|
The Densification of the point cloud from PS-InSAR Method in Urban Area
|
Sajjad Sajedizadeh   , Yasser Maghsoudi Mehrani * |
| K. N. Toosi University of Technology. |
|
|
Abstract: (1635 Views) |
3D point Clouds have made a significant contribution to airborne and spaceborne observations in recent years. The sensor limitations and processing challenges of these observations have been investigated in several studies. We generated 3D point clouds using the persistent scatterers interferometric SAR method in order to estimate the obstacles heights. By estimating the height error of the topographic model used in PS-InSAR processing, the permanent scatterer's heights were estimated. The height accuracy was improved by making changes in master image selection. Due to the low density as well as SAR side-looking geometry, the derived 3D point clouds do not represent the complete geometry of complications. In this article, the shape completion deep learning neural network was used to increase the point density and complete the shape geometry. By performing learning steps, these networks directly map non-dense and incomplete shape to dense and complete shape geometry. The global features of the incomplete shapes were determined while retaining the details to an optimal extent. The cost criterion of this network is based on the Chamfer Distance, which measures the distance between the non-dense input and dense output point clouds. The PS-InSAR processing was done on 27 images of the Sentinel-1 satellite in Philadelphia city, USA. This output obtained from PS-InSAR will be able to estimate the height of various urban complications. We prepared 30000 individual building datasets for training the network in the urban areas. The amount of obtained loss was 0.048 in the training process and 0.0482 in the network evaluation process. By evaluating the surface elevation model extracted by lidar reference data of the studied area, the average absolute height estimation error was 4. 67 meters which is quite near the worldwide amounts.
|
|
| Keywords: 3D Point Cloud Completion, Interferometric SAR, Permanent Scatterers, Elevation Model |
|
|
Full-Text [PDF 2224 kb]
(284 Downloads)
|
Type of Study: Research |
Subject:
RS
Received: 2022/09/22 | Accepted: 2023/03/6 | ePublished ahead of print: 2024/08/6 | Published: 2024/10/29
|
|
|
|
|
|
|
| Send email to the article author |
|
|
