Tagging the main entrances of public buildings based on OpenStreetMap and binary imbalanced learning

ABSTRACT

Determining the location of a building’s entrance is crucial to location-based services, such as wayfinding for pedestrians. Unfortunately, entrance information is often missing from current mainstream map providers such as Google Maps. Frequently, automatic approaches for detecting building entrances are based on street-level images that are not widely available. To address this issue, we propose a more general approach for inferring the main entrances of public buildings based on the association between spatial elements extracted from OpenStreetMap. In particular, we adopt three binary classification approaches, weighted random forest, balanced random forest, and smooth-boost to model the association relationship. There are two types of features considered in the classification: intrinsic features derived from building footprints and extrinsic features derived from spatial contexts, such as roads, green spaces, bicycle parking areas, and neighboring buildings. We conducted extensive experiments on 320 public buildings with an average perimeter of 350 m. The experimental results showed that the locations of building entrances estimated by the weighted random forest and balanced random forest models have a mean linear distance error of 21 m and a mean path distance error of 22 m, ruling out 90% of the incorrect locations of the main entrance of buildings.

KEYWORDS:

• Main entrance tagging
• OpenStreetMap
• imbalanced learning
• random forest

Supplementary material

Supplemental data for this article can be accessed here.

Disclosure statement

No potential conflict of interest was reported by the author(s).

Data and codes availability statement

The data and codes that support the findings of this study are available in github with the identifier at the link https://github.com/uhuohuy/entrance_tagging

Notes

1. Definition of public buildings on OSM https://wiki.openstreetmap.org/wiki/Tag:building%3Dpublic.

2. Entrance on OSM https://wiki.openstreetmap.org/wiki/Key:entrance.

Additional information

Funding

This study is supported by the China Scholarship Council.

Notes on contributors

Xuke Hu

Xuke Hu received his PhD degree in Geoinformatics from Heidelberg University, Germany in 2020. He is now a full-time postdoctoral researcher at the data science institute of the German Aerospace Center (DLR). His research interests include indoor localization/navigation/mapping, VGI, social sensing, earth observation, and disaster management.

Alexey Noskov

Dr. Alexey Noskov is a PostDoc Researcher at Marburg University. His MSc thesis was devoted to using GIS for Acric coastal dynamics research (2007, Moscow Univesity, Russia). His PhD thesis, “3D Generalization of Urban Environment”, has been defended at the Israel Institute of Technology (The Technion) in 2016. Moreover, geospatial data integration was a significant part of the thesis. His first PostDoc (Heidelberg University, 2016-2019) was mainly about the VGI data quality within the Horizons-2020 WeGovNow project. He currently works on the Nature 4.0 (Sensing biodiversity) project, where insect radar, autonomous rover systems, and forest inventory survey solutions are his primary responsibility.

Hongchao Fan

Hongchao Fan is professor for 3D Geoinformatics at the Department of Civil and Environmental Engineering at the Norwegian University of Science and Technology (NTNU). He received his master’s degree in Geodesy and Geoinformatics at the University of Stuttgart and obtained his PhD at the Technical University of Munich in Germany. After that he worked as Group Leader for 3D Data Infrastructure at the Heidelberg University for six years. In 2018, he started his work as professor at NTNU in Trondheim, Norway. His research interests include 3D city modelling, spatial data mining from VGI data and laser scanning.

Tessio Novack

Tessio Novack received his doctoral degree in photogrammetry and remote sensing from the Technical University of Munich, Germany. As a postdoctoral researcher at the GIScience Group, Heidelberg University, Germany, he conducted research and teaching activities in topics including user-generated geospatial data analysis and urban mobility. He recently joined the Centre for Interdisciplinary Methodologies at the University of Warwick (United Kingdom) as Assistant Professor.

Hao Li

Hao Li is currently a research associate and Ph.D. candidate at the GIScience group of Heidelberg University. He received his B.S. degree in both Geographical Information System and Computer Science from Wuhan University in 2015, and his M.S. in Geomatic Engineering from University of Stuttgart in 2018. His research interest lies in volunteered geographic information, geospatial machine learning, multi-sensor data fusion, and geo-semantics.

Fuqiang Gu

Fuqiang Gu is currently an associate professor in the College of Computer Science of the Chongqing University.  He obtained his PhD in Geomatics from the University of Melbourne in 2018. He was a research fellow in the School of Computing of the National University of Singapore from October 2019 to November 2020, and a postdoctoral researcher in the Department of Mechanical and Industrial Engineering of the University of Toronto from October 2018 to September 2019. His research interests include mobile sensing, activity recognition, robotics, and machine learning.

Jianga Shang

Jianga Shang is currently a Professor with the School of Geography and Information Engineering, China University of Geosciences, Wuhan. He received the Ph.D. degree in computer system architecture from the Huazhong University of Science and Technology. He is also the director of research group for intelligent system Software technology in the National Engineering Research Center for Geographic Information System. Dr Shang is a committee member of ISPRS WG IV/5 on indoor/outdoor seamless modeling, LBS, and mobility. He is also a member of the IEEE, ACM, China Computer Federation (CCF), and GNSS & LBS Association of China(GLAC). His research interests include indoor location-awareness, mobile and context-aware computing, geospatial information systems, and human-cyber-physical integration software.

Alexander Zipf

Alexander Zipf received his PhD degree from Heidelberg University, Germany. He was a Professor of applied computer science and geoinformatics with the University of Applied Sciences, Mainz, Germany. Later he led the Chair of Cartography, Bonn University, Germany. Since 2009, he is the Chair of GIScience at Heidelberg University and since 2019 he is also managing director of the Heidelberg Institute for Geoinformation Technology (HeiGIT gGmbH).