Loading...
Loading...
Self-driving perception, LiDAR/camera fusion, trajectory prediction, drone perception, robot manipulation
2,016 datasets
A dataset hosted on Hugging Face by fengyi233, last updated on 2026-04-07. The description suggests it contains synthetic driving scene data from the CARLA simulator, organized into sequences with camera images, LiDAR data, and occupancy grids for foreground and background actors.
Road pothole imagery likely collected via drone for computer vision tasks. The dataset is hosted on Kaggle, a platform for data science competitions and projects. Specific details regarding the collection date, author, and dataset size are not provided in the available metadata.
Daly City, California experienced landslides in December 2003 and January 2007, sending debris up to 290 meters downhill and 90 meters into the ocean. The U.S. Geological Survey collected high-resolution terrestrial LIDAR data to map these events. The dataset includes downloadable contour data, images, and metadata, along with geometric and volumetric measurements.
2021 terrestrial LiDAR data captures detailed 3D vegetation structure at the Calperum Mallee SuperSite in South Australia. The dataset is part of a standardised national collection by the Terrestrial Ecosystem Research Network aimed at understanding vegetation dynamics and ecosystem function.
A geospatial habitat model for Whitebark Pine in Alberta, created from LiDAR data with 1-square-meter pixel resolution. The model incorporates variables like elevation, aspect, slope, landscape mesotopography, and canopy height. It was produced under contract for Alberta Forestry and Parks in 2015-2016, with accuracy assessed against field observations.
Worldengine is an open-source, production-validated framework for Physical AI post-training in autonomous driving. It is a joint effort by OpenDriveLab at The University of Hong Kong, Huawei Inc., and the Shanghai Innovation Institute. The dataset page was last updated on 2026-04 10.
NASA's Cloud-Aerosol Transport System (CATS) instrument on the International Space Station collected calibrated lidar profile data from February 10, 2015 to March 21, 2015. The instrument orbited between approximately 230 and 270 miles above Earth's surface, providing vertical profiles at three wavelengths. This Level 1B data product enabled the first study of diurnal changes in cloud and aerosol effects from space.
A compact subset of the KITTI dataset, likely focused on depth estimation with temporal consistency constraints. It is hosted on Kaggle, but detailed metadata such as the number of samples, specific file formats, and the original author are not provided. The dataset's content and structure must be verified after download.
Synoptic measurements from the Chukchi and Beaufort Seas in July 2014 captured the first airborne lidar observations of subsurface phytoplankton layers in the Arctic Ocean's Marginal Ice Zone. The Fish Lidar, Oceanic, Experimental (FLOE) system, mounted on a NOAA Twin Otter aircraft, simultaneously measured layer characteristics and fractional ice cover. These thin, stratified layers, not captured by satellite data, influence primary productivity, fisheries recruitment, and carbon export.
Thermal-UAV is a dataset for cross-modal thermal geo-localization, designed for Unmanned Aerial Vehicles in GNSS-denied environments. It addresses the modality gap between thermal queries and visible-light satellite imagery. The dataset was created by FloralHercules and was last updated in April 2026.
HI_NOAAMauiOahu_3_B20 is a QL1 lidar dataset covering approximately 306 square miles on the eastern side of Hawaii's Big Island. The National Oceanic and Atmospheric Administration (NOAA) and the USGS managed the project, with data collected between February 14 and March 15, 2023. The processed data is delivered as 3,450 individual 500-meter tiles in LAZ 1.4 format, collected at an aggregate nominal pulse spacing of 0.35 meters.
2022-2023 NOAA-USGS lidar collection covers approximately 1,428 square miles across Kahoolawe, Lanai, Maui, Molokai, and Oahu. Data is delivered as processed LAZ 1.4 files formatted to 16,760 individual 500-meter tiles, collected at an aggregate nominal pulse spacing of 0.35 meters and 8 points per square meter. The project was conducted by Woolpert and the USGS, with specifications based on the National Geospatial Program Lidar Base Specification Version 2.1.
Integrated Drone Dataset (IDD) is a combination of VDD, UDD, and UAVid datasets, re-annotated to a common standard. It was published in the Journal of Visual Communication and Image Representation, with a related paper available on arXiv. The dataset was last updated on the Hugging Face platform on 2026-04-08.
23 sets of aerial lidar data collected in Texas between 2014 and 2018 were processed into rasters of tree canopy heights, expressed in meters. The data were created by the Department of the Interior and were used to model habitat for the golden-cheeked warbler. The dataset includes files in XML, JSONLD, and ZIP formats.
Kitti_BEV is a dataset likely containing sensor data for autonomous vehicle perception. The dataset is hosted on Kaggle, but its specific contents, such as the number of samples or collection dates, are not detailed in the available metadata. The author and organization responsible for its creation are unknown.
Fifteen geotiff files provide 4m to 32m resolution bathymetric data from a 47-day marine survey aboard the RV Falkor. The dataset, published by Geoscience Australia, maps submarine canyons, drowned reefs, and seabed features in the frontier Cape York Peninsula region and the Swain slide underwater landslide.
A 10-year cross-sectional analysis of U.S. military Unmanned Aerial Vehicle (UAV) mishaps. The study reviewed 221 Class A-C mishap reports, finding 133 (60.2%) were human-related. Human factors were coded using the Human Factors Analysis and Classification System (HFACS), with statistical models identifying different predictors of unsafe acts across Air Force, Army, and Navy services.
The Altus II Unmanned Aerial Vehicle (Altus II UAV) system recorded aircraft and mechanical data during the Altus Cumulus Electrification Study (ACES) based at the Naval Air Facility Key West in Florida. ACES aimed to provide observations of cloud electrification and validate satellite lightning measurements. The National Aeronautics and Space Administration (NASA) made the data available from July 10 through August 30, 2002.
Drone_Dataset is a collection of data related to unmanned aerial vehicles, sourced from the Kaggle platform. Its specific content, such as imagery, sensor readings, or flight logs, must be verified after download. The dataset's author, size, and other metadata are currently unknown.
VTUAV_V1 is a dataset published on Kaggle, likely containing visual data related to Unmanned Aerial Vehicles. Its specific content, size, and collection details are not provided in the available metadata. The dataset's author, organization, and license information are also unknown.