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.
979
datasets available to search
ShareScore release 0.9.0
Dataset results
979 results for “image dataset”
Parcel3D - A Synthetic Dataset of Damaged and Intact Parcel Images with 2D and 3D Annotations
<p>Synthetic dataset of over 13,000 images of damaged and intact parcels with full 2D and 3D annotations in the <a href="https://cocodataset.org/#format-data">COCO format</a>. For details see our <a href="https://openaccess.thecvf.com/content/CVPR2023W/VISION/html/Naumann_Parcel3D_Shape_Reconstruction_From_Single_RGB_Images_for_Applications_in_CVPRW_2023_paper.html">paper</a> and for visual samples our <a href="https://a-nau.github.io/parcel3d/">project page</a>.</p> <p><br> Relevant computer vision tasks:</p> <ul> <li>bounding box detection</li> <li>classification</li> <li>instance segmentation</li> <li>keypoint estimation</li> <li>3D bounding box estimation</li> <li>3D voxel reconstruction</li> <li>3D reconstruction</li> </ul> <p> </p> <p>The dataset is for <strong>academic research use only</strong>, since it uses resources with restrictive licenses.<br> For a detailed description of how the resources are used, we refer to our <a href="https://openaccess.thecvf.com/content/CVPR2023W/VISION/html/Naumann_Parcel3D_Shape_Reconstruction_From_Single_RGB_Images_for_Applications_in_CVPRW_2023_paper.html">paper</a> and <a href="https://a-nau.github.io/parcel3d/">project page</a>.</p> <p>Licenses of the resources in detail:</p> <ul> <li><a href="https://research.google/resources/datasets/scanned-objects-google-research/">Google Scanned Objects</a>: <a href="https://creativecommons.org/licenses/by/4.0/">CC BY 4.0</a> (for details on which files are used, see the respective <em>meta </em>folder)</li> <li><a href="https://zenodo.org/record/8041823">Cardboard Dataset</a>: <a href="https://creativecommons.org/licenses/by/4.0/">CC BY 4.0</a></li> <li><a href="https://ieeexplore.ieee.org/abstract/document/8999123">Shipping Label Dataset</a>: <a href="https://creativecommons.org/licenses/by-nc/4.0/">CC BY-NC 4.0</a></li> <li>Other Labels: See file <em>misc/source_urls.json</em></li> <li><a href="https://github.com/weberhen/learning_indoor_lighting">LDR Dataset</a>: License for Non-Commercial Use</li> <li><a href="https://data.vision.ee.ethz.ch/sagea/lld/">Large Logo Dataset (LLD)</a>: Please notice that this dataset is made available for academic research purposes only. All the images are collected from the Internet, and the copyright belongs to the original owners. If any of the images belongs to you and you would like it removed, please kindly inform us, we will remove it from our dataset immediately.</li> </ul> <p>You can use our textureless models (i.e. the <em>obj</em> files) of damaged parcels under <a href="https://creativecommons.org/licenses/by/4.0/">CC BY 4.0</a> (note that this does not apply to the textures).</p> <p> </p> <p>If you use this resource for scientific research, please consider citing</p> <pre><code>@inproceedings{naumannParcel3DShapeReconstruction2023, author = {Naumann, Alexander and Hertlein, Felix and D\"orr, Laura and Furmans, Kai}, title = {Parcel3D: Shape Reconstruction From Single RGB Images for Applications in Transportation Logistics}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR) Workshops}, month = {June}, year = {2023}, pages = {4402-4412} }</code></pre>
Imaging dataset from: Longitudinal tracking of acute kidney injury reveals injury propagation along the nephron
<div> <span><span>Acute kidney injury (AKI) is a risk factor for chronic kidney disease (CKD), but the cellular mechanisms leading to i</span><span>m</span><span>paired tubular recovery and </span><span>subsequent</span> <span>AKI-CKD-transition are not yet fully understood. In this study, we combined </span><span>transgenic mice to </span><span>monitor</span><span> proliferation in vivo, </span><span>a novel </span><span>injury </span><span>model of AKI, in which </span><span>ischemia</span></span><span><span>-</span></span><span><span>reperfusion injury </span><span>(IRI) was induced in half of the kidney (partial</span></span><span><span>-</span></span><span><span>IRI), and serial intravital 2-photon imaging via an </span><span>Abdominal I</span><span>maging </span><span>W</span><span>indow (AIW) to track tissue remodeling in post- and non-ischemic kidney regions longitudinally over 3 weeks. Our results and novel findings are presented in the associated pre-print "Longitudinal tracking of acute kidney injury reveals injury propagation along the nephron".</span></span><span> </span> </div> <div> <span><span>In this dataset, we </span><span>provide</span><span> the imaging data which we </span><span>acquired</span><span> during the study.</span><span> Overall, the dataset consists of: #1: serial intravital imaging via 2-photon microscopy and genetic identification of proliferating cells in kidneys undergoing partial IRI; #2: serial intravital imaging via 2-photon microscopy and genetic identification of proliferating cells of control, uninjured kidneys; #3: intravital imaging of kidney epithelial cells during intravenous injection of a fluorescent bolus to determine the identity of tubular segments across the nephron; #4: intravital imaging of </span><span>and genetic identification of proliferating cells </span><span>after selective laser injury of </span><span>S1 </span><span>proximal tubule cells; #5 in vivo and ex-vivo imaging of kidney and kidney slices after VCAM1 staining. The data descriptors </span><span>provide</span><span> detailed guidelines on how to place individual imaging files in the context of the pathophysiological states used in the study.</span></span><span> </span> </div> <div> <span><span>Our goal is to </span><span>provide</span><span> an organize</span><span>d</span> <span>and accessible </span><span>unique and unprocessed </span><span>in vivo imaging dataset </span><span>that </span><span>documents </span></span><span><span>in vivo</span></span><span><span> tubule cell remodeling in </span><span>the mouse kidney </span></span><span><span>longitudinally and</span></span> <span><span>during </span><span>physiological and pathological conditions. Sharing </span><span>of </span><span>th</span><span>is</span><span> dataset </span><span>ensures</span><span> </span><span>reproducing</span><span> and expanding </span><span>of </span><span>our preclinical findings of </span><span>tubule injury and (failed)</span><span> recovery during AKI</span><span>. Furthermore, this dataset may also be </span><span>utilized</span> <span>for teaching purposes, as the combination of fluorescent imaging techniques allow</span><span>s</span><span> the </span><span>detail</span><span>ed</span><span> visualization of</span><span> kidney anatomy and physiology over multiple conditions.</span></span> </div>
Edge illumination X-ray phase contrast imaging with alternative gratings: dataset
<p>This dataset contains results from Edge illumunation X-ray phase contrast simulations with alternative gratings, as shown in 'Setup.png' The simulations are performed with the monte-carlo software Gate. Postprocessing is done in Matlab. Four different grating geometries were simulated: Conventional, sheared, curved and folded gratings. As phantom, a row of Aluminum cylinders is chosen.</p> <p>The simulation parameters can be found in the excel-file 'Simulation_parameters.xlsx'.</p> <p>The folder 'gate' contains the macros that where used for the monte carlo-simulation.</p> <p>The folder 'matlab' contains the results of post-processing in matlab for each grating geometry. They can be opened with the file 'results_script.m</p> <p>The folder 'results' contains images of the results for each geometry, including, flatfield, projection, threefold contrast and fitting parameters.</p> <table> <tbody> <tr> <td>This research was supported by EU Interreg Flanders - Netherlands Smart*Light (0386), Fonds wetenschappelijk onderzoek (G090020N, G094320N), and Agentschap Innoveren \& Ondernemen (Vlaio) (HBC.2020.2159). Nathanaël Six and Ben Huyge have a PhD fellowship of the FWO (11D8319N, 1S46122N).</td> </tr> </tbody> </table> <p> </p> <p></p>
Hyperspectral Placenta Dataset: Hyperspectral Image Acquisition, Annotations, and Processing of Biological Tissues in Microsurgical Training
<p>The dataset consists of 101 hyperspectral images of four fresh human placentas and six hyperspectral images of contrast dyes (i.e., indocyanine green and red and blue food colorant) that were captured in the range 515-900 nm, step = 5 nm. The hyperspectral images were manually annotated, delineating the key anatomical structures: arteries, veins, stroma, and the umbilical cord. Standard reference materials were used for flat-field correction. The dataset can be used to develop machine learning algorithms for the automated classification of biological structures, particularly the classification of superficial and deep vessels and transparent tissue layers.</p>
Dataset and images illustrating the 2022 gorgonian mass mortality event in the Calanques National Park
<p><strong>gorgonian_population_2012.JPG</strong>: A healthy gorgonian population in the Calanques National Park in 2012</p> <p><strong>gorgonian_population_2022.JPG:</strong> The same gorgonian population after the 2022 mass mortality event. The colonies show denuded axis</p> <p><strong>Marseille_Monitoring_Mortality_2022.xlsx:</strong> Raw data acquired during the survey of the health of red gorgonian and red coral populations in the Calanques National Park during late summer and autumn 2022</p>
A Dataset Containing Tiny Vehicle Images Collected in Low Quality Imaging Conditions
<p>This dataset contains 4800 tiny and low resolution vehicle images collected in low lighting and different weather conditions. The vehicles in the images are grouped in six classes: Bike, Car, Juggernaut, Minibus, Pickup, and Truck. For each class, there are 800 vehicle images with 100 × 100 pixels and 96 dpi resolution.</p> <p>The peer-reviewed data descriptor for this dataset has been published in MDPI Sustainability - an open access journal, and can be accessed here: <a href="https://doi.org/10.3390/su152316292">https://doi.org/10.3390/su152316292</a>. Please cite this when using the dataset.</p>
Monte Carlo based dataset to train a deep learning based partial volume correction for 177Lu-SPECT imaging
<p>This dataset contains pairs of random activity distribution and Monte Carlo simulated SPECT reconstructions used for the training of a deep learning based partial volume correction method. More detailed information on the creation of the data set, the partial volume correction and the use of the data can be found in the publication listed below and in the readme file.</p> <p> </p> <p>Publication: Will be updated, when published.</p>
Imaging dataset 04 for mtFociCounter
<p>This is the fourth dataset associated with the updated manuscript on mtFociCounter.</p> <p>Images are Spinning Disk Confocal Images of unsorted U2OS cells treated with siRNA against TFAM (siTFAM) or neutral siRNA (siNT). Cells were stained with antibodies against tom20 (<strong>mitochondria</strong>) and against dsDNA (<strong>nucleoids</strong>).<br> The second folder contains SIM2 images acquired on an Elyra7 microscope of 3t3 wild-type fibroblasts, which express <strong>mitochondrially </strong>targeted dsRed, and are stained by immunofluorescence against dsDNA (<strong>nucleoids</strong>) and AlexaFluor 647, as well as Hoecst for <strong>nuclei</strong>.</p> <p>This repository contains all data necessary to reproduce the analysis of siTFAM and 3t3-superresolution, as described in the manuscript. The dataset contains the following data:</p> <p>U2OS treated with siTFAM or neutral (WT):<br> 20210212 siTFAM vs. siNT<br> 20210217 siTFAM vs. siNT<br> 20210222 siTFAM vs. siNT</p> <p>3t3 WT fibroblasts images by Elyra7 SIM2:<br> 20221221<br> 20230118<br> 20230120</p> <p><br> The third folder contains images from Spinning Disk Confocal Images of unsorted U2OS cells. Cells were stained with antibodies against tom20 (mitochondria) and against FASTKD2 (MRGs).<br> The fourth folder contains raw Western Blot and Coomassie staining images from unsorted U2OS cells treated with a neutral siRNA or an siRNA against TFAM for 3 days. Antibodies against tubulin, TFAM or pre-TFAM were used, as indicated.</p> <p>This repository contains all data necessary to reproduce the analysis of MRG numbers or TFAM knockdown assessment, as described in the manuscript.</p> <p>U2OS WT cells:<br> 20230429 FASTKD2<br> 20230505 FASTKD2<br> 20230505 FASTKD2<br> <br> For details of the experimental procedure, please refer to the accompanying manuscript, which will soon be made available on BioRxiv.</p>
Dataset for "Data-driven empirical conductance relations during auroral precipitation using incoherent scatter radar and all sky imagers" JGR-Space Physics
<p><strong>Dataset for "Data-driven empirical conductance relations during auroral precipitation using incoherent scatter radar and all sky imagers" JGR-Space Physics.</strong></p> <p>Processed ACF level data can be provided by contacting me.</p> <p><strong>DOI of the publication:</strong></p> <p><strong>README file:</strong></p> <p>PFISRInversions_ASI_v1.1_Fang_01042023_v08162023.h5</p> <p>HallConductance: Altitude integrated Hall Conductance from 85-150 km altitude, [ntime], mho<br> PedersenConductance: Altitude integrated Pedersen Conductance from 85-150 km, [ntime], mho<br> EnergyFlux: Energy flux after integrating the differential number flux, [ntime], W/m^2<br> AverageEnergy: Average Energy after integrating the differential number flux, [ntime], eV<br> Measured_ElectronDensity: measured electron density from PFISR, [ntime, naltitude], #/m^3<br> Modeled_ElectronDensity: modeled electron density produced by the MEM version, [ntime,naltitude], #/m^3<br> UnixTime: time in seconds since 1970-01-01 00:00:00 UT, [ntime], seconds<br> NumberFlux: differential number flux, [ntime, nenergy], #/m^2 s^-1 eV^-1<br> EnergyGrid: energy grid spanning 1 keV - 100 keV in 25 steps, [nenergy], eV<br> ASIStatus: auroral identification number, [ntime], no units<br> 1: Discrete aurora<br> 2: Diffuse aurora<br> 3: Pulsating aurora<br> 8: Unidentified aurora<br> -1: data that was flagged as unsuitable:<br> either TEC was too low (no auroral E-region possibly associated with red aurora),<br> the modeled electron density was not consistent at all with the observed electron density (bad fit)</p> <p>ASIYEAR-Final_date.xlsx<br> This is an excel file that contains the original auroral image identification near the zenith direction<br> We used all sky imager videos located: http://optics.gi.alaska.edu/realtime/data/MPEG/PKR_DASC_256/<br> These files were converted into python pickle files and used internally for the rest of the investigation.</p> <p>The columns corresponds to days, and the rows correspond to time in UT as decimal hours:<br> The ASI Key is the following:<br> # 1 Discrete<br> # 2 Diffuse<br> # 3 Pulsating<br> # 4 Cloudy/Clear<br> # 5 Moon<br> # 6 Possible faint Aurora with moon out<br> # 7 Substorm Breakup<br> # 8 Cloudy with aurora (can't make out type)</p>
Image Dataset of Structures Damaged by Wildfire in California 2020-2022
<p>The dataset contains over 18,000 images of homes damaged by wildfire between 2020 and 2022 in California, USA, captured by the California Department of Forestry and Fire Protection (Cal Fire) during the damage assessment process. The dataset spans across more than 18 wildfire events, including the 2020 August Complex Fire, the first recorded "gigafire" event in California where the area burned exceeded 1 million acres. Each image, corresponding to a built structure, is classified by government damage assessors into 6 different categories: No Damage, Affected (1-9%), Minor (10-25%), Major (26-50%), Destroyed (>50%), and Inaccessible (image taken but not assessment made). While over 57,000 structures were evaluated during the damage assessment process, only about 18,000 contains images; additional data about the structures, such as the street address or structure materials, for both those with and without corresponding images can be accessed in the "Additional Attribute Data" file.</p> <p>The 18 wildfire events captured in the dataset are:</p> <ol> <li>[AUG] August Complex (2020)</li> <li>[BEA] Bear Fire (2020)</li> <li>[BEU] BEU Lightning Complex Fire (2020)</li> <li>[CAL] Caldor Fire (2021)</li> <li>[CAS] Castle Fire (2020)</li> <li>[CRE] Creek Fire (2020)</li> <li>[DIN] DINS Statewide (Collection of Smaller Fires, 2021)</li> <li>[DIX[ Dixie Fire (2021)</li> <li>[FAI] Fairview Fire (2022)</li> <li>[FOR] Fork Fire (2022)</li> <li>[GLA] Glass Fire (2020)</li> <li>[MIL] Mill Mountain Fire (2022)</li> <li>[MON] Monument Fire (2021)</li> <li>[MOS] Mosquito Fire (2022)</li> <li>[POST] Post Fire (2020)</li> <li>[SCU] SCU Complex Fire (2020)</li> <li>[VAL] Valley Fire (2020)</li> <li>[ZOG] Zogg Fire (2020)</li> </ol> <p>The author retrieved the data, originally published as GIS features layers, from from the publicly accessible <a href="https://hub-calfire-forestry.hub.arcgis.com/">CAL FIRE Hub</a>, then subsequently processed it into image and tabular formats. The author collaborated with Cal Fire in working with the data, and has received explicit permission for republication. </p>
Sound field image dataset
<p><strong>Description</strong></p> <p>This <strong>sound field image dataset</strong> contains clean-noisy pairs of complex-valued sound-field images generated by 2D acoustic simulations. The dataset was initially prepared for <strong>deep sound-field denoiser </strong>(<a href="https://github.com/nttcslab/deep-sound-field-denoiser">https://github.com/nttcslab/deep-sound-field-denoiser</a>)<strong>,</strong> a DNN-based denoising method for optically measured sound fields. Since the data is a two-dimensional sound field based on the Helmholtz equation, one can use this dataset for any acoustic application. Please check our <a href="https://github.com/nttcslab/deep-sound-field-denoiser">GitHub repository</a> and <a href="https://arxiv.org/abs/2304.14923">paper</a> for details.</p> <p> </p> <p><strong>Directory structure</strong></p> <p>The dataset contains three directories: training, validation, and evaluation. Each directory contains "soundsource#" sub-directories (# represents the number of sound sources used in the acoustic simulation). Each sub-directory has three h5 files for data (clean, white noise, and speckle noise) and three CSV files listing random parameter values used in the simulation.</p> <p>- /training</p> <p> - /soundsource#</p> <p> - constants.csv</p> <p> - random_variable_ranges.csv</p> <p> - random_variables.csv</p> <p> - sf_true.h5</p> <p> - sf_noise_white.h5</p> <p> - sf_noise_speckle.h5</p> <p> </p> <p><strong>Condition of use</strong></p> <p>This dataset is available under the attached license file. Read the terms and conditions in NTTSoftwareLicenseAgreement.pdf carefully.</p> <p> </p> <p><strong>Citation</strong></p> <p>If you use this dataset, please cite the following paper.</p> <ul> <li> <p>K. Ishikawa, D. Takeuchi, N. Harada, and T. Moriya ``Deep sound-field denoiser: optically-measured sound-field denoising using deep neural network,'' arXiv:2304.14923 (2023).</p> </li> </ul>
"CausalXtract: a flexible pipeline to extract causal effects from live-cell time-lapse imaging data" datasets
<p>Datasets from the article:</p> <p><strong>CausalXtract: a flexible pipeline to extract causal effects from live-cell time-lapse imaging data </strong></p> <p>by Franck Simon, Maria Colomba Comes, Tiziana Tocci, Louise Dupuis, Vincent Cabeli, Nikita Lagrange, Arianna Mencattini, Maria Carla Parrini, Eugenio Martinelli, Hervé Isambert.</p> <p> </p> <p>The <strong>original videos</strong> are uploaded as: "20161230.zip", "20170105.rar", "Video_2017_0517.zip".</p> <p><strong>Details </strong>for each <strong>experiment </strong>can be found in: "Experiments' details.zip".</p> <p>The <strong>ROIs </strong>(ROI: Region of Interest) are uploaded as .tif files in: "EXTRACTED ROIs.zip".</p> <p>The <strong>MATLAB data</strong> is uploaded in "MATLAB_DATA.rar" and includes: the cancer cells' trajectories (subfolder: "TUMOR TRAJECTORIES"), the immune cells' trajectories (subfolder: "IMMUNE TRAJECTORIES"), the ROIs videos as .mat files for the detection of cells (subfolder: "ROI MAT"), the ROIs further cropped for the extraction of shape descriptors (folder: "ROI_TU MAT"). The ROIs videos .mat files included in the last two subfolders are stopped after their apoptosis has been detected.</p>
Dataset of 1000 CT Images of Thoracic Vertebrae with Segmentation
<p>Dataset of 1000 CT Images of Thoracic Vertebrae with Segmentation<br> </p> <p>B08 - DICOM scaled to 0-255</p> <p>B16 - DICOM 1:1 without Interslope</p> <p>B12 - DICOM scaled to 0-255 - division by 16 (4bits)</p> <p>BoneWnd - DICOM scaled to 0-255 - division by 8 (3bit), window of bone only</p>
Dataset of 1000 CT Images of Thoracic Vertebrae with Segmentation
<p>Dataset of 1000 CT Images of Thoracic Vertebrae with Segmentation</p> <p>B08 - DICOM scaled to 0-255</p> <p>B16 - DICOM 1:1 without Interslope</p> <p>B12 - DICOM scaled to 0-255 - division by 16 (4bits)</p> <p>BoneWnd - DICOM scaled to 0-255 - division by 8 (3bit), window of bone only<br> </p>
UAV-PDD2023: A benchmark dataset for pavement distress detection based on UAV images
<p>The images in the dataset ( VOC format) were captured by a UAV at an altitude of 30 meters. The collected images were annotated in PASCAL VOC format. A total of 11,158 instances in 2,440 images are incorporated in the dataset.</p> <ul> <li>The UAV-PDD2023 dataset, captured by unmanned aerial vehicles (UAVs), provides a benchmark for road damage detection. It is highly useful for municipal authorities and road agencies to conduct low-cost road condition monitoring. </li> <li>Six types of road damages are labeled in the dataset: Longitudinal cracks (LC), Transverse cracks (TC), Alligator cracks (AC), Oblique cracks (OC), Repair (RP), and Potholes (PH). </li> <li>Researchers can use this dataset as a benchmark to evaluate the performance of different algorithms in addressing similar problems, such as image classification and object detection. </li> </ul> <p> </p>
Spatial transcriptomics images for papillary and anaplastic thyroid cancer IRIBHM dataset
<p>This dataset includes the image files for spatial transcriptomics data associated with the publication "Idiosyncratic and generic single nuclei and spatial transcriptional patterns in papillary and anaplastic thyroid cancers".</p>
maDLC Tri-Mouse Benchmark Dataset - Test Images
<p>see https://benchmark.deeplabcut.org/ for more information.</p>
Annotated dataset of microscope images of pollen grains in honey from 17 beekeeping taxa
<p><strong>Annotated dataset of microscope images of pollen grains in honey from 17 beekeeping taxa</strong></p><p>Melissopalynology is a method based on the separation of pollen grains present in honey and the identification of the plant species to which they belong. It is used to determine the botanical, but also the geographical origin of the honey, as well as its commercial value. For this reason, a database including microscope images and characteristics of pollen grains of 17 beekeeping taxa, usually present in honey samples, was created. </p><p>For the honey preparations the methodology of Louveaux et al. (1978) and Von Der Ohe et al. (2004) was followed. Specifically, 5.0 g of honey were weighed and dissolved in 10 ml of distilled water. The solution was centrifuged for 10 min at 2300 r/min. The supernatant solution was discarded and the precipitate was transferred with a disposable plastic Pasteur pipette onto a slide, where it was spread with the addition of fuchsin on a 22 x 22 mm surface. Staining with fuchsin helps to see in greater detail the morphological characteristics of the pollen grains. The preparation was dried by gentle heating to 40°C, on a heating plate and covered with a coverslip on which a small amount of Entellan adhesive (Merck) has been placed. The pollen grains were photographed on an optical microscope (Olympus SZX12), with lens 40× (Olympus DF PLAPO 1X DF) and a digital analysis camera (Olympus SC30), while a morphometry software (Image Pro Plus Software, V1.1.19) was used for their determination. For the microscopic identification of the pollen types, the collection of reference slides from the Laboratory of Apiculture of the Aristotle University of Thessaloniki, which is accredited to ISO 17025:2017, was used. </p><p>The dataset contains 1404 training captured microscope images of pollen grains from 17 major beekeeping taxa (class list can be found below) and 85 testing captured images. Polygon annotations were created using LabelMe software and saved in COCO Annotation format (train.json and val.json files). </p><p>Further information about the related project (SmartBeeKeep) can be found in the following article and presentation (please site if you use these data):</p><ul><li>Vasilios Liolios, Dimitrios Kanelis, Maria-Anna Rodopoulou, Chrysoula Tananaki (2023). A Comparative Study of Methods Recording Beekeeping Flora. Forests, 14(8), 1677; <a href="https://doi.org/10.3390/f14081677">https://doi.org/10.3390/f14081677</a> </li><li>Nikos Grammalidis, Andreas Stergioulas, Aggelos Avramidis, Konstantinos Karystinakis, Athanasios Partozis, Athanasios Topaloudis, Georgia Kalantzi, Chrisoula Tananaki, Dimitrios Kanelis, Vasilis Liolios, and Madesis Panagiotis "A smart beekeeping platform based on remote sensing and artificial intelligence", Proc. SPIE 12786, Ninth International Conference on Remote Sensing and Geoinformation of the Environment (RSCy2023), 127860C (21 September 2023); <a href="https://doi.org/10.1117/12.2681866%20">https://doi.org/10.1117/12.2681866</a> Event: Ninth International Conference on Remote Sensing and Geoinformation of the Environment (RSCy2023), 2023, Ayia Napa, Cyprus <a href="https://smartbeekeep.eu/files/rscyp23_sbk_paper.pdf">Author preprint available</a></li></ul><p><strong>Annotation - Latin name</strong></p><p>Myrtus - Myrtus communis</p><p>Brassicaceae - Brassicaceae</p><p>Cercis - Cercis siliquastrum</p><p>Helianthus annuus - Helianthus annuus</p><p>Lavandula - Lavandula angustifolia</p><p>Robinia pseudacacia - Robinia pseudoacacia</p><p>Olea - Olea europaea</p><p>Citrus - Citrus sp.</p><p>Paliurus - Paliurus spina-christi</p><p>Eucalyptus - Eucalyptus sp.</p><p>Polygonum - Polygonum aviculare</p><p>Carduus - Silybum marianum</p><p>Cistus - Cistus sp.</p><p>thymus - Thymus sp.</p><p>Castanea - Castanea sativa</p><p>erica - Erica manipuliflora</p><p>Gossypium - Gossypium hirsutum</p><p> </p>
Annotated dataset of pollen pellet images from 40 major beekeeping plants
<p>Pollen is the main source of proteins, amino acids, lipids, sterols, fatty acids, vitamins and other nutrients for honeybees. Knowing the pollinating plants of an area and identifying the incoming pollen sources inside the hive can be extremely useful information for beekeepers in controlling the development of their colonies and implementing appropriate manipulations throughout the year. Thus, a database was created, including images and characteristics of the pollen pellets of 40 major beekeeping plants. Bee pollen was collected from pollen traps, which were placed at the hive entrances of experimental bee colonies.</p><p>Freshly collected pollen was cleaned of foreign matter and placed -18 oC in glass jars until the time of analysis. Every 15 days a representative sample of 10% of the total quantity was separated mainly by color, shape and size in order to assess the contribution of each species. For the identification of pollen grains, the Louveaux method was used, according to which a small amount of pollen was placed on a slide and the pellets were dissolved with 2-3 drops of diethyl ether. After evaporation of the solvent, a drop of aqueous isoglucose solution (2:1) was added to hydrate the pollen grains and a drop of alcoholic fuchsin solution was added to stain them. The preparations were then placed on a hot plate to evaporate the moisture. This was followed by placement of a coverslip with Entellan to fix the preparation. The final preparation was examined under the microscope to identify the plant from which the pollen pellet came. For the microscopic identification of the pollen types, the collection of reference slides from the Laboratory of Apiculture of the Aristotle University of Thessaloniki, which is accredited to ISO 17025:2017, was used. Pollen pellets from the various taxa were placed on a special white plate to ensure a neutral background and to limit possible reflections as much as possible. Photographs were taken with smartphone cameras, in order to simulate the actual conditions of photography for potential users in the field.</p><p>The dataset contains 139 training captured images of bee pollen pellets from 40 major beekeeping plants (class list can be found below) and 13 testing captured images. Polygon annotations were created using LabelMe software and saved in COCO Annotation format (train.json and val.json files).</p><p>Further information about the related project (SmartBeeKeep) can be found in the following article and presentation (please site if you use these data):</p><ul><li>Vasilios Liolios, Dimitrios Kanelis, Maria-Anna Rodopoulou, Chrysoula Tananaki (2023). A Comparative Study of Methods Recording Beekeeping Flora. Forests, 14(8), 1677; <a href="https://doi.org/10.3390/f14081677">https://doi.org/10.3390/f14081677</a> </li><li>Nikos Grammalidis, Andreas Stergioulas, Aggelos Avramidis, Konstantinos Karystinakis, Athanasios Partozis, Athanasios Topaloudis, Georgia Kalantzi, Chrisoula Tananaki, Dimitrios Kanelis, Vasilis Liolios, and Madesis Panagiotis "A smart beekeeping platform based on remote sensing and artificial intelligence", Proc. SPIE 12786, Ninth International Conference on Remote Sensing and Geoinformation of the Environment (RSCy2023), 127860C (21 September 2023); <a href="https://doi.org/10.1117/12.2681866%20">https://doi.org/10.1117/12.2681866</a> Event: Ninth International Conference on Remote Sensing and Geoinformation of the Environment (RSCy2023), 2023, Ayia Napa, Cyprus <a href="https://smartbeekeep.eu/files/rscyp23_sbk_paper.pdf">Author preprint available</a></li></ul><p><strong>Annotation - Latin name</strong></p><p>Anthemis - Anthemis sp.</p><p>Asphodelus - Asphodelus fistulosus</p><p>Brassica napus - Brassica napus</p><p>Castanea sativa - Castanea sativa</p><p>Cephalaria transsylvanica - Cephalaria transsylvanica</p><p>Chenopodium album - Chenopodium album</p><p>Cichorium - Cichorium intybus</p><p>Cistus - Cistus creticus</p><p>Cistus salvifolius - Cistus salvifolius</p><p>Convolvulus - Convolvulus arvensis</p><p>Daucus - Daucus carota</p><p>Echium - Echium plantagineum</p><p>Erica - Erica manipuliflora</p><p>Hedera helix - Hedera helix</p><p>Helianthus - Helianthus annuus</p><p>Heliotropium - Heliotropium europaeum</p><p>Hypericum - Hypericum perforatum</p><p>Lavandula - Lavandula angustifolia</p><p>Ligustrum - Ligustrum japonicum</p><p>Matricaria - Matricaria chamomilla</p><p>Olea_europaea_9cm - Olea europaea</p><p>Paliurus - Paliurus spina-christi</p><p>Papaver - Papaver rhoeas</p><p>Pinus - Pinus sp.</p><p>Polygonum_aviculare - Polygonum aviculare</p><p>Portulaca - Portulaca oleracea</p><p>Pyrus - Pyrus spinosa</p><p>Quercus - Quercus coccifera</p><p>Rosmarinus - Rosmarinus officinalis</p><p>Rubus - Rubus ulmifolius</p><p>Carduus - Silybum marianum</p><p>sinapis - Sinapis arvensis</p><p>Sonchus - Sonchus asper</p><p>Taraxacum - Taraxacum officinale</p><p>Tamarix - Tamarix sp.</p><p>Tilia - Tilia sp.</p><p>Tribulus - Tribulus terrestis</p><p>Trifolium pratensis - Trifolium campestre</p><p>Verbascum - Verbascum nigrum</p><p>Vicia - Vicia villosa</p>
Image dataset: Applicability of hyperspectral imaging during salinity stress in rice for tracking Na+ and K+ levels in planta
Open the record for dataset details and reuse information.
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.