Loading...
Loading...
Self-driving perception, LiDAR/camera fusion, trajectory prediction, drone perception, robot manipulation
2,000 datasets
Two Saildrone uncrewed surface vehicles collected surface ocean and atmospheric data in the Bering and Chukchi Seas from 6 July to 20 September 2021. The 76-day mission focused on measuring air-sea covariance near the sea ice edge and validating satellite sea-surface temperature measurements. The dataset includes measurements of air temperature, wind, waves, seawater temperature and salinity, chlorophyll fluorescence, dissolved oxygen, and near-surface currents.
Northern Great Barrier Reef bathymetry data acquired over 47 days in 2020 by the RV Falkor. The survey used Kongsberg EM302 multibeam sonar to map the Cape York Peninsula shelf edge, the Swain underwater landslide, and reefs in the eastern Coral Sea Marine Park. This dataset contains fifteen geotiff files at resolutions from 4m to 32m, published by Geoscience Australia.
A dataset of 85 soybean genotypes evaluated under irrigated and rainfed conditions in Stuttgart, Arkansas from 2023 to 2025. It compares visual canopy wilting scores with UAV-derived multispectral vegetation indices and their correlation with grain yield. The data was authored by Popat Shivaji Pawar and shared under a CC-BY-4.0 license.
Popat Shivaji Pawar's dataset compares UAV-based multispectral phenotyping against visual canopy wilting scores for evaluating soybean drought tolerance and yield retention. The data covers 85 genotypes from breeding programs in Arkansas, Missouri, Kansas, and North Carolina, tested under irrigated and rainfed conditions in Stuttgart, Arkansas from 2023 to 2025. UAV-derived vegetation indices showed significant correlations with yield, while visual scores showed weak associations.
85 soybean genotypes from multiple U.S. breeding programs were evaluated under irrigated and rainfed conditions from 2023 to 2025. Unmanned Aerial Vehicle (UAV)-based multispectral imagery captured vegetation indices at the R4/R5 growth stage, which showed significant correlations with yield under rainfed conditions. The dataset, authored by Popat Shivaji Pawar and shared under a CC-BY-4.0 license, compares these quantitative UAV metrics against traditional visual canopy wilting scores.
VineLiDAR is a dataset hosted by Voxel51 on Hugging Face. It contains 10 samples and is designed to be loaded and used with the FiftyOne data management platform. The dataset was last updated on July 10, 2026.
Crown-BERT achieved overall accuracies of 83.1% to 90.8% on three UAV datasets for classifying individual tree species. The lightweight deep learning framework, proposed by Xin-Bo Wang, uses fused hyperspectral and LiDAR data and was last updated in May 2026. It introduces crown-morphology-aware techniques like dynamic crown masking and self-supervised pre-training to improve accuracy and reduce manual annotation.
A handbook published by the NSW Government, last updated on 2026-06-26. It provides essential information for learner drivers and other road users on driving rules, legal responsibilities, and safe driving behavior. The content is available as a PDF document.
One of five storyboards created by Kilu von Prince for the MelaTAMP project at Humboldt-Universität zu Berlin. The package contains 20 PDF picture files, a compiled storyboard with English subtitles, and source files in SVG and TeX formats. It is published under a CC BY 4.0 license and targets epistemic possibilities and indicative conditionals.
A 22.2 KB dataset quantifying transverse oscillations of the soleus muscle in response to impact forces during human locomotion. The data, shared by Emma Tole under a CC-0 license, was collected using 2D ultrasound imaging during walking and running at various speeds. It was last updated on 2026-05-28.
A methodology for generating damage maps from orthoimages of building facades captured by UAVs. The study applied dense stereo matching and the Tyche (2015) software to map and quantify staining defects, with results also classified qualitatively. The work was authored by Carlos Mariano Melo Júnior and is available via the paperswithcode platform.
Turbulence dissipation rate estimates derived from Doppler lidar measurements during the 2018 LAPSE-RATE field campaign. Data originates from University of Colorado Windcube v1 and University of Oklahoma Halo Streamline lidars deployed in Colorado's San Luis Valley from July 14-21, 2018. The dataset includes intercomparison data from co-located instruments and uses a standard missing data flag.
2020 predictions of aboveground biomass density for Australia, generated by NASA's Global Ecosystem Dynamics Investigation (GEDI) mission. Data were collected using a full-waveform LIDAR instrument on the International Space Station and include both Level 4A (~25 m footprints) and gridded Level 4B (1 km x 1 km) Version 2 products.
April 1, 2015 to present, this dataset provides global, gridded sea surface salinity measurements from NASA's Soil Moisture Active Passive (SMAP) satellite. The Level 3, 8-day running mean product includes both 40KM and 70KM resolution data, with the 70KM variable recommended for open ocean use due to lower noise. It incorporates enhancements like improved land correction, a revised sea-ice mask, and estimated salinity uncertainty.
663,763 species occurrence records from the Global Biodiversity Information Facility (GBIF) matching a specific query for Colombia. The data was compiled by GBIF.Org User and aggregates records from 579 constituent datasets, focusing on the Amazonas, Putumayo, Guainía, Guaviare, Caquetá, and Vaupés departments. Records are filtered to exclude those with a 'Country coordinate mismatch' issue.
Dronescape integrates uncrewed aerial vehicle remote sensing into Australia's terrestrial ecosystem monitoring framework. The project has surveyed over 120 plots across multiple bioregions as of 2025, with each plot covering approximately 90,000 m². It generates analysis-ready products including orthomosaics, reflectance maps, vegetation indices, and 3D point clouds from RGB, 10-band multispectral, and LiDAR sensors.
A 5.5 KB Excel file containing Denavit-Hartenberg (D-H) parameters for a 6-degree-of-freedom Cartesian coordinate robotic arm used in mine pipeline installation. The dataset supports a study proposing an improved trajectory planning algorithm (AS-DTRRT) to reduce runtime by up to 20.22% and path length by up to 21.17% compared to other methods. Author Zhixiang Liu uploaded it to figshare under a CC-BY-4.0 license, with a last update timestamp of 2026-05-22.
900 lactating Holstein cows were evaluated quarterly over two years for body condition and locomotion scores by trained veterinarians. The dataset likely contains longitudinal records of these subjective health assessments from a semi-extensive breeding regime. A negative correlation (r=-0.57) was found between body condition score and locomotion score during the study period.
Terrestrial LiDAR data captures detailed vegetation structural information at the Alice Mulga SuperSite on Pine Hill Cattle Station in the Northern Territory, Australia. The dataset is part of a broader collection from all TERN SuperSites, aimed at achieving a standardized and highly detailed capture of 3D vegetation structure across Australia. It was last updated on 2026-06-13.
New England region data provides 30-meter gridded estimates of aboveground biomass density, forest canopy height, and tree canopy coverage for the nominal year 2015. The dataset, produced by NASA, integrates high-resolution leaf-off LiDAR data from 2010-2015, agricultural imagery, and U.S. Forest Service plot measurements. It supports the development of a cohesive forest carbon accounting system at national and international scales.