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.
88
datasets available to search
ShareScore release 0.9.0
Dataset results
88 results for “orthomosaic”
Doodleverse/Segmentation Gym SegFormer models for 4-class (other, water, sediment, wood) segmentation of RGB aerial orthomosaic imagery
<p><strong>Doodleverse/Segmentation Gym SegFormer models for 4-class (other, water, sediment, wood) segmentation of RGB aerial orthomosaic imagery</strong></p> <p>This model release is part of the Doodleverse: https://github.com/Doodleverse</p> <p>These Residual-UNet model data are based on RGB (red, green, and blue) images of alluvial river corridors and associated labels. Models are designed to identify water, wood, sediment, and other in orthomosaic imagery. Models have been created using Segmentation Gym* using a dataset of images published here:</p> <p><em>Ritchie, A.C., Curran, C.A., Magirl, C.S., Bountry, J.A., Hilldale, R.C., Randle, T.J., and Duda, J.J., 2018, Data in support of 5-year sediment budget and morphodynamic analysis of Elwha River following dam removals: U.S. Geological Survey data release, https://doi.org/10.5066/F7PG1QWC.</em></p> <p>Classes: {0=other, 1=water, 2=sediment, 3=large woody debris / driftwood}. See https://github.com/Doodleverse for more information about how this model was trained, and how to use it for inference</p> <p>File descriptions</p> <p>1. '.json' config file: this is the file that was used by Segmentation Gym* to create the weights file. It contains instructions for how to make the model and the data it used, as well as instructions for how to use the model for prediction. It is a handy wee thing and mastering it means mastering the entire Doodleverse.</p> <p>2. '.h5' weights file: this is the file that was created by the Segmentation Gym* function `train_model.py`. It contains the trained model's parameter weights. It can called by the Segmentation Gym* function `seg_images_in_folder.py`. Models may be ensembled.</p> <p>3. '_modelcard.json' model card file: this is a json file containing fields that collectively describe the model origins, training choices, and dataset that the model is based upon. There is some redundancy between this file and the `config` file (described above) that contains the instructions for the model training and implementation. The model card file is not used by the program but is important metadata so it is important to keep with the other files that collectively make the model and is such is considered part of the model</p> <p>4. '_model_history.npz' model training history file: this numpy archive file contains numpy arrays describing the training and validation losses and metrics. It is created by the Segmentation Gym function `train_model.py`</p> <p>5. '.png' model training loss and mean IoU plot: this png file contains plots of training and validation losses and mean IoU scores during model training. A subset of data inside the .npz file. It is created by the Segmentation Gym function `train_model.py`</p> <p>Additionally, </p> <p>1. BEST_MODEL.txt contains the name of the model with the best validation loss and mean IoU<br> 2. sample_images.zip contains a few example input files, for model testing</p> <p>References</p> <p>*Segmentation Gym: Buscombe, D., & Goldstein, E. B. (2022). A reproducible and reusable pipeline for segmentation of geoscientific imagery. Earth and Space Science, 9, e2022EA002332. https://doi.org/10.1029/2022EA002332 See: https://github.com/Doodleverse/segmentation_gym</p>
Doodleverse/Segmentation Gym SegFormer models for 2-class (other, sediment) segmentation of RGB aerial orthomosaic imagery
<p><strong>Doodleverse/Segmentation Gym SegFormer models for 2-class (other, sediment) segmentation of RGB aerial orthomosaic imagery</strong></p> <p>This model release is part of the Doodleverse: https://github.com/Doodleverse</p> <p>These Residual-UNet model data are based on RGB (red, green, and blue) images of alluvial river corridors and associated labels. Models are designed to identify water, wood, sediment, and other in orthomosaic imagery. Models have been created using Segmentation Gym* using a dataset of images published here:</p> <p><em>Ritchie, A.C., Curran, C.A., Magirl, C.S., Bountry, J.A., Hilldale, R.C., Randle, T.J., and Duda, J.J., 2018, Data in support of 5-year sediment budget and morphodynamic analysis of Elwha River following dam removals: U.S. Geological Survey data release, https://doi.org/10.5066/F7PG1QWC.</em></p> <p>Classes: {0=other, 1=sediment}. See https://github.com/Doodleverse for more information about how this model was trained, and how to use it for inference</p> <p>File descriptions</p> <p>1. '.json' config file: this is the file that was used by Segmentation Gym* to create the weights file. It contains instructions for how to make the model and the data it used, as well as instructions for how to use the model for prediction. It is a handy wee thing and mastering it means mastering the entire Doodleverse.</p> <p>2. '.h5' weights file: this is the file that was created by the Segmentation Gym* function `train_model.py`. It contains the trained model's parameter weights. It can called by the Segmentation Gym* function `seg_images_in_folder.py`. Models may be ensembled.</p> <p>3. '_modelcard.json' model card file: this is a json file containing fields that collectively describe the model origins, training choices, and dataset that the model is based upon. There is some redundancy between this file and the `config` file (described above) that contains the instructions for the model training and implementation. The model card file is not used by the program but is important metadata so it is important to keep with the other files that collectively make the model and is such is considered part of the model</p> <p>4. '_model_history.npz' model training history file: this numpy archive file contains numpy arrays describing the training and validation losses and metrics. It is created by the Segmentation Gym function `train_model.py`</p> <p>5. '.png' model training loss and mean IoU plot: this png file contains plots of training and validation losses and mean IoU scores during model training. A subset of data inside the .npz file. It is created by the Segmentation Gym function `train_model.py`</p> <p>Additionally, </p> <p>1. BEST_MODEL.txt contains the name of the model with the best validation loss and mean IoU<br> 2. sample_images.zip contains a few example input files, for model testing</p> <p>References</p> <p>*Segmentation Gym: Buscombe, D., & Goldstein, E. B. (2022). A reproducible and reusable pipeline for segmentation of geoscientific imagery. Earth and Space Science, 9, e2022EA002332. https://doi.org/10.1029/2022EA002332 See: https://github.com/Doodleverse/segmentation_gym</p>
Orthomosaic of pumpkin field
<p># Orthomosaic of pumpkin field</p> <p>This is an orthomosaic or a pumpkin field with halloween pumpkins.<br> The pumpkin fruits are ripe with an orange color.<br> The leaf part of the pumpkin plants have withered away.</p> <p>Images were collected 2019-09-20 and then processed to create the orthomosaic with a GSD of 2.5 cm using Agisoft Metashape.<br> The images were collected with the purpose of counting the pumpkins in the field.<<br> This is described in the paper </p> <p>Midtiby, Henrik Skov, and Elżbieta Pastucha. 2022. "Pumpkin Yield Estimation Using Images from a UAV" Agronomy 12, no. 4: 964. https://doi.org/10.3390/agronomy12040964</p> <p>If you have any questions related to the data set, please contact Henrik Skov Midtiby on hemi@mmmi.sdu.dk.<br> </p>
Dataset: Drone orthomosaics for remote detection of Pacific oysters (Kingsbridge Estuary, UK)
<p><span>A field campaign was carried out at two distinctive intertidal cases at </span><span>Kingsbridge Estuary, UK. Drone images were collected around low tide on </span><span>each site of the estuary selected by the high number of Pacific oysters reported </span><span>and their very different characteristic landscapes of mudflats and rocky shore. D<span>rone images were collected using </span><span>a DJI Phantom4 Pro v2.0 in a pre-planned grid mission using the ”DJI </span><span>GS Pro” mission planner software.</span><span> </span><span>Photos were acquired at 10 m altitude </span><span>(resulting in a pixel size of</span><span> </span><span>∼</span><span>0.3 px/cm) with a front overlap ratio of 80% </span><span>and a side overlap of 70%.</span><span> </span></span></p> <p><span>The two sites included in this work are:</span><br><span>•</span><span> </span><span>Site A: Collapit Creek mudflats</span><span>. An area of approximately 1.67 ha</span> <span>intertidal mudflat was surveyed on 13th May 2022 </span><span>(lat, lon = 50.259245, -3.771041).</span><br><span>•</span><span> </span><span>Site B: Scoble Point rocky shore</span><span>. The intertidal region that follows </span><span>the shoreline for approximately 250 m was surveyed on 16th May 2022, </span><span>Figure 3 (50.240164, -3.755421).</span></p>
UAV orthomosaic at 80m altitude - Ria de Vigo (Spain) pilot site
<table> <tbody> <tr> <td> <p><strong>Identification</strong></p> </td> </tr> <tr> <td> <p>Full Title</p> </td> <td> <p>UAV orthomosaic at 80m altitude - Ria de Vigo (Spain) pilot site</p> </td> </tr> <tr> <td> <p>Abstract</p> </td> <td> <p>UAV orthomosaic orthorectified with DGPS, compiled from images collected at 80m altitude using a DJI Mini 2 UAV, in the area of Vao beach and Santa Marta - Limens beach at the Ria de Vigo pilot site. Data were aquired in March 2024 field campaign.</p> </td> </tr> <tr> <td> <p>Keywords</p> </td> <td> <p> UAV, orthomosaic, Ria De Vigo, coastal area</p> </td> </tr> <tr> <td> <p>Pilot area</p> </td> <td> <p> Ria De Vigo</p> </td> </tr> <tr> <td> <p>Associated resources</p> </td> <td> <p> </p> </td> </tr> <tr> <td> <p>Language</p> </td> <td> <p> English</p> </td> </tr> <tr> <td> <p>URL</p> </td> <td> <p> </p> </td> </tr> <tr> <td> <p>Categories</p> </td> <td> <p> UAV</p> </td> </tr> <tr> <td> <p><strong>Temporal reference</strong></p> </td> </tr> <tr> <td> <p>Creation date (dd.mm.yyyy)</p> </td> <td> <p> 23.08.2024</p> </td> </tr> <tr> <td> <p>Revision date (dd.mm.yyyy)</p> </td> <td> <p> 23.08.2024</p> </td> </tr> <tr> <td> <p><strong>Quality and validity</strong></p> </td> </tr> <tr> <td> <p>Representation type</p> </td> <td> <p> Raster</p> </td> </tr> <tr> <td> <p>Format</p> </td> <td> <p> GeoTIFF</p> </td> </tr> <tr> <td> <p>Lineage</p> </td> <td> <p> </p> </td> </tr> <tr> <td> <p>Spatial resolution</p> </td> <td> <p> 0.023m</p> </td> </tr> <tr> <td> <p>Positional accuracy</p> </td> <td> <p> 0.25m</p> </td> </tr> <tr> <td> <p>Maintenance information</p> </td> <td> <p> </p> </td> </tr> <tr> <td> <p>Coordinate system</p> </td> <td> <p> EPSG:32630</p> </td> </tr> <tr> <td> <p><strong>Constraints related to access and use</strong></p> </td> </tr> <tr> <td> <p>Use limitation</p> </td> <td> <p> Free</p> </td> </tr> <tr> <td> <p>Access constraint</p> </td> <td> <p> None</p> </td> </tr> <tr> <td> <p>Public/Private</p> </td> <td> <p> Public</p> </td> </tr> <tr> <td> <p><strong>Responsible organisation</strong></p> </td> </tr> <tr> <td> <p>Responsible Contact</p> </td> <td> <p> <a href="mailto:izananiri@eagme.gr">izananiri@eagme.gr</a></p> </td> </tr> <tr> <td> <p>Responsible Party</p> </td> <td> <p> HSGME</p> </td> </tr> <tr> <td> <p><strong>Metadata on metadata</strong></p> </td> </tr> <tr> <td> <p>Contact</p> </td> <td> <p> <a href="mailto:izananiri@eagme.gr">izananiri@eagme.gr</a></p> </td> </tr> <tr> <td> <p>Metadata language</p> </td> <td> <p> English</p> </td> </tr> </tbody> </table>
UAV orthomosaic at 50m altitude - Ria de Vigo (Spain) pilot site
<table> <tbody> <tr> <td> <p><strong>Identification</strong></p> </td> </tr> <tr> <td> <p>Full Title</p> </td> <td> <p>UAV orthomosaic at 50m altitude - Ria de Vigo (Spain) pilot site</p> </td> </tr> <tr> <td> <p>Abstract</p> </td> <td> <p>UAV orthomosaic orthorectified with DGPS, compiled from images collected at 50m altitude using a DJI Mini 2 UAV, in the area of Vao beach and Santa Marta - Limens beach at the Ria de Vigo pilot site. Data were aquired in March 2024 field campaign.</p> </td> </tr> <tr> <td> <p>Keywords</p> </td> <td> <p> UAV, orthomosaic, Ria De Vigo, coastal area</p> </td> </tr> <tr> <td> <p>Pilot area</p> </td> <td> <p> Ria De Vigo</p> </td> </tr> <tr> <td> <p>Associated resources</p> </td> <td> <p> </p> </td> </tr> <tr> <td> <p>Language</p> </td> <td> <p> English</p> </td> </tr> <tr> <td> <p>URL</p> </td> <td> <p> </p> </td> </tr> <tr> <td> <p>Categories</p> </td> <td> <p> UAV</p> </td> </tr> <tr> <td> <p><strong>Temporal reference</strong></p> </td> </tr> <tr> <td> <p>Creation date (dd.mm.yyyy)</p> </td> <td> <p> 23.08.2024</p> </td> </tr> <tr> <td> <p>Revision date (dd.mm.yyyy)</p> </td> <td> <p> 23.08.2024</p> </td> </tr> <tr> <td> <p><strong>Quality and validity</strong></p> </td> </tr> <tr> <td> <p>Representation type</p> </td> <td> <p> Raster</p> </td> </tr> <tr> <td> <p>Format</p> </td> <td> <p> GeoTIFF</p> </td> </tr> <tr> <td> <p>Lineage</p> </td> <td> <p> </p> </td> </tr> <tr> <td> <p>Spatial resolution</p> </td> <td> <p> 0.014m</p> </td> </tr> <tr> <td> <p>Positional accuracy</p> </td> <td> <p> 0.25m</p> </td> </tr> <tr> <td> <p>Maintenance information</p> </td> <td> <p> </p> </td> </tr> <tr> <td> <p>Coordinate system</p> </td> <td> <p> EPSG:32630</p> </td> </tr> <tr> <td> <p><strong>Constraints related to access and use</strong></p> </td> </tr> <tr> <td> <p>Use limitation</p> </td> <td> <p> Free</p> </td> </tr> <tr> <td> <p>Access constraint</p> </td> <td> <p> None</p> </td> </tr> <tr> <td> <p>Public/Private</p> </td> <td> <p> Public</p> </td> </tr> <tr> <td> <p><strong>Responsible organisation</strong></p> </td> </tr> <tr> <td> <p>Responsible Contact</p> </td> <td> <p> <a href="mailto:izananiri@eagme.gr">izananiri@eagme.gr</a></p> </td> </tr> <tr> <td> <p>Responsible Party</p> </td> <td> <p> HSGME</p> </td> </tr> <tr> <td> <p><strong>Metadata on metadata</strong></p> </td> </tr> <tr> <td> <p>Contact</p> </td> <td> <p> <a href="mailto:izananiri@eagme.gr">izananiri@eagme.gr</a></p> </td> </tr> <tr> <td> <p>Metadata language</p> </td> <td> <p> English</p> </td> </tr> </tbody> </table>
Orthomosaics and digital elevation model of the 'Bear Trap' - a Norse ruin in Northwest Greenland
<p>This dataset consists of a digital elevation model (DEM) and an orthomosaic of the ‘Bear Trap’ (also called ‘Bjørnefælden’ in Danish, and ‘Putdlagssuaq’ or ‘The Great Trap’ Greenlandic Kalaallisut), a Norse ruin at the western end of the Nuussuaq Peninsula in NW Greenland. Images comprise 1032 low-altitude aerial images acquired from an unoccupied aerial vehicle (DJI Phantom 3 Standard). These images were processed using Agisoft Metashape Pro (v1.7; Linux Ubuntu) following the USGS protocols for processing imagery in coastal areas. The locations of 8 ground control points (GCPs) were surveyed with a high accuracy global navigation satellite system (GNSS) receiver (Emlid Reach). The base station and rover data were processed using the Emlid distribution of the free RTKLib software (<a href="https://docs.emlid.com/reach/common/tutorials/gps-post-processing/">https://docs.emlid.com/reach/common/tutorials/gps-post-processing/</a>). Geoid height was computed using the online UNAVCO Geoid Height Calculator (<a href="https://www.unavco.org/software/geodetic-utilities/geoid-height-calculator/geoid-height-calculator.html">https://www.unavco.org/software/geodetic-utilities/geoid-height-calculator/geoid-height-calculator.html</a>). During the image alignment step in Metashape, the ‘High’ accuracy setting and key point and tie point limits of 60000 and 0 were used. Generic and reference preselection were not used. Gradual selection was used to remove tie points that exceeded thresholds for the projection accuracy, reconstruction uncertainty, and reprojection error and the intrinsic camera parameters were computed for each camera calibration group. GCPs were then imported and placed in each image. The dense point cloud was then computed using the ‘Ultra High’ quality setting, followed by the DEM and orthomosaic. The resolution of the orthomosaic is 1.83 cm/pixel. 5 cm resolution orthomosaic and DEM were also exported for use in QGIS. </p> <p> </p> <p>A complete file list is provided in the README file that accompanies this dataset.</p> <p> </p> <p>The image survey was conducted as part of the Vaigat Iceberg-Microbial Oil Degradation and Archaeological Heritage Investigation (VIMOA) project, which was funded by the Danish Centre for Marine Research and supported by the Arctic Research Centre at Aarhus University, in affiliation with the National Museum of Denmark, the Greenland Institute of Natural Resources, and The Greenland National Museum and Archives in Nuuk. Proper archaeological permits for the survey were obtained in advance from the Greenland National Museum and Archives in Nuuk. Walsh et al. (2020) provide an overview of the archaeological surveys conducted during the VIMOA project and Walsh et al. (in prep) provide further details specific to The Bear Trap and surrounding archaeological contexts observed during the 2019 survey.</p> <p>Walsh et al. (2020) The VIMOA project and archaeological heritage in the Nuussuaq Peninsula of north-west Greenland. <em>Antiquity</em> 94:e6 doi:10.15184/aqy.2019.230</p> <p>Walsh, Matthew J., Daniel F. Carlson, Pelle Tejsner, and Steffen Thomsen. The Bear Trap: Reinvestigating a unique stone structure on the northwest tip of the Nuussuaq Peninsula, Greenland. Submitted to <em>Arctic Anthropology</em>.</p>
UAV RGB imagery dataset captured at nadir and oblique angles over pistachio trees in Spain, including images, GCPs, 3D point cloud and orthomosaic.
<p>The dataset comprises 248 images taken in two flights on 29 July 2021 over a pistachio orchard in Spain. In addition, GCPs (ground control points) were collected to improve the photogrammetric process accuracy. The photos were taken using a UAV DJI Phantom Advance quadcopter equipped with a DJI FC6310 RGB 20-megapixel camera. The first flight mission was planned to take nadir images (-90º gimbal pitch degree), whereas the second flight was scheduled to take oblique images (-60º gimbal pitch degree), both at 55 metres above the ground. In addition, the images were used to generate a 3D point cloud, DEM and orthomosaic, which were included in the dataset.This dataset is useful for precision agriculture researchers interested in photogrammetric reconstruction.</p>
SfM-MVS derived orthomosaics of the Otemma glacier forefield (2020)
<p><strong>Orthomosaics (2020) of the Otemma glacier forefield derived from SfM-MVS photogrammetry</strong></p> <p>This dataset includes the orthomosaics of the Otemma glacier forefield generated through SfM-MVS photogrammetry. This dataset is based upon the images collected during summer 2020. Details on the image acquisition and image processing can be found in Roncoroni et al. (2022) at this URL: https://doi.org/10.1080/01431161.2022.2079963</p> <p>Details:</p> <ul> <li>Format: .tif </li> <li>Name format: mmddyyyy<em>x</em>m_Orthomosaic (where mm is the month, dd the day, yyyy the year, and xm is AM or PM)</li> <li>Coordinate system: CH1903+ LV95 (EPSG:2056)</li> <li>Spatial resolution: 0.05 m</li> </ul> <p> </p>
Drone orthomosaic and digital elevation model of the Atanikerluk archaeological site in NW Greenland
<p>This dataset consists of a digital elevation model (DEM) and an orthomosaic of the Atanikerluk archaeological site (NKAH 1724), located on the Nuussuaq Peninsula in NW Greenland near the settlement of Saqqaq. The DEM and orthomosaic were produced from 612 aerial images that were acquired by a DJI Phantom 3 drone. The images were processed using Agisoft Metashape Professional (version 1.7.1) following protocols established by the United States Geological Survey (USGS) for drone surveys of coastal regions (Over et al., 2021). Five ground control points were distributed throughout the survey area. The drone survey of the Atanikerluk site was conducted as part of the Vaigat Iceberg-Microbial Oil Degradation and Archaeological Heritage Investigation (VIMOA) project, which was funded by the Danish Centre for Marine Research and supported by the Arctic Research Centre at Aarhus University, in affiliation with the National Museum of Denmark, the Greenland Institute of Natural Resources, and The Greenland National Museum and Archives in Nuuk. Proper archaeological permits for the survey were obtained in advance from the Greenland National Museum and Archives in Nuuk. Walsh et al. (2020) provide an overview of the archaeological surveys conducted during the VIMOA project.</p> <p>Over et al. (2021) Processing Coastal Imagery With Agisoft Metashape Professional Edition, Version 1.6—Structure From Motion Workflow Documentation. USGS Open File Report 2021-1039. doi:10.3133/ofr20211039. <a href="https://pubs.er.usgs.gov/publication/ofr20211039">https://pubs.er.usgs.gov/publication/ofr20211039</a></p> <p>Walsh et al. (2020) The VIMOA project and archaeological heritage in the Nuussuaq Peninsula of north-west Greenland. Antiquity 94:e6 doi:10.15184/aqy.2019.230</p>
Drone orthomosaic and DEM of the coastline near Qaamasoq north of Paamiut on 2 July 2022
<p>This dataset consists of a digital elevation model (DEM) and an orthomosaic of the coastline at Qaamasoq, near the town of Paamiut. The DEM and orthomosaic were produced from 247 aerial images that were acquired by an Autel Evo II drone on 2 July 2022. The images were processed using Agisoft Metashape Professional (version 1.7.1) following protocols established by the United States Geological Survey (USGS) for drone surveys of coastal regions (Over et al., 2021). The drone survey was conducted as part of a sailing science expedition that was funded by the German Scholars Organization and supported by Helmholtz-Zentrum Hereon.</p> <p>Over et al. (2021) Processing Coastal Imagery With Agisoft Metashape Professional Edition, Version 1.6—Structure From Motion Workflow Documentation. USGS Open File Report 2021-1039. doi:10.3133/ofr20211039. <a href="https://pubs.er.usgs.gov/publication/ofr20211039">https://pubs.er.usgs.gov/publication/ofr20211039</a></p>
Drone orthomosaic and DEM of the Nuusaq archaeological site in NW Greenland
<p>This dataset consists of a digital elevation model (DEM) and an orthomosaic of the Nuusaq archaeological site, located on the Nuussuaq Peninsula in NW Greenland. The DEM and orthomosaic were produced from 2143 aerial images that were acquired by a DJI Phantom 3 drone. The images were processed using Agisoft Metashape Professional (version 1.7.1) following protocols established by the United States Geological Survey (USGS) for drone surveys of coastal regions (Over et al., 2021). The drone survey of the Nuusaq site was conducted as part of the Vaigat Iceberg-Microbial Oil Degradation and Archaeological Heritage Investigation (VIMOA) project, which was funded by the Danish Centre for Marine Research and supported by the Arctic Research Centre at Aarhus University, in affiliation with the National Museum of Denmark, the Greenland Institute of Natural Resources, and The Greenland National Museum and Archives in Nuuk. Archaeological permits for the survey were obtained in advance from the Greenland National Museum and Archives in Nuuk. Walsh et al. (2020) provide an overview of the archaeological surveys conducted during the VIMOA project.</p> <p>Over et al. (2021) Processing Coastal Imagery With Agisoft Metashape Professional Edition, Version 1.6—Structure From Motion Workflow Documentation. USGS Open File Report 2021-1039. doi:10.3133/ofr20211039. <a href="https://pubs.er.usgs.gov/publication/ofr20211039">https://pubs.er.usgs.gov/publication/ofr20211039</a></p> <p>Walsh et al. (2020) The VIMOA project and archaeological heritage in the Nuussuaq Peninsula of north-west Greenland. Antiquity 94:e6 doi:10.15184/aqy.2019.230</p>
UAV-based multispectral image data of a tree nursery, Eberswalde, Brandenburg, 2023 (Orthomosaics, DEMs, point clouds)
<p>This data set contains three multispectral surveys conducted with an unoccupied aerial vehicle (UAV DJI M300 RTK) of an oak tree nursery experiment</p> <ul> <li>Date of acquisition: 16.08.2023</li> <li>Location: Tree nursery, Eberswalde, Brandenburg, Germany</li> <li>UAV: DJI M300 RTK with active SAPOS connection</li> <li>Flight altitude above ground level: 30 m, 40 m, 60 m</li> <li>Image Overlap forward/side: 80 % / 80 %</li> <li>Camera: MicaSense Altum multispectral</li> <li>EPSG: 32632</li> </ul> <p>Data products: </p> <ul> <li>Orthomosaic multispectral (Resolution: 1.35 cm, 1.79 cm, 2.65 cm)</li> <li>Orthomosaic RGB</li> <li>Orthomosaic thermal LWIR in pseudo °C according to <a href="https://support.micasense.com/hc/en-us/articles/360022446473-Converting-Altum-Thermal-to-degrees-C-after-processing-in-Agisoft-or-Pix4D">Micasense</a> empirical formula</li> <li>DEM</li> <li>Dense point cloud RGB</li> <li>Spectral indices calculated: NDVI, NDRE</li> <li>Agisoft Report</li> </ul> <p><strong>Acknowledgment:</strong></p> <p><strong>Frank Becker</strong></p> <p>Landesbetrieb Forst Brandenburg</p> <p>Landeskompetenzzentrum Forst Eberswalde (LFE)</p>
Orthomosaic of the Demining Research Community's seeded minefield
<p>This orthomosaic was processed using Pix4Dmapper and georeferened in QGIS using ground control point coordinates collected with the Trimble- Geo7x. The seeded field consists of 150 diverse explosive remnants of war buried at systematic varying depths located in Pawnee, Oklahoma. The purpose of this field is to serve as a resource and benchmark to the humanitarian mine community, allowing researchers to thoroughly test methods and instruments for landmine and UXO detection. The field is operated by the Demining Research Community and the OSU Global Consortium for Explosive Hazard Mitigation.</p>
Doodleverse/Segmentation Zoo UNet models for identifying water in orthomosaic photos of coasts.
<p><strong>Doodleverse/Segmentation Zoo UNet models for identifying water in orthomosaic photos of coasts.</strong></p> <p> </p> <p><strong>Based on Coast Train data</strong></p> <p>Wernette, P.A., Buscombe, D.D., Favela, J., Fitzpatrick, S., and Goldstein E., 2022, Coast Train--Labeled imagery for training and evaluation of data-driven models for image segmentation: U.S. Geological Survey data release, <a href="https://doi.org/10.5066/P91NP87I">https://doi.org/10.5066/P91NP87I</a>.</p> <p>These model data are based on images of coasts and associated labels. Models have been fitted to the following types of data</p> <p>1. RGB (3 band): red, green, blue</p> <p>Classes are: {0: null, 1: water}.</p> <p>These files are used in conjunction with Segmentation Zoo*</p> <p>For each model, there are 3 files with the same root name:</p> <p>1. <strong>'.json' </strong>config file: this is the file that was used by Segmentation Gym** to create the weights file. It contains instructions for how to make the model and the data it used, as well as instructions for how to use the model for prediction. It is a handy wee thing and mastering it means mastering the entire Doodleverse.</p> <p> </p> <p>2.<strong> '.h5'</strong> weights file: this is the file that was created by the Segmentation Gym** function `train_model.py`. It contains the trained model's parameter weights. It can called by the Segmentation Gym** function `seg_images_in_folder.py` or the Segmentation Zoo* function `select_model_and_batch_process_folder.py` to segment a folder of images</p> <p> </p> <p>3.<strong> '_modelcard.json'</strong> model card file: this is a json file containing fields that collectively describe the model origins, training choices, and dataset that the model is based upon. There is some redundancy between this file and the `config` file (described above) that contains the instructions for the model training and implementation. The model card file is not used by the program but is important metadata so it is important to keep with the other files that collectively make the model and is such is considered part of the model</p> <p> </p> <p>References</p> <p>* https://github.com/Doodleverse/segmentation_zoo</p> <p>** https://github.com/Doodleverse/segmentation_gym</p>
Orthomosaics from panoramic photos for Hawaiian roadways
<p>Natural hazards pose a significant risk to transport infrastructure and can cause annual direct damage of 3.1 to 22 billion US dollars globally, with 84% of it being flooding-related. Cost-effective approaches to assessing road damage and conditions are vital for repairing and reconstructing the transportation infrastructure after hazards. We conducted a study that presents a novel methodology developed for generating highly detailed orthomosaics of road surfaces, achieving millimeter-level spatial resolution. The approach utilizes panoramic photos obtained from a mobile camera system, coupled with Structure-from-Motion (SfM) technology. A key aspect of the methodology is the accurate masking of the ego-vehicle, sky, and moving objects (such as vehicles, bicycles, and pedestrians) present in the street scenes captured by the photos. This masking process involves a combination of deep learning algorithms, image processing techniques, and manual editing. The study demonstrates that removing these objects from the images significantly improves photo alignment precision and enhances the overall quality of the orthomosaics. The resulting orthomosaics are found to be highly applicable for GIS analysis and the assessment of road conditions and damages.</p>
The UAV-derived orthomosaics and DEMs of 23K Glacier and 24K Glacier in southeastern Tibetan Plateau (2019-2020)
<p>The UAV-derived orthomosaics and DEMs of 23K Glacier and 24K Glacier in southeastern Tibetan Plateau (Agu. 2019, Oct. 2019, Agu. 2020, Oct. 2020). </p>
High-resolution digital elevation models and orthomosaics generated from historical aerial photographs (since the 1960s) of the Bale Mountains in Ethiopia
<p>This dataset contains the results of photogrammetric processing (Digital Elevation Models, Orthomosaics and subset data used for volumetric calculation and visualization) named: “DEM_1967.7z”: inside the zipped folder “1967_DEM.tif” (digital elevation model produced for the year 1967), “DEM_1984.7z”: inside the zipped folder “1984_DEM.tif” exist (digital elevation model produced for the year 1984). In addition, under “1967_Orthomosaic.7z" and "1984_Orthomosaic.7z” zipped folders, there are orthomosaic files produced namely, “1967_orthomosaic.tif” and "1984_orthomosaic.tif” for the year 1967 and 1984, respectively. The DEMs and Orthomosaics subset from the results for sites (data example 1 and data example 2) reside under "Data_Examples.zip". Accuracy of the resulted data were assessed and the extracted elevation values are under "Accuracy_assessment.zip". All DEMs and Orthomosaics are in GeoTIFF format in the Adindan UTM Zone 37 N (EPSG: 20137) projected coordinate system.</p> <p> Potential application of the presented dataset include:</p> <p>1. watershed management</p> <p>2. analyses of historical landscape change</p> <p>3. detailed mapping and analyses of geological and archaeological features, as well as natural resources</p> <p>4. analyses of geomorphological processes</p> <p>5. socioecological patterns and dynamics</p> <p>6. modelling and planning for telecommunications </p> <p>7. biodiversity research. </p> <p>The inputs for the above resulted DEMs and Orthomosaics are found under Zenodo repository "10.5281/zenodo.7271617". </p>
High-resolution digital elevation models and orthomosaics generated from historical aerial photographs (since the 1960s) of the Bale Mountains in Ethiopia
<p>This dataset contains the inputs used for Structure from Motion Multiview Stereo photogrammetry processing for the year 1967 and 1984 i.e Unprocessed scanned historical aerial Photographs, camera position coordinates, flight index and Ground Control Points. All the scanned historical aerial photographs data are in TIFF format except four photographs in JPEG format under a zipped folder ("1967_Scanned_HAPs_Part1.7z and 1967_Scanned_HAPs_Part2.7z" for the 1967 Historical Aerial Photographs and "1984_Scanned_HAPs_Part1.7z and 1984_Scanned_HAPs_Part2.7z" for the 1984 Historical Aerial Photographs). The "Flight_Index.Zip" contains shapefiles of the camera position and polygon of consecutive aerial photograph index; "GCP.Zip" contains text file of the GCPs used for the 1967 and 1984; and "Camera_Position.Zip" contains the file of the camera position (Label, Easting, Northing and Altitude) of each historical aerial photographs. </p> <p>The results of the above dataset could be accessible on Zenodo repository "10.5281/zenodo.7269999".</p> <p>Anyone can reuse the presented dataset to produce DEMs and Orthomosaics; and use for the following application areas:</p> <p>1. watershed management</p> <p>2. analyses of historical landscape change</p> <p>3. detailed mapping and analyses of geological and archaeological features, as well as natural resources</p> <p>4. analyses of geomorphological processes</p> <p>5. socioecological patterns and dynamics</p> <p>6. modelling and planning for telecommunications </p> <p>7. biodiversity research. </p> <p> </p>
Orthomosaics from panoramic photos for Hawaiian roadways
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.