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.

datasets available to search

ShareScore release 0.9.0

Dataset results

51 results for “Aerial Images”

Learn how ShareScore rates datasets ↗

zenodo44/100

Roundabout Aerial Images for Vehicle Detection

If you use this dataset, please cite this paper: Puertas, E.; De-Las-Heras, G.; Fernández-Andrés, J.; Sánchez-Soriano, J. Dataset: Roundabout Aerial Images for Vehicle Detection. Data 2022, 7, 47. https://doi.org/10.3390/data7040047 This publication presents a dataset of Spanish roundabouts aerial images taken from an UAV, along with annotations in PASCAL VOC XML files that indicate the position of vehicles within them. Additionally, a CSV file is attached containing information related to the location and characteristics of the captured roundabouts. This work details the process followed to obtain them: image capture, processing and labeling. The dataset consists of 985,260 total instances: 947,400 cars, 19,596 cycles, 2,262 trucks, 7,008 buses and 2,208 empty roundabouts, in 61,896 1920x1080px JPG images. These are divided into 15,474 extracted images from 8 roundabouts with different traffic flows and 46,422 images created using data augmentation techniques. The purpose of this dataset is to help research on computer vision on the road, as such labeled images are not abundant. It can be used to train supervised learning models, such as convolutional neural networks, which are very popular in object detection.   <table align="center"> <tbody> <tr> <td> Roundabout (scenes) </td> <td> Frames </td> <td> Car </td> <td> Truck </td> <td> Cycle </td> <td> Bus </td> <td> Empty </td> </tr> <tr> <td> 1 (00001) </td> <td> 1,996 </td> <td> 34,558 </td> <td> 0 </td> <td> 4229 </td> <td> 0 </td> <td> 0 </td> </tr> <tr> <td> 2 (00002) </td> <td> 514 </td> <td> 743 </td> <td> 0 </td> <td> 0 </td> <td> 0 </td> <td> 157 </td> </tr> <tr> <td> 3 (00003-00017) </td> <td> 1,795 </td> <td> 4822 </td> <td> 58 </td> <td> 0 </td> <td> 0 </td> <td> 0 </td> </tr> <tr> <td> 4 (00018-00033) </td> <td> 1,027 </td> <td> 6615 </td> <td> 0 </td> <td> 0 </td> <td> 0 </td> <td> 0 </td> </tr> <tr> <td> 5 (00034-00049) </td> <td> 1,261 </td> <td> 2248 </td> <td> 0 </td> <td> 550 </td> <td> 0 </td> <td> 81 </td> </tr> <tr> <td> 6 (00050-00052) </td> <td> 5,501 </td> <td> 180,342 </td> <td> 1420 </td> <td> 120 </td> <td> 1376 </td> <td> 0 </td> </tr> <tr> <td> 7 (00053) </td> <td> 2,036 </td> <td> 5,789 </td> <td> 562 </td> <td> 0 </td> <td> 226 </td> <td> 92 </td> </tr> <tr> <td> 8 (00054) </td> <td> 1,344 </td> <td> 1,733 </td> <td> 222 </td> <td> 0 </td> <td> 150 </td> <td> 222 </td> </tr> <tr> <td> Total </td> <td> 15,474 </td> <td> 236,850 </td> <td> 2,262 </td> <td> 4,899 </td> <td> 1,752 </td> <td> 552 </td> </tr> <tr> <td> Data augmentation </td> <td> x4 </td> <td> x4 </td> <td> x4 </td> <td> x4 </td> <td> x4 </td> <td> x4 </td> </tr> <tr> <td> Total </td> <td> 61,896 </td> <td> 947,400 </td> <td> 9048 </td> <td> 19,596 </td> <td> 7,008 </td> <td> 2,208 </td> </tr> </tbody> </table>

opencc-by-4.0Mar 2022View details →

zenodo44/100

Dataset of polygons with the contour of 900 juniper shrubs used to track shrub growth from 1977 to 2020 in Sierra Nevada (Spain) using very high resolution aerial and satellite RGB images.

This database provides as polygons the contours of 900 juniper shrubs (Juniperus communis L. and Juniperus sabina L.) along 5 decades (years 1977, 1984, 2001, 2010 and 2020). The contour of each of 900 shrubs manually mapped using the Google Satellite composite for the year 2020) was tracked back in time using orthophotos provided by REDIAM. Contours were obtained by manual annotation as polygon shapefiles in QGIS 3.10.3. Additionally, for the year 2020, the polygons were characterized with five attributes that gather ecological information: Morphotype (Hemispherical, Striped, Senescent, With rock), Presence of surrounding vegetation (Bare Soil, Surrounding Vegetation), Presence of nearby human land-uses (Surrounded by human facilities within 250 meters, Non-anthropized environment) Health status (as percentage of canopy cover with brown foliage: values between 0-5, where 0 corresponds to 100% photosynthetically active cover, decreasing the photosynthetically active cover until category 5 which corresponds to 100% damaged cover), and the subjective annotation certainty of the GIS technician (values between 0-5, where the value 0 corresponds to a very uncertain annotation up to the value 5 which corresponds to a fairly certain annotation).

opencc-by-4.0Jul 2022View details →

zenodo44/100

Unmanned Aerial Vehicle Image Dataset of the Built Environment for 3D reconstruction (UAVID3D)

Unmanned Aerial Vehicles (UAV) provide increased access to unique types of urban imagery traditionally not available. Advanced machine learning and computer vision techniques when applied to UAV RGB image data can be used for automated extraction of building asset information and if applied to UAV thermal imagery data can detect potential thermal anomalies. However,  these UAV datasets are not easily available to researchers, thereby creating a barrier to accelerating research in this area.  To assist researchers with added data to develop machine learning algorithms, we present UAVID3D (Unmanned Aerial Vehicle (UAV) Image Dataset of the Built Environment for 3D reconstruction). The raw images for our dataset were recorded with a Zenmuse XT2 visual (RGB) and a FLIR Tau 2 (thermal, https://flir.netx.net/file/asset/15598/original/) camera on a DJI Mavic 2 pro drone (https://www.dji.com/matrice-200-series). The thermal camera is factory calibrated. All data is organized and structured to comply with FAIR principles, i.e. being findable, accessible, interoperable, and reusable. It is publicly available and can be downloaded from the Zenodo data repository.  RGB images were recorded during UAV fly-overs of two different commercial buildings in Northern California. In addition,  thermographic images were recorded during 2 subsequent UAV fly-overs of the same two buildings. UAV flights were recorded at flight heights between 60–80 m above ground with a flight speed of 1 m s and contain GPS information. All images were recorded during drone flights on May 10, 2021 between 8:45 am and 10:30 am and on May 19, 2021 between 2:15 pm and 4:30 pm. Outdoor air temperatures on these two days during the flights were between 78 and 83 degree fahrenheit and  between 58 and 65 degree fahrenheit respectively.  For the RGB flights, UAV path was planned and captured using an orbital flight plan in PIX4D capture at normal flight speed and overlap angle of 10 degree. Thermal images were captured by manual flights approximately 5 m away from each building facade. Due to the high overlap of images,  similarities from feature points identified in each image can be extracted to conduct photogrammetry. Photogrammetry allows estimation of the three-dimensional coordinates of points on an object in a generated 3D space involving measurements made on images taken with a high overlap rate. Photogrammetry can be used to create a 3D point cloud model of the recorded region. UAVID3D dataset is a series of compressed archive files totaling 21GB. Useful pipelines to process these images can be found at these two repositories <a href="https://github.com/LBNL-ETA/a3dbr">https://github.com/LBNL-ETA/a3dbr</a>, and <a href="https://github.com/LBNL-ETA/AutoBFE">https://github.com/LBNL-ETA/AutoBFE</a> This work was supported by the Assistant Secretary for Energy Efficiency and Renewable Energy, Building Technologies Program, of the U.S. Department of Energy under Contract No. DE-AC02-05CH11231.

opencc-by-4.0Feb 2023View details →

edi44/100

Georectified Mosaic of Aerial Images of Baltimore City in 1953

Landscape analyses are typically done using spatially explicit color aerial imagery. However, working with non-spatial black and white historical aerial photographs presents several challenges that require a combination of techniques and approaches. We analyzed 113 aerial images covering approx. 700 km2 (270 mi2) including all of Baltimore City, and a portion of Baltimore County surrounding the City. The images were taken between August 23rd 1952 and February 14th 1953. High-resolution scans were georeferenced and georectified against modern satellite imagery of the area and then combined to create a single raster mosaic. This process converted the images from a disparate set of photographs into a spatially explicit GIS data set that can be used to observe changes in land patches over time—and ultimately integrated with other long-term social, economic, and ecological data.

openCC (other)Feb 2022View details →

zenodo40/100

AIDER (Aerial Image Dataset for Emergency Response Applications)

AIDER (Aerial Image Dataset for Emergency Response applications): The dataset construction involved manually collecting all images for four disaster events, namely Fire/Smoke, Flood, Collapsed Building/Rubble, and Traffic Accidents, as well as one class for the Normal case. The aerial images for the disaster events were collected through various online sources (e.g. google images, bing images, youtube, news agencies web sites, etc.) using the keywords ”Aerial View” or ”UAV” or”Drone” and an event such as Fire”,”Earthquake”,”Highway accident”, etc. Images are initially of different sizes but are standardized prior to training. All images where manually inspected to first contain the event that was of interested and then to have the event centered at the image so that any geometric transformations during augmentation would not remove it from the image view. During the data collection process the various disaster events were captured with different resolutions and under various condition with regards to illumination and viewpoint. Finally, to replicate real world scenarios the dataset is imbalanced in the sense that it contains more images from the Normal class. This subset includes around 500 images for each disaster class and over 4000 images for the normal class. This makes it an imbalanced classification problem. It is advised to further enhance the dataset that random augmentations are probabilistically applied to each image prior to adding it to the batch for training. Specifically there are a number of possible transformations such as geometric (rotations, translations, horizontal axis mirroring, cropping and zooming), as well as image manipulations (illumination changes, color shifting, blurring, sharpening, and shadowing).

opencc-by-4.0Jun 2020View details →

zenodo40/100

Aerial and Terrestrial Thermal Images of German Multi-Family Buildings

This dataset consists of 968 thermal images including 693 captured by hand-held camera on the ground and 275 via UAV. Of the aerial images, 139 were recorded manually and 136 in automatic flight mode. The images depict four multi-family buildings of 18 m height in the German city of Karlsruhe belonging to the local municipal housing association Volkswohnung Karlsruhe GmbH. Table 1 gives an overview of the buildings in question, all of which were fully rented out on the days of image acquisition. Table 1: Building information <table> <tbody> <tr> <td>                      Building Details </td> <td> Sophienstr. 201-203 </td> <td> Volzstr. 2 </td> <td> Wichernstr. 4 </td> <td> Wichernstr. 10-18 </td> </tr> <tr> <td> construction year </td> <td> 1957 </td> <td> 1954 </td> <td> 1953 </td> <td> 1953 </td> </tr> <tr> <td> apartments </td> <td> 30 </td> <td> 12 </td> <td> 25 </td> <td> 30 </td> </tr> </tbody> </table> The aerial images were acquired using DJI’s “Matrice 600” UAV (DJI, 2022) equipped with the “Zenmuse XT2”, a combination of FLIR’s “Duo Pro R” thermal and RGB camera technology and DJI’s gimbal (FLIR, 2021a). All thermal images were recorded in FLIR’s proprietary image format RJPEG. The terrestrial thermographic images were captured with FLIR’s “T200” hand-held camera (FLIR, 2021b) in the standard JPEG format. The emissivity was set to 0.95 throughout the acquisition of both aerial and terrestrial images. Thermographic image processing and analysis was realized using the "FLIR Thermal Studio" software (FLIR Systems Inc., 2022). The temperature scale was set to -8 °C to +13 °C and color distribution function "signal linear" selected. The thermal images of this dataset were recorded on February 28th and March 1st, 2022, between 8 p.m. and 1 a.m. On February 28th the outside air temperature registered at between 1 °C and 3 °C. Wind speeds reached a maximum of 17 km/h. The sky was cloudless both during the flights and in the preceding 24 hours. A maximum temperature of 11 °C was recorded by local weather stations in that time period. Very similar weather conditions were present on March 1st. The outside air temperature was recorded at between -1 °C and 5 °C during acquisition, with wind speeds of max. 11 km/h. Again, the sky was entirely clear both during the flights and in the preceding 24 hours, with a maximum temperature of 9 °C present in that time period. The sun set at around 6:10 p.m. on both days (timeanddate, 2022). The images were recorded using ten different flight settings of varying speed, flight height, and camera angle. Details are summarized in Table 2. Table 2: Flight settings <table align="center"> <tbody> <tr> <td> Flight </td> <td> Building </td> <td> Automatically/ manually performed flight route </td> <td> Camera angle [°] </td> <td> Height above ground [m] </td> <td> Height above building [m] </td> <td> Distance to façade [m] </td> <td> Flight speed [m/s] </td> </tr> <tr> <td> 1 </td> <td> Full area </td> <td> Automatically </td> <td> 45 (oblique) </td> <td> 40 </td> <td> 22 </td> <td> - </td> <td> 1 </td> </tr> <tr> <td> 2 </td> <td> Full area </td> <td> Automatically </td> <td> 45 (oblique) </td> <td> 40 </td> <td> 22 </td> <td> - </td> <td> 3 </td> </tr> <tr> <td> 3 </td> <td> Full area </td> <td> Automatically </td> <td> 45 (oblique) </td> <td> 40 </td> <td> 22 </td> <td> - </td> <td> 5 </td> </tr> <tr> <td> 4 </td> <td> Full area </td> <td> Automatically </td> <td> 45 (oblique) </td> <td> 60 </td> <td> 42 </td> <td> - </td> <td> 3 </td> </tr> <tr> <td> 5 </td> <td> Full area </td> <td> Automatically </td> <td> 90 (nadir) </td> <td> 40 </td> <td> 22 </td> <td> - </td> <td> 3 </td> </tr> <tr> <td> 6 </td> <td> Full area </td> <td> Automatically </td> <td> 90 (nadir) </td> <td> 60 </td> <td> 42 </td> <td> - </td> <td> 3 </td> </tr> <tr> <td> 7 </td> <td> Wichernstr. 4 </td> <td> Manually </td> <td> 0 (manual) </td> <td> 4 to 12 </td> <td> - </td> <td> 4 </td> <td> - </td> </tr> <tr> <td> 8 </td> <td> Wichernstr. 4 </td> <td> Manually </td> <td> 0 (manual) </td> <td> 4 to 12 </td> <td> - </td> <td> 8 </td> <td> - </td> </tr> <tr> <td> 9 </td> <td> Wichernstr. 4 </td> <td> Manually </td> <td> 0 (manual) </td> <td> 4 to 12 </td> <td> - </td> <td> 15 </td> <td> - </td> </tr> <tr> <td> 10 </td> <td> Wichernstr. 10-18 </td> <td> Manually </td> <td> 0 (manual) </td> <td> 4 to 12 </td> <td> - </td> <td> 15 </td> <td> - </td> </tr> </tbody> </table>   Acknowledgments: The authors appreciate the support of Marinus Vogl (Air Bavarian GmbH) in acquiring the thermal images via UAV. Moreover, they thank Harald Schneider (Karlsruhe Institute of Technology) for his advice and assistance. Lastly, they gratefully acknowledge the consent and support of Karlsruher Volkswohnung GmbH within this research project.   References: DJI (2022).  Matrice 600 - DJI. URL: https://www.dji.com/de/matrice600 (accessed 10th January 2022) FLIR (2021a).  FLIR XT2 product information (Wilsonville, USA). URL: https://www.flir.de/products/xt2/ (accessed 10th January 2022) FLIR (2021b).  FLIR T-series (Wilsonville, USA). URL: https://www.flir.com/instruments/t-series/  (accessed 10th January 2022) FLIR Systems Inc. (2022). User’s manual Flir Thermal Studio. URL: https://www.sahkonumerot.fi/6708162/doc/operatinginstructions/ (accessed 12th August 2022) Timeanddate (2022). Wetter im Februar 2022 in Karlsruhe, Baden-Württemberg, Deutschland. URL: https://www.timeanddate.de/wetter/deutschland/karlsruhe/rueckblick?month=2&year=2022  (accessed 12th March 2022)

opencc-by-4.0Oct 2022View details →

zenodo40/100

Train and Evaluation Code, Road Classification Models and Test set of the paper "Insights into the Effects of Image Overlap and Image Size on Semantic Segmentation Models Trained for Road Surface Area Extraction from Aerial Orthophotography"

This repository contains the Python scripts built for training and evaluation of the implementation, together with the test data and the resulting road segmentation models corresponding to the paper "Insights into the Effects of Image Overlap and Image Size on Semantic Segmentation Models Trained for Road Surface Area Extraction from Aerial Orthophotography". The scripts make use of the Tensorflow with Keras framework and their additional required dependencies. The training and validation set is based on the binary SROADEX dataset (<a href="../records/6482346">https://zenodo.org/records/6482346</a>) that was re-split into tiles that feature the image resolutions (256 x 256, 512 x 512, and 1024 x 1024 pixels) and image overlaps (0% and 12.5%) considered in this study. The data have been generated using scripts developed in Python using Open Source libraries (GDAL/OGR and MapScript) for rasterization of vector cartography that represents the axes of the different types of roads (urban, interurban and rural). This binary road data contains information from 16 full orthoimages (28.5 km * 18.5 km) with spatial resolution of 0.5 m/pixel from the insular and peninsular Spanish territory. Due to the size on disk of approximately 492 gigabytes, this training and validation data is only available upon request from the corresponding author. The test set has been generated from a novel area from Palencia (Spain) and features 18 million pixels labelled with the positive "Road" class. The test sets are provided in the repository for each resolution (with no overlap), so that additional DL models can be evaluated on the same data and compared with the results achieved in this study. The structure of the information shared in this repository is as follows: The scripts have been grouped by tile resolution (256, 512 and 1024). First, the test set and the evaluation script can be found. For each tile resolution, there are two subfolders (corresponding to the "no overlap" and "12.5% overlap"). In each case, the Python scripts for training the models in the three repetitions are shared, and the trained models (H5 format) are shared in compressed form. Finally, for each resolution we also share the testing dataset which consists of two folders. The material is distributed under a CC-BY 4.0 license.

opencc-by-4.0Jun 2024View details →

zenodo40/100

Figure 4 in A comparison of image and observer based aerial surveys of narwhal

Figure 4. Detection function plot of chosen DS model when sightings of both aerial observer pairs were pooled. Intercept obtained from the MR model. The solid black line indicates the probability detection function from the DS model and the open symbols indicate the probability of each detection given its perpendicular distance and other covariate values.

opencc-by-4.0Jan 2019View details →

zenodo40/100

Figure 3. Detection functions for Observer pair 1 in A comparison of image and observer based aerial surveys of narwhal

Figure 3. Detection functions for Observer pair 1 (upper panel) and Observer pair 2 (lower panel) during aerial surveys in Melville Bay from 25 to 30 August 2014. Data are truncated at 1,300 m.

opencc-by-4.0Jan 2019View details →

zenodo40/100

Figure 2 in A comparison of image and observer based aerial surveys of narwhal

Figure 2. Narwhal sighting locations in the Melville Bay survey area in 2014 recorded by aerial observers in real-time and identified by analysts in digital imagery. Most of "observer only" sightings are detections beyond the area covered by images (i.e., beyond 500 m from the trackline). The image of ice distribution was of 30 August 2014. We acknowledge the use of imagery from the NASA Worldview application (https://worldview.earthdata.nasa.gov/) operated by the NASA/Goddard Space Flight Center Earth Science Data and Information System (ESDIS) project.

opencc-by-4.0Jan 2019View details →

zenodo40/100

Figure 1 in A comparison of image and observer based aerial surveys of narwhal

Figure 1. Survey strata and transects designed for the aerial survey in Melville Bay from 25 to 30 August 2014. Transects that were surveyed zero, two, or three times, are marked in blue, green or red, respectively. All black transects were surveyed once.

opencc-by-4.0Jan 2019View details →

zenodo40/100

Bottom-of-atmosphere reflectance data from aerial imaging for Lake Mulargia (Sardinia, Italy) (2020/09/24)

This dataset contains the surface reflectance Hyspex images derived with ATCOR code by CNR of Lake Mulargia (Sardinia, Italy). The acquisition was done by CGR Spa (Italy).

opencc-by-4.0Sep 2021View details →

zenodo40/100

EO-derived water quality parameters using aerial imaging spectrometry for Lake Mulargia (Sardinia, Italy) (2020/09/24)

This dataset contains Hyspex-derived water quality (WQ) products of Lake Mulargia (Sardinia, Italy) for the 24 September 2020. The acquisition was done by CGR Spa (Italy). Available parameters are: True-color image (RGB), Colored Dissolved Organic Matter (CDOM), Chlorophyll-a (CHL), and Suspended Particulate Matter (SPM). WQ parameters have been calculated using CNR’s bio-optical model BOMBER parameterized with the inherent optical properties specific of the case study. The data are available as GeoTiff files in WGS 84 / UTM zone 32N (EPSG: 32632).

opencc-by-4.0Sep 2021View details →

zenodo40/100

At-sensor-radiance data from aerial imaging for Lake Mulargia (Sardinia, Italy) (2020/09/24)

This dataset contains the radiance data collected from Hyspex images of Lake Mulargia (Sardinia, Italy) for the VNIR bands. The acquisition was done by CGR Spa (Italy).

opencc-by-4.0Sep 2021View details →

zenodo40/100

A crowdsourced dataset of aerial images with annotated solar photovoltaic arrays and installation metadata

Summary Photovoltaic (PV) energy generation plays a crucial role in the energy transition. Small-scale, residential PV installations are deployed at an unprecedented pace, and their safe integration into the grid necessitates up-to-date, high-quality information. Overhead imagery is increasingly used to improve the knowledge of residential PV installations with machine learning models capable of automatically mapping these installations. However, these models cannot be reliably transferred from one region or imagery source to another without incurring a decrease in accuracy. To address this issue, known as distribution shift, and foster the development of PV array mapping pipelines, we propose a dataset containing aerial images, segmentation masks, and installation metadata. We provide installation metadata for more than 28000 installations. We provide ground truth segmentation masks for 13000 installations, including 7000 with annotations for two different image providers. Finally, we provide installation metadata that matches the annotation for more than 8000 installations. Dataset applications include end-to-end PV registry construction, robust PV installations mapping, and analysis of crowdsourced datasets. This dataset contains the complete records associated with the article "A crowdsourced dataset of aerial images of solar panels, their segmentation masks, and characteristics", published in Scientific data. The article is accessible here : <a href="https://www.nature.com/articles/s41597-023-01951-4">https://www.nature.com/articles/s41597-023-01951-4</a> These complete records consist of: <ol> <li>The complete training dataset containing RGB overhead imagery, segmentation masks and metadata of PV installations (folder bdappv),</li> <li>The raw crowdsourcing data, and the postprocessed data for replication and validation (folder data).</li> </ol> Data records Folders are organized as follows: <ul> <li>bdappv/ Root data folder <ul> <li>google / ign:  One folder for each campaign <ul> <li>img/: Folder containing all the images presented to the users. This folder contains 28807 images for Google and 17325 images for IGN.</li> <li>mask/: Folder containing all segmentations masks generated from the polygon annotations of the users. This folder contains 13303 masks for Google and 7686 masks for IGN.</li> </ul> </li> <li>metadata.csv The <code>.csv</code>  file with the installations' metadata.</li> </ul> </li> </ul>   <ul> <li>data/ Root data folder <ul> <li>raw/ Folder containing the raw crowdsourcing data and raw metadata; <ul> <li>input-google.json: <code>.json </code>input data data containing all information on images and raw annotators’ contributions for both phases (clicks and polygons) during the first annotation campaign;</li> <li>input-ign.json: <code>.json </code>input data containing all information on images and raw annotators’ contributions for both phases (clicks and polygons) during the second annotation campaign;</li> <li>raw-metadata.json: <code>.json </code>output containing the PV systems’ metadata extracted from the BDPV database before filtering. It can be used to replicate the association between the installations and the segmentation masks, as done in the notebook metadata.</li> </ul> </li> <li>replication/ Folder containing the compiled data used to generate the segmentation masks; <ul> <li>campaign-google/campaign-ign: One folder for each campaign <ul> <li>click-analysis.json: <code>.json </code>output on the click analysis, compiling raw input into a few best-guess locations for the PV arrays. This dataset enables the replication of our annotations,</li> <li>polygon-analysis.json: <code>.json </code>output of polygon analysis, compiling raw input into a best-guess polygon for the PV arrays.</li> </ul> </li> </ul> </li> <li>validation/ Folder containing the compiled data used for technical validation. <ul> <li>campaign-google/campaign-ign: One folder for each campaign <ul> <li>click-analysis-thres=1.0.json: <code>.json </code>output of the click analysis with a lowered threshold to analyze the effect of the threshold on image classification, as done in the notebook annotation;</li> <li>polygon-analysis-thres=1.0.json: <code>.json </code>output of polygon analysis, with a lowered threshold to analyze the effect of the threshold on polygon annotation, as done in the notebook annotations.</li> </ul> </li> <li>metadata.csv: the <code>.csv </code>file of filtered installations' metadata.</li> </ul> </li> </ul> </li> </ul> License We extracted the thumbnails contained in the google/img/ folder using Google Earth Engine API and we generated the thumbnails contained in the ign/img/ folder from high resolution tiles downloaded from the online IGN portal accessible here: <a href="https://geoservices.ign.fr/bdortho">https://geoservices.ign.fr/bdortho</a>. Images provided by Google are subjet to Google's terms and conditions. Images provided by the IGN are subject to an open license 2.0. Access the terms and conditions of Google images at this URL: <a href="https://www.google.com/intl/en/help/legalnotices_maps/">https://www.google.com/intl/en/help/legalnotices_maps/</a> Access the terms and conditions of IGN images at this URL: <a href="https://www.etalab.gouv.fr/wp-content/uploads/2018/11/open-licence.pdf">https://www.etalab.gouv.fr/wp-content/uploads/2018/11/open-licence.pdf</a>

opencc-by-4.0Jul 2022View details →

dryad40/100

Counting animals in aerial images with a density map estimation model

Animal abundance estimation is increasingly based on drone or aerial survey photography. Manual post-processing has been used extensively, however, volumes of such data are increasing, necessitating some level of automation, either for complete counting or as a labour-saving tool. Any automated processing can be challenging when using such tools on species that nest in close formation such as Pygoscelis penguins. We present here a customized CNN-based density map estimation method for counting of penguins from low-resolution aerial photography. Our model, an indirect regression algorithm, performed significantly better in terms of counting accuracy than standard detection algorithm (Faster RCNN) when counting small objects from low-resolution images and gave an error rate of only 0.8 percent. Density map estimation methods as demonstrated here can vastly improve our ability to count animals in tight aggregations, and demonstrably improve monitoring efforts from aerial imagery.

opencc-zeroMar 2023View details →

dryad40/100

Counting animals in aerial images with a density map estimation model

Open the record for dataset details and reuse information.

publicMar 2023View details →

edi40/100

Georectified Mosaic of Aerial Images of Baltimore City in 1927

Landscape analyses are typically done using spatially explicit color aerial imagery. However, working with non-spatial black and white historical aerial photographs presents several challenges that require a combination of techniques and approaches. We analyzed 93 aerial images covering 544 km2 (210 mi2) including all of Baltimore City, and an area immediately adjacent to the city known at the time as the Metropolitan District of Baltimore County. The images were taken from a biplane between October 1926 and February 1927. High-resolution scans were georeferenced and georectified against modern satellite imagery of the area and then combined to create a single raster mosaic. This process converted the images from a disparate set of photographs into a spatially explicit GIS data set that can be used to observe changes in land patches over time—and ultimately integrated with other long-term social, economic, and ecological data.

openCC (other)Jul 2021View details →

zenodo36/100

A curated dataset of aerial survey images over the central Congo Basin, 1958

This dataset contains a subset data from the Belgian Science Policy Office funded “Congo basin eco-climatological data recovery and valorisation" project (COBECORE, contract BR/175/A3/COBECORE). The data included is curated and pre-processed aerial survey imagery as used in a a land-use land-cover change analysis "Historical aerial surveys map long-term changes of forest cover and structure in the central Congo Basin".  The dataset includes: <ul> <li>the pre-processed images (aerial_images.tar.gz)</li> <li>the meta-data associated with the aerial images (flight_paths*)</li> <li>the final orthomosaic (yangambi_orthomosaic.tif)</li> </ul> For the full methodology we refer to the full paper: Hufkens K., et al. (2020) Historical Aerial Surveys Map Long-Term Changes of Forest Cover and Structure in the Central Congo Basin. Remote Sensing, 12, 638. Please cite the work as such.

opencc-by-4.0Nov 2019View details →

zenodo36/100

Aerial Images_Part 2_Integrating Remote Sensing and Machine Learning for Developing Spatio-Temporal Model to Predict Aquatic Larval Habitats of Malaria

Aerial Images_Part 2_Integrating Remote Sensing and Machine Learning for Developing Spatio-Temporal Model to Predict Aquatic Larval Habitats of Malaria

opencc-by-4.0Nov 2024View details →

ScienceDex guides

Understand access before you commit

These curated guides explain access requirements, typical timelines, costs, and reuse considerations for widely used research datasets.

Compare curated 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.

allen-brain-atlas

neuroscienceopenDocumentation, web resources, and API references are available online.

Last verified 2026-04-30Open record

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.

abode-home-cage

behavioral-neuroscienceopenThe DataShare record exposes download links for annotations, documentation, license text, and the zipped per-snippet data directory.

Last verified 2026-04-30Open record

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.

dandi-nwb

electrophysiologyopenPublished Dandiset metadata and archive endpoints are available through the production DANDI API.

Last verified 2026-04-30Open record

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.

ibl

behavioral-neuroscienceopenPublic sessions can be searched and loaded from the IBL public data server through ONE.

Last verified 2026-04-29Open record

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.

openneuro

neuroscienceopenPublished datasets are available on demand over the internet.

Last verified 2026-04-29Open record