangyunhu demextractionfromalspointcloudsinforestareasviagraphconvolutionnetwork AT hengmingdai demextractionfromalspointcloudsinforestareasviagraphconvolutionnetwork AT shenrunqu demextractionfromalspointcloudsinforestareasviagraphconvolutionnetwork |
_version_ |
1725066049216315392 |