DLR Portal
Home
|
Sitemap
|
Contact
|
Accessibility
Imprint and terms of use
Privacy
Cookies & Tracking
|
Deutsch
You are here:
Home
:
IMF
:
Department: Photogrammetry and Image Analysis
Advanced Search
Earth Observation Center
DFD
IMF
Department: Atmospheric Processors
Department: EO Data Science
Department: Experimental Methods
Department: Photogrammetry and Image Analysis
Team: Projekte und Missionen
Team: 3D Modeling
Team: Hyperspektral Remote Sensing and Traffic Monitoring
Team: Optical Remote Sensing of Water (BA)
Team: Young Researchers Group ARIADNE
Department: SAR Signal Processing
Services
Technology
Applications and Projects
Satellite Data
Media Library
News / Archive
Blogs & Features
Public Datasets
The following public dataset have been created to be used in various research publications. Please quote the specified publications when using the datasets.
DLR HySU (HyperSpectral Unmixing) dataset
The DLR HySU (HyperSpectral Unmixing) dataset provides a publicly available benchmark to assess the performance of spectral unmixing algorithms. The dataset consists of airborne data acquired by a HySpex imaging spectrometer and a 3K RGB camera system over DLR premises at Oberpfaffenhofen, complemented by in-situ spectra recorded with an SVC field spectrometer.
Full article
DLR-SkyScapes: Aerial Semantic Segmentation Dataset for HD-mapping
High-Definition(HD) mapping is in many applications from autonomous driving to infrastructure monitoring, and urban management essential for the understanding of complex urban infrastructure with centimeter-level accuracy. Aerial images provide valuable information over a large area instantaneously; nevertheless, no current dataset captures the complexity of aerial scenes at the level of granularity required by real-world applications. To address this, we introduce SkyScapes, an aerial image dataset with highly-accurate, fine-grained annotations for pixel-level semantic labeling.
Full article
DLR’s Aerial Crowd Dataset (DLR-ACD)
The DLR-ACD dataset is a collection of aerial images for crowd counting and density estimation, as well as for person localization at mass events.
Full article
DLR Multi-class Vehicle Detection and Orientation in Aerial Imagery (DLR-MVDA)
DLR-MVDA is an open aerial image dataset with annotated vehicles. The automatic detection of vehicles from aerial imagery is of interest for various applications such as traffic management, parking surveillance, and urban planning.
Full article
Enhancing Road Maps by Parsing Aerial Images around the World (ERM-PAIW)
In this dataset, we provide the image characteristics used and the source code of the method. With this methodology, freely available worldwide road maps, such as OpenStreetMap, are supplemented and improved by automated analysis of aerial photographs.
Full article
Fine-grained Road Segmentation by Parsing Ground and Aerial Images (HD-Maps)
HD-Maps is a dataset used in our research for proposing a method which enriches road maps by including spatially high-resolution features such as the number and width of lanes, sidewalks, and parking lanes.
Full article
Multi-Sensor Land-Cover Classification (MSLCC)
The MSLCC dataset has been created for multi-sensor land-cover classification, and has been used and published in [1]. It includes multispectral and SAR images acquired by Sentinel-1B and Sentinel-2A for two cities in Germany (Munich and Berlin) and their surrounding areas.
Full article
Copyright © 2023 German Aerospace Center (DLR). All rights reserved.