Loading...
Loading...
Self-driving perception, LiDAR/camera fusion, trajectory prediction, drone perception, robot manipulation
1,662 datasets
A 47-day survey from September 30 to November 17, 2020 collected bathymetry data in the northern Great Barrier Reef and Coral Sea. The dataset contains fifteen geotiff files at resolutions from 4 to 32 meters, produced from processed EM302 multibeam sonar data. It is published by Geoscience Australia with the objective of mapping submarine canyons, drowned reefs, and underwater landslides.
Raw2Event is a paired dataset and benchmark containing Bayer raw, ISP-RGB, and real-event camera data. The data was captured by displaying CIFAR-10 image samples on a screen while a robotic arm with a Raspberry Pi camera and a DAVIS346 event camera followed a fixed circular trajectory. The dataset was created by the author 'raw2event' and was last updated on the Hugging Face platform in May 2026.
A Government of Yukon study describes hundreds of conical mounds formed during the 2008 Little Salmon Lake landslide reactivation and proposes a mechanism for their formation. The analysis includes a preliminary slope stability assessment of the 2007 Mount Steele rock and ice avalanche using discontinuity orientation measurements from an airborne-LiDAR digital elevation model and COLTOP-3D software. Kinematic, surface wedge, and three-dimensional distinct element slope stability analyses were performed.
CMS provides global maps of maximum mangrove canopy height for 2015 at 12-meter resolution. Estimates were derived from TanDEM-X digital surface models, trained and validated using GEDI lidar data, and constrained to Global Mangrove Watch extent maps. The dataset includes GeoTIFF raster maps and CSV files of heights for individual GEDI tiles.
From 17 April to 30 April 2019, NASA conducted a five-flight airborne campaign using the High Altitude Lidar Observatory (HALO) instrument aboard a DC-8 aircraft. The dataset contains aerosol and water vapor profiles and images, collected to validate the European Space Agency's Aeolus satellite mission and demonstrate the performance of airborne wind, water vapor, and aerosol lidar instruments. Flights, totaling 46 hours, were based out of Palmdale, CA and Kona, HI, covering the Eastern Pacific and Southwest U.S.
NASA's Aeolus CalVal-MetNav_DC8 dataset contains GPS-derived meteorological and navigational data from a 2019 airborne campaign. Five DC-8 flights, totaling 46 flight hours, collected data over the Eastern Pacific and Southwest U.S. to validate satellite and airborne lidar wind, water vapor, and aerosol measurements.
An inter-laboratory study evaluated the reproducibility of multi-dimensional spinal loading protocols using lumbar surrogate models. The results demonstrated strong agreement between two distinct biomechanical testing systems, with inter-laboratory range of motion differences of 0.53°–0.55° and peak load differences of 0.92–1.64 Nm. This work by Emma C. Coltoff lays a foundation for future multidimensional testing of complex spine biomechanics.
A dataset of 124 experimental trials on Crown-of-Thorns starfish locomotion and orientation behavior. The data includes individual identification, reproductive phase, seawater conditions, trial results, coral species count, coral mass, and starfish sex. It was authored by Masumi Kamata and last updated on 2026-05-05.
R. P. Karthik published a dataset summarizing UAV-based mango leaf disease data on figshare in May 2026. The dataset is 5.5 KB in size and is available in XLS format under a CC-BY-4.0 license. The row count and column-level details are unknown.
Coastal LiDAR data provides a 0.25-meter resolution contour model for the City of Hobart. This dataset, sourced from the City of Hobart Open Data platform, is available in multiple geospatial formats including GeoJSON and KML. Its cross-platform presence indicates its established use for terrain analysis in the region.
A 3D topographic point cloud representation of territory captured via aerial LiDAR in 2015. The technology recorded up to 400,000 3D points per second, providing detailed ground and surface elevation data. It was sourced from XEOS Imaging Inc. for the Government and Municipalities of Québec.
Table S11 provides a summary of Generalized Linear Mixed Model (GLMM) analysis results for Crown-of-Thorns Starfish (COTS) locomotion, based on a full dataset of 248 observations. The table includes statistical metrics such as effect estimates, standard errors, confidence intervals, Z-values, p-values, and the Akaike Information Criterion (AIC). It was authored by Masumi Kamata and last updated on 2026-04-25.
Pre-Delta-X: L1 UAVSAR Single Look Complex and Interferograms, MRD, LA, USA, 2016 is a Level 1 dataset containing single look complex stack products and co-registered interferograms. The data were collected by NASA's UAVSAR L-band radar on a Gulfstream-III aircraft over the Atchafalaya Basin in Louisiana during October 2016. A single flight line was sampled six times at roughly 30-minute intervals to observe changing water levels.
NASA's Cloud Physics LiDAR (CPL) IMPACTS dataset contains airborne lidar measurements from the ER-2 high-altitude research aircraft. The data, collected from January 15, 2020, to March 2, 2023, supports a three-year field campaign studying snowband formation and microphysics over the U.S. Atlantic Coast. It includes parameters like backscatter coefficient, depolarization ratio, layer heights, and ice water content to improve snowfall prediction models.
Historic Environment Scotland (HES) LiDAR data captured in 2016/17 for eight heritage sites and their immediate landscapes. The data was procured from Blom Aerofilms Ltd and processed to 0.25m resolution. It is delivered in *.laz and GeoTiff formats, including DTM and DSM data.
SAVANT is a model-agnostic reasoning framework that reformulates anomaly detection in autonomous driving as a layered semantic consistency verification. Approximately 10,000 real-world driving images were curated to address the challenge of detecting rare, out-of-distribution semantic anomalies. The dataset, created by Brusnicki, includes structured scene descriptions and multi-modal evaluations.
CALIPSO, launched in 2006, provides calibrated infrared radiance data on a 1 km grid centered on its orbital track to study clouds and aerosols. This Level 1B product contains half-orbit geolocated radiances from the Imaging Infrared Radiometer, part of a joint NASA-CNES mission flying in the A-Train constellation. The data is formatted in HDF files and supports research into Earth's radiation budget and climate.
This dataset maps 0.1429 million km of arterial roads across Iran, featuring AI-derived surface types, widths, and passability scores produced by HeiGIT. Using PlanetScope satellite imagery from 2020 and 2024, the data supplements OpenStreetMap (OSM) segments where surface information is missing for over 53% of the network.
7,000 keyframes of multi-modal data for off-road 3D traversability prediction, collected by autonomous ground vehicles. The dataset includes surround-view imagery from six cameras, 128-channel LiDAR scans, and voxel-level terrain annotations. It was created by harpreetsahota and last updated on 2026-05-29.
Twelve intensive measurement days from July 5 to August 3, 2017, captured ozone and pollutant gradients over the Chesapeake Bay. The Ozone Water-Land Environmental Transition Study (OWLETS-1) campaign used a Sherpa aircraft equipped with the GeoTASO instrument to collect trace gases, greenhouse gases, and navigational data. This dataset supports research on fundamental atmospheric processes at the challenging land-water interface.