Quality assessment of building footprint data using a deep autoencoder network

ABSTRACT Volunteered geographic information (VGI), OpenStreetMap (OSM), has been used in many applications, especially when official spatial data are unavailable or outdated. However, the quality of VGI remains a valid concern. In this paper, we use the matched results between OSM building footprints and official data as the samples for training an autoencoder network, which encodes and reconstructs the sample populations according to unknown complex multivariate probability distributions. Then, the OSM data are assessed based on the theory that small probability samples contribute little to the autoencoder network and that they can be recognized by the higher reconstructed errors during training. In the method described here, the selected measures, including data completeness, positional accuracy, shape accuracy, semantic accuracy and orientation consistency between OSM and official data, are used as the inputs for a deep autoencoder network. Finally, building footprint data from Toronto, Canada, are evaluated, and experiments show that the proposed method can assess the OSM data comprehensively, objectively and accurately.

[1]  A. Comber,et al.  Approaches to Uncertainty in Spatial Data , 2010 .

[2]  Geoffrey E. Hinton,et al.  Reducing the Dimensionality of Data with Neural Networks , 2006, Science.

[3]  Alexander Zipf,et al.  Quality Evaluation of VGI Using Authoritative Data - A Comparison with Land Use Data in Southern Germany , 2015, ISPRS Int. J. Geo Inf..

[4]  Andrew P. Valentine,et al.  Data space reduction, quality assessment and searching of seismograms: autoencoder networks for waveform data , 2012 .

[5]  Julian Hagenauer,et al.  OSMatrix – Grid-based Analysis and Visualiza- tion of OpenStreetMap , 2011 .

[6]  Geoffrey E. Hinton.  Training Products of Experts by Minimizing Contrastive Divergence , 2002, Neural Computation.

[7]  Michael F. Goodchild,et al.  Assuring the quality of volunteered geographic information , 2012 .

[8]  T. H. Kolbe,et al.  OpenGIS City Geography Markup Language (CityGML) Encoding Standard, Version 1.0.0 , 2008 .

[9]  Yoshua. Bengio,et al.  Learning Deep Architectures for AI , 2007, Found. Trends Mach. Learn..

[10]  Alan F. Murray,et al.  Continuous restricted Boltzmann machine with an implementable training algorithm , 2003 .

[11]  M. Haklay.  How Good is Volunteered Geographical Information? A Comparative Study of OpenStreetMap and Ordnance Survey Datasets , 2010 .

[12]  Alexander Zipf,et al.  A polygon-based approach for matching OpenStreetMap road networks with regional transit authority data , 2016, Int. J. Geogr. Inf. Sci..

[13]  Michael F. Goodchild,et al.  Please Scroll down for Article International Journal of Digital Earth Crowdsourcing Geographic Information for Disaster Response: a Research Frontier Crowdsourcing Geographic Information for Disaster Response: a Research Frontier , 2022 .

[14]  Yongliang Chen.  Mineral potential mapping with a restricted Boltzmann machine , 2015 .

[15]  Pascal Neis,et al.  The Street Network Evolution of Crowdsourced Maps: OpenStreetMap in Germany 2007-2011 , 2011, Future Internet.

[16]  Peter Mooney,et al.  Characterising the metric and topological evolution of OpenStreetMap network representations , 2013, The European Physical Journal Special Topics.

[17]  Alexander Zipf,et al.  Towards Defining a Framework for the Automatic Derivation of 3D CityGML Models from Volunteered Geographic Information , 2012, Int. J. 3 D Inf. Model..

[18]  Yoshua Bengio,et al.  Exploring Strategies for Training Deep Neural Networks , 2009, J. Mach. Learn. Res..

[19]  Rahim Ali Abbaspour,et al.  Assessment of Logical Consistency in OpenStreetMap Based on the Spatial Similarity Concept , 2015, OpenStreetMap in GIScience.

[20]  Geoffrey E. Hinton.  A Practical Guide to Training Restricted Boltzmann Machines , 2012, Neural Networks: Tricks of the Trade.

[21]  Pascal Neis,et al.  Quality assessment for building footprints data on OpenStreetMap , 2014, Int. J. Geogr. Inf. Sci..

[22]  Miriam J. Metzger,et al.  The credibility of volunteered geographic information , 2008 .

[23]  Guillaume Touya,et al.  Quality Assessment of the French OpenStreetMap Dataset , 2010, Trans. GIS.

[24]  A. Rajabifard,et al.  Methods for assessing the credibility of volunteered geographic information in flood response: A case study in Brisbane, Australia , 2016 .

[25]  Pascal Neis,et al.  Recent Developments and Future Trends in Volunteered Geographic Information Research: The Case of OpenStreetMap , 2014, Future Internet.

[26]  Norbert Pfeifer,et al.  A Comparison of Evaluation Techniques for Building Extraction From Airborne Laser Scanning , 2009, IEEE Journal of Selected Topics in Applied Earth Observations and Remote Sensing.

[27]  Angi Voß,et al.  A Comparison of the Street Networks of Navteq and OSM in Germany , 2011, AGILE Conf..

[28]  Ahmed Loai Ali,et al.  Data Quality Assurance for Volunteered Geographic Information , 2014, GIScience.

[29]  Jianghua Zheng,et al.  Assessing the Completeness and Positional Accuracy of OpenStreetMap in China , 2014 .

[30]  Yongyang Xu,et al.  Shape similarity measurement model for holed polygons based on position graphs and Fourier descriptors , 2017, Int. J. Geogr. Inf. Sci..

[31]  M. Goodchild.  Citizens as sensors: the world of volunteered geography , 2007 .

[32]  Alfredo De Santis,et al.  Network anomaly detection with the restricted Boltzmann machine , 2013, Neurocomputing.

[33]  Mahmoud Reza Delavar,et al.  A Quality Study of the OpenStreetMap Dataset for Tehran , 2014, ISPRS Int. J. Geo Inf..

[34]  Jianwen Sun,et al.  Application of Deep Belief Networks for Precision Mechanism Quality Inspection , 2014, IPAS.

[35]  Geoffrey E. Hinton.  Reducing the Dimensionality of Data with Neural , 2008 .

[36]  David Fairbairn,et al.  Assessing similarity matching for possible integration of feature classifications of geospatial data from official and informal sources , 2012, Int. J. Geogr. Inf. Sci..

[37]  Anoop M. Namboodiri,et al.  Learning Fingerprint Orientation Fields Using Continuous Restricted Boltzmann Machines , 2013, 2013 2nd IAPR Asian Conference on Pattern Recognition.

[38]  J. A. Glennona.  Crowdsourcing geographic information for disaster response: a research , 2010 .

[39]  Alan F. Murray,et al.  Novelty detection using products of simple experts--a potential architecture for embedded systems , 2001, Neural Networks.