Loading...
Loading...
Self-driving perception, LiDAR/camera fusion, trajectory prediction, drone perception, robot manipulation
1,981 datasets
Airborne LIDAR surveys provide high-resolution elevation data for river basins in Northern Ireland. The dataset includes both Digital Terrain Models (DTM) and Digital Surface Models (DSM), typically delivered as 1km x 1km tiles with a 1m x 1m grid resolution. Data from 2009 and 2010 also contains the underlying point cloud files with a 0.2m point spacing.
March 19, 2019 from 7 a.m. to 8 a.m. is the temporal coverage for this collection of 5,696 raw drone images (2,848 RGB and 2,848 thermal) of building rooftops in Karlsruhe, Germany. The data was recorded by J. Kahn of the Karlsruhe Institute of Technology using a DJI M600 drone equipped with RGB and FLIR-XT2 thermal cameras. Images show six large building blocks with high overlap, capturing each building from multiple angles.
Rasterized canopy top height models at 10m ground sampling distance derived from airborne LIDAR. The data was created by Nico Lang of ETH Zurich to be comparable to GEDI satellite canopy heights, using NASA's LVIS campaigns and European small-footprint ALS data. More details are available in the associated Nature Ecology & Evolution paper from 2023.
A 10-band multispectral orthomosaic raster of Cockatoo Hills, Tasmania, collected via an Uncrewed Aerial System. The imagery was captured using a DJI Matrice 300 RTK with a Zenmuse P1 RGB camera and a Micasense RedEdge-MX Dual sensor during a flight on June 19, 2026. The Terrestrial Ecosystem Research Network processed the data to produce a cloud-optimized GeoTIFF with 5-centimeter resolution and relative reflectance values.
A 5-band multispectral orthomosaic with 5 cm resolution was generated from UAV imagery collected for the TERN Drone project. The Terrestrial Ecosystem Research Network's Data Discovery platform published this cloud-optimised GeoTIFF, which contains relative reflectance values for Blue, Green, Red, Red Edge, and NIR bands. Flights were conducted at 80m altitude using a DJI Matrice 300 RTK equipped with a Zenmuse P1 camera and a Micasense RedEdge-MX sensor.
LiDAR point cloud data covering the Australian Capital Territory and Queanbeyan, collected in 2015. The dataset provides high-resolution elevation information with a density of 8 points per square meter in city centers and 4 points per square meter elsewhere. It was published by the ACT Government Geospatial Data Catalogue (ACTmapi) and is delivered in LAS 1.4 format.
Northern Ireland's entire coastline is covered by this natural colour orthophotography dataset, extending approximately 200 meters landward from the high water mark and including the intertidal zone. The imagery was captured in 2021 as part of a 3D coastal survey and has been ortho-rectified to remove geometric distortion, providing a uniform 10cm ground resolution. This dataset offers a detailed, geometrically accurate visual baseline for coastal analysis.
TERN and Airborne Research Australia collected airborne hyperspectral, thermal, and LiDAR data for 5 km x 5 km field sites across Australia. The data includes 0.5m resolution hyperspectral imagery and 0.3m resolution LiDAR point clouds, captured using a Riegl Q560 and SPECIM scanners mounted on an ECO-Dimona aircraft. Supplementary field measurements for calibration and validation, such as ground control targets and Sun-photometer observations, are also provided.
On March 19, 2019, a drone flight captured 926 aligned RGB and thermal images of building rooftops in Karlsruhe, Germany. The dataset includes 6,927 polygon annotations identifying thermal bridges, with each structure annotated multiple times from different angles due to high image overlap. It also contains a height map, providing a multimodal view for analyzing building heat loss.
10 consumer and prosumer drone models were recorded in an isolated anechoic chamber at Tampere University. The database contains IQ-baseband recordings of radio-control and video signals at 2.44 GHz and 5.8 GHz center frequencies, with sampling rates of 120 MHz and 200 MHz respectively. Recordings were made with the drone on a turntable and the controller nearby, capturing complete hopping sequences where possible.
2021 airborne LiDAR data provides a precise and accurate Digital Surface Model of the Northern Ireland coastline. The survey captured the intertidal zone and extended approximately 200 meters landward of the high-water mark. This dataset represents the topographic surface, including buildings and vegetation, for the NI 3D Coastal Survey.
Terrestrial Ecosystem Research Network's TERN Drone project field trial data includes an RGB orthomosaic generated from UAV imagery. The imagery was collected by a DJI Matrice 300 RTK with a Zenmuse P1 camera at 80 m flying height between 10:26 am and 10:47 am AEDT. The final orthomosaic has a 1 cm resolution and uses the EPSG 7855 coordinate reference system.
A 2021 airborne LiDAR survey captured the complete Northern Ireland coastline, extending approximately 200 meters landward from the high-water mark and including the intertidal zone. The dataset provides a precise Digital Surface Model (DSM) representing the first-return elevation of all surface features. This data documents current coastal morphology for environmental monitoring and planning.
2021 saw a complete airborne LiDAR survey of the Northern Ireland coastline, commissioned as part of the NI 3D Coastal Survey. The resulting Digital Terrain Model provides precise data on current coastal morphology, covering the intertidal area and extending approximately 200 meters landward of the high-water mark. This dataset is available on multiple open data platforms under a permissive license.
A module from the Davis Logic V2 architecture, last updated June 2, 2026, by Jamie Davis. It provides a runtime-adaptive sliding-window filtering matrix and sensor fault isolation engine for real-time data streams. The module is implemented in freestanding, zero-heap C++11 and is designed for safety-critical processing in harsh environments.
A photovoltaic dataset from satellite and aerial imagery includes three groups of PV samples collected at spatial resolutions of 0.8m, 0.3m, and 0.1m. The dataset, authored by Jiang Hou of the Chinese Academy of Sciences, categorizes ground and rooftop samples by background land use and roof type. Data documentation is referenced in a preprint on the Copernicus ESSD platform.
TRANSSET is a dataset of 4,704 high-resolution (1024×1024) drone-captured images for traffic detection and vehicle classification. It contains 21,661 annotated vehicle instances across 8 classes, extracted from 4K video footage taken at two highway locations in North Carolina, USA. The dataset includes annotations in PASCAL VOC XML, YOLO TXT, and COCO JSON formats.
Terrain and surface elevation models for river basins derived from airborne LIDAR surveys. Data is provided in 1km x 1km tiles containing a 1m x 1m grid of elevation points, with some areas also offering the original 0.2m spaced point cloud files. This dataset is provided by OpenDataNI under the Open Government Data Licence and was last updated on 2026-07-08.
Terrain and surface elevation models for river basins derived from airborne LIDAR survey systems. The data consists of Digital Terrain Models and Digital Surface Models provided in 1km x 1km tiles with elevations on a 1m x 1m grid. It was produced by OpenDataNI and the data was acquired in 2009 and 2010.
2004 airborne LIDAR surveys provide Digital Terrain and Surface Models (DTMs and DSMs) for river basins. The data, provided by OpenDataNI, consists of 1km x 1km tiles with elevations on a 1m x 1m grid. Some data from 2009 and 2010 also includes the original Point Cloud files with a 0.2m irregular grid.