A MACHINE LEARNING PIPELINE ARTICULATING SATELLITE IMAGERY AND OPENSTREETMAP FOR ROAD DETECTION

<p>Satellite imagery from earth observation missions enable processing big data to gather information about the world. Automatizing the creation of maps that reflect ground truth is a desirable outcome that would aid decision makers to take adequate actions in alignment with the United Nations...

Full description

Bibliographic Details
Main Authors: M. A. Zurbaran, P. Wightman, M. A. Brovelli
Format: Article
Language:English
Published: Copernicus Publications 2019-08-01
Series:The International Archives of the Photogrammetry, Remote Sensing and Spatial Information Sciences
Online Access:https://www.int-arch-photogramm-remote-sens-spatial-inf-sci.net/XLII-4-W14/255/2019/isprs-archives-XLII-4-W14-255-2019.pdf
id doaj-35dfaa288a3c428d8f0db7af21954f81
record_format Article
spelling doaj-35dfaa288a3c428d8f0db7af21954f812020-11-24T22:15:15ZengCopernicus PublicationsThe International Archives of the Photogrammetry, Remote Sensing and Spatial Information Sciences1682-17502194-90342019-08-01XLII-4-W1425526010.5194/isprs-archives-XLII-4-W14-255-2019A MACHINE LEARNING PIPELINE ARTICULATING SATELLITE IMAGERY AND OPENSTREETMAP FOR ROAD DETECTIONM. A. Zurbaran0P. Wightman1M. A. Brovelli2Dept. of Civil and Environmental Engineering, Politecnico di Milano, Piazza Leonardo da Vinci, 32, 20133 Milano MI, ItalyDept. of Systems Engineering, Universidad del Norte, km 5 via Pto. Colombia, Atlántico, ColombiaDept. of Civil and Environmental Engineering, Politecnico di Milano, Piazza Leonardo da Vinci, 32, 20133 Milano MI, Italy<p>Satellite imagery from earth observation missions enable processing big data to gather information about the world. Automatizing the creation of maps that reflect ground truth is a desirable outcome that would aid decision makers to take adequate actions in alignment with the United Nations Sustainable Development Goals. In order to harness the power that the availability of the new generation of satellites enable, it is necessary to implement techniques capable of handling annotations for the massive volume and variability of high spatial resolution imagery for further processing. However, the availability of public datasets for training machine learning models for image segmentation plays an important role for scalability.</p><p>This work focuses on bridging remote sensing and computer vision by providing an open source based pipeline for generating machine learning training datasets for road detection in an area of interest. The proposed pipeline addresses road detection as a binary classification problem using road annotations existing in OpenStreetMap for creating masks. For this case study, Planet images of 3m resolution are used for creating a training dataset for road detection in Kenya.</p>https://www.int-arch-photogramm-remote-sens-spatial-inf-sci.net/XLII-4-W14/255/2019/isprs-archives-XLII-4-W14-255-2019.pdf
collection DOAJ
language English
format Article
sources DOAJ
author M. A. Zurbaran
P. Wightman
M. A. Brovelli
spellingShingle M. A. Zurbaran
P. Wightman
M. A. Brovelli
A MACHINE LEARNING PIPELINE ARTICULATING SATELLITE IMAGERY AND OPENSTREETMAP FOR ROAD DETECTION
The International Archives of the Photogrammetry, Remote Sensing and Spatial Information Sciences
author_facet M. A. Zurbaran
P. Wightman
M. A. Brovelli
author_sort M. A. Zurbaran
title A MACHINE LEARNING PIPELINE ARTICULATING SATELLITE IMAGERY AND OPENSTREETMAP FOR ROAD DETECTION
title_short A MACHINE LEARNING PIPELINE ARTICULATING SATELLITE IMAGERY AND OPENSTREETMAP FOR ROAD DETECTION
title_full A MACHINE LEARNING PIPELINE ARTICULATING SATELLITE IMAGERY AND OPENSTREETMAP FOR ROAD DETECTION
title_fullStr A MACHINE LEARNING PIPELINE ARTICULATING SATELLITE IMAGERY AND OPENSTREETMAP FOR ROAD DETECTION
title_full_unstemmed A MACHINE LEARNING PIPELINE ARTICULATING SATELLITE IMAGERY AND OPENSTREETMAP FOR ROAD DETECTION
title_sort machine learning pipeline articulating satellite imagery and openstreetmap for road detection
publisher Copernicus Publications
series The International Archives of the Photogrammetry, Remote Sensing and Spatial Information Sciences
issn 1682-1750
2194-9034
publishDate 2019-08-01
description <p>Satellite imagery from earth observation missions enable processing big data to gather information about the world. Automatizing the creation of maps that reflect ground truth is a desirable outcome that would aid decision makers to take adequate actions in alignment with the United Nations Sustainable Development Goals. In order to harness the power that the availability of the new generation of satellites enable, it is necessary to implement techniques capable of handling annotations for the massive volume and variability of high spatial resolution imagery for further processing. However, the availability of public datasets for training machine learning models for image segmentation plays an important role for scalability.</p><p>This work focuses on bridging remote sensing and computer vision by providing an open source based pipeline for generating machine learning training datasets for road detection in an area of interest. The proposed pipeline addresses road detection as a binary classification problem using road annotations existing in OpenStreetMap for creating masks. For this case study, Planet images of 3m resolution are used for creating a training dataset for road detection in Kenya.</p>
url https://www.int-arch-photogramm-remote-sens-spatial-inf-sci.net/XLII-4-W14/255/2019/isprs-archives-XLII-4-W14-255-2019.pdf
work_keys_str_mv AT mazurbaran amachinelearningpipelinearticulatingsatelliteimageryandopenstreetmapforroaddetection
AT pwightman amachinelearningpipelinearticulatingsatelliteimageryandopenstreetmapforroaddetection
AT mabrovelli amachinelearningpipelinearticulatingsatelliteimageryandopenstreetmapforroaddetection
AT mazurbaran machinelearningpipelinearticulatingsatelliteimageryandopenstreetmapforroaddetection
AT pwightman machinelearningpipelinearticulatingsatelliteimageryandopenstreetmapforroaddetection
AT mabrovelli machinelearningpipelinearticulatingsatelliteimageryandopenstreetmapforroaddetection
_version_ 1725795195198373888