Abstract

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%).

Highlights

  • Spatial analysis of vector data remain very complex because of the diversity of configurations and the heterogeneity of datasets

  • The experiments presented in this paper show that deep learning greatly improves the detection of highway interchanges in vector road data

  • A simple image classification convolutional neural networks (CNNs) model greatly reduces the number of false positive interchange detection when coupled with the vector-based detection method

Read more

Summary

Introduction

Spatial analysis of vector data remain very complex because of the diversity of configurations and the heterogeneity of datasets. Map generalization, i.e. the process to simplify map information when scale is reduced, is dependent on vector pattern recognition [1] to make explicit the implicit structures of the map (e.g. buildings aligned along a road). This vector pattern recognition task is very complex and the existing techniques are not completely satisfying. Applications to the assessment of OpenStreetMap data quality [10], car trajectory analysis [11], or map generalization [12, 13] were recently proposed This papers follows the same principles, i.e. generating images of the vector data, to explore the possibilities offered by deep learning for vector spatial analysis.

Highway Interchange Detection in Vector Datasets
Detection by Image Classification
Generating a Training Dataset
Detecting Interchange Roads in Predicted Images
Detection by Image Segmentation
Deriving Training Images from Vector Spatial Datasets
Scale and Image Resolution
Styling Vector Data
Data Augmentation
Conclusion and Future Work
Full Text
Published version (Free)

Talk to us

Join us for a 30 min session where you can share your feedback and ask us any queries you have

Schedule a call