A Novel Method Based on Deep Learning, GIS and Geomatics Software for Building a 3D City Model from VHR Satellite Stereo Imagery

Massimiliano Pepe,Elena Cartellino,Domenica Costantino,Vincenzo Saverio Alfio,Gabriele Vozza

doi:10.3390/ijgi10100697

Massimiliano Pepe, Elena Cartellino + Show 3 more

Open Access

https://doi.org/10.3390/ijgi10100697

Copy DOI

Abstract

The aim of the paper is to identify a suitable method for the construction of a 3D city model from stereo satellite imagery. In order to reach this goal, it is necessary to build a workflow consisting of three main steps: (1) Increasing the geometric resolution of the color images through the use of pan-sharpening techniques, (2) identification of the buildings’ footprint through deep-learning techniques and, finally, (3) building an algorithm in GIS (Geographic Information System) for the extraction of the elevation of buildings. The developed method was applied to stereo imagery acquired by WorldView-2 (WV-2), a commercial Earth-observation satellite. The comparison of the different pan-sharpening techniques showed that the Gram–Schmidt method provided better-quality color images than the other techniques examined; this result was deduced from both the visual analysis of the orthophotos and the analysis of quality indices (RMSE, RASE and ERGAS). Subsequently, a deep-learning technique was applied for pan sharpening an image in order to extract the footprint of buildings. Performance indices (precision, recall, overall accuracy and the F1measure) showed an elevated accuracy in automatic recognition of the buildings. Finally, starting from the Digital Surface Model (DSM) generated by satellite imagery, an algorithm built in the GIS environment allowed the extraction of the building height from the elevation model. In this way, it was possible to build a 3D city model where the buildings are represented as prismatic solids with flat roofs, in a fast and precise way.

Highlights

The 3D city model can be built using active and or passive sensors mounted on terrestrial, aerial or satellite platforms
Starting from the Digital Surface Model (DSM) generated by satellite imagery, an algorithm built in the GIS environment allowed the extraction of the building height from the elevation model
This latter approach is based on three main steps: (i) The ground and nonground LIDAR measurements are first separated using a progressive morphological filter; (ii) building measurements are identified from nonground measurements using a region-growing algorithm based on the plane-fitting technique; (iii) raw footprints for segmented building measurements are derived from connecting boundary points, and the raw footprints are further simplified and adjusted to remove noise caused by irregularly spaced LIDAR measurements

Summary

Introduction

The 3D city model can be built using active and or passive sensors mounted on terrestrial, aerial or satellite platforms. Several city models were built using airborne laser scanning (ALS) data; Zhang et al, 2006 [5], present a framework that applies a series of algorithms to automatically extract building footprints from ALS data. This latter approach is based on three main steps: (i) The ground and nonground LIDAR measurements are first separated using a progressive morphological filter; (ii) building measurements are identified from nonground measurements using a region-growing algorithm based on the plane-fitting technique; (iii) raw footprints for segmented building measurements are derived from connecting boundary points, and the raw footprints are further simplified and adjusted to remove noise caused by irregularly spaced LIDAR measurements. Kumar and Bhardwaj, 2020 [16], through a case study of the dense urban areas in parts of Chandigarh (India) show a method to extract building imaging using Pleiades panchromatic and multispectral stereo satellite datasets

Objectives

Methods

Results