Deep Learning for Enrichment of Vector Spatial Databases

Spatial analysis and pattern recognition with vector spatial data is particularly useful to enrich raw data. In road networks, for instance, there are many patterns and structures that are implicit with only road line features, among which highway interchange appeared very complex to recognize with vector-based techniques. The goal is to find the roads that belong to an interchange, such as the slip roads and the highway roads connected to the slip roads. To go further than state-of-the-art vector-based techniques, this article proposes to use raster-based deep learning techniques to recognize highway interchanges. The contribution of this work is to study how to optimally convert vector data into small images suitable for state-of-the-art deep learning models. Image classification with a convolutional neural network (i.e., is there an interchange in this image or not?) and image segmentation with a u-net (i.e., find the pixels that cover the interchange) are experimented and give better results than existing vector-based techniques in this specific use case (99.5% against 74%).

[1]  Yongyang Xu,et al.  Quality assessment of building footprint data using a deep autoencoder network , 2017, Int. J. Geogr. Inf. Sci..

[2]  Rodrigo F. Berriel,et al.  Deep Learning-Based Large-Scale Automatic Satellite Crosswalk Classification , 2017, IEEE Geoscience and Remote Sensing Letters.

[3]  Abhishek Das,et al.  Grad-CAM: Visual Explanations from Deep Networks via Gradient-Based Localization , 2016, 2017 IEEE International Conference on Computer Vision (ICCV).

[4]  M. Rumor,et al.  DATA ENRICHMENT FOR ROAD GENERALIZATION THROUGH ANALYSIS OF MORPHOLOGY IN THE CARGEN PROJECT , 2010 .

[5]  Ramprasaath R. Selvaraju,et al.  Grad-CAM: Why did you say that? Visual Explanations from Deep Networks via Gradient-based Localization , 2016 .

[6]  Birgit Elias,et al.  Extracting Landmarks with Data Mining Methods , 2003, COSIT.

[7]  Iasonas Kokkinos,et al.  DeepLab: Semantic Image Segmentation with Deep Convolutional Nets, Atrous Convolution, and Fully Connected CRFs , 2016, IEEE Transactions on Pattern Analysis and Machine Intelligence.

[8]  Hichem Sahbi,et al.  Domain Adaptation for Large Scale Classification of Very High Resolution Satellite Images with Deep Convolutional Neural Networks , 2018, IGARSS 2018 - 2018 IEEE International Geoscience and Remote Sensing Symposium.

[9]  Karl-Heinrich Anders,et al.  Characterising Space via Pattern Recognition Techniques: Identifying Patterns in Road Networks , 2007 .

[10]  William A. Mackaness,et al.  Automating the Detection and Simplification of Junctions in Road Networks , 1999, GeoInformatica.

[11]  Torben Peters,et al.  Conditional Adversarial Networks for Multimodal Photo-Realistic Point Cloud Rendering , 2020, PFG – Journal of Photogrammetry, Remote Sensing and Geoinformation Science.

[12]  Nitish Srivastava,et al.  Dropout: a simple way to prevent neural networks from overfitting , 2014, J. Mach. Learn. Res..

[13]  Jiaoyan Chen,et al.  DeepVGI: Deep Learning with Volunteered Geographic Information , 2017, WWW.

[14]  Song Gao,et al.  Transferring multiscale map styles using generative adversarial networks , 2019, International Journal of Cartography.

[15]  Thomas Brox,et al.  U-Net: Convolutional Networks for Biomedical Image Segmentation , 2015, MICCAI.

[16]  Alexei A. Efros,et al.  Image-to-Image Translation with Conditional Adversarial Networks , 2016, 2017 IEEE Conference on Computer Vision and Pattern Recognition (CVPR).

[17]  Qingnian Zhang,et al.  Modeling Structure and Patterns in Road Network Generalization , 2004 .

[18]  Yoshua Bengio,et al.  Gradient-based learning applied to document recognition , 1998, Proc. IEEE.

[19]  Guillaume Touya,et al.  Is deep learning the new agent for map generalization? , 2019, International Journal of Cartography.

[20]  Bertrand Le Saux,et al.  Joint Learning from Earth Observation and OpenStreetMap Data to Get Faster Better Semantic Maps , 2017, 2017 IEEE Conference on Computer Vision and Pattern Recognition Workshops (CVPRW).

[21]  Martin Simonovsky,et al.  Large-Scale Point Cloud Semantic Segmentation with Superpoint Graphs , 2017, 2018 IEEE/CVF Conference on Computer Vision and Pattern Recognition.

[22]  Chunhong Pan,et al.  Building extraction from multi-source remote sensing images via deep deconvolution neural networks , 2016, 2016 IEEE International Geoscience and Remote Sensing Symposium (IGARSS).

[23]  N. V. D. Weghe,et al.  CLASSIFICATION OF ROAD JUNCTIONS BASED ON MULTIPLE REPRESENTATIONS: ADDING VALUE BY INTRODUCING ALGORITHMIC AND CARTOGRAPHIC APPROACHES , 2007 .

[24]  Ali Farhadi,et al.  You Only Look Once: Unified, Real-Time Object Detection , 2015, 2016 IEEE Conference on Computer Vision and Pattern Recognition (CVPR).

[25]  Guillaume Touya,et al.  A Road Network Selection Process Based on Data Enrichment and Structure Detection , 2010, Trans. GIS.

[26]  Robert C. Thomson,et al.  The’ stroke’ Concept in Geographic Network Generalization and Analysis , 2006 .

[27]  Qingjie Liu,et al.  Road Extraction by Deep Residual U-Net , 2017, IEEE Geoscience and Remote Sensing Letters.

[28]  Qingquan Li,et al.  An adaptive method for identifying the spatial patterns in road networks , 2010, Comput. Environ. Urban Syst..

[29]  Progressive Block Graying and Landmarks Enhancing as Intermediate Representations between Buildings and Urban Areas , 2017 .

[30]  Stuart Thom.  A Strategy for Collapsing OS Integrated Transport Network™ dual carriageways. , 2005 .

[31]  Monika Sester,et al.  GRAPH BASED APPROACHES FOR RECOGNITION OF PATTERNS AND IMPLICIT INFORMATION IN ROAD NETWORKS , 2005 .

[32]  Geoffrey Edwards,et al.  - 1The Importance of Modelling Pattern and Structure in Automated Map Generalisation , 2002 .

[33]  Monika Sester,et al.  Building generalization using deep learning , 2018 .