Next Article in Journal
Consideration of Level of Confidence within Multi-Approach Satellite-Derived Bathymetry
Next Article in Special Issue
Bangkok CCTV Image through a Road Environment Extraction System Using Multi-Label Convolutional Neural Network Classification
Previous Article in Journal
GEOBIA at the Terapixel Scale: Toward Efficient Mapping of Small Woody Features from Heterogeneous VHR Scenes
Article Menu
Issue 1 (January) cover image

Export Article

Open AccessArticle
ISPRS Int. J. Geo-Inf. 2019, 8(1), 47; https://doi.org/10.3390/ijgi8010047

Deep Learning Segmentation and 3D Reconstruction of Road Markings Using Multiview Aerial Imagery

1
German Aerospace Center (DLR), Remote Sensing Technology Institute, 82234 Weßling, Germany
2
Bosch AG., 3801-856 Stuttgart, Germany
*
Author to whom correspondence should be addressed.
Current address: Münchener Straße 20, 82234 Weßling, Germany.
Received: 14 December 2018 / Revised: 15 January 2019 / Accepted: 16 January 2019 / Published: 18 January 2019
(This article belongs to the Special Issue Innovative Sensing - From Sensors to Methods and Applications)
Full-Text   |   PDF [52187 KB, uploaded 22 January 2019]   |  

Abstract

The 3D information of road infrastructures is growing in importance with the development of autonomous driving. In this context, the exact 2D position of road markings as well as height information play an important role in, e.g., lane-accurate self-localization of autonomous vehicles. In this paper, the overall task is divided into an automatic segmentation followed by a refined 3D reconstruction. For the segmentation task, we applied a wavelet-enhanced fully convolutional network on multiview high-resolution aerial imagery. Based on the resulting 2D segments in the original images, we propose a successive workflow for the 3D reconstruction of road markings based on a least-squares line-fitting in multiview imagery. The 3D reconstruction exploits the line character of road markings with the aim to optimize the best 3D line location by minimizing the distance from its back projection to the detected 2D line in all the covering images. Results showed an improved IoU of the automatic road marking segmentation by exploiting the multiview character of the aerial images and a more accurate 3D reconstruction of the road surface compared to the semiglobal matching (SGM) algorithm. Further, the approach avoids the matching problem in non-textured image parts and is not limited to lines of finite length. In this paper, the approach is presented and validated on several aerial image data sets covering different scenarios like motorways and urban regions. View Full-Text
Keywords: aerial image sequences; road marking detection; 3D line-features reconstruction; fully convolutional neural network aerial image sequences; road marking detection; 3D line-features reconstruction; fully convolutional neural network
Figures

Figure 1

This is an open access article distributed under the Creative Commons Attribution License which permits unrestricted use, distribution, and reproduction in any medium, provided the original work is properly cited (CC BY 4.0).
SciFeed

Share & Cite This Article

MDPI and ACS Style

Kurz, F.; Azimi, S.M.; Sheu, C.-Y.; d’Angelo, P. Deep Learning Segmentation and 3D Reconstruction of Road Markings Using Multiview Aerial Imagery. ISPRS Int. J. Geo-Inf. 2019, 8, 47.

Show more citation formats Show less citations formats

Note that from the first issue of 2016, MDPI journals use article numbers instead of page numbers. See further details here.

Related Articles

Article Metrics

Article Access Statistics

1

Comments

[Return to top]
ISPRS Int. J. Geo-Inf. EISSN 2220-9964 Published by MDPI AG, Basel, Switzerland RSS E-Mail Table of Contents Alert
Back to Top