Find research datasets worth reusing
Search datasets from major research repositories and use ShareScore to quickly assess how well each record supports discovery, access, and reuse.
533
datasets available to search
ShareScore release 0.9.0
Dataset results
533 results for “Aerial”
Annotated Cows in Aerial Images - Test Set for Livestock Detection Models
<p>This dataset contains a test set of aerial images from fields in Juchowo, Poland and Wageningen, the Netherlands, with annotated cows. The annotations are provided in a CSV format containing image file paths, bounding box coordinates (<code>xmin</code>, <code>ymin</code>, <code>xmax</code>, <code>ymax</code>), and labels for the objects (cows). The dataset is intended for evaluating livestock detection models in deep learning, particularly DeepForest.</p> <p>The images and their corresponding bounding box annotations are included in this archive. The test set consists of 10% of the total images, split from the original dataset created by G.J. Franke and Sander Mucher, which is available in [Harvard Dataverse](https://dataverse.harvard.edu/dataset.xhtml?persistentId=doi:10.7910/DVN/N7GJYU). This dataset is part of the GenTORE project (<a href="https://www.gentore.eu" target="_new" rel="noopener">https://www.gentore.eu</a>), focusing on precision livestock farming using automated detection and deep learning techniques.</p> <p><strong>Contributions</strong></p> <p><em>Notebook</em></p> <ul> <li> <p>Alejandro Coca-Castro (author), The Alan Turing Institute, <a href="https://github.com/acocac">@acocac</a></p> </li> </ul> <p><em>Dataset reference and documentation</em></p> <ul> <li> <p>Franke, G.J., & Mucher, S. (2021). Annotated cows in aerial images for use in deep learning models. Harvard Dataverse. <a href="https://doi.org/10.7910/DVN/N7GJYU" target="_new" rel="noopener">https://doi.org/10.7910/DVN/N7GJYU</a></p> </li> </ul>
Data set - Monitoring light pollution with an unmanned aerial vehicle
<p>Dataset used in the study Monitoring light pollution with an unmanned aerial vehicle. A digital camera and a sky quality meter mounted on a UAV have been used to study the relationship between indices computed on night images and night ground brightness (NGB) measured by an optical device pointed downward towards the ground. Both measurements were taken contemporarily during flights at 70 meter and 100 meters altitude, and also varying exposure time.</p>
Colour illustrations. Flowers, fruits, leaves and seeds of Musa itinerans (background photo by D.T. Vu); from top to bottom and left to right: colony on PDA after 14 d at 24 °C in darkness (left = obverse,right = reverse), sporodochia formed on CLA, aerial conidiophore, aerial conidiogenous cells, aerial conidia, sporodochial conidia. Scale bars: black = 20 µm, white = 10 µm. in Fusarium chuoi R. Hill, Gaya, D.T. Vu, Sand.-Den. & Crous, R. Hill, Gaya, D.T. Vu, Sand.-Den. & Crous sp. nov.
Colour illustrations. Flowers, fruits, leaves and seeds of Musa itinerans (background photo by D.T. Vu); from top to bottom and left to right: colony on PDA after 14 d at 24 °C in darkness (left = obverse,right = reverse), sporodochia formed on CLA, aerial conidiophore, aerial conidiogenous cells, aerial conidia, sporodochial conidia. Scale bars: black = 20 µm, white = 10 µm.
Unmanned aerial vehicles as a useful tool for investigating animal movements - samples
<p><span>Determining animal abundance is crucial for assessing the effectiveness of management measures against pest animals. Meanwhile, investigating animal movements has become important for conducting abundance estimations of unmarked animals since the random encounter model (REM)</span><span> was published. REM is a camera-trapping method </span><span>that derives animal density by using contact ratio between camera-traps and targeted animals that randomly move at a certain speed in a given area. However, it</span><span> requires an independent value, which is animal speed. F</span><span>or investigating animal speed, camera-traps with video recording and GPS tagging are the commonly used tools.</span></p> <p><span>U</span><span>nmanned aerial vehicles (UAVs) are currently used in wildlife monitoring to investigate the abundance of target species. It is evaluated as a tool that is non-invasive and suitable for surveys in inaccessible landscapes. Considering these characteristics, we regarded a distant survey using this technology as suitable for investigating animal movements. </span><span>Therefore, we proposed a method for estimating animal movements using UAVs and conducted a case study that aimed to investigate wild boars' movements.</span></p> <p><span>We collected 11 video samples that successfully followed the movements of wild boars from 26 UAV flights in total, and the average speed of their movements derived from all the samples was 1.54 km/24 h.</span></p> <p><span>We found that issues can be improved, including species identification, video sample length, and animal behaviours or activity patterns. On the other hand, our method showed potential for applying to species with specific characteristics in their body size, shape or activity patterns. With improvements in the issues mentioned above, UAVs would become an alternative tool for investigating animal movements.</span></p>
Melt pond from aerial photographs of the Healy–Oden Trans Arctic Expedition (HOTRAX)
<p>The dataset contains mapped melt pond zones from aerial photographs which were obtained during helicopter photography flights as part of the Healy–Oden Trans Arctic Expedition (HOTRAX) between 5 August and 30 September 2005. The detection has been done using an original detection algorithm based on machine learning (U-Net). The areas in the images were divided into four classes: sea ice/snow, melt ponds, sub-merged ice and open water. The filenames contain IDs from the original dataset [Perovich et al 2008].</p>
Raw images, annotations, and vvipr code archive to support 'Evaluating thermal and color sensors for automating detection of penguins and pinnipeds in images collected with an unoccupied aerial system''
<p>Images, annotations, and code archived here were used in the paper "Evaluating a machine learning approach to detect penguins and pinnipeds in thermal and color images collected with an unoccupied aerial system" submitted for publication in Drones. The files contain raw thermal and color images of aggregations of gentoo (<em>Pygoscelis papua</em>) and chinstrap (<em>P. antarcticus</em>) penguins and Antarctic fur seals (<em>Arctocephalus gazella</em>). All images were collected with the Flir DuoPro R camera (Teledyne FLIR LLC, Wilsonville, OR, U.S.A.), carried into flight under an APH-28 hexacopter (Aerial Imaging Solutions, LLC, Old Lyme, CT, U<strong>.</strong>S<strong>.</strong>A<strong>.)</strong> at Cape Shirreff, Livingston Island, Antarctica (60.79 °W, 62.46 °S), during the austral summer of 2019-20. All aerial surveys occurred under the Marine Mammal Protection Act Permit No. 20599 granted by the Office of Protected Resources/National Marine Fisheries Service, the Antarctic Conservation Act Permit No. 2017-012, NMFS-SWFSC Institutional Animal Care and Use Committee Permit No. SWPI 2014-03R, and all domestic and international UAS flight regulations. The annotations of the images were conducted using VIAME desktop software (v 0.16.1 or later;<a href="https://github.com/VIAME/VIAME">https://github.com/VIAME</a>) or the online using the DIVE interface (https://viame.kitware.com/). Model results were assessed with the vvipr code (v.0.3.2), archived here and available online (https://github.com/us-amlr/vvipr/releases/tag/v0.3.2).</p> <p> </p>
Dataset with square plots across Sierra Nevada (Spain) where the contours of all juniper shrubs were annotated as polygons using centimetric GPS and very high resolution aerial and satellite RGB images
<p><strong>This dataset is a shapefile of 767 polygons describing the contours of Juniperus communis L. and Juniperus sabina L. shrubs for the year 2021 in rectangular plots across Sierra Nevada. The coordinates of the polygons were obtained from a field work campaign with a differential centimetric GPS, and their contours were drawn manually in QGIS using the Google Earth satellite image for 2020 and the PNOA aerial image for the 2020. </strong></p> <p><strong>This dataset also contains an excel file describing the features of each polygon: the polygon centroid coordinates, the type of species, the sexgender, the morphotype, the damage in the vegetation cover estimated in the field and telematically, certainty of the digitalization with QGIS and also if the differential centimetric GPS used belongs to the University of Granada or the University of Almeria. </strong></p>
Unmanned Aerial Vehicle (UAV) image dataset.
<p>The dataset contains 2,919 images and separated into five classes of car, taxi, truck, bus and motorcycle.<br> </p>
Palace of Fine Arts photogrammetry (aerial)
Palacio de Bellas Artes , Mexico City Realizado usando el dataset de Open Heritage/ Cyark de fotos aereas. El Palacio de Bellas Artes es un recinto cultural ubicado en el Centro Histórico de la Ciudad de México, considerado el más importante en la manifestación de las artes en México y una de las casas de ópera más renombradas del mundo. Éste mismo ha sido escenario y testigo de impactantes acontecimientos tanto artísticos, sociales y políticos del país; su construcción data del final de mandato de Porfirio Díaz, por encargo del presidente mexicano con motivo de la celebración del centenario del inicio de la Independencia de México, más fue inaugurado hasta el 29 de septiembre de 1934 tras el estallido de la Revolución mexicana. Como institución, depende del Instituto Nacional de Bellas Artes (INBA), parte de la Secretaría de Cultura del gobierno federal. En 1987 fue declarado por la Unesco un monumento patrimonio de la humanidad. DOI for this dataset is 10.26301/vdae-mr89 Source: Objaverse 1.0 / Sketchfab
Estimating belowground carbon stocks in isolated wetlands of the Northern Everglades Watershed, central Florida, using ground penetrating radar (GPR) and aerial imagery
<p>This data set includes raw GPR profiles for isolated wetlands in the Disney Wilderness Preserve (Kissimmee, FL) for the purpose of below ground soil C stock estimations. </p>
Asymmetric Collaborative Bar Stabilization Tethered to Two Heterogeneous Aerial Vehicles
<p>We consider a system composed of a bar tethered to two unmanned aerial vehicles (UAVs), where the cables behave as rigid links under tensile forces, and with the control objective of stabilizing the bar's pose around a desired pose. Each UAV is equipped with a PID control law, and we verify that the bar's motion is decomposable into three decoupled motions, namely a longitudinal, a lateral and a vertical. We then provide relations between the UAVs' gains, which, if satisfied, allows us to decompose each of those motions into two cascaded motions; the latter relations between the UAVs' gains are found so as to counteract the system asymmetries, such as the different cable lengths and the different UAVs' weights. Finally, we provide conditions, based on the system's physical parameters, that describe good and bad types of asymmetries. We present experiments that demonstrate the stabilization of the bar's pose.</p>
Real-time Dense Surface Reconstruction for Aerial Manipulation
<p>This video illustrates the content of the paper referenced below.</p> <p><strong> Reference:</strong></p> <p>Marco Karrer, Mina Kamel, Roland Siegwart and Margarita Chli, "Real-time Dense Surface Reconstruction for Aerial Manipulation", in Proceedings of the IEEE/RSJ Conference on Intelligent Robots and Systems (IROS), 2016.</p> <p><strong>Abstract:</strong></p> <p>With robotic systems reaching considerable maturity in basic self-localization and environment mapping, new research avenues open up pushing for interaction of a robot with its surroundings for added autonomy. However, the transition from traditionally sparse feature-based maps to dense and accurate scene-estimation imperative for realistic manipulation is not straightforward. Moreover, achieving this level of scene perception in real-time from a computationally constrained and highly shaky and agile platform, such as a small an Unmanned Aerial Vehicle (UAV) is perhaps the most challenging scenario for perception for manipulation. Drawing inspiration from otherwise computationally constraining Computer Vision techniques, we present a system combining visual, inertial and depth information to achieve dense, local scene reconstruction of high precision in real-time. Our evaluation testbed is formed using ground-truth not only in the pose of the sensor-suite, but also the scene reconstruction using a highly accurate laser scanner, offering unprecedented comparisons of scene estimation to ground-truth using real sensor data. Given the lack of any real, ground-truth datasets for environment reconstruction, our V4RL Dense Surface Reconstruction dataset is publicly available.</p>
Cooperative UAVs as a Tool for Aerial Inspection of the Aging Infrastructure
<p>This video shows the cooperative UAVs as a tool for aerial inspection of the aging infrastructure. In the presented approach the UAVs are relying only on their onboard computer and sensory system, deployed for inspection of the 3D structure. In this application each agent covers a different part of the scene autonomously, while avoiding collisions. The visual information collected from the aerial team is collaboratively processed to create the 3D model.</p>
RiGaD: An aerial dataset of rice seedlings for assessing germination rates and density
<p><span>The dataset contains 5,364 images of rice seedlings with a combined size of 35 MB. These images are organized in three folders: single rice seed plants (1367 images), clustered rice seed plants (1437 images), and undefined objects (2560 images)</span></p>
The Aerial Elephant Dataset
<p>Aerial surveying is a key tool for effective wildlife management. However, the high costs associated with large scale surveys means that this tool is often underutilized. We believe that computer vision can be used to dramatically decrease the costs associated with surveying, while at the same time improving the consistency of results. We present the Aerial Elephant Dataset, a challenging dataset to enable research on game detection under real-world conditions. The dataset consists of 2 074 images containing a total of 15 581 African bush elephants in their natural habitats, imaged with a consistent methodology over a range of background types, resolutions and times-of-day.</p>
Generating aerial flood prediction imagery
<h1>Flood Generation Dataset</h1> <h2>Dataset Overview</h2> <p>The dataset contains paired sets of pre- and post-flooding satellite images, which can be used for training models on flood prediction tasks, particularly on generating photorealistic visualisations of floods. Each image is also associated with topographical factors, which can be used to assist the model in making predictions. These factors are a digital elevation model (DEM), flow accumulation, distance to rivers, and cartographical map. Every image set was manually verified and adjusted, in order to ensure perfect pixel alignment, where each pixel represents the same 0.5m x 0.5m geographical area in all of the factors.</p> <p>The dataset contains 1229 unique image sets, 235 of Hurricane Florence, 335 of Hurricane Harvey, 147 of the Midwest floods, and 512 of the India monsoon. 408 of the image sets (from Hurricane Harvey and some of the Midwest floods) have an additional alternative version with a 1m/pixel resolution DEM.</p> <h2>Dataset Structure</h2> <p>The <strong>dataset input </strong>folder contains images with the pre-flooding satellite image and topographical factors represented in 9 stacked channels (see the table below) and stored as a .tif file. The <strong>dataset output </strong>folder contains the post-flooding satellite image, stored as a .tif file. The name of the file contains which disaster it represents.</p> <table> <tbody> <tr> <td><strong>Channel</strong></td> <td><strong>Contents</strong></td> </tr> <tr> <td>0, 1, 2</td> <td>Pre-flooding satellite image</td> </tr> <tr> <td>3</td> <td>DEM</td> </tr> <tr> <td>4</td> <td>Flow accumulation</td> </tr> <tr> <td>5</td> <td>Distance to rivers</td> </tr> <tr> <td>6, 7, 8</td> <td>Cartographical map</td> </tr> </tbody> </table> <h2>Dataset Contents</h2> <h3>Pre- and post satellite images.</h3> <p>Each image has 1024x1024 pixels in a three-band RGB format, with a resolution of approximately 0.5 metres/pixel. The satellite images were extracted from the xBD dataset, captured by the Maxar Open Data Program. It was released under the Creative Commons Attribution-Noncommercial-Sharealike 4.0 International licence (CC BY-NC-SA 4.0). </p> <h3>Digital elevation model and flow accumulation</h3> <p>The USGS 3D Elevation Program DEM, which has a 1/3 arc-second (10 metre) resolution, describes the topography of the images within the USA. The elevations in this DEM represent the topographic bare-earth surface. The Copernicus GLO-30 DEM, which has a resolution of only 30 metres, was used for the flood areas in India. The flow accumulation was calculated from the DEMs.</p> <p>The USGS 3D Elevation Program DEM is released by the U.S. Geological Survey, 2023, 1/3rd arc-second Digital Elevation Models (DEMs) - USGS National Map 3DEP Downloadable Data Collection. All 3DEP products are public domain. The Copernicus Global Digital Elevation model was produced using Copernicus WorldDEM-30 DLR e.V. 2010-2014 and Airbus Defence and Space GmbH 2014-2018, provided under COPERNICUS by the European Union and ESA.</p> <h3>Distance to rivers and cartographical map</h3> <p>OpenStreetMap data was downloaded from Planet OSM and processed using the Osmium tool. The Maperitive software was then used to apply a custom ruleset to the maps' appearance, removing all of the text, and enhancing the clarity of the land use types. The distance to rivers representation was producing by creating buffer distances (at 0.5km intervals) to all major rivers and waterways, as classified by the Open Street Map. The OpenStreetMap (OSM) data is distributed under the Open Database License (ODbL). https://www.openstreetmap.org/copyright</p> <h1>Flood Segmentation Dataset</h1> <h2>Dataset Overview</h2> <p>In order to evalate the flood predictive accuracy of post-flooding images generated by a model that has been trained on the flood generation dataset, the synthetic and ground truth post-flooding images can be compared using a flood segmentation model trained on this dataset. A post-flooding satellite image is input into the the segmentation model, and it then classifies whether each pixel is flooded or not, and outputs a 1-channel binary flood mask, where white (1) corresponds to a predicted flooded pixel, and black (0) corresponds to a predicted non-flooded pixel. The flood masks corresponding to both real and synthetic images can then be compared using metrics such as MSE, precision, recall, etc, thus determining whether the generative model correctly flooded the same areas that are actually flooded in the real ground truth image.</p> <h2>Dataset Structure</h2> <p>The flood segmentation dataset contains 1028 images, depicting the same disasters as in the flood generation dataset. The <strong>masks input</strong> folder contains 256x256 pixel 3-channel RGB post-flooding .tif images, which are comprised of a mix of ground truth and synthetic images generated by different GAN architectures. The <strong>masks output </strong>folder contains the corresponding 1 channel binary flood masks.</p> <p>332 of the flood masks were published openly by: https://huggingface.co/datasets/blutjens/eie-earth-intelligence-engine. The rest of the masks were manually labelled by myself.</p>
FIGURE 1. Palhinhaea cerrojefensis. A. Erect aerial shoot. B in New neotropical Lycopodiaceae
FIGURE 1. Palhinhaea cerrojefensis. A. Erect aerial shoot. B. Main stem of erect aerial shoot with leaves. C. Ultimate branchlets with strobili. (Correa, Dressler, Escobar, & Carrasquill 1796, holotype MO).
FIGURES 2–17. Microcostatus aerophilus. 2–6 in Study of the type material of Navicula egregia Hustedt and descriptions of two new aerial Microcostatus (Bacillariophyta) species from Central Europe
FIGURES 2–17. Microcostatus aerophilus. 2–6. LM photographs from Hustedt German material. 7–12. Holotype population from Husów material. 13–15. SEM photographs in external valve view illustrating variation in size, outline and conopea with perforation. 16. External girdle view from Husów. 17. External valve view with clearly visible asymmetrical constricted sternum from Hustedt German material.
FIGURES 18–28. Microcostatus edaphicus. 18–23 in Study of the type material of Navicula egregia Hustedt and descriptions of two new aerial Microcostatus (Bacillariophyta) species from Central Europe
FIGURES 18–28. Microcostatus edaphicus. 18–23. LM photographs of type material from Hustedt Collection. 24–25, 27. SEM photographs of external valve view with characteristic clearly visible elongated pores as continuation of striae. 26, 28. Internal valve view with helictoglossae.
FIGURES 29–56. Microcostatus egregius. 29 in Study of the type material of Navicula egregia Hustedt and descriptions of two new aerial Microcostatus (Bacillariophyta) species from Central Europe
FIGURES 29–56. Microcostatus egregius. 29. Drawing of Navicula egregia Hustedt 1942a. 30–52. LM photographs of Hustedt type material. 53, 55–56. SEM photographs of external valve view illustrating a row of perforation in the place of sternum and conopeum connection. 54. Internal valve view with helictoglossae.
ScienceDex guides
Understand access before you commit
These curated guides explain access requirements, typical timelines, costs, and reuse considerations for widely used research datasets.
Allen Brain Atlas
Allen Brain Atlas is an Allen Institute collection of brain map atlases, datasets, APIs, and analysis tools covering mouse, human, and non-human primate brain resources.
Annotated Behaviour and Observability Dataset (ABODe)
ABODe is a University of Edinburgh DataShare dataset for behavior classification in group-housed mice using home-cage video, identities, bounding boxes, ground-plate positions, and annotator labels.
DANDI Archive for NWB datasets
DANDI is a BRAIN Initiative archive for publishing and sharing neurophysiology data, including electrophysiology, optophysiology, and behavioral data packaged as NWB and related standards.
International Brain Laboratory public data
The International Brain Laboratory public data releases expose standardized mouse decision-making experiments, including Neuropixels recordings, widefield calcium imaging, behavior, and session metadata accessed through the ONE API.
OpenNeuro
OpenNeuro is a free, open platform for sharing neuroimaging datasets, with public search, dataset pages, and download paths for web, S3, DataLad, and the OpenNeuro CLI.