Change Detection from Remote Sensing to Guide OpenStreetMap Labeling

Autor: Rui Zhang, Fernando J. Marianno, Levente Klein, Norman Bobroff, Ulrich Finkler, Conrad M. Albrecht, Siyuan Lu, Marcus Freitag, Johannes Schmude, Wei Zhang, Xiaodong Cui, Carlo Siebenschuh, Hendrik F. Hamann
Jazyk: angličtina
Rok vydání: 2020
Předmět:
Geospatial analysis
010504 meteorology & atmospheric sciences
Computer science
Geography
Planning and Development

lcsh:G1-922
02 engineering and technology
computer.software_genre
01 natural sciences
remote sensing
0202 electrical engineering
electronic engineering
information engineering

Earth and Planetary Sciences (miscellaneous)
OpenStreetMap data collection
Computers in Earth Sciences
image segmentation
Supervised training
big geospatial databases
0105 earth and related environmental sciences
Remote sensing
Focus (computing)
Artificial neural network
business.industry
geospatial change detection
Image segmentation
Remote sensing (archaeology)
Analytics
020201 artificial intelligence & image processing
business
computer
artificial neural networks
Change detection
lcsh:Geography (General)
Zdroj: ISPRS International Journal of Geo-Information, Vol 9, Iss 427, p 427 (2020)
ISPRS International Journal of Geo-Information
Volume 9
Issue 7
ISSN: 2220-9964
Popis: The growing amount of openly available, meter-scale geospatial vertical aerial imagery and the need of the OpenStreetMap (OSM) project for continuous updates bring the opportunity to use the former to help with the latter, e.g., by leveraging the latest remote sensing data in combination with state-of-the-art computer vision methods to assist the OSM community in labeling work. This article reports our progress to utilize artificial neural networks (ANN) for change detection of OSM data to update the map. Furthermore, we aim at identifying geospatial regions where mappers need to focus on completing the global OSM dataset. Our approach is technically backed by the big geospatial data platform Physical Analytics Integrated Repository and Services (PAIRS). We employ supervised training of deep ANNs from vertical aerial imagery to segment scenes based on OSM map tiles to evaluate the technique quantitatively and qualitatively.
Databáze: OpenAIRE