Loading...
Loading...
Self-driving perception, LiDAR/camera fusion, trajectory prediction, drone perception, robot manipulation
1,662 datasets
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 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.
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 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.
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.
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.
EgoSPT is a dataset of 11,515 episodes of robot manipulation trajectories collected from three scenes. It contains egocentric RGB videos aligned with end-effector poses and gripper widths for vision-conditioned trajectory prediction. The dataset was created by JackYFL233 and is hosted on Hugging Face.
California forests are analyzed in this dataset providing LiDAR-derived aboveground biomass estimates and uncertainty from 53 airborne surveys conducted between 2005 and 2014. The data was created by performing individual tree crown detection and applying a remote sensing aware allometric equation, with results available per-tree and in gridded formats. The dataset is provided by ORNL_CLOUD and includes the canopy height models used for the estimation.
A 2018-updated spatial dataset shows the modelled extent of Old Growth Forest in Victoria, Australia. It is based on the MOG2009 model, with reductions for disturbances from fire and timber harvesting up to July 2018. The dataset is provided by the Department of Energy, Environment and Climate Action and is licensed under CC-BY-4.0.
From April 1, 2015 to present, this dataset provides monthly averaged, globally gridded sea surface salinity (SSS) measurements from NASA's Soil Moisture Active Passive (SMAP) satellite. It is the validated Version 4.0 Level 3 product, processed by Remote Sensing Systems (RSS) with a one-month latency and includes both 40KM and 70KM resolution SSS fields along with estimated uncertainty. The data is intended for monitoring ocean salinity patterns, studying freshwater fluxes, and validating ocean circulation models.
Four years of UAV-LiDAR data (2022–2025) were used to evaluate four individual tree segmentation algorithms at a coastal Douglas-fir genetic trial site near Jordan River, Vancouver Island. The dataset includes normalized point clouds with a density of approximately 100 points/m² and performance metrics assessed against a field-referenced dataset of 1,526 live trees. The study was authored by Gayatri Deepak Kulkarni and harvested from Borealis Dataverse.
A 2026 study by Kate Mcintyre produced a map of individual Garry oak tree crowns across the Greater Victoria region. The dataset was created using an automated workflow that fused airborne laser scanning and four-band multispectral imagery to train a Random Forest classifier. The model achieved an overall accuracy of 89.7% and a specificity of 96.2%.