An automatic method for road centerline extraction from post-earthquake aerial images

Abstract Road vector database plays an important role in post-earthquake relief, rescue and reconstruction. However, due to data privacy policy, it is difficult for general users to obtain high-precision and complete vector data of road network. The OpenStreetMap (OSM) project provides an open-source, global free road dataset, but there are inevitable geo-localization/projection errors, which will lead to large errors in hazard survey analysis. In this paper, we proposed a road centerline correction method using post-earthquake aerial images. Under the constraint of the vector road map (OpenStreetMap), we rectified the centerline by the context feature and spectral gradient feature of post-event images automatically. The experiment implemented on 0.5 m/pixel post-event aerial images of Haiti, 2010, showed that the completeness and extraction quality of proposed method were over 90% and 80% without any manual intervention.

[1]  A. Mookambiga,et al.  Automated road network extraction using artificial neural network , 2011, 2011 International Conference on Recent Trends in Information Technology (ICRTIT).

[2]  Qiang Li,et al.  Damaged road extraction from post-seismic remote sensing images based on gis and object-oriented method , 2016, IGARSS.

[3]  Brenda K. Jones,et al.  USGS remote sensing coordination for the 2010 Haiti earthquake , 2011 .

[4]  Liu Sheng,et al.  Extracting roads based on Retinex and improved Canny operator with shape criteria in vague and unevenly illuminated aerial images , 2012 .

[5]  Shi Wen.  Road Feature Extraction from Remotely Sensed Image:Review and Prospects , 2001 .

[6]  Li Qiang,et al.  Research on Earthquake Damaged Building Extraction by Different Features Fusion , 2016 .

[7]  Lian Jian.  Road Damage Assessment from High Resolution Satellite Remote Sensing Imagery in Wenchuan Earthquake , 2008 .

[8]  Wenzhong Shi,et al.  A Semi-Automatic Method for Road Centerline Extraction From VHR Images , 2014, IEEE Geoscience and Remote Sensing Letters.

[9]  Wan Jun-li.  Algorithm of Image Edge Detection Based on Mathematical Morphology Gradient , 2007 .

[10]  Wenzhong Shi,et al.  An Integrated Method for Urban Main-Road Centerline Extraction From Optical Remotely Sensed Imagery , 2014, IEEE Transactions on Geoscience and Remote Sensing.

[11]  Christophe Simler,et al.  An improved road and building detector on VHR images , 2011, 2011 IEEE International Geoscience and Remote Sensing Symposium.

[12]  Tang Lulian.  Road Damage Detection from Remote Sensing Imagery Based on Road Network Vector Data , 2011 .

[13]  M. J. V. Zoej,et al.  Road Detection from High Resolution Satellite Imagery Using Texture Parameters in Neural Network , 2007 .

[14]  Yang Jinghui.  Semi-automatic Extraction of Ribbon Road from High Resolution Remotely Sensed Imagery by a T-shaped Template Matching , 2009 .

[15]  Sanja Fidler,et al.  Enhancing Road Maps by Parsing Aerial Images Around the World , 2015, 2015 IEEE International Conference on Computer Vision (ICCV).