Automatic 3-D Building Model Reconstruction from Very High Resolution Stereo Satellite Imagery

Tahmineh Partovi, Friedrich Fraundorfer, Reza Bahmanyar, Hai Huang, Peter Reinartz

Publikation: Beitrag in einer FachzeitschriftArtikelForschungBegutachtung

Abstract

Recent advances in the availability of very high-resolution (VHR) satellite data together with efficient data acquisition and large area coverage have led to an upward trend in their applications for automatic 3-D building model reconstruction which require large-scale and frequent updates, such as disaster monitoring and urban management. Digital Surface Models (DSMs) generated from stereo satellite imagery suffer from mismatches, missing values, or blunders, resulting in rough building shape representations. To handle 3-D building model reconstruction using such low-quality DSMs, we propose a novel automatic multistage hybrid method using DSMs together with orthorectified panchromatic (PAN) and pansharpened data (PS) of multispectral (MS) satellite imagery. The algorithm consists of multiple steps including building boundary extraction and decomposition, image-based roof type classification, and initial roof parameter computation which are prior knowledge for the 3-D model fitting step. To fit 3-D models to the normalized DSM (nDSM) and to select the best one, a parameter optimization method based on exhaustive search is used sequentially in 2-D and 3-D. Finally, the neighboring building models in a building block are intersected to reconstruct the 3-D model of connecting roofs. All corresponding experiments are conducted on a dataset including four different areas of Munich city containing 208 buildings with different degrees of complexity. The results are evaluated both qualitatively and quantitatively. According to the results, the proposed approach can reliably reconstruct 3-D building models, even the complex ones with …
Originalspracheenglisch
Aufsatznummer1660
FachzeitschriftRemote Sensing
Jahrgang11
Ausgabenummer14
DOIs
PublikationsstatusVeröffentlicht - 2019

Fingerprint

satellite imagery
roof
data acquisition
satellite data
disaster
decomposition
monitoring

Dies zitieren

Automatic 3-D Building Model Reconstruction from Very High Resolution Stereo Satellite Imagery. / Partovi, Tahmineh; Fraundorfer, Friedrich; Bahmanyar, Reza; Huang, Hai; Reinartz, Peter.

in: Remote Sensing , Jahrgang 11, Nr. 14, 1660, 2019.

Publikation: Beitrag in einer FachzeitschriftArtikelForschungBegutachtung

Partovi, Tahmineh ; Fraundorfer, Friedrich ; Bahmanyar, Reza ; Huang, Hai ; Reinartz, Peter. / Automatic 3-D Building Model Reconstruction from Very High Resolution Stereo Satellite Imagery. in: Remote Sensing . 2019 ; Jahrgang 11, Nr. 14.
@article{0e5e94f0379b4b2b96e63864ad5636eb,
title = "Automatic 3-D Building Model Reconstruction from Very High Resolution Stereo Satellite Imagery",
abstract = "Recent advances in the availability of very high-resolution (VHR) satellite data together with efficient data acquisition and large area coverage have led to an upward trend in their applications for automatic 3-D building model reconstruction which require large-scale and frequent updates, such as disaster monitoring and urban management. Digital Surface Models (DSMs) generated from stereo satellite imagery suffer from mismatches, missing values, or blunders, resulting in rough building shape representations. To handle 3-D building model reconstruction using such low-quality DSMs, we propose a novel automatic multistage hybrid method using DSMs together with orthorectified panchromatic (PAN) and pansharpened data (PS) of multispectral (MS) satellite imagery. The algorithm consists of multiple steps including building boundary extraction and decomposition, image-based roof type classification, and initial roof parameter computation which are prior knowledge for the 3-D model fitting step. To fit 3-D models to the normalized DSM (nDSM) and to select the best one, a parameter optimization method based on exhaustive search is used sequentially in 2-D and 3-D. Finally, the neighboring building models in a building block are intersected to reconstruct the 3-D model of connecting roofs. All corresponding experiments are conducted on a dataset including four different areas of Munich city containing 208 buildings with different degrees of complexity. The results are evaluated both qualitatively and quantitatively. According to the results, the proposed approach can reliably reconstruct 3-D building models, even the complex ones with …",
author = "Tahmineh Partovi and Friedrich Fraundorfer and Reza Bahmanyar and Hai Huang and Peter Reinartz",
year = "2019",
doi = "10.3390/rs11141660",
language = "English",
volume = "11",
journal = "Remote Sensing",
issn = "2072-4292",
publisher = "MDPI AG",
number = "14",

}

TY - JOUR

T1 - Automatic 3-D Building Model Reconstruction from Very High Resolution Stereo Satellite Imagery

AU - Partovi, Tahmineh

AU - Fraundorfer, Friedrich

AU - Bahmanyar, Reza

AU - Huang, Hai

AU - Reinartz, Peter

PY - 2019

Y1 - 2019

N2 - Recent advances in the availability of very high-resolution (VHR) satellite data together with efficient data acquisition and large area coverage have led to an upward trend in their applications for automatic 3-D building model reconstruction which require large-scale and frequent updates, such as disaster monitoring and urban management. Digital Surface Models (DSMs) generated from stereo satellite imagery suffer from mismatches, missing values, or blunders, resulting in rough building shape representations. To handle 3-D building model reconstruction using such low-quality DSMs, we propose a novel automatic multistage hybrid method using DSMs together with orthorectified panchromatic (PAN) and pansharpened data (PS) of multispectral (MS) satellite imagery. The algorithm consists of multiple steps including building boundary extraction and decomposition, image-based roof type classification, and initial roof parameter computation which are prior knowledge for the 3-D model fitting step. To fit 3-D models to the normalized DSM (nDSM) and to select the best one, a parameter optimization method based on exhaustive search is used sequentially in 2-D and 3-D. Finally, the neighboring building models in a building block are intersected to reconstruct the 3-D model of connecting roofs. All corresponding experiments are conducted on a dataset including four different areas of Munich city containing 208 buildings with different degrees of complexity. The results are evaluated both qualitatively and quantitatively. According to the results, the proposed approach can reliably reconstruct 3-D building models, even the complex ones with …

AB - Recent advances in the availability of very high-resolution (VHR) satellite data together with efficient data acquisition and large area coverage have led to an upward trend in their applications for automatic 3-D building model reconstruction which require large-scale and frequent updates, such as disaster monitoring and urban management. Digital Surface Models (DSMs) generated from stereo satellite imagery suffer from mismatches, missing values, or blunders, resulting in rough building shape representations. To handle 3-D building model reconstruction using such low-quality DSMs, we propose a novel automatic multistage hybrid method using DSMs together with orthorectified panchromatic (PAN) and pansharpened data (PS) of multispectral (MS) satellite imagery. The algorithm consists of multiple steps including building boundary extraction and decomposition, image-based roof type classification, and initial roof parameter computation which are prior knowledge for the 3-D model fitting step. To fit 3-D models to the normalized DSM (nDSM) and to select the best one, a parameter optimization method based on exhaustive search is used sequentially in 2-D and 3-D. Finally, the neighboring building models in a building block are intersected to reconstruct the 3-D model of connecting roofs. All corresponding experiments are conducted on a dataset including four different areas of Munich city containing 208 buildings with different degrees of complexity. The results are evaluated both qualitatively and quantitatively. According to the results, the proposed approach can reliably reconstruct 3-D building models, even the complex ones with …

U2 - 10.3390/rs11141660

DO - 10.3390/rs11141660

M3 - Article

VL - 11

JO - Remote Sensing

JF - Remote Sensing

SN - 2072-4292

IS - 14

M1 - 1660

ER -