Multi-information PointNet++ fusion method for DEM construction from airborne LiDAR data
Airborne light detection and ranging (LiDAR) is a popular technology in remote sensing that can significantly improve the efficiency of digital elevation model (DEM) construction. However, it is challenging to identify the real terrain features in complex areas using LiDAR data. To solve this proble...
| Main Authors: | , , , , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
Taylor & Francis Group
2023-12-01
|
| Series: | Geocarto International |
| Subjects: | |
| Online Access: | http://dx.doi.org/10.1080/10106049.2022.2153929 |
| _version_ | 1797681603717103616 |
|---|---|
| author | Hong Hu Guanghe Zhang Jianfeng Ao Chunlin Wang Ruihong Kang Yanlan Wu |
| author_facet | Hong Hu Guanghe Zhang Jianfeng Ao Chunlin Wang Ruihong Kang Yanlan Wu |
| author_sort | Hong Hu |
| collection | DOAJ |
| description | Airborne light detection and ranging (LiDAR) is a popular technology in remote sensing that can significantly improve the efficiency of digital elevation model (DEM) construction. However, it is challenging to identify the real terrain features in complex areas using LiDAR data. To solve this problem, this work proposes a multi-information fusion method based on PointNet++ to improve the accuracy of DEM construction. The RGB data and normalized coordinate information of the point cloud was added to increase the number of channels on the input side of the PointNet++ neural network, which can improve the accuracy of the classification during feature extraction. Low and high density point clouds obtained from the International Society for Photogrammetry and Remote Sensing (ISPRS) and the United States Geological Survey (USGS) were used to test this proposed method. The results suggest that the proposed method improves the Kappa coefficient by 8.81% compared to PointNet++. The type I error was reduced by 2.13%, the type II error was reduced by 8.29%, and the total error was reduced by 2.52% compared to the conventional algorithm. Therefore, it is possible to conclude that the proposed method can obtain DEMs with higher accuracy. |
| first_indexed | 2024-03-11T23:47:20Z |
| format | Article |
| id | doaj.art-b8e89b4b8629464baad258f774b184ae |
| institution | Directory Open Access Journal |
| issn | 1010-6049 1752-0762 |
| language | English |
| last_indexed | 2024-03-11T23:47:20Z |
| publishDate | 2023-12-01 |
| publisher | Taylor & Francis Group |
| record_format | Article |
| series | Geocarto International |
| spelling | doaj.art-b8e89b4b8629464baad258f774b184ae2023-09-19T09:13:17ZengTaylor & Francis GroupGeocarto International1010-60491752-07622023-12-0138110.1080/10106049.2022.21539292153929Multi-information PointNet++ fusion method for DEM construction from airborne LiDAR dataHong Hu0Guanghe Zhang1Jianfeng Ao2Chunlin Wang3Ruihong Kang4Yanlan Wu5School of Resource and Environmental Engineering, Anhui UniversitySchool of Resource and Environmental Engineering, Anhui UniversitySchool of Civil Engineering and Surveying Engineering, Jiangxi University of Science and TechnologyAnhui & Huaihe River Institute of Hydraulic ResearchSchool of Resource and Environmental Engineering, Anhui UniversitySchool of Artificial Intelligence Engineering Center for Geographic Information of Anhui ProvinceAirborne light detection and ranging (LiDAR) is a popular technology in remote sensing that can significantly improve the efficiency of digital elevation model (DEM) construction. However, it is challenging to identify the real terrain features in complex areas using LiDAR data. To solve this problem, this work proposes a multi-information fusion method based on PointNet++ to improve the accuracy of DEM construction. The RGB data and normalized coordinate information of the point cloud was added to increase the number of channels on the input side of the PointNet++ neural network, which can improve the accuracy of the classification during feature extraction. Low and high density point clouds obtained from the International Society for Photogrammetry and Remote Sensing (ISPRS) and the United States Geological Survey (USGS) were used to test this proposed method. The results suggest that the proposed method improves the Kappa coefficient by 8.81% compared to PointNet++. The type I error was reduced by 2.13%, the type II error was reduced by 8.29%, and the total error was reduced by 2.52% compared to the conventional algorithm. Therefore, it is possible to conclude that the proposed method can obtain DEMs with higher accuracy.http://dx.doi.org/10.1080/10106049.2022.2153929digital elevation modellight detection and rangingdeep learningpointnet++ |
| spellingShingle | Hong Hu Guanghe Zhang Jianfeng Ao Chunlin Wang Ruihong Kang Yanlan Wu Multi-information PointNet++ fusion method for DEM construction from airborne LiDAR data Geocarto International digital elevation model light detection and ranging deep learning pointnet++ |
| title | Multi-information PointNet++ fusion method for DEM construction from airborne LiDAR data |
| title_full | Multi-information PointNet++ fusion method for DEM construction from airborne LiDAR data |
| title_fullStr | Multi-information PointNet++ fusion method for DEM construction from airborne LiDAR data |
| title_full_unstemmed | Multi-information PointNet++ fusion method for DEM construction from airborne LiDAR data |
| title_short | Multi-information PointNet++ fusion method for DEM construction from airborne LiDAR data |
| title_sort | multi information pointnet fusion method for dem construction from airborne lidar data |
| topic | digital elevation model light detection and ranging deep learning pointnet++ |
| url | http://dx.doi.org/10.1080/10106049.2022.2153929 |
| work_keys_str_mv | AT honghu multiinformationpointnetfusionmethodfordemconstructionfromairbornelidardata AT guanghezhang multiinformationpointnetfusionmethodfordemconstructionfromairbornelidardata AT jianfengao multiinformationpointnetfusionmethodfordemconstructionfromairbornelidardata AT chunlinwang multiinformationpointnetfusionmethodfordemconstructionfromairbornelidardata AT ruihongkang multiinformationpointnetfusionmethodfordemconstructionfromairbornelidardata AT yanlanwu multiinformationpointnetfusionmethodfordemconstructionfromairbornelidardata |