Loading...
Loading...
Self-driving perception, LiDAR/camera fusion, trajectory prediction, drone perception, robot manipulation
1,676 datasets
A source of the data and statistical code necessary to replicate the findings of the study 'Does Islamist Terrorism Still Affect Political Attitudes?', forthcoming in the European Journal of Political Research. It was authored by Micha Germann and hosted by Harvard Dataverse.
July 12-14, 2013 lidar elevation data for Dauphin Island, Alabama, and Chandeleur, Stake, Grand Gosier and Breton Islands, Louisiana. The dataset includes classified point cloud data in LAS format and bare earth digital elevation models in IMG format, collected by Photo Science, Inc. under contract for the U.S. Geological Survey. The survey was acquired to document short- and long-term changes in barrier island systems.
7 signal categories comprising RF recordings from 6 consumer-grade drone models and background noise. The data is provided in dual formats, featuring both raw IQ-data and processed spectrograms for signal analysis.
Two categories of data representing drones and birds. It facilitates the training of models to distinguish between mechanical unmanned aerial vehicles and biological avian species.
5-class UAV maritime image dataset for Search and Rescue (SAR) object detection. The collection provides aerial imagery specifically labeled for identifying targets in marine environments.
Two categories of data labeled as 'Bird' and 'Drone' for binary classification. The dataset focuses on distinguishing natural avian flight from synthetic drone movement in sky-based environments.
RFUAV contains 1.3 TB of raw radio-frequency (RF) signal data collected from 37 distinct unmanned aerial vehicle (UAV) models for detection and identification tasks. Developed by kitofrank and released in 2025, this benchmark provides high-volume signal data to address the limitations of smaller, less diverse drone signal repositories.
A dataset focused on tracking Unmanned Aerial Vehicles (UAVs), likely for computer vision and autonomous systems research. It is published on Kaggle, but specific details about its size, creation date, and authors are not provided in the available metadata. The content appears to be related to detecting and tracking drones, a common challenge in security and robotics applications.
Facebear's dataset contains approximately 1,500 episodes of robotic cloth folding, collected using an Agilex Aloha robotic arm. It was created for the X-VLA paper and demonstrates a near-perfect success rate in the folding task. The dataset was last updated on Hugging Face in November 2025.
UAVDetectTF likely contains imagery for detecting unmanned aerial vehicles. The dataset is hosted on Kaggle, but its specific size, origin, and creation date are not provided in the metadata. Columns and sample data are unknown, requiring download for detailed inspection.
A dataset titled 'UAV2UAV_Dataset' is hosted on Kaggle. The dataset's content likely pertains to interactions between Unmanned Aerial Vehicles (UAVs), as suggested by its name. No further metadata regarding its size, origin, or specific contents is provided.
DroneScapes2 Annotated Train Set provides 218 drone-view images with segmentation and classification labels, curated by Voxel51. This dataset is a specific subset of the larger DroneScapes2 repository, formatted for use with the FiftyOne library as of late 2025.
Drone_cache is a dataset hosted on Kaggle, likely containing information related to unmanned aerial vehicle operations or sensor data. The dataset's specific content, size, and origin are not detailed in the available metadata. Its Kaggle platform tags suggest a focus on robotics and aerial data collection.
A multilingual benchmark dataset designed to evaluate the alignment of large language models with general Islamic values and principles. Created by Abderraouf000 and last updated on December 21, 2025, it contains questions categorized by evaluation type, such as 'Other faiths', with multiple-choice answers and a correct choice index.
VisDrone is a dataset hosted on Kaggle. The title suggests it contains visual data captured by drones, likely for computer vision tasks. No further metadata on size, columns, or origin is provided.
170.8 square kilometers of 3x3 meter resolution relative seafloor reflectivity data were collected for shallow waters around St. Thomas and St. John. The dataset was acquired by Fugro LADS in collaboration with NOAA, the University of New Hampshire, and the National Park Service during thirteen sorties from January to February 2011. It captures seabed characteristics at depths between 0 and 40 meters using a Nd:YAG laser system.
KITTI Processed is a dataset derived from the KITTI Vision Benchmark Suite, likely containing sensor data for autonomous vehicle research. The dataset is hosted on Kaggle and appears to be a processed version of the original KITTI data, which includes images, LiDAR point clouds, and annotations. Its specific content, scale, and processing details require verification after download.
September 2024 data from the High Spectral Resolution Lidar-2 instrument flown on NASA's ER-2 aircraft during the PACE-PAX campaign. The dataset supports validation and refinement of data products from the PACE satellite mission. It was collected by the LARC_CLOUD organization and published in October 2024.
VisDrone2020 is a dataset of drone-captured images and videos. The dataset is hosted on Kaggle and likely contains visual data for tasks such as object detection and tracking. Its specific scale, collection method, and geographic origin are not detailed in the provided metadata.
Drone_NightVision likely contains images captured by drones using night vision technology. The dataset is hosted on Kaggle, but its size, creator, and update date are unknown. Columns and specific content details are not provided.