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.
26
datasets available to search
ShareScore release 0.9.0
Dataset results
26 results for “semantic image segmentation”
S1S2-Water: A global dataset for semantic segmentation of water bodies from Sentinel-1 and Sentinel-2 satellite images
<p>The S1S2-Water dataset is a global reference dataset for training, validation and testing of convolutional neural networks for semantic segmentation of surface water bodies in publicly available Sentinel-1 and Sentinel-2 satellite images. The dataset consists of 65 triplets of Sentinel-1 and Sentinel-2 images with quality checked binary water mask. Samples are drawn globally on the basis of the Sentinel-2 tile-grid (100 x 100 km) under consideration of pre-dominant landcover and availability of water bodies. Each sample is complemented with metadata and Digital Elevation Model (DEM) raster from the Copernicus DEM.</p><p>This work was supported by the German Federal Ministry of Education and Research (BMBF) through the project "Künstliche Intelligenz zur Analyse von Erdbeobachtungs- und Internetdaten zur Entscheidungsunterstützung im Katastrophenfall" (AIFER) under Grant 13N15525, and by the Helmholtz Artificial Intelligence Cooperation Unit through the project "AI for Near Real Time Satellite-based Flood Response" (AI4FLOOD) under Grant ZT-IPF-5-39. </p>
Semantic segmentation model of construction waste landfill based on high-resolution satellite images
<p>CWLD_model project shows scripts and instructions on how to use this dataset (<a href="../records/10686118">https://zenodo.org/records/10686118</a>) to train a segmentation model. requirements.txt files provide the libraries you need to run your project. The README.md document details the deployment process and features of each module.</p> <p>You can also visit the GitHub page for scripts and instructions on how to use this dataset for visualizing and plotting basic statistics. The models and the code to execute them are released on <a href="https://github.com/huangleinxidimejd/CWLD_Model">https://github.com/huangleinxidimejd/CWLD_Model</a>.</p> <h2>Training details</h2> <p>The model was trained with two GPUs, an Nvidia GeForce RTX 2080Ti, and the following parameters:</p> <ul> <li>'train_batch_size': 4,</li> <li>'val_batch_size': 4,</li> <li>'train_crop_size': 512,</li> <li>'val_crop_size': 512,</li> <li>'lr': 0.001, # the learning rate used during training. It determines how quickly the model learns from the data</li> <li>'Epoch Times': 200,</li> <li>'gpu': correct,</li> <li>'weight_decay': 5E-4,</li> <li>'Momentum': 0.9,</li> <li>'print_freq': 100,</li> <li>'predict_step': 5,</li> </ul> <h2>usage</h2> <ul> <li>After downloading the dataset from Zenodo, place the train and val files from the Deep Learning Datasets file into the data folder of the CWLD semantic segmentation model.</li> <li>Open: CWLD_ Open the root directory in CWLD_model/dataset/ and start training with the WasteSeg_Train.py file. The modelss module provides five convolutional networks, Improved_DeeplabV3_plus, PSPNet, ResNet, SegNet, and UNet, which can be selected and modified accordingly.</li> <li>The utils package provides a large number of data processing tools to use.</li> <li>The trained model can be predicted from a EvalSeg.py file.</li> </ul>
Images and 4-class labels for semantic segmentation of Sentinel-2 and Landsat RGB, NIR, and SWIR satellite images of coasts (water, whitewater, sediment, other)
<p><em><strong>Images and 4-class labels for semantic segmentation of Sentinel-2 and Landsat RGB, NIR, and SWIR satellite images of coasts (water, whitewater, sediment, other)</strong></em></p> <p><strong>Description</strong></p> <p>579 images and 579 associated labels for semantic segmentation of Sentinel-2 and Landsat RGB satellite images of coasts. The 4 classes are 0=water, 1=whitewater, 2=sediment, 3=other</p> <p>These images and labels have been made using the Doodleverse software package, Doodler*. These images and labels could be used within numerous Machine Learning frameworks for image segmentation, but have specifically been made for use with the Doodleverse software package, Segmentation Gym**.</p> <p>Some (422) of these images and labels were originally included in the Coast Train*** data release, and have been modified from their original by reclassifying from the original classes to the present 4 classes.</p> <p>The label images are a subset of the following data release**** <a href="https://doi.org/10.5281/zenodo.7335647">https://doi.org/10.5281/zenodo.7335647</a></p> <p>Imagery comes from the following 10 sand beach sites:</p> <ol> <li>Duck, NC, Hatteras NC, USA</li> <li>Santa Cruz CA, USA</li> <li>Galveston TX, USA</li> <li>Truc Vert,France</li> <li>Sunset State Beach CA, USA</li> <li>Torrey Pines CA, USA</li> <li>Narrabeen, NSW, Australia</li> <li>Elwha WA, USA</li> <li>Ventura region, CA, USA</li> <li>Klamath region, CA USA</li> </ol> <p>Imagery are a mixture of 10-m Sentinel-2 and 15-m pansharpened Landsat 7, 8, and 9 visible-band imagery of various sizes. Red, Green, Blue, NIR, and SWIR bands only</p> <p><strong>File descriptions</strong></p> <ol> <li>classes.txt, a file containing the class names</li> <li>images.zip, a zipped folder containing the 3-band RGB images of varying sizes and extents</li> <li>nir.zip, a zipped folder containing the corresponding near-infrared (NIR) imagery</li> <li>swir.zip, a zipped folder containing the corresponding shortwave-infrared (SWIR) imagery</li> <li>labels.zip, a zipped folder containing the 1-band label images</li> <li>overlays.zip, a zipped folder containing a semi-transparent overlay of the color-coded label on the image (blue=0=water, red=1=whitewater, yellow=2=sediment, green=3=other)</li> <li>resized_images.zip, RGB images resized to 512x512x3 pixels</li> <li>resized_nir.zip, NIR images resized to 512x512x3 pixels</li> <li>resized_swir.zip, SWIR images resized to 512x512x3 pixels</li> <li>resized_labels.zip, label images resized to 512x512 pixels</li> </ol> <p><strong>References</strong></p> <p>*Doodler: Buscombe, D., Goldstein, E.B., Sherwood, C.R., Bodine, C., Brown, J.A., Favela, J., Fitzpatrick, S., Kranenburg, C.J., Over, J.R., Ritchie, A.C. and Warrick, J.A., 2021. Human‐in‐the‐Loop Segmentation of Earth Surface Imagery. Earth and Space Science, p.e2021EA002085<a href="https://doi.org/10.1029/2021EA002085">https://doi.org/10.1029/2021EA002085</a>. See <a href="https://github.com/Doodleverse/dash_doodler">https://github.com/Doodleverse/dash_doodler.</a></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. <a href="https://doi.org/10.1029/2022EA002332">https://doi.org/10.1029/2022EA002332</a> See: <a href="https://github.com/Doodleverse/segmentation_gym">https://github.com/Doodleverse/segmentation_gym</a></p> <p>***Coast Train data release: 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>. See <a href="https://coasttrain.github.io/CoastTrain/">https://coasttrain.github.io/CoastTrain/ </a>for more information</p> <p>**** Buscombe, Daniel, Goldstein, Evan, Bernier, Julie, Bosse, Stephen, Colacicco, Rosa, Corak, Nick, Fitzpatrick, Sharon, del Jesús González Guillén, Anais, Ku, Venus, Paprocki, Julie, Platt, Lindsay, Steele, Bethel, Wright, Kyle, & Yasin, Brandon. (2022). Images and 4-class labels for semantic segmentation of Sentinel-2 and Landsat RGB satellite images of coasts (water, whitewater, sediment, other) (v1.0) [Data set]. Zenodo. <a href="https://doi.org/10.5281/zenodo.7335647">https://doi.org/10.5281/zenodo.7335647</a></p>
Images and 4-class labels for semantic segmentation of Sentinel-2 and Landsat RGB satellite images of coasts (water, whitewater, sediment, other)
<p><strong>Description</strong></p> <p>1018 images and 1018 associated labels for semantic segmentation of Sentinel-2 and Landsat RGB satellite images of coasts. The 4 classes are 0=water, 1=whitewater, 2=sediment, 3=other</p> <p>These images and labels have been made using the Doodleverse software package, Doodler*. These images and labels could be used within numerous Machine Learning frameworks for image segmentation, but have specifically been made for use with the Doodleverse software package, Segmentation Gym**.</p> <p>Some (473) of these images and labels were originally included in the Coast Train*** data release, and have been modified from their original by reclassifying from the original classes to the present 4 classes.</p> <p>Imagery comes from the following 10 sand beach sites:</p> <ol> <li>Duck, NC, Hatteras NC, USA</li> <li>Santa Cruz CA, USA</li> <li>Galveston TX, USA</li> <li>Truc Vert,France</li> <li>Sunset State Beach CA, USA</li> <li>Torrey Pines CA, USA</li> <li>Narrabeen, NSW, Australia</li> <li>Elwha WA, USA</li> <li>Ventura region, CA, USA</li> <li>Klamath region, CA USA</li> </ol> <p>Imagery are a mixture of 10-m Sentinel-2 and 15-m pansharpened Landsat 7, 8, and 9 visible-band imagery of various sizes. Red, Green, and Blue bands only</p> <p><strong>File descriptions</strong></p> <ol> <li>classes.txt, a file containing the class names</li> <li>images.zip, a zipped folder containing the 3-band images of varying sizes and extents</li> <li>labels.zip, a zipped folder containing the 1-band label images</li> <li>overlays.zip, a zipped folder containing a semi-transparent overlay of the color-coded label on the image (blue=0=water, red=1=whitewater, yellow=2=sediment, green=3=other)</li> <li>resized_images.zip, RGB images resized to 512x512x3 pixels</li> <li>resized_labels.zip, label images resized to 512x512 pixels</li> </ol> <p><strong>References</strong></p> <p>*Doodler: Buscombe, D., Goldstein, E.B., Sherwood, C.R., Bodine, C., Brown, J.A., Favela, J., Fitzpatrick, S., Kranenburg, C.J., Over, J.R., Ritchie, A.C. and Warrick, J.A., 2021. Human‐in‐the‐Loop Segmentation of Earth Surface Imagery. Earth and Space Science, p.e2021EA002085<a href="https://doi.org/10.1029/2021EA002085">https://doi.org/10.1029/2021EA002085</a>. See <a href="https://github.com/Doodleverse/dash_doodler">https://github.com/Doodleverse/dash_doodler.</a></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. <a href="https://doi.org/10.1029/2022EA002332">https://doi.org/10.1029/2022EA002332</a> See: <a href="https://github.com/Doodleverse/segmentation_gym">https://github.com/Doodleverse/segmentation_gym</a></p> <p>***Coast Train data release: 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>. See <a href="https://coasttrain.github.io/CoastTrain/">https://coasttrain.github.io/CoastTrain/ </a>for more information</p> <p> </p>
Images and 2-class labels for semantic segmentation of Sentinel-2 and Landsat RGB satellite images of coasts (water, other)
<p><em><strong>Images and 2-class labels for semantic segmentation of Sentinel-2 and Landsat RGB satellite images of coasts (water, other)</strong></em></p> <p>Images and 2-class labels for semantic segmentation of Sentinel-2 and Landsat RGB satellite images of coasts (water, other)</p> <p><strong>Description</strong></p> <p>4088 images and 4088 associated labels for semantic segmentation of Sentinel-2 and Landsat RGB satellite images of coasts. The 2 classes are 1=water, 0=other. Imagery are a mixture of 10-m Sentinel-2 and 15-m pansharpened Landsat 7, 8, and 9 visible-band imagery of various sizes. Red, Green, Blue bands only</p> <p>These images and labels could be used within numerous Machine Learning frameworks for image segmentation, but have specifically been made for use with the Doodleverse software package, Segmentation Gym**.</p> <p>Two data sources have been combined</p> <p><strong>Dataset 1</strong></p> <ul> <li>1018 image-label pairs from the following data release**** https://doi.org/10.5281/zenodo.7335647</li> <li>Labels have been reclassified from 4 classes to 2 classes.</li> <li>Some (422) of these images and labels were originally included in the Coast Train*** data release, and have been modified from their original by reclassifying from the original classes to the present 2 classes.</li> <li>These images and labels have been made using the Doodleverse software package, Doodler*.</li> </ul> <p><strong>Dataset 2</strong></p> <ul> <li>3070 image-label pairs from the Sentinel-2 Water Edges Dataset (SWED)***** dataset, https://openmldata.ukho.gov.uk/, described by Seale et al. (2022)******</li> <li>A subset of the original SWED imagery (256 x 256 x 12) and labels (256 x 256 x 1) have been chosen, based on the criteria of more than 2.5% of the pixels represent water</li> </ul> <p><strong>File descriptions</strong></p> <ul> <li> classes.txt, a file containing the class names</li> <li> images.zip, a zipped folder containing the 3-band RGB images of varying sizes and extents</li> <li> labels.zip, a zipped folder containing the 1-band label images</li> <li> overlays.zip, a zipped folder containing a semi-transparent overlay of the color-coded label on the image (red=1=water, bllue=0=other)</li> <li> resized_images.zip, RGB images resized to 512x512x3 pixels</li> <li> resized_labels.zip, label images resized to 512x512x1 pixels</li> </ul> <p><strong>References</strong></p> <p>*Doodler: Buscombe, D., Goldstein, E.B., Sherwood, C.R., Bodine, C., Brown, J.A., Favela, J., Fitzpatrick, S., Kranenburg, C.J., Over, J.R., Ritchie, A.C. and Warrick, J.A., 2021. Human‐in‐the‐Loop Segmentation of Earth Surface Imagery. Earth and Space Science, p.e2021EA002085https://doi.org/10.1029/2021EA002085. See https://github.com/Doodleverse/dash_doodler.</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> <p>***Coast Train data release: 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, https://doi.org/10.5066/P91NP87I. See https://coasttrain.github.io/CoastTrain/ for more information</p> <p>****Buscombe, Daniel, Goldstein, Evan, Bernier, Julie, Bosse, Stephen, Colacicco, Rosa, Corak, Nick, Fitzpatrick, Sharon, del Jesús González Guillén, Anais, Ku, Venus, Paprocki, Julie, Platt, Lindsay, Steele, Bethel, Wright, Kyle, & Yasin, Brandon. (2022). Images and 4-class labels for semantic segmentation of Sentinel-2 and Landsat RGB satellite images of coasts (water, whitewater, sediment, other) (v1.0) [Data set]. Zenodo. https://doi.org/10.5281/zenodo.7335647</p> <p>*****Seale, C., Redfern, T., Chatfield, P. 2022. Sentinel-2 Water Edges Dataset (SWED) https://openmldata.ukho.gov.uk/</p> <p>******Seale, C., Redfern, T., Chatfield, P., Luo, C. and Dempsey, K., 2022. Coastline detection in satellite imagery: A deep learning approach on new benchmark data. Remote Sensing of Environment, 278, p.113044.</p>
June 2023 Supplement Images and 4-class labels for semantic segmentation of Sentinel-2 and Landsat RGB, NIR, and SWIR satellite images of coasts (water, whitewater, sediment, other)
<p><strong>June 2023 Supplement of Images and 4-class labels for semantic segmentation of Sentinel-2 and Landsat RGB, NIR, and SWIR satellite images of coasts (water, whitewater, sediment, other)</strong></p> <p><strong>Description</strong></p> <p>Supplementary dataset to:</p> <p>Buscombe, Daniel, Goldstein, Evan, Bernier, Julie, Bosse, Stephen, Colacicco, Rosa, Corak, Nick, Fitzpatrick, Sharon, del Jesús González Guillén, Anais, Ku, Venus, Paprocki, Julie, Platt, Lindsay, Steele, Bethel, Wright, Kyle, & Yasin, Brandon. (2022). Images and 4-class labels for semantic segmentation of Sentinel-2 and Landsat RGB satellite images of coasts (water, whitewater, sediment, other) (v1.0) [Data set]. Zenodo. https://doi.org/10.5281/zenodo.7335647</p> <p>This supplemental dataset consists of 283 RGB images and 283 associated labels for semantic segmentation of Sentinel-2 and Landsat RGB satellite images of coasts. Of these, 77 images-label pairs also have a corresponding NIR and SWIR satellite image. The 4 classes are 0=water, 1=whitewater, 2=sediment, 3=other</p> <p>These images and labels have been made using the Doodleverse software package, Doodler*. These images and labels could be used within numerous Machine Learning frameworks for image segmentation, but have specifically been made for use with the Doodleverse software package, Segmentation Gym**.</p> <p>Imagery are a mixture of 10-m Sentinel-2 and 15-m pansharpened Landsat 7, 8, and 9 visible-band imagery of various sizes. NIR, SWIR, Red, Green, and Blue bands only</p> <p><strong>File descriptions</strong></p> <ol> <li>classes.txt, a file containing the class names</li> <li>images.zip, a zipped folder containing the 3-band images of varying sizes and extents</li> <li>labels.zip, a zipped folder containing the 1-band label images</li> <li>overlays.zip, a zipped folder containing a semi-transparent overlay of the color-coded label on the image (blue=0=water, red=1=whitewater, yellow=2=sediment, green=3=other)</li> <li>nir.zip</li> <li>swir.zip</li> </ol> <p><strong>References</strong></p> <p>Buscombe, Daniel, Goldstein, Evan, Bernier, Julie, Bosse, Stephen, Colacicco, Rosa, Corak, Nick, Fitzpatrick, Sharon, del Jesús González Guillén, Anais, Ku, Venus, Paprocki, Julie, Platt, Lindsay, Steele, Bethel, Wright, Kyle, & Yasin, Brandon. (2022). Images and 4-class labels for semantic segmentation of Sentinel-2 and Landsat RGB satellite images of coasts (water, whitewater, sediment, other) (v1.0) [Data set]. Zenodo. https://doi.org/10.5281/zenodo.7335647</p> <p>*Doodler: Buscombe, D., Goldstein, E.B., Sherwood, C.R., Bodine, C., Brown, J.A., Favela, J., Fitzpatrick, S., Kranenburg, C.J., Over, J.R., Ritchie, A.C. and Warrick, J.A., 2021. Human‐in‐the‐Loop Segmentation of Earth Surface Imagery. Earth and Space Science, p.e2021EA002085<a href="https://doi.org/10.1029/2021EA002085">https://doi.org/10.1029/2021EA002085</a>. See <a href="https://github.com/Doodleverse/dash_doodler">https://github.com/Doodleverse/dash_doodler.</a></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. <a href="https://doi.org/10.1029/2022EA002332">https://doi.org/10.1029/2022EA002332</a> See: <a href="https://github.com/Doodleverse/segmentation_gym">https://github.com/Doodleverse/segmentation_gym</a></p> <p> </p>
An urban traffic dataset composed of visible images and their semantic segmentation generated by the CARLA simulator
<p><strong>If you use this dataset please cite this paper: Rosende, S.B.; Gavilán, D.S.J.; Fernández-Andrés, J.; Sánchez-Soriano, J. An Urban Traffic Dataset Composed of Visible Images and Their Semantic Segmentation Generated by the CARLA Simulator. <em>Data</em> 2024, <em>9</em>, 4. <a href="https://doi.org/10.3390/data9010004">https://doi.org/10.3390/data9010004</a></strong></p> <p>A dataset of aerial urban traffic images and their semantic segmentation is presented to be used to train computer vision algorithms, among which those based on convolutional neural networks stand out. The images have been generated using the CARLA simulator (but would be like those that could be obtained with fixed aerial cameras or by using AUVs) in the field of intelligent transportation management. The presented dataset is available and accessible to improve the performance of vision and road traffic management systems, especially for the detection of incorrect or dangerous maneuvers.</p>
A Dataset of Synthetic Images of Outdoor Scenes Taken from Sidewalks, for Temporal Semantic Segmentation Applications
<p>This dataset has been generated using the CARLA simulator (release 0.9.11), an open-source 3D simulator for experiments in autonomous vehicle, based on the Unreal Engine game engine. It comes with pre-made city environment maps. CARLA is distributed with several integrated maps as well as parameters to increase the variety in the dataset. In the release that we have used, there are 13 semantic segmentation classes: None, Building, Fence, Other, Pedestrian, Pole, Lane-marking, Road, Sidewalk, Vegetation, Vehicle, Wall, and Traffic sign. The "None" category corresponds to textures that are not part of an object, such as lawns which are not part of "Vegetation", or sky. In the “Other” category are found objects that are not included in the other classes like plant and flower pots. For smart mobility applications, the “Sidewalks” and “Road” classes are of particular importance to find the way forward, as well as “Buildings” and “Poles” for obstacle avoidance. Sequences are made of 4 images. The dataset is composed of 46436 frames (11609 sequences) partitioned in 41024 frames (10256 sequences) for train, 2696 frames (674 sequences) for validation, and 2716 for test (679 sequences). The size of the images is 800 x 600 (resp. width x height).</p> <p>Additionaly, we have generated another smaller dataset with images taken from 2 different viewpoints: one located on the road and the other located on the sidewalk. The number of frames for train/validation/test is respectively 7288 (1822 sequences) partitioned in 6344 (1687 sequences) for train, 416 frames (104 sequences) for validation, and 424 for test (106 sequences). This smaller dataset is aimed at showing the importance of the viewpoint in the result of semantic segmentation. This can be done by cross-validation: learning on images taken from a viewpoint located on the road and test on images with a viewpoint located on the sidewalk, and vice versa.</p>
Train and Evaluation Code, Road Classification Models and Test set of the paper "Insights into the Effects of Image Overlap and Image Size on Semantic Segmentation Models Trained for Road Surface Area Extraction from Aerial Orthophotography"
<p>This repository contains the Python scripts built for training and evaluation of the implementation, together with the test data and the resulting road segmentation models corresponding to the paper "Insights into the Effects of Image Overlap and Image Size on Semantic Segmentation Models Trained for Road Surface Area Extraction from Aerial Orthophotography". The scripts make use of the Tensorflow with Keras framework and their additional required dependencies.</p> <p>The training and validation set is based on the binary SROADEX dataset (<a href="../records/6482346">https://zenodo.org/records/6482346</a>) that was re-split into tiles that feature the image resolutions (256 x 256, 512 x 512, and 1024 x 1024 pixels) and image overlaps (0% and 12.5%) considered in this study. The data have been generated using scripts developed in Python using Open Source libraries (GDAL/OGR and MapScript) for rasterization of vector cartography that represents the axes of the different types of roads (urban, interurban and rural). This binary road data contains information from 16 full orthoimages (28.5 km * 18.5 km) with spatial resolution of 0.5 m/pixel from the insular and peninsular Spanish territory. Due to the size on disk of approximately 492 gigabytes, this training and validation data is only available upon request from the corresponding author. The test set has been generated from a novel area from Palencia (Spain) and features 18 million pixels labelled with the positive "Road" class. The test sets are provided in the repository for each resolution (with no overlap), so that additional DL models can be evaluated on the same data and compared with the results achieved in this study.</p> <p>The structure of the information shared in this repository is as follows:<br>The scripts have been grouped by tile resolution (256, 512 and 1024). First, the test set and the evaluation script can be found. For each tile resolution, there are two subfolders (corresponding to the "no overlap" and "12.5% overlap"). In each case, the Python scripts for training the models in the three repetitions are shared, and the trained models (H5 format) are shared in compressed form. Finally, for each resolution we also share the testing dataset which consists of two folders.</p> <p>The material is distributed under a CC-BY 4.0 license.</p>
WE3DS: An RGB-D image dataset for semantic segmentation in agriculture
<p>Here, we introduce a novel RGB-D image database (WE3DS) for semantic segmentation in crop farming. It contains 2,568 RGB-D images (color image and distance map) and hand-annotated ground-truth masks for semantic segmentation and is the first RGB-D image dataset for multi-class plant species semantic segmentation task. Images were taken under natural light conditions using an RGB-D sensor consisting of two RGB cameras in a stereo setup.</p> <p> </p> <p><strong>Please cite the original source when using this dataset.</strong></p> <p>Kitzler, F.; Barta, N.; Neugschwandtner, R.W.; Gronauer, A.; Motsch, V. WE3DS: An RGB-D Image Dataset for Semantic Segmentation in Agriculture. <em>Sensors</em> <strong>2023</strong>, <em>23</em>, 2713. <a href="https://doi.org/10.3390/s23052713">https://doi.org/10.3390/s23052713 </a></p>
WhiteRoadLines: Dataset of 27,025 images (256x256 pixeles at 0.15 m/ pixel) containing representative road lines and markings labelled for multi-class semantic segmentation
<p>The dataset consists of 27,025 PNG images (256x256 pixels) of high resolution aerial orthoimages at 0,15 m/pixel of resolution. The images contain information related to representative road lines and markings found on highway pavement and is labelled for multi-class semantic segmentation with tree classes of white road<br>lines and markings: (1) continuous line (black color), (2) dashed line (dark gray color) and (3) separation of entry and exit lanes (light gray color), together with (4) the background (white color). <br> </p><p>The dataset has been created in the framework of the SROADEX project to train a multiclass semantic segmentation process based on Deep Learning.<br>The data have been generated using scripts developed in Python using Open Source libraries (GDAL/OGR and MapScript) for rasterization of vector cartography representing the three different types of white road lines. This cartography has been obtained from Spanish official sources (National Geographic Institute) that we have<br>revised and edited in a meticulous and systematic way to verify that the road lines are represented on the cartography according to the orthoimages, available on January 1, 2022 in the download center of the National Center of Geographic Information (CNIG). </p><p>In the digitisation process, 46 homogeneously distributed areas of Spain have been selected. The orthoimages used have been resampled from the original resolution of 0,25m/pixel to 0,15m/pixel, as this is closer to the width of two of the three classes of white lines in the dataset. It resulted in 80% of the images for training (21622), 10% for validation (2702) and 10% for testing (2701). The following table summarises the number of pixels of each category included in each of the three sub-datasets</p><p> </p><p>Set Nº images Class_1 (continuous line) Class_2 (discontinuous line) Class_3 (line defining highway entrance or exit) Class_4 (background)</p><p>Train 21,622 27,633,537 4,543,552 3,284,380 1,381,557,923</p><p>Validation 2,702 3,433,103 570,741 395,646 172,678,782</p><p>Test 2,701 3,435,072 536,838 429,527 172,611,299</p><p>Total 27,025 34,501,712 5,651,131 4,109,553 1,726,848,004</p>
Amazon and Atlantic Forest image datasets for semantic segmentation
<p>This database contains images from<strong> Amazon </strong>and <strong>Atlantic Forest </strong>brazilian biomes used for training a fully convolutional neural network for the semantic segmentation of forested areas in images from the Sentinel-2 Level 2A Satellite.</p> <p>The images refer to the composition of bands 4, 3, 2 and 8. Each band was converted to a byte type (0-255).</p> <p>The images are still divided into three main sets: training, validation and testing:</p> <ol> <li><strong>Training dataset: </strong>it contains 499 and 485 GeoTIFF images (Amazon and Atlantic Forest, respectively) with 512x512 pixels and associated PNG masks (forest indicated in white and background in black color).</li> <li><strong>Validation dataset</strong>: it contains 100 GeoTIFF images for each biome with 512x512 pixels and associated PNG masks used for validation step.</li> <li><strong>Test dataset: </strong>it contains 20 GeoTIFF images for each biome with 512x512 pixels for testing.</li> </ol>
Test Dataset for 3D semantic image segmentation of the various organs from CT and MR scans
<p>These test cases are for the <a href="https://github.com/MIC-DKFZ/nnUNet/releases/tag/v1.7.1">nnUnet v1</a> models trained on the following datasets:<br><br></p> <table> <tbody> <tr> <td>Dataset </td> <td>Task</td> <td>Model Details on Zenodo</td> </tr> <tr> <td> <a href="../record/6802614">TotalSegmentator</a> and <a href="../record/5903672">FLARE21</a> datasets</td> <td>Segment Liver from CT scans</td> <td>https://zenodo.org/record/8274976</td> </tr> <tr> <td><a href="https://kits-challenge.org/kits23/">KiTS23</a> datasets and a subset of the<a href="https://wiki.cancerimagingarchive.net/pages/viewpage.action?pageId=5800386#5800386566e265abf95408aa64c4917f0cbe5d9"> TCGA-KIRC </a>dataset</td> <td>Segment Kidney, Cyst, and Tumors from CT Scans</td> <td>https://zenodo.org/records/8277846</td> </tr> <tr> <td><a href="http://ji%20yuanfeng.%20(2022).%20amos%20a%20large-scale%20abdominal%20multi-organ%20benchmark%20for%20versatile%20medical%20image%20segmentation%20[data%20set].%20zenodo.%20https">AMOS</a> and <a href="http://macdonald,%20jacob%20a.,%20zhu,%20zhe,%20konkel,%20brandon,%20mazurowski,%20maciej,%20wiggins,%20walter,%20&%20bashir,%20mustafa.%20(2020).%20duke%20liver%20dataset%20(mri)%20v2%20(2.0.0)%20[data%20set].%20zenodo.%20https//doi.org/10.5281/zenodo.7774566">DUKE Liver</a> datasets</td> <td>Segment Liver from the MR scans</td> <td>https://zenodo.org/record/8290124</td> </tr> <tr> <td>Data from m <a href="../record/6624726">pi-cai</a></td> <td>Segment Prostate region from MR scans</td> <td>https://zenodo.org/record/8290093</td> </tr> </tbody> </table>
A dataset for semantic segmentation of typical oceanic and atmospheric phenomena from Sentinel-1 images
<p>We have constructed a SAR (Synthetic Aperture Radar) image semantic segmentation dataset that includes 12 oceanic and atmospheric phenomena: Atmospheric Front (AF), Oceanic Front (OF), Rainfall (RF), Iceberg (IC), Sea Ice (SI), Pure Ocean Wave (POW), Wind Streak (WS), Low Wind Area (LWA), Biological Slick (BS), Micro Convective Cells (MCC), Internal Wave (IW), and Eddy.</p> <p>This dataset is built using Sentinel-1 IW and WV mode images. For WV mode data, we referenced TenGeoP-SARwv and SAR_WV_SemanticSegmentation and selected 2,383 images for semantic segmentation and annotation. For IW mode images, we incorporated some images from Tao et al.'s internal wave detection dataset. We selected 484 Sentinel-1 IW mode images obtained from 2015 to 2022 and divided them into 2,628 sub-images.</p> <p>The dataset contains a total of 5,011 image slices, with approximately 400 images for each phenomenon. All images are 16-bit .tiff files with a resolution of 100m and a size of 256x256 pixels. The images were manually annotated using the Labelme software, generating corresponding JSON files, which were then used to create the related annotation .png files.</p> <p>The updated version(V2) provides geographic information for each image.</p> <p>Thank you for your interest in our dataset. Here are the meanings of each label:</p> <p>1. BG: The unlabelled parts in JSON files are "BG" (Background)<br>2. AF: Atmospheric Front<br>3. BS: Biological Slick<br>4. I: “I” is equivalent to “IB”, representing icebergs<br>5. LWA: Low Wind Area<br>6. MCC: Micro Convective Cells<br>7. OF: Oceanic Front<br>8. POW: Pure Ocean Wave<br>9. RC: “RC” (Rain Cells) is equivalent to “RF” (Rainfall), both representing the rainfall phenomenon in the SAR image. <br>10. SI: Sea Ice<br>11. WS: Wind Streak<br>12. Eddy<br>13. IW: Internal Wave<br><em>14. HM: Represents the artificial objects appearing in the image, such as ships, aquaculture floating rafts, wind power facilities, etc.</em><br><em>15. OS: Unlike “BS”,“OS” represents mineral oil spills appearing in the SAR image (currently, there is insufficient data available for training, which will be supplemented in the future).</em></p>
Data, code, models for "Weakly Supervised Semantic Segmentation for Joint Key Local Structure Localization and Classification of Aurora Image"
<p>Data, code and models for https://ieeexplore.ieee.org/document/8410588/</p>
Test Dataset for 3D semantic image segmentation of the Breast, Fibrograndular Tissue, and Breast Carcinoma
Open the record for dataset details and reuse information.
A Comprehensive Analysis of Weakly-Supervised Semantic Segmentation in Different Image Domains
<p><strong>Content</strong></p> <p>This repository contains pre-trained computer vision models, data labels, and images used in the pre-print publication "A Comprehensive Analysis of Weakly-Supervised Semantic Segmentation in Different Image Domains":</p> <ol> <li><em>ADPdevkit</em>: a folder containing the 50 validation ("tuning") set and 50 evaluation ("segtest") set of images from the Atlas of Digital Pathology database formatted in the VOC2012 style--the full database of 17,668 images is available for download from the original website</li> <li><em>VOCdevkit</em>: a folder containing the relevant files for the PASCAL VOC2012 Segmentation dataset, with both the trainaug and test sets</li> <li><em>DGdevkit</em>: a folder containing the 803 test images of the DeepGlobe Land Cover challenge dataset formatted in the VOC2012 style</li> <li><em>cues</em>: a folder containing the pre-generated weak cues for ADP, VOC2012, and DeepGlobe datasets, as required for the SEC and DSRG methods</li> <li><em>models_cnn</em>: a folder containing the pre-trained CNN models</li> <li><em>models_wsss</em>: a folder containing the pre-trained SEC, DSRG, and IRNet models, along with dense CRF settings</li> </ol> <p><strong>More information</strong></p> <p>For more information, please refer to the following article. <strong>Please cite this article when using the data set.</strong></p> <p>@misc{chan2019comprehensive,<br> title={A Comprehensive Analysis of Weakly-Supervised Semantic Segmentation in Different Image Domains},<br> author={Lyndon Chan and Mahdi S. Hosseini and Konstantinos N. Plataniotis},<br> year={2019},<br> eprint={1912.11186},<br> archivePrefix={arXiv},<br> primaryClass={cs.CV}<br> }</p> <p>For the full code released on GitHub, please visit the repository at: <a href="https://github.com/lyndonchan/wsss-analysis">https://github.com/lyndonchan/wsss-analysis</a></p> <p><strong>Contact</strong></p> <p>For questions, please contact:<br> Lyndon Chan<br> lyndon.chan@mail.utoronto.ca<br> http://orcid.org/0000-0002-1185-7961</p>
DepthMars Dataset for Semantic Segmentation of the Martian Surface from Rover Images
<p>This dataset is resulted from a research article, "DepthFormer: Depth-Enhanced Transformer Network for Semantic Segmentation of the Martian Surface from Rover Images", which includes surface images on Mars collected by the Zhurong rover along its traverse, depth images generated from stereo images, and corresponding manually labeled images.</p>
Materials in Vessels Dataset, Annotated images of materials in transparent vessels for semantic segmentation
<p> Data set of materials in vessels<br> The handling of materials in glassware vessels is the main task in chemistry laboratory research as well as a large number of other activities. Visual recognition of the physical phase of the<br> materials is essential for many methods ranging from a simple task such as fill-level evaluation to the<br> identification of more complex properties such as solvation, precipitation, crystallization and phase<br> separation. To help train neural nets for this task, a new data set was created. The data set contains a<br> thousand images of materials, in different phases and involved in different chemical processes, in a<br> laboratory setting. Each pixel in each image is labeled according to several layers of classification, as<br> given below:</p> <p>a. Vessel/Background: For each pixel assign value of one if it is part of the vessel and zero otherwise.<br> This annotation was used as the ROI map for the valve filter method.</p> <p>b. Filled/Empty: This is similar to the above, but also distinguishes between the filled and empty<br> regions of the vessel. For each pixel, one of the following three values is assigned:0 (background); 1<br> (empty vessel); or 2 (filled vessel).</p> <p>c. Phase type: This is similar to the above but distinguishes between liquid and solid regions of the<br> filled vessel. For each pixel, one of the following four values: 0 (background); 1 (empty vessel); 2<br> (liquid); or 3 (solid).</p> <p>d. Fine-grained physical phase type: This is similar to the above but distinguishes between specific<br> classes of physical phase. For each pixel, one of 15 values is assigned: 1 (background); 2 (empty<br> vessel); 3 (liquid); 4 (liquid phase two, in the case where more than one phase of the liquid appears in<br> the vessel); 5 (suspension); 6 (emulsion); 7 (foam); 8 (solid); 9 (gel); 10 (powder); 11 (granular); 12<br> (bulk); 13 (solid-liquid mixture); 14 (solid phase two, in the case where more than one phase of solid<br> exists in the vessel): and 15 (vapor).<br> The annotations are given as images of the size of the original image, where the pixel value is the<br> class number. The annotation of the vessel region (a) is used in the ROI input for the valve filter net .</p> <p>4.1. Validation/testing set<br> The data set is divided into training and testing sets. The testing set is itself divided into two subsets;<br> one contains images extracted from the same YouTube channels as the training set, and therefore was<br> taken under similar conditions as the training images. The second subset contains images extracted<br> from YouTube channels not included in the training set, and hence contains images taken under<br> different conditions from those used to train the net.</p> <p>4.2. Creating the data set<br> The creation of a large number of images with a variety of chemical processes and settings could have<br> been a daunting task. Luckily, several YouTube channels dedicated to chemical experiments exist<br> which offer high-quality footage of chemistry experiments. Thanks to these channels, including<br> NurdRage, NileRed, ChemPlayer, it was possible to collect a large number of high-quality images in a<br> short time. Pixel-wise annotation of these images was another challenging task, and was performed by<br> Alexandra Emanuel and Mor Bismuth.</p> <p>For more details see: <a href="https://arxiv.org/pdf/1708.08711.pdf">Setting attention region for convolutional neural networks using region selective features, for recognition of materials within glass vessels</a></p> <p>This dataset was first published in 2017.8</p> <p>For newer and Bigger datasets see</p> <p>https://zenodo.org/record/4736111#.YbG-RrtyZH4</p> <p>https://zenodo.org/record/3697452#.YbG-TLtyZH4</p> <p> </p>
Images and 2-class labels for semantic segmentation of Sentinel-2 and Landsat RGB, NIR, and SWIR satellite images of coasts (water, other)
<p><em><strong>Images and 2-class labels for semantic segmentation of Sentinel-2 and Landsat RGB, NIR, and SWIR satellite images of coasts (water, other)</strong></em></p> <p>Images and 2-class labels for semantic segmentation of Sentinel-2 and Landsat 5-band (R+G+B+NIR+SWIR) satellite images of coasts (water, other)</p> <p><strong>Description</strong></p> <p>3649 images and 3649 associated labels for semantic segmentation of Sentinel-2 and Landsat 5-band (R+G+B+NIR+SWIR) satellite images of coasts. The 2 classes are 1=water, 0=other. Imagery are a mixture of 10-m Sentinel-2 and 15-m pansharpened Landsat 7, 8, and 9 visible-band imagery of various sizes. Red, Green, Blue, near-infrared, and short-wave infrared bands only</p> <p>These images and labels could be used within numerous Machine Learning frameworks for image segmentation, but have specifically been made for use with the Doodleverse software package, Segmentation Gym**.</p> <p>Two data sources have been combined</p> <p><strong>Dataset 1</strong></p> <p>* 579 image-label pairs from the following data release**** https://doi.org/10.5281/zenodo.7344571<br> * Labels have been reclassified from 4 classes to 2 classes.<br> * Some (422) of these images and labels were originally included in the Coast Train*** data release, and have been modified from their original by reclassifying from the original classes to the present 2 classes.<br> * These images and labels have been made using the Doodleverse software package, Doodler*.</p> <p><strong>Dataset 2</strong></p> <ul> <li>3070 image-label pairs from the Sentinel-2 Water Edges Dataset (SWED)***** dataset, https://openmldata.ukho.gov.uk/, described by Seale et al. (2022)******</li> <li>A subset of the original SWED imagery (256 x 256 x 12) and labels (256 x 256 x 1) have been chosen, based on the criteria of more than 2.5% of the pixels represent water</li> </ul> <p><strong>File descriptions</strong></p> <ul> <li> classes.txt, a file containing the class names</li> <li> images.zip, a zipped folder containing the 3-band RGB images of varying sizes and extents</li> <li> labels.zip, a zipped folder containing the 1-band label images</li> <li> nir.zip, a zipped folder containing the 1-band near-infrared (NIR) images</li> <li> swir.zip, a zipped folder containing the 1-band shorttwave infrared (SWIR) images</li> <li> overlays.zip, a zipped folder containing a semi-transparent overlay of the color-coded label on the image (red=1=water, blue=0=other)</li> <li> resized_images.zip, RGB images resized to 512x512x3 pixels</li> <li> resized_labels.zip, label images resized to 512x512x1 pixels</li> <li> resized_nir.zip, NIR images resized to 512x512x1 pixels</li> <li> resized_swir.zip, SWIR images resized to 512x512x1 pixels</li> </ul> <p>References</p> <p>*Doodler: Buscombe, D., Goldstein, E.B., Sherwood, C.R., Bodine, C., Brown, J.A., Favela, J., Fitzpatrick, S., Kranenburg, C.J., Over, J.R., Ritchie, A.C. and Warrick, J.A., 2021. Human‐in‐the‐Loop Segmentation of Earth Surface Imagery. Earth and Space Science, p.e2021EA002085https://doi.org/10.1029/2021EA002085. See https://github.com/Doodleverse/dash_doodler.</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> <p>***Coast Train data release: 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, https://doi.org/10.5066/P91NP87I. See https://coasttrain.github.io/CoastTrain/ for more information</p> <p>****Buscombe, Daniel. (2022). Images and 4-class labels for semantic segmentation of Sentinel-2 and Landsat RGB, NIR, and SWIR satellite images of coasts (water, whitewater, sediment, other) (v1.0) [Data set]. Zenodo. https://doi.org/10.5281/zenodo.7344571</p> <p>*****Seale, C., Redfern, T., Chatfield, P. 2022. Sentinel-2 Water Edges Dataset (SWED) https://openmldata.ukho.gov.uk/</p> <p>******Seale, C., Redfern, T., Chatfield, P., Luo, C. and Dempsey, K., 2022. Coastline detection in satellite imagery: A deep learning approach on new benchmark data. Remote Sensing of Environment, 278, p.113044.</p>
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.