Loading...
Loading...
Self-driving perception, LiDAR/camera fusion, trajectory prediction, drone perception, robot manipulation
2,016 datasets
Lidar-derived raster data provides the first reflective surface, including treetops, rooftops, and ground features. The dataset is organized into 1 km by 1 km non-overlapping tiles compiled from multiple acquisition projects. It is produced by the Government of Ontario and was last updated in March 2026.
Bathymetry points contain water depth measurements collected across bodies of water in Ontario. Data originates from surveys conducted by the Government of Ontario using echo-sounders with GPS positioning and bathymetric LiDAR. The dataset was last updated in March 2026.
Ontario's bare-earth terrain is represented in this raster dataset derived from classified lidar point clouds. Data is organized into non-overlapping 1-km by 1-km tiles for download. The Government of Ontario compiled this dataset from multiple lidar acquisition projects, with specifications varying by project.
A dynamic image service from the Government of Yukon provides aerial photographs and LiDAR imagery for locations in Yukon, Canada. The data is projected in Yukon Albers equal area and is accessible via the GeoYukon web application.
Approximately 300 km offshore of San Francisco, this dataset contains shipboard windcube LiDAR observations from the Sub-Mesoscale Ocean Dynamics Experiment (S-MODE). It includes data from a pilot campaign in October 2021 and two intensive operating periods in Fall 2022 and Spring 2023. The experiment aims to understand how short-scale ocean dynamics influence vertical exchange of physical and biological variables.
Montreal's Fort Sainte-Hélène and its immediate context are documented in this point cloud dataset. It was created in 2026 by Reina Ortiz, Miquel from drone-acquired images as part of a digital heritage documentation project.
A geospatial index illustrating the extents of LiDAR imagery and data for the Department of Water and Environmental Regulation. Each area is represented by a polygon with attributes detailing coverage, status, and availability. The data is compiled and maintained by the department's Geospatial and Data Services Manager.
August 2023 lidar data covering approximately 161.5 square kilometers from Whitefish Point to Bay Mills, MI in Eastern Lake Superior. These processed Classified LAS files are formatted to 983 individual 500 m x 500 m tiles. The data was collected by the National Oceanic and Atmospheric Administration and calibrated using 4 ground control points.
Humanitarian funding records for the Islamic Republic of Iran are provided by the IFRC, covering both Emergency Appeals and Disaster Response Emergency Fund (DREF) allocations. These records from the world's largest humanitarian network track financial requests for complex disasters and smaller-scale emergencies as of March 2026.
A preview demonstration of a dataset for orchard mapping across seasons, accompanying a paper slated for IEEE Robotics and Automation Letters in 2026. The dataset is authored by foxmirko and was last updated on April 29, 2026. The complete dataset is scheduled for future release.
CosFly-Track is a pre-release open-source dataset for UAV visual tracking via multi-constraint trajectory optimization. The dataset contains simulated UAV visual tracking trajectories for target tracking and waypoint prediction. It was created by AutelRobotics and a filtered local snapshot was released on HuggingFace in May 2026.
DC3_AircraftRemoteSensing_DIAL_DC8_Data are remotely sensed data collected by the Differential Absorption Lidar (DIAL) onboard the DC-8 aircraft during the Deep Convective Clouds and Chemistry (DC3) field campaign. The campaign was conducted from May to June 2012 with a base in Salina, Kansas, and observations in Colorado, Texas, Oklahoma, and Alabama. The National Aeronautics and Space Administration (NASA) produced this dataset to investigate storm dynamics, lightning, and the impact of deep convection on upper tropospheric chemistry.
Yu-Yun Zhang's supplementary file contains data from a 12-month prospective longitudinal study of 443 adults with type 2 diabetes mellitus. The study measured diabetes distress, demographics, diabetes characteristics, lifestyles, and psychological factors at baseline and follow-ups to identify five distinct distress trajectories. The dataset was last updated on 2026-03-18 and is shared under a CC-BY-4.0 license.
SnowEx20 Grand Mesa IOP QSI Lidar Snow Depth Data V001 contains rasterized snow depth maps derived from lidar point cloud data. The data was collected from Grand Mesa, Colorado during the SnowEx20 campaign and served as input for deriving snow water equivalent and snow density products. This dataset is produced by the National Aeronautics and Space Administration.
Raw 4K drone footage intended for environmental monitoring applications. The dataset's author, organization, and specific collection details are not provided. The last update date for this dataset is unknown.
Frames extracted at 1 frame per second from a drone survey of dense forestry. The dataset is intended for environmental computer vision applications. The author, organization, and specific collection details are not provided.
Extracted frames from a 4K drone survey, captured at 1 frame per second, intended for aquatic terrain analysis. The dataset is hosted on Kaggle and includes platform tags for image, aquatic terrain, water bodies, and geospatial data. Details on the specific water bodies, collection dates, and dataset size are not provided in the available metadata.
Raw 4K drone footage for urban infrastructure analysis. The dataset is hosted on Kaggle, but the author, organization, and specific collection details are not provided. The last update date and data volume are unknown.
Climate TRACE provides greenhouse gas and air pollutant emission estimates for Iran, featuring annual country-level data since 2015 and monthly source-level data since 2021. The dataset covers specific sub-sectors and gases, derived from a global inventory of over 2.7 million emission sources. It includes confidence scores for monthly estimates and ownership details for specific assets where available.
47,098 time-synchronized frames combine trichromatic linear polarization, co-boresighted RGB, 128-channel LiDAR, and RTK-GNSS/INS data. The PRISM dataset is a benchmark for polarimetric road-surface sensing and measurement, captured from an in-vehicle sensor rig. It was submitted anonymously to the NeurIPS 2026 Evaluations & Datasets Track.