Loading...
Loading...
Self-driving perception, LiDAR/camera fusion, trajectory prediction, drone perception, robot manipulation
2,016 datasets
AutomatumData provides high-precision movement data of traffic participants extracted from drone recordings. The dataset is suited for the simulation, validation, and development of automated driving algorithms and for traffic analysis. It was last updated on 2026-04-13.
drone_ds is a dataset hosted on Kaggle. The title suggests it contains data related to drones, likely for computer vision or autonomous systems tasks. The dataset's specific content, size, and origin are not detailed in the provided metadata.
A dataset likely containing sensor data for visual odometry, derived from the CARLA autonomous driving simulator version 0.9.16. It was published on the Kaggle platform. The specific data volume, collection method, and author are unknown from the provided metadata.
SoftArmControl is a collection of CSV files containing experimental data for a soft robotic arm. The data includes pose information (yaw and pitch angles) while varying motor positions, and is organized into three datasets for model identification, pose-reaching control, and trajectory-following control. The dataset was created by Carlos Relaño and includes associated Matlab and C++ code for reproducing results from a related paper.
Cloud Lidar System (CLS) data collected by a NASA ER-2 aircraft during the Atlantic Stratocumulus Transition Experiment (ASTEX) in June 1992. The dataset records cloud altitudes, layer boundaries, and geophysical location information to study the transition from stratocumulus to trade cumulus clouds. It was produced by the National Aeronautics and Space Administration as part of the First ISCCP Regional Experiments (FIRE) to improve cloud parameterizations in climate models.
The First ISCCP Regional Experiment (FIRE) Atlantic Stratocumulus Transition Experiment (CIRRUS 2) dataset contains Cloud Lidar System (CLS) data collected by NASA's ER-2 airplane. The instrument recorded cloud altitudes, the number of cloud layers, and boundary heights for up to 5 layers across four calibrated data channels at 532nm and 1064nm wavelengths. Data were collected during the second cirrus intensive field-observation period from November 13 to December 7, 1991, in southeastern Kansas.
Lidar returned signal data from the First ISCCP Regional Experiment, designed to improve cloud and radiation models. The data includes background-subtracted raw signals with a minimum value of 0, a maximum value of 25600, and a scaling factor of 100. Four intensive field-observation periods were conducted between 1986 and 1992, combining satellite, airborne, and surface observations.
Cloud top and ground height calculations from the NASA ER-2 Cloud Lidar System during the First ISCCP Regional Experiment (FIRE) Cirrus field campaign. The data was collected by the National Aeronautics and Space Administration during an intensive observation period from October 13 to November 2, 1986. It was designed to improve understanding of cirrus cloud life cycles and their radiative properties for use in general circulation models.
Four intensive field-observation periods were conducted between 1986 and 1992 as part of the First ISCCP Regional Experiments (FIRE). This data set contains images of cirrus clouds from the second cirrus IFO in southeastern Kansas in November and December 1991. The images consist of lidar backscatter and depolarization ratio data collected by a High Spectral Resolution Lidar (HSRL) in Coffeyville, Kansas.
LIDAR signal data from the First ISCCP Regional Experiment (FIRE) designed to improve cloud and radiation models. The dataset contains raw, background-subtracted signals from four intensive field observation periods between 1986 and 1992, focusing on cirrus and marine stratocumulus clouds. Data was collected by the National Aeronautics and Space Administration using coordinated satellite, airborne, and surface observations.
301 UAV images and ground measurements for 1,291 Valencia orange trees across two rootstock trials. Data includes 305 total files, with images captured under both partially sunny and overcast conditions on May 12, 2021, at a research farm in Fort Pierce, Florida. Ground measurements were collected in 2020 and 2021.
VisDrone is a dataset published on Kaggle. Its title suggests it contains drone-captured imagery, likely for computer vision tasks. The dataset's specific content, size, and creation details require verification after download.
The OWM benchmark comprises 95 curated videos with motion annotations, sourced from Pexels under the Pexels License. It was proposed in the paper 'Envisioning the Future, One Step at a Time' and used to evaluate the MYRIAD model. The dataset was created by CompVis and last updated on 2026-04-10.
A 2012 airborne LiDAR survey covering approximately 75 square miles across the islands of Tutuila, Aunu'u, Ofu, Olosega, Ta'u, and Rose Atoll. The data was collected by GMR Aerial Surveys Inc. for the NOAA Office for Coastal Management, providing high-resolution elevation and intensity data with a nominal post spacing of 1.0 meter. The dataset includes classified points such as ground, water, and noise, and uses multiple vertical datums specific to each island.
Py123D is a unified library for multi-modal autonomous driving data, hosted on GitHub. The project is authored and maintained by kesai-labs under the Apache-2.0 license. It was last updated on 2026-05-19.
VisDrone2019 is a dataset published on Kaggle. The title suggests it contains aerial imagery captured by drones, likely for computer vision tasks. The dataset's specific content, scale, and creation details require verification after download.
KITTI360-mini-projected-LiDAR is a dataset derived from the KITTI 360 benchmark, likely containing a smaller, processed selection of LiDAR point clouds. The data appears to be projected, suggesting a transformation from 3D scans into a different coordinate system or format. Published on Kaggle, its specific size, collection date, and original authors are not detailed in the available metadata.
KITTI360-Left-SemanticsLables is a dataset from Kaggle. The title suggests it contains semantic segmentation labels for images, likely associated with the KITTI or KITTI-360 benchmark for autonomous driving. The dataset's specific content, size, and origin require verification after download.
KITTI360-mini-semanticlabel is a dataset likely containing semantic labels for street scenes. The dataset is published on Kaggle. Columns suggest it may provide annotations for objects in urban environments.
Ontario-based university researchers are listed with their work on connected vehicles, electric powertrains, and new materials. The dataset includes details on institution, researcher name, associated facilities, research areas, and funding. It is provided by the Government of Ontario and was last updated in March 2026.