Images for Inland navigation and vessel optimal path planning
- Description:
- Laboratoire d'Automatique et de Robotique interactive, Université du Québec à Chicoutimi, Québec, Canada LAR.i - UQAC, 02 Feb. 2024
855 satellite images and their ground truth masks. The original satellite images could be accessed by email.
Manual acquisition of 60 unlabelled aerial satellite images with varying dimensions (area ranging from 500 meters to 5 kilometers) from Google Maps. A manual segmentation is executed into three labels: water, land, and obstacle.
Parametric augmentation pipeline:
-random cropping,
-horizontal and vertical flipping,
-rotation,
-brightness and contrast,
-Contrast Limited Adaptive Histogram Equalization (CLAHE) and
-Grid Distortion, or Optical Distortion. - Otis, Martin J.-D. and
- Contributor(s):
- Otis, Martin
- Source Repository:
- Dataverse de l'Université du Québec à Chicoutimi
- Series:
- Martin Otis Dataverse // Laboratoire d’Automatique et de Robotique interactive (LAR.i) Dataverse
- Publisher(s):
- Borealis
- Access:
- Public
- URL:
- https://doi.org/10.5683/SP3/KZNEOU
- Publication date:
- 2024-04-22
- Subjects:
- Keywords:
- Identifier:
- https://doi.org/10.5683/SP3/KZNEOU
Geospatial information
There is no geographic information available for this record.
Select geospatial feature(s) to view on map: