Loading...
Loading...
Self-driving perception, LiDAR/camera fusion, trajectory prediction, drone perception, robot manipulation
2,007 datasets
NASA Operation IceBridge campaign data includes spot elevation measurements of Arctic and Antarctic sea ice, Greenland, and Antarctic ice surfaces acquired using the Airborne Topographic Mapper (ATM). The collection also contains lidar energy waveform and surface elevation data from the Land, Vegetation, and Ice Sensor (LVIS) aboard a Global Hawk UAV, and magnetic field readings over Antarctica from a cesium magnetometer. Data were collected as part of NASA-funded aircraft survey campaigns and are hosted on AWS.
A 2-meter resolution raster Digital Surface Model (DSM) produced by the Environment Agency in 2020. The dataset was created by resampling a 1m first return DSM composite, which was itself derived from LIDAR surveys conducted across England between November 2016 and March 2020. The data is available as GeoTiff rasters in 5km tiles, with heights in meters referenced to the Ordnance Survey Newlyn datum.
2024 Surface Runoff Modeling - version 2 provides geospatial data identifying topographic depressions and water flow paths in the Montreal metropolitan region. The Montreal Metropolitan Community produced this mapping based on high-precision 2024 metropolitan lidar surveys. The dataset was updated on the platform on April 1, 2026.
Longitudinal survey data from two panels of Asian, Black, Latino, and Multiracial adults spans the 2024 U.S. presidential contest between Kamala Harris and Donald Trump. The data, authored by Andrew Engelhardt and published in May 2026, was collected to examine the dynamic relationship between partisanship and solidarity between people of color. It likely contains repeated measures of partisanship and solidarity attitudes across multiple survey waves.
Experimental data from 2026 by Jeremy Koob compares six organized guide RNA (ogRNA) and linear sensor designs cloned into RADARS vectors. The dataset contains luciferase activity and mNeon fluorescent protein expression measurements from HEK293FT cells under different ADAR1 and target RNA ENO1 modulation conditions. It is a small, processed dataset (17.6 KB) supporting the selection of an optimal RADAR sensor.
Table S7 contains Generalized Linear Mixed Model (GLMM) data files for Crown-of-Thorns Starfish (COTS) locomotion experiments, with 248 total observations. The dataset was authored by Masumi Kamata and last updated on 2026-04-25. It records individual trials, including environmental conditions, coral mass, and starfish sex and reproductive phase.
5.5 KB of tabular data presents performance metrics for the MSCNet semantic segmentation model. The dataset, authored by Xuewen Feng and uploaded in April 2026, contains results from experiments on the SemanticKITTI, SemanticPOSS, and Pandasets.
MSCNet, a multi-scale LiDAR semantic segmentation method, is evaluated on datasets including SemanticKITTI, SemanticPOSS, and Pandaset. The research by Xuewen Feng, published in April 2026, focuses on improving segmentation accuracy and reducing model complexity for real-time applications. It analyzes the effect of range on view resolution in projected two-dimensional LiDAR data.
Experimental results evaluate a multi-scale LiDAR semantic segmentation network, MSCNet, across three public datasets. The analysis, authored by Xuewen Feng, was last updated in April 2026. The 5.5 KB file contains performance metrics comparing the model's parameters, accuracy, and running time against other methods.
5.5 KB of tabular data from Xuewen Feng, published in April 2026, analyzes hyperparameter impacts on loss functions for LiDAR-based semantic segmentation models. The data supports research on the MSCNet architecture, which was validated on SemanticKITTI, SemanticPOSS, and Pandaset benchmarks. It documents experiments balancing model parameters, accuracy, and computational speed for real-time robotics applications.
Light Detection and Ranging (LIDAR) data collected by the Environment Agency's remote sensing team provides highly detailed terrain models for Scotland. Up to 100,000 ground measurements per second allow for spatial resolutions ranging from 25 centimeters to 2 meters. This dataset is derived from a merged and re-sampled combination of surveys, available as Digital Surface Models (including objects) or Digital Terrain Models (ground only).
Up to 300,000 laser measurements per second are made of the ground, allowing highly detailed terrain models to be generated. This dataset is a composite of the Environment Agency's LIDAR archive, offering Digital Surface and Terrain Models for Scotland at resolutions from 25cm to 2 meters. The data is managed by the Government Digital Service, though the original source is no longer available on the Defra Data Services Platform.
A shapefile dataset from the Environment Agency's archive shows the tile extents used to create a composite LIDAR Digital Surface and Terrain Model for Scotland. The underlying LIDAR data is collected via airborne laser scanning, capturing up to 300,000 measurements per second to generate terrain models at resolutions from 25cm to 2 meters. Data is provided by the Government Digital Service and is accessed via the Scottish Remote Sensing Portal.
A matrix of terrain slopes in degrees, produced from mosaics of digital terrain model images for different years and sectors from 2008 to 2020. The dataset is provided by the Government and Municipalities of Québec and was last updated on the platform in April 2026. It is available in GEOTIF format under a CC-BY-4.0 license.
Etablissement Finess 76 dec2025 MinSolidaritesSante 20260105 is a French administrative dataset listing healthcare establishments. The data originates from the French Ministry of Solidarity and Health and was uploaded to the data.gouv.fr platform by the user Data-Gouv-FR. The dataset was last updated on the Hugging Face platform on May 31, 2026.
Bioclimatic variables retained after multicollinearity screening for Leptanilla argamani and Leptanilla islamica. The dataset includes Pearson correlation values derived from figures in a supplementary analysis. Mohamed Nasser published the data on figshare in May 2026.
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 includes fifteen 4m, 9m, 10m, 16m, and 32m resolution geotiff files produced from Kongsberg EM302 multibeam sonar data. It is published by the Australian Ocean Data Network with permission from Geoscience Australia.
Raw data, codes, and supplementary material for a forthcoming article in Political Research Quarterly. The dataset supports the study 'Women Representing Women: Maternal Health Advocacy and the Limits of Gendered Solidarity' by Andrene Wright-Johnson. It was last updated on 2026-06-19.
Alaska and Yukon's 583,200 km² Fortymile region is covered by modeled lichen ground cover estimates at 30 m resolution for 2000 and 2015, derived using a random forest model with inputs from in-situ plots, aerial surveys, and UAS imagery. The dataset also includes high-resolution (<1 m to 2 m) site-level presence-absence and cover maps from 22 forested and alpine sites surveyed in summer 2017. These maps, produced by ORNL_CLOUD, support analysis of winter forage for nine resident caribou herds.
CAMEX-3 LiDAR Atmospheric Sensing Experiment (LASE) Imagery consists of plotted reflectivity data collected by a NASA DC-8 aircraft-mounted LiDAR. The dataset covers a 16-day period from August 21 to September 5, 1998, during a campaign to study tropical cyclones based out of Florida. Files are provided in GIF format for browse-only access.