Loading...
Loading...
Self-driving perception, LiDAR/camera fusion, trajectory prediction, drone perception, robot manipulation
1,672 datasets
DexCanvas is a large-scale hybrid dataset for robotic hand-object interaction research, combining real human demonstrations with physics-validated simulation data. The v0.1 test release contains approximately 30 million multi-view RGB-D frames, representing about 70 hours of dexterous hand-object interaction. It was created by DEXROBOT and last updated on February 2, 2026.
Replication materials for a study analyzing drivers of European solidarity, published in European Union Politics. It includes the PSDE dataset and analysis scripts for replicating the full study findings. The replication package requires separate download of GLES data from external sources for a complete analysis.
Responses from 840 participants in Amsterdam, Den Haag, Rotterdam, and Utrecht to a survey with 22 questions. The survey includes demographic details and a choice experiment with 9 questions, each presenting 5 transport modes. The data was collected by Konstanze Winter.
The KAZR-ARSCL VAP merges corrected radar moments from the Ka-band ARM Zenith Radar (KAZR) with cloud observations from a micropulse lidar, ceilometer, soundings, rain gauge, and microwave radiometer. It produces two data streams, one with cloud boundaries and another with best-estimate time-height fields of radar moments. This specific DOI provides the all-inclusive data stream containing all variables produced by the VAP, authored by Karen Johnson.
A dataset derived from the NuScenes autonomous driving dataset, focusing on reasoning tasks. It was uploaded by user 'tejeshbhalladhanyog' to Hugging Face and last updated on April 2, 2026. The dataset's specific content and scale are not detailed in the provided metadata.
Sobhi Mahmassani's course materials aim to show the alignment between international law principles and Islamic doctrine. The dataset likely contains lecture notes or textual content from a course presentation on general principles. The data is sourced from the paperswithcode platform and has a closed license.
United Nations Cartographic Section provides a country profile map for the Islamic Republic of Iran in PDF format. The map is released by the United Nations and hosted on the NASA Earthdata platform. The specific creation date and spatial detail are not provided in the available metadata.
UAVSAR repeat pass interferometry scenes provide ground-projected amplitude data for geophysical analysis. The data is hosted by NASA Earthdata and originates from the Alaska Satellite Facility (ASF). The specific temporal and geographic coverage, row count, and file formats are not detailed in the available metadata.
UAVSAR_INSAR_INTERFEROGRAM_GRD is a dataset of ground-projected scenes from NASA's UAVSAR platform using repeat-pass interferometry. The data is hosted by the Alaska Satellite Facility (ASF) on the NASA Earthdata platform. The specific temporal and spatial coverage, file formats, and data volume are not detailed in the provided metadata.
NASA airborne campaigns collected this set of geotagged images using Digital Mapping Cameras mounted alongside the Land, Vegetation, and Ice Sensor (LVIS) lidar altimeter. The data is provided by the NSIDC_CPRD organization. The exact temporal coverage, geographic scope, and volume of images are not specified in the provided metadata.
A processed version of the nuScenes dataset, a key benchmark for autonomous driving. The title suggests it may contain sensor data like images and LiDAR point clouds, aggregated or downsampled with a stride of 4. It is hosted on Kaggle, but the specific processing steps and content are not detailed in the available metadata.
A dataset titled 'tinyperson_visdrone_widerperson' is hosted on Kaggle. The title suggests it is likely a benchmark collection for object detection, potentially combining or relating to the TinyPerson, VisDrone, and WiderPerson datasets. Its specific content, size, and creation details are not provided in the available metadata.
UAV-SEAD provides real-world multivariate time-series telemetry for state estimation anomaly detection in Unmanned Aerial Vehicles (UAVs), released by Aykut Kabaoglu and Sanem Sariel in 2026. The data supports research into Fault Detection and Identification (FDI) specifically for PX4-based flight systems.
Malaysian Borneo canopy height data contains 36,655 repeated measurements from airborne LiDAR before and after the 2015-16 El Niño event. The dataset includes coordinates for spatial analysis and features like Topographic Position Index and distance from oil palm plantations to study environmental effects. It was collected in November 2014 and April 2016 across a human-modified tropical landscape.
13 January 2023 terrestrial LiDAR scans capture two overlapping 3D point clouds for a nearly 18,000 m² wooded area in Nottinghamshire, UK. The dataset provides forest structure measurements for trees infested with common ivy (Hedera helix) and a non-infested sample, collected for a study on associated soil organisms.
A model of woody linear features on field boundaries in England, derived from Environment Agency lidar captured between 2016 and 2021. The dataset maps the extent and height class of hedgerows, tree lines, and thickets, excluding urban areas, woodlands, open water, and mountain terrain.
78,000 vegetation outlines and tree tops above 1 meter in height, processed from LiDAR data. The data were created for Cornwall and Devon as part of the Tellus South West project during July and August 2013.
2010 global raster datasets of forest biomass, comprising four layers: growing stock volume (GSV), above-ground biomass (AGB), and their respective per-pixel uncertainty estimates. The data was produced by Maurizio Santoro using spaceborne SAR, optical, LiDAR, and auxiliary datasets with multiple estimation procedures. GSV and AGB data are available as 40-degree by 40-degree tiles.
LiDAR geospatial data were collected on approximately 60,000 acres of White River National Wildlife Refuge in late fall-winter 2016-17. The data, provided by the Department of the Interior, are delivered as geo-referenced files in zipped folders. Associated metadata is described as fully compliant.
An aerial imagery dataset focused on detecting vehicles in urban environments. The dataset is described as high-precision and is hosted on Kaggle. The author, organization, and specific collection details are unknown.