Road information extraction based purely on remote sensing can be affected by occlusions of the road surface caused by trees, shadows, and buildings. We propose a multimodal fusion method that addresses road extraction and road width estimation by combining aerial imagery, monocular images taken at ground level (street-level), and geospatial data (OpenStreetMap). The method combines semantic segmentation through convolutional neural networks, Voronoi diagram processing, and graph matching.
ROAD EXTRACTION AND ROAD WIDTH ESTIMATION VIA FUSION OF AERIAL OPTICAL IMAGERY, GEOSPATIAL DATA, AND STREET-LEVEL IMAGES
Grillo A.;Moser G.;Serpico S. B.
2021-01-01
Abstract
Road information extraction based purely on remote sensing can be affected by occlusions of the road surface caused by trees, shadows, and buildings. We propose a multimodal fusion method that addresses road extraction and road width estimation by combining aerial imagery, monocular images taken at ground level (street-level), and geospatial data (OpenStreetMap). The method combines semantic segmentation through convolutional neural networks, Voronoi diagram processing, and graph matching.
File in questo prodotto:
| File | Dimensione | Formato | |
|---|---|---|---|
|
21.igarss.vladimir.pdf
accesso chiuso
Tipologia:
Altro materiale allegato
Dimensione
12.76 MB
Formato
Adobe PDF
|
12.76 MB | Adobe PDF | Visualizza/Apri Richiedi una copia |
I documenti in IRIS sono protetti da copyright e tutti i diritti sono riservati, salvo diversa indicazione.
