Loading...
Loading...
Self-driving perception, LiDAR/camera fusion, trajectory prediction, drone perception, robot manipulation
2,015 datasets
A 2019 lidar survey commissioned by the Scottish Environment Protection Agency (SEPA) covers approximately 1705 km² of the Outer Hebrides. The aerial survey was conducted by Bluesky International Ltd. between June and September, capturing point cloud data at 4 points per square metre. This dataset reflects the 50 cm resolution Digital Surface Model (DSM) produced from that data, processed using the OSGM15 geoid model and OSTN15 transformation.
A 2019 lidar survey covering approximately 1705 km² of the Outer Hebrides, commissioned by the Scottish Environment Protection Agency (SEPA) and flown by Bluesky International Ltd. The point cloud data was captured at 4 points per square metre and processed using the OSGM15 geoid model and OSTN15 transformation. This dataset reflects the resulting 50 cm resolution Digital Terrain Model (DTM).
Provincial LiDAR sensor data acquisition project in Québec produced a Topographic Wetness Index (TWI) from a digital terrain model. The matrix layers indicate water accumulation potential based on slope and upslope contributing area per pixel.
19.0 GB of UAV-derived data from Grenspark Kalmthoutse Heide accompanies a manuscript comparing thermal, correlative, and mechanistic approaches to microclimate modeling. The dataset, authored by Christophe Metsu and last updated in April 2026, includes thermal, multispectral, and LiDAR derivatives aggregated with in-situ microclimate measurements from TOMST TMS4 loggers. This large-scale collection is designed to uncover microclimate patterns in an open ecosystem.
Samer K. Al-Mashharawi's dataset explores the use of Cosmic Ray Neutron Sensor (CRNS) thermal neutron counts to track orchard development. It contains 10 months of continuous CRNS observations from a cherry orchard in southeastern France in 2022, correlated with UAV LiDAR-derived Plant Area Index and satellite vegetation indices. The results show a strong correlation (R² = 0.86) between thermal neutron intensity and canopy structure.
NVIDIA's PhysicalAI-Autonomous-Vehicles dataset contains 1,700 hours of multi-sensor driving data for end-to-end autonomous vehicle research. Collected via automatic sensor methods, it focuses on geographic diversity to support Physical AI development as of early 2026.
Encyclopaedia of Islam, Second Edition is a foundational reference work for Islamic studies. The dataset likely contains the text of the encyclopedia, published on the paperswithcode platform. Specific details on the data's scope, format, and creation are not provided in the available metadata.
MBDD2025 contains 14,471 UAV images of building wall defects. The images are annotated in the VOC format and released under a CC BY 4.0 license. The dataset is hosted on Kaggle.
815 samples across 475 scenes from the nuScenes dataset. The benchmark, created by causaldrivebench, bundles curated causal scene graphs with three types of multiple-choice and open-ended QA tasks. It was last updated on May 7, 2026.
2018 orthophotomosaic of the Waal river area, created from aerial photographs captured during a LIDAR survey for height data. The dataset is provided by the Dutch Ministry of the Interior and Kingdom Relations under a CC0-1.0 license and is available in multiple geospatial and image formats.
An orthophotomosaic mesh created in 2021 from aerial photographs taken during LIDAR recording. The data is provided by the Dutch Ministry of the Interior and Kingdom Relations under a CC0-1.0 license. File formats include JPEG, ZIP, WCS, and WMS.
1,402 square miles of high-resolution topographic LiDAR data were collected for Mobile County, Alabama from January 12-22, 2014. The National Oceanic and Atmospheric Administration provides classified point cloud data and derived Digital Elevation Models. Available classifications include Ground, Water, and Model Key Points, with low vegetation points removed from the delivery.
Álvaro Esteban-Muñoz provides a 1-meter resolution Digital Surface-River Bathymetry Model (DSRBM) for a 5.4 km urban reach of the Duero River in Zamora, Spain, including its 500-year floodplain. The model integrates airborne LiDAR with 33 field-surveyed bathymetric cross-sections and was validated using 3,407 terrestrial and 8,472 bathymetric control points.
Evaluation results compare the performance of 31 distinct methods on the SemanticKITTI test set. The dataset contains results for point-based, voxel-based, image-based, and projection-based semantic segmentation approaches. Xuewen Feng compiled these results, which were last updated in April 2026.
Gabon's Lope National Park and Rabi Forest are mapped in this dataset of three-dimensional forest height profiles. Data was acquired in 2016 during the collaborative AfriSAR airborne campaign involving NASA, ESA, and the Gabonese Space Agency. The profiles are derived from UAVSAR radar data using synthetic aperture radar tomography (TomoSAR) to reveal vertical structure.
A large indica rice diversity panel (>300 accessions) was evaluated across three dry seasons. The dataset includes 45 traits derived from unmanned aerial vehicle (UAV) phenotyping, leaf gas-exchange measurements, stomatal and anatomical traits, and agronomic traits. It was created by Hsiang-Chun Lin and hosted on the IRRI Dataverse, with a last update recorded in May 2026.
161.5 square kilometers of coastal topography and bathymetry for Eastern Lake Superior, collected via airborne lidar. The National Oceanic and Atmospheric Administration produced this tiled raster dataset covering the area from Whitefish Point to Bay Mills, Michigan. The data includes specific grounded land cover classes and falls partially within an EPA Area of Concern.
WorldPop provides gridded population estimates for Iran from 2015 to 2030. The data is available as a 3 arc-second (approximately 100m) resolution GeoTIFF using a Random Forest-based dasymetric redistribution method. This is the 2025 Alpha release version constructed in September 2025.
High Altitude Lidar Observatory (HALO) data was collected onboard the NASA LaRC G-III aircraft during the Arctic Radiation-Cloud-Aerosol-Surface Interaction EXperiment (ARCSIX). The campaign consisted of two deployments from May to June and July to August 2024, based out of Greenland, to study surface radiation and sea ice melt. This dataset is part of a NASA field investigation managed by LARC_CLOUD to validate remote sensing algorithms and model parameterizations in the Arctic.
MARLi lidar data was collected onboard a NASA P-3B aircraft during the 2024 ARCSIX campaign to quantify factors influencing the Arctic summer surface radiation budget and sea ice melt. The campaign involved multiple aircraft and a ground observatory in Greenland across two deployments from May to August 2024. This dataset is part of a NASA field investigation led by LARC_CLOUD to validate remote sensing algorithms and improve model predictions for the Arctic region.