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.
108
datasets available to search
ShareScore release 0.7.1
Dataset results
108 results for “imagery data”
Data from: A convolutional neural network for detecting sea turtles in drone imagery
1. Marine megafauna are difficult to observe and count because many species travel widely and spend large amounts of time submerged. As such, management programs seeking to conserve these species are often hampered by limited information about population levels. 2. Unoccupied aircraft systems (UAS, aka drones) provide a potentially useful technique for assessing marine animal populations, but a central challenge lies in analyzing the vast amounts of data generated in the images or video acquired during each flight. Neural networks are emerging as a powerful tool for automating object detection across data domains and can be applied to UAS imagery to generate new population-level insights. To explore the utility of these emerging technologies in a challenging field setting, we used neural networks to enumerate olive ridley turtles (Lepidochelys olivacea) in drone images acquired during a mass-nesting event on the coast of Ostional, Costa Rica. 3. Results revealed substantial promise for this approach; specifically, our model detected 8% more turtles than manual counts while effectively reducing the manual validation burden from 2,971,554 to 44,822 image windows. Our detection pipeline was trained on a relatively small set of turtle examples (N=944), implying that this method can be easily bootstrapped for other applications, and is practical with real-world UAS datasets. 4. Our findings highlight the feasibility of combining UAS and neural networks to estimate population levels of diverse marine animals and suggest that the automation inherent in these techniques will soon permit monitoring over spatial and temporal scales that would previously have been impractical.
Data files for Sheehan et al. 2023 'City Scale Traffic Monitoring Using WorldView Satellite Imagery and Deep Learning: A Case Study of Barcelona' DOI: https://doi.org/10.3390/rs15245709
<p>Data files for Sheehan et al. (2023) City Scale Traffic Monitoring Using WorldView Satellite Imagery and Deep Learning: A Case Study of Barcelona. Remote Sensing. 15(24) DOI: <a href="https://doi.org/10.3390/rs15245709">https://doi.org/10.3390/rs15245709</a></p> <p>Description of contents: </p> <p>xView-YOLOv3_Model6_Barcelona_weights.pt</p> <p>This file contains the pre-trained weights for the xView-YOLOv3 model (model code available here: https://github.com/ultralytics/xview-yolov3). These weights were trained on a manually created training data set of vehicles present in WorldView 2/3 imagery covering the city of Barcelona. The weights relate to Model 6 set up: a single vehicle class (parked, static and moving), RGB imagery, Barcelona training data set derived anchor boxes, 1500 x 1500 pixel sized images and to 1000 epochs. </p> <p> </p>
Data set: Al-Biruni Earth Radius Optimization with Deep Transfer Learning based Scene Image Classification on Remote Sensing Imagery
Open the record for dataset details and reuse information.
Heron Island Satellite Imagery Classified Benthic Data and Halo Analyses and Models
<p>This dataset includes satellite imagery data from Heron Island, Australia downloaded from Google Earth Pro in 2023, with image from Maxar Technologies dated 2016 clipped to the shallow lagoon layer from the Allen Coral Atlas shape file classified into benthic categories: corals, algae and sand using a combination of unsupervised machine learning spectral classification and manual training and assignment of classes. This dataset also includes scoring of selected coral patch reefs for isolated halos across time using historical aerial imagery.</p> <p>We also include 2 notebooks with code used to generate figures and run analyses for data, geometric, and consumer-resource models for coral halo patterns supporting the work entitled, "Consumer-resource interactions reflected in coral halo patterns" by the authors listed. A knitted html for R Markdown file is also included.</p>
Data and models for "Center-fixing of tropical cyclones using uncertainty-aware deep learning applied to high-temporal-resolution geostationary satellite imagery" by Lagerquist et al.
<p><span><span><span>The file geocenter_models.tar contains all models comprising the GeoCenter ensemble: 3 convolutional neural networks (CNN), 3 isotonic-regression files (one for correcting each CNN’s mean estimate), and 3 more isotonic-regression files (one for correcting each CNN’s ensemble spread). Every model is found in a subdirectory whose names indicate which infrared (IR) wavelengths are used as input to the CNN. For example:</span></span></span></p> <ul> <li> <p><span><span><span>wavelengths-microns=3.900-7.340-13.300/model.weights.h5: An HDF5 file containing the trained CNN that uses data from bands 7, 10, 16 (corresponding to 3.9, 7.34, and 13.3 microns on the GOES ABI imager). The trained CNN can always be read by neural_net_utils.read_model() in the ml4tccf library (https://doi.org/10.5281/zenodo.15116854).</span></span></span></p> </li> <li> <p><span><span><span>wavelengths-microns=3.900-7.340-13.300/model_metadata.p: A Pickle file containing metadata for the trained CNN. This file is needed to read the CNN itself with neural_net_utils.read_model(). Otherwise, you will probably never need to access this metafile directly.</span></span></span></p> </li> <li> <p><span><span><span>wavelengths-microns=3.900-7.340-13.300/isotonic_regression/isotonic_regression.dill: A Dill file </span></span></span><span><span><span>containing isotonic-regression models used to bias-correct the ensemble mean from the same CNN. </span></span></span><span><span><span> The trained isotonic-regression models can always be read by scalar_isotonic_regression.read_file() in the ml4tccf library. Note that there are technically two isotonic-regression models for every CNN’</span></span></span><span><span><span>s ensemble mean</span></span></span><span><span><span>: one that bias-corrects the </span></span></span><em><span><span><span>x</span></span></span></em><span><span><span>-coordinate of the TC-center, another that bias-corrects the </span></span></span><em><span><span><span>y</span></span></span></em><span><span><span>-coordinate.</span></span></span></p> </li> <li> <p><span><span><span>wavelengths-microns=3.900-7.340-13.300/</span></span></span><span><span><span>uncertainty_calibration</span></span></span><span><span><span>/</span></span></span><span><span><span>uncertainty_calibration.dill: A Dill file containing isotonic-regression models used to bias-correct the ensemble spread from the same CNN. In the ml4tccf code, I make a distinction between “isotonic_regression” (correcting the ensemble mean) and “uncertainty_calibration” (correcting the ensemble spread), but note that both models are isotonic regression and use the sklearn.isotonic.IsotonicRegression class. The trained uncertainty-calibration models can always be read by scalar_uncertainty_calibration.read_file() in the ml4tccf library. Again, note that there are technically two uncertainty-calibration models per CNN: one for spread in the </span></span></span><span><span><span><em>x</em></span></span></span><span><span><span>-coordinate, one for spread in the </span></span></span><span><span><span><em>y</em></span></span></span><span><span><span>-coordinate.</span></span></span></p> </li> </ul> <p><span> </span></p> <p><span><span><span>As mentioned above, every trained CNN can be read by neural_net_utils.read_model(). Also, every trained CNN can be applied to new data (inference mode) by neural_net_utils.apply_model(). The input argument model_object should be the object returned by neural_net_utils.read_model(), and I suggest setting num_examples_per_batch = 10 to avoid out-of-memory errors. The only other input argument is predictor_matrices, which is a list of two numpy arrays. The first numpy array contains IR imagery centered at the first-guess TC center, and the second numpy array contains ATCF scalars. The first numpy array should have dimensions S (number of TC samples) x </span></span></span><span><span><span>3</span></span></span><span><span><span>00 (grid rows) x </span></span></span><span><span><span>3</span></span></span><span><span><span>00 (grid columns) x </span></span></span><span><span><span>9</span></span></span><span><span><span> (lag times) x 3 (wavelengths). Lag times should be in the following order: </span></span></span><span><span><span>240, 210, </span></span></span><span><span><span>180, 150, 120, 90, 60, 30, 0 min ago. Wavelengths should be in the order indicated by the subdirectory name. The numpy array itself should contain </span></span></span><em><span><span><span>normalized</span></span></span></em><span><span><span> brightness temperatures at the given lag times and wavelengths, following the grid specifications laid out in the journal paper (a </span></span></span><em><span><span><span>plate carrée</span></span></span></em><span><span><span> grid with 2-km spacing). The original IR data (brightness temperatures) must be normalized to </span></span></span><em><span><span><span>z</span></span></span></em><span><span><span>-scores using the same normalization parameters as in the journal paper, </span></span></span><em><span><span><span>i.e.,</span></span></span></em><span><span><span> those based on the training data. See details below. The second numpy array in predictor_matrices should have dimensions S (number of TC samples) x 9 (variables). The variables must in the order: absolute latitude, cosine of longitude, sine of longitude, TC intensity, minimum central pressure, tropical flag, subtropical flag, extratropical flag, disturbance flag. The journal paper contains details on all these variables in one table. These variables must come from A-deck files at the </span></span></span><span><span><span>second-</span></span></span><span><span><span>most recent synoptic time. Like the IR data, these ATCF scalars must be normalized to </span></span></span><em><span><span><span>z</span></span></span></em><span><span><span>-scores using the same normalization parameters as in the journal paper. See details below.</span></span></span></p> <p> </p> <p><span><span><span>Once you have predictions (estimated TC-center locations) from a CNN, you can bias-correct these predictions. To read the isotonic-regression model for the given CNN’s ensemble mean, use scalar_isotonic_regression.read_file() in the ml4tccf library. To apply the same model, use scalar_isotonic_regression.apply_models(). For the CNN’s ensemble spread, use scalar_uncertainty_calibration.read_file() and scalar_uncertainty_calibration.apply_models().</span></span></span></p> <p> </p> <p><span><span><span>To normalize the IR data, you will need the file ir_satellite_normalization_params.tar included with this dataset. Within the tar file is a single zarr file. You can read the zarr file with normalization.read_file() in the ml4tccf library; then you can normalize new data with normalization.normalize_data().</span></span></span></p> <p> </p> <p><span><span><span>To normalize the ATCF data, you will need the file a_deck_normalization_params.nc included with this dataset. This is a NetCDF file, containing the full set of training values for all 5 ATCF variables that are normalized (the binary storm-type flags are not normalized). You can read this file using any of the standard Python methods for reading NetCDF files, such as xarray.open_dataset(). To normalize new ATCF data, you can use the method normalization._normalize_one_variable(), where the argument actual_values_training is the list of training values from a_deck_normalization_params.nc for the given variable, while actual_values_new is the list of values to be normalized (currently in physical units, to be converted to </span></span></span><em><span><span><span>z</span></span></span></em><span><span><span>-score units).</span></span></span></p>
Arctic sea ice concentration data record in 6.25 km polar stereographic grid from three-year Landsat-8 imagery
<p>This dataset consists of true-like sea ice concentration (SIC) data records over the Arctic Ocean, which was derived from the 30 m resolution imagery from the Operational Land Imager (OLI) onboard Landsat-8. Each SIC map are given in a 6.25 km polar stereographic grid, and are catalogued into one of the twelve sub-regions (Baffin Bay and Labarador Seas, Barents Sea, Beaufort Sea, Bering Sea, Canadian Archipelago, Central Arctic, Chukchi Sea, East Greenland Sea, East Siberian Sea, Hudson Bay, Kara Sea, Laptev Sea) of the Arctic Ocean. This dataset also contains the number of Landsat-8 pixels used in the calculation of each SIC values, the coastal mask, and the sub-region mask.</p> <p>The naming convention for the files is "sic_landsat08_{sub-region name}.nc".</p> <p>The dataset is in netCDF format and is compliant with the CF 1.8 and ACDD 1.3 convention for netCDF files. The description of the variables along with some key global attributes of the data are provide below.</p> <table> <tbody> <tr> <td><strong>Global Attribute</strong></td> <td><strong>Meaning</strong></td> <td><strong> Attributes</strong></td> <td> </td> </tr> <tr> <td>title</td> <td>Title of the dataset</td> <td><strong> </strong></td> <td><strong> </strong></td> </tr> <tr> <td>sub_region</td> <td>Name of the sub-region for each dataset</td> <td><strong> </strong></td> <td><strong> </strong></td> </tr> <tr> <td><strong>Variable Name</strong></td> <td><strong>Meaning</strong></td> <td><strong>Attributes</strong></td> <td><strong>Dimension</strong></td> </tr> <tr> <td>time</td> <td>Reference time of satellite image</td> <td>seconds since 1981-01-01 00:00:00Z</td> <td>[time]</td> </tr> <tr> <td>lon</td> <td>Longitude</td> <td> </td> <td>[Y, X]</td> </tr> <tr> <td>lat</td> <td>Latitude</td> <td> </td> <td>[Y, X]</td> </tr> <tr> <td>X</td> <td>x coordinate of projection</td> <td> </td> <td>[X]</td> </tr> <tr> <td>Y</td> <td>y coordinate of projection</td> <td> </td> <td>[Y]</td> </tr> <tr> <td>sea_ice_concentration</td> <td>Estimated fractional sea ice area from Landsat-8 measurements</td> <td>_FillValue : -99</td> <td>[time, Y, X]</td> </tr> <tr> <td>sample_size</td> <td>Number of Landsat-8 pixels used to estimate the sea ice concentration</td> <td>_FillValue : 0</td> <td>[time, Y, X]</td> </tr> <tr> <td>coastal_mask</td> <td>Open-sea/Coastal Flag</td> <td>[Open_sea, Coast] = [0, 1]</td> <td>[Y, X]</td> </tr> <tr> <td>sub_region_mask</td> <td>Sub-region Flag</td> <td>[inside_sub_region, outside_sub_region] = [0, 1]</td> <td>[Y, X]</td> </tr> <tr> <td>cloud_contamination_category</td> <td>Qualitatively assessed cloud contamination for Landsat-8 Level 1 Collection 2 data used to produce SIC</td> <td>[underestimated_cloud_cover, overestimated_cloud_cover, correctly_estimated_cloud_cover_for_clear_sky, correctly_estimated_cloud_cover_for_cloudy_sky] = [1, 2, 3, 4]</td> <td>[time]</td> </tr> <tr> <td>source_name</td> <td>Filename of original Landsta-8 Level 1 Collection 2 data used to produce SIC</td> <td> </td> <td>[time]</td> </tr> </tbody> </table> <p> </p>
Mental imagery data from words
<p>Full database with norms and collected data for a corpus of descriptors varying in familiarity and vividness of imagery. </p>
Code and Data for "A machine learning approach for estimating snow depth across the European Alps from Sentinel-1 imagery"
<p>Here we share the data and code for “A machine learning approach for estimating snow depth across the European Alps from Sentinel-1 imagery”</p> <p>Corresponding author: Devon Dunmire devon.dunmire@kuleuven.be</p> <p>‘model_training’ - contains script to train the ML model, and training data sets from (1) in-situ snow measurement sites (training_data.p) and (2) photogrammetry snow depth maps (map_training_data.p)</p> <p>‘Cross_val_predictions’ contains model predictions for our cross-validation of all the in-situ snow measurement sites</p> <p>‘run_model’ contains the trained model (final_model_xg.pkl) and scripts to retrieve snow depth with our ML model.</p> <p>‘SD_*’ zip folders contains daily ML snow depth output over the European Alps for each snow year from Sept. 1 2015 - Apr. 30 2023. Data from multiple orbits is averaged.</p> <p>Naming convention: ‘S1_ml_SD_{yyyymmdd}_.nc’</p>
music_imagery_data
<p><strong>Data for the study reported in:</strong></p> <ul> <li>Martinez, D. R. Q., Rubio, G. F., Bonetti, L., Achyutuni, K. G., Tzovara, A., Knight, R. T., & Vuust, P. (2024). <br>Decoding reveals the neural representation of perceived and imagined musical sounds (p. 2023.08.15.553456). <br>bioRxiv. https://doi.org/10.1101/2023.08.15.553456</li> </ul> <p><strong>Description</strong></p> <ul> <li><strong>demographics.csv</strong>: Participant demographics.</li> <li><strong>decoding_accuracies</strong>: Time-generalized neural decoding accuracy per participant stored as Python dict containing 2d arrays (training_times x testing_times), with each entry indexing a condition or contrast of interest.</li> <li><strong>decoding_patterns</strong>: Decoding patterns per participant obtained from model coefficients stored as dict containing mne.Epochs arrays indexed by condition or contrast name.</li> <li><strong>epochs</strong>: Per participant single-trial epochs stored as dict containing mne.Epochs arrays after preprocessing (ica removed, high-pass >= 0.05Hz, smoothing with tstep= 25ms and twin=50ms, sfreq=40Hz).</li> <li><strong>figures_data</strong>: Values plotted in each figure and/or the data necessary to obtain them. Excel sheets or csv.</li> <li><strong>inverse_solutions</strong>: Inverse operator per participant to project sensor data into source space (mne inverse class).</li> <li><strong>logs</strong>: Experiment log files. Recall=recognize, manipulation=invert.</li> <li><strong>MNI_transforms</strong>: Transformation matrices per subject to convert source data into common MNI space.</li> <li><strong>neural_accuracy</strong>: Diagonal neural decoding accuracies per subject and time-point, together with behavioral and demographic data.</li> <li><strong>statistics</strong>: Statistical output for the different tests. Dictionaries with entries containing t-statisitcs, p-values, clusters, etc...</li> </ul>
Data from: Processing citizen science- and machine-annotated time-lapse imagery for biologically meaningful metrics
Time-lapse cameras facilitate remote and high-resolution monitoring of wild animal and plant communities, but the image data produced require further processing to be useful. Here we publish pipelines to process raw time-lapse imagery, resulting in count data (number of penguins per image) and 'nearest neighbour distance' measurements. The latter provide useful summaries of colony spatial structure (which can indicate phenological stage) and can be used to detect movement – metrics which could be valuable for a number of different monitoring scenarios, including image capture during aerial surveys. We present two alternative pathways for producing counts: 1) via the Zooniverse citizen science project Penguin Watch and 2) via a computer vision algorithm (Pengbot), and share a comparison of citizen science-, machine learning-, and expert- derived counts. We provide example files for 14 Penguin Watch cameras, generated from 63,070 raw images annotated by 50,445 volunteers. We encourage the use of this large open-source dataset, and the associated processing methodologies, for both ecological studies and continued machine learning and computer vision development.
Data from: The music of silence. Part I: Responses to musical imagery encode melodic expectations and acoustics
<p>Musical imagery is the voluntary internal hearing of music in the mind without the need for physical action or external stimulation. Numerous studies have already revealed brain areas activated during imagery. However, it remains unclear to what extent imagined music responses preserve the detailed temporal dynamics of the acoustic stimulus envelope and, crucially, whether melodic expectations play any role in modulating responses to imagined music, as they prominently do during listening. These modulations are important as they reflect aspects of the human musical experience, such as its acquisition, engagement, and enjoyment. This study explored the nature of these modulations in imagined music based on EEG recordings from 21 professional musicians (6 females and 15 males). Regression analyses were conducted to demonstrate that imagined neural signals can be predicted accurately, similarly to the listening task, and were sufficiently robust to allow for accurate identification of the imagined musical piece from the EEG. In doing so, our results indicate that imagery and listening tasks elicited an overlapping but distinctive topography of neural responses to sound acoustics, which is in line with previous fMRI literature. Melodic expectation, however, evoked very similar frontal spatial activation in both conditions, suggesting that they are supported by the same underlying mechanisms. Finally, neural responses induced by imagery exhibited a specific transformation from the listening condition, which primarily included a relative delay and a polarity inversion of the response. This transformation demonstrates the top-down predictive nature of the expectation mechanisms arising during both listening and imagery.</p>
Ulex (Ulex europaeus) UAV imagery and reference data (raw)
<p>This dataset includes drone (Uncrewed Aerial Vehicles, UAV) orthomosaics (RGB, n =4) of Ulex europaeus acquired between 2016-2017 in Chile. The resolution (ground sampling distance) of the orthomosaics amounts to approx. 3-4 cm. The orthomosaics are partially labelled (polygon shapefiles) in terms of Ulex cover. Each orthomosaic comes with an AOI (area of interest, polygon shapefile) that indicates the areas where the labelling was performed. Within the extent of this AOI Ulex canopies are assumed to be completely delineated (by visual interpretation).</p> <p>For visual inspection of the imagery we recommend to generate image pyramids since the image data has a very high spatial resolution.</p> <p>Details on the dataset are mentioned in the corresponding publication:</p> <p>Kattenborn, T., Lopatin, J., Förster, M., Braun, A. C., & Fassnacht, F. E. (2019). UAV data as alternative to field sampling to map woody invasive species based on combined Sentinel-1 and Sentinel-2 data. <em>Remote sensing of environment</em>, <em>227</em>, 61-73.</p> <p><a href="https://doi.org/10.1016/j.rse.2019.03.025">https://doi.org/10.1016/j.rse.2019.03.025</a></p> <p><a href="https://www.sciencedirect.com/science/article/abs/pii/S0034425719301166">https://www.sciencedirect.com/science/article/abs/pii/S0034425719301166</a></p>
Acacia (Acacia dealbata) UAV imagery and reference data (raw)
<p>This dataset includes drone (Uncrewed Aerial Vehicles, UAV) orthomosaics (RGB, n =2) of Pinus radiata acquired between 2016-2017 in Chile. The resolution (ground sampling distance) of the orthomosaics amounts to approx. 3-4 cm. The orthomosaics are partially labelled (polygon shapefiles) in terms of Pinus cover. Each orthomosaic comes with an AOI (area of interest, polygon shapefile) that indicates the areas where the labelling was performed. Within the extent of this AOI Pinus canopies are assumed to be completely delineated (by visual interpretation).</p> <p>For visual inspection of the imagery we recommend to generate image pyramids since the image data has a very high spatial resolution.</p> <p>Details on the dataset are mentioned in the corresponding publication:</p> <p>Kattenborn, T., Lopatin, J., Förster, M., Braun, A. C., & Fassnacht, F. E. (2019). UAV data as alternative to field sampling to map woody invasive species based on combined Sentinel-1 and Sentinel-2 data. <em>Remote sensing of environment</em>, <em>227</em>, 61-73.</p> <p><a href="https://doi.org/10.1016/j.rse.2019.03.025">https://doi.org/10.1016/j.rse.2019.03.025</a></p> <p><a href="https://www.sciencedirect.com/science/article/abs/pii/S0034425719301166">https://www.sciencedirect.com/science/article/abs/pii/S0034425719301166</a></p>
Tree species Waititu (New Zealand) UAV imagery and reference data (raw)
<p>This dataset includes drone (Uncrewed Aerial Vehicles, UAV) orthomosaics of three plots (each plot covers approx. 100 by 100 m) acquired in November 2017 in Waititu (Fjordland) New Zealand. The resolution (ground sampling distance) of the orthomosaics amounts to approx. 2-3 cm. The orthomosaics feature RGB information and an estimated canopy height (normalized digital surface model, nDSM). The canopy height was derived by subtracting digital surface models (DSM) with digital terrain models (DTM). The DTMs were estimated from the lowest points. Details are given in the publication below.</p> <p>The orthomosaics are partially labelled (polygon shapefiles) for the two tree species, which are <em>Metrosideros umbellata</em>, an angiosperm of the Myrtaceae and <em>Dacrydium cupressinum,</em> a gymnosperm of the Podocarpaceae. The two species are abbreviated as <em>metumb </em>and <em>daccup</em>, respectively. The covered forests are primary forests with a high species richness and endemism.</p> <p>Each orthomosaic comes with an AOI (area of interest, polygon shapefile) that indicates the areas where the labelling was performed. Within the extent of this AOI the two tree species are assumed to be completely delineated (by visual interpretation guided with insitu data; details see publication below).</p> <p>For visual inspection of the imagery we recommend to generate image pyramids since the image data has a very high spatial resolution.</p> <p>Details on the dataset are mentioned in the corresponding publication:</p> <p>Kattenborn, T., Eichel, J., Wiser, S., Burrows, L., Fassnacht, F. E., & Schmidtlein, S. (2020). Convolutional Neural Networks accurately predict cover fractions of plant species and communities in Unmanned Aerial Vehicle imagery. <em>Remote Sensing in Ecology and Conservation</em>, <em>6</em>(4), 472-486.</p> <p><a href="https://doi.org/10.1002/rse2.146">https://doi.org/10.1002/rse2.146</a></p> <p><a href="https://www.sciencedirect.com/science/article/abs/pii/S0034425719301166">https://zslpublications.onlinelibrary.wiley.com/doi/full/10.1002/rse2.146</a></p> <p> </p> <p>Acknowledgements: The data acquisition was funded by the Catalyst: Leaders program financed by the New Zealand Ministry of Business, Innovation and Employment (MBIE) and administered by the Royal Society of New Zealand and the MBIE Strategic Science Investment Fund to Manaaki Whenua-Landcare Research</p>
Data for: Non-invasive measurements of respiration and heart rate across wildlife species using Eulerian Video Magnification of infrared thermal imagery
<p><strong>Background</strong>: An animal's metabolic rate, or energetic expenditure, both impacts and is impacted by interactions with its environment. However, techniques for obtaining measurements of metabolic rate are invasive, logistically difficult, and costly. Red-green-blue (RGB) imaging tools have been used in humans and select domestic mammals to accurately measure heart and respiration rate, as proxies of metabolic rate. The purpose of this study was to investigate if infrared thermography (IRT) coupled with Eulerian video magnification (EVM) would extend the applicability of imaging tools towards measuring vital rates in exotic wildlife species with different physical attributes.</p> <p><strong>Results</strong>: We collected IRT and RGB video of 52 total species (39 mammalian, 7 avian, 6 reptilian) from 36 taxonomic families at zoological institutions and used EVM to amplify subtle changes in temperature associated with blood flow for respiration and heart rate measurements. IRT-derived respiration and heart rates were compared to 'true' measurements determined simultaneously by expansion of the ribcage/nostrils and stethoscope readings, respectively. Sufficient temporal signals were extracted for measures of respiration rate in 36 species (85% success in mammals; 50% success in birds; 100% success in reptiles) and heart rate in 24 species (67% success in mammals; 33% success in birds; 0% success in reptiles) using IRT-EVM. Infrared-derived measurements were obtained with high accuracy (respiration rate, mean absolute error: 1.9 breaths per minute, average percent error: 4.4%; heart rate, mean absolute error: 2.6 beats per minute, average percent error: 1.3%). Thick integument and animal movement most significantly hindered successful validation.</p> <p><strong>Conclusion</strong>: The combination of IRT with EVM analysis provides a non-invasive method to assess individual animal health in zoos, with great potential to monitor wildlife metabolic indices in situ.</p>
Data obtained during classification of intertidal habitats using UAV imagery in the Galapagos Archipelago (Orthophotos, digital elevation models (DEM) and orthophoto-draped 3D models)
<p>In the repository 5 folders exist. 1) Digital elevation models (DEMs), 2) Intertidal habitat map, 3) Othophoto draped 3D models, 4) Orthophotos, and 5) Processing reports. The data has been collected in Puerto Ayora at Santa Cruz in August 2017, the most urbanized island of the Galapagos Archipelago. The purpose of this study was to investigate the image classification opportunities for these intertidal habitats using Uncrewed Aerial Vehicle (UAV) imagery. This dataset is cited in an open-access publication: https://doi.org/10.3390/drones7070416. </p>
Data used in article "Self-calibration of UAV Thermal Imagery Using Gradient Descent"
<p>This repository contains data allowing for reproduction of research described in article "Self-calibration of UAV Thermal Imagery Using Gradient Descent".</p> <p>Each zip archive available in repository contains:</p> <ul> <li>Thermal images produced using Zenmuse H20T camera (rjpg directory)</li> <li>Geojson vector shape of river centerline (centerline.json file)</li> <li>Configuration file used by Python implementation available at https://github.com/radekszostak/aerial-thermal-tuner (config.py file)</li> </ul> <p> </p>
Kenai Mountains to Sea: Using Thermal Infrared Imagery to Implement Long-Term Salmon Conservation - thermal imagery data set
<p>Cook Inletkeeper contracted NV5 Geospatial (formerly, Quantum Spatial Incorporated) to collect thermal infrared (TIR) during the summer of 2020 along four streams on the Kenai Peninsula in southern Alaska: Beaver Creek, Crooked Creek, Funny River, and Moose River under a project name “Kenai Rivers”. All streams were contracted to be flown in the summer of 2020 and during the afternoon hours in order to maximize the thermal contrast between the river’s water and the banks. The survey extends for a total length of 59.1 km miles of the Kenai Rivers. The Data were collected to aid the Cook Inletkeeper team to identify the spatial variability in surface temperatures as well as thermal influence of point sources, tributaries, and surface springs. The data will also be used to identify high-value habitats for the salmonids population within the four streams.</p> <p>Note: These data and related items of information have not been formally disseminated by NOAA and do not represent any agency determination, view, or policy.</p> <p>Funding for this project came, in part, from the Alaska Sustainable Salmon Fund (AKSSF Project #53003).</p>
Scaled laboratory experiments of analogue magma intrusion in granular material: X-ray Computed Tomography imagery and displacement data
<p>This data set contains X-ray Computed Tomography (CT) images and surface displacement data of 15 scaled laboratory experiments of analogue magma intrusion in granular material. The experimental methodology and the experimental results were described in detail by Poppe et al. (2019). Displacement data of experiment SPCTIN14 was used by Poppe et al. (2023).<br> When using the experimental imagery or their derivatives please reference at a minimum Poppe et al. (2019) and this data set (Poppe et al., 2023, Zenodo data set).<br> The included explanatory notice reproduces the experimental method and presents the structure and file types contained in this data set.</p>
Data from: A convolutional neural network for detecting sea turtles in drone imagery
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.