TY - GEN
T1 - Semi-Supervised Learning from Street-View Images and OpenStreetMap for Automatic Building Height Estimation
AU - Li, Hao
AU - Yuan, Zhendong
AU - Dax, Gabriel
AU - Kong, Gefei
AU - Fan, Hongchao
AU - Zipf, Alexander
AU - Werner, Martin
N1 - Publisher Copyright:
© Hao Li, Zhendong Yuan, Gabriel Dax, Gefei Kong, Hongchao Fan, Alexander Zipf, and Martin Werner.
PY - 2023/9
Y1 - 2023/9
N2 - Accurate building height estimation is key to the automatic derivation of 3D city models from emerging big geospatial data, including Volunteered Geographical Information (VGI). However, an automatic solution for large-scale building height estimation based on low-cost VGI data is currently missing. The fast development of VGI data platforms, especially OpenStreetMap (OSM) and crowdsourced street-view images (SVI), offers a stimulating opportunity to fill this research gap. In this work, we propose a semi-supervised learning (SSL) method of automatically estimating building height from Mapillary SVI and OSM data to generate low-cost and open-source 3D city modeling in LoD1. The proposed method consists of three parts: first, we propose an SSL schema with the option of setting a different ratio of “pseudo label” during the supervised regression; second, we extract multi-level morphometric features from OSM data (i.e., buildings and streets) for the purposed of inferring building height; last, we design a building floor estimation workflow with a pre-trained facade object detection network to generate “pseudo label” from SVI and assign it to the corresponding OSM building footprint. In a case study, we validate the proposed SSL method in the city of Heidelberg, Germany and evaluate the model performance against the reference data of building heights. Based on three different regression models, namely Random Forest (RF), Support Vector Machine (SVM), and Convolutional Neural Network (CNN), the SSL method leads to a clear performance boosting in estimating building heights with a Mean Absolute Error (MAE) around 2.1 meters, which is competitive to state-of-the-art approaches. The preliminary result is promising and motivates our future work in scaling up the proposed method based on low-cost VGI data, with possibilities in even regions and areas with diverse data quality and availability.
AB - Accurate building height estimation is key to the automatic derivation of 3D city models from emerging big geospatial data, including Volunteered Geographical Information (VGI). However, an automatic solution for large-scale building height estimation based on low-cost VGI data is currently missing. The fast development of VGI data platforms, especially OpenStreetMap (OSM) and crowdsourced street-view images (SVI), offers a stimulating opportunity to fill this research gap. In this work, we propose a semi-supervised learning (SSL) method of automatically estimating building height from Mapillary SVI and OSM data to generate low-cost and open-source 3D city modeling in LoD1. The proposed method consists of three parts: first, we propose an SSL schema with the option of setting a different ratio of “pseudo label” during the supervised regression; second, we extract multi-level morphometric features from OSM data (i.e., buildings and streets) for the purposed of inferring building height; last, we design a building floor estimation workflow with a pre-trained facade object detection network to generate “pseudo label” from SVI and assign it to the corresponding OSM building footprint. In a case study, we validate the proposed SSL method in the city of Heidelberg, Germany and evaluate the model performance against the reference data of building heights. Based on three different regression models, namely Random Forest (RF), Support Vector Machine (SVM), and Convolutional Neural Network (CNN), the SSL method leads to a clear performance boosting in estimating building heights with a Mean Absolute Error (MAE) around 2.1 meters, which is competitive to state-of-the-art approaches. The preliminary result is promising and motivates our future work in scaling up the proposed method based on low-cost VGI data, with possibilities in even regions and areas with diverse data quality and availability.
KW - 3D city model
KW - Facade parsing
KW - GeoAI
KW - OpenStreetMap
KW - Street-view Images
KW - VGI
UR - http://www.scopus.com/inward/record.url?scp=85172326313&partnerID=8YFLogxK
U2 - 10.4230/LIPIcs.GIScience.2023.7
DO - 10.4230/LIPIcs.GIScience.2023.7
M3 - Conference contribution
AN - SCOPUS:85172326313
T3 - Leibniz International Proceedings in Informatics, LIPIcs
BT - 12th International Conference on Geographic Information Science, GIScience 2023
A2 - Beecham, Roger
A2 - Long, Jed A.
A2 - Smith, Dianna
A2 - Zhao, Qunshan
A2 - Wise, Sarah
PB - Schloss Dagstuhl- Leibniz-Zentrum fur Informatik GmbH, Dagstuhl Publishing
T2 - 12th International Conference on Geographic Information Science, GIScience 2023
Y2 - 12 September 2023 through 15 September 2023
ER -