Find research datasets worth reusing

opencc-by-4.0Jun 2021View details →

Cu dataset – A copper ore labeled images dataset for segmentation training and testing

This dataset is composed of 121 pairs of correlated images. Each pair contains one image of a copper ore sample acquired through reflected light microscopy (RGB, 24-bit), and the corresponding binary reference image (8-bit), in which the pixels are labeled as belonging to one of two classes: ore (0) or embedding resin (255). The sample came from a copper ore from Yauri Cusco (Peru) with a complex mineralogy, mainly composed of sulfides, oxides, silicates, and native copper. It was classified by size. The fraction +74-100 μm was cold mounted with epoxy resin and subsequently ground and polished. Correlative microscopy was employed for image acquisition. Thus, 121 fields were imaged on a reflected light microscope with a 20× (NA 0.40) objective lens and on a scanning electron microscope (SEM). In sequence, they were registered, resulting in images of 1017×753 pixels with a resolution of 0.53 µm/pixel. As matter of fact, some images (the images No. 2, 3, 24, 25, 46, 47, 69, 91, and 113) have slightly smaller sizes because they were cropped during the registration procedure to correct co-localization errors of the order of a few pixels. Finally, the images from SEM were thresholded to generate the reference images. Further description of this sample and its imaging procedure can be found in the work by Gomes and Paciornik (2012). This dataset was created for developing and testing deep learning models on semantic segmentation tasks. The paper of Filippo et al. (2021) presented a variant of the DeepLabv3+ model (Chen et al., 2018) that reached mean values of 90.56% and 92.12% for overall accuracy and F1 score, respectively, for 5 rounds of experiments (training and testing), each with a different, random initialization of network weights. For further questions and suggestions, please do not hesitate to contact us.   Contact email: ogomes@gmail.com   If you use this dataset in your own work, please cite this DOI: 10.5281/zenodo.5020566   Please also cite this paper, which provides additional details about the dataset: Michel Pedro Filippo, Otávio da Fonseca Martins Gomes, Gilson Alexandre Ostwald Pedro da Costa, Guilherme Lucio Abelha Mota. Deep learning semantic segmentation of opaque and non-opaque minerals from epoxy resin in reflected light microscopy images. Minerals Engineering, Volume 170, 2021, 107007, https://doi.org/10.1016/j.mineng.2021.107007.

opencc-by-4.0Jun 2021View details →

FeM dataset – An iron ore labeled images dataset for segmentation training and testing

This dataset is composed of 81 pairs of correlated images. Each pair contains one image of an iron ore sample acquired through reflected light microscopy (RGB, 24-bit), and the corresponding binary reference image (8-bit), in which the pixels are labeled as belonging to one of two classes: ore (0) or embedding resin (255). The sample came from an itabiritic iron ore concentrate from Quadrilátero Ferrífero (Brazil) mainly composed of hematite and quartz, with little magnetite and goethite. It was classified by size and concentrated with a dense liquid. Then, the fraction -149+105 μm with density greater than 3.2 was cold mounted with epoxy resin and subsequently ground and polished. Correlative microscopy was employed for image acquisition. Thus, 81 fields were imaged on a reflected light microscope with a 10× (NA 0.20) objective lens and on a scanning electron microscope (SEM). In sequence, they were registered, resulting in images of 999×756 pixels with a resolution of 1.05 µm/pixel. Finally, the images from SEM were thresholded to generate the reference images. Further description of this sample and its imaging procedure can be found in the work by Gomes and Paciornik (2012). This dataset was created for developing and testing deep learning models on semantic segmentation tasks. The paper of Filippo et al. (2021) presented a variant of the DeepLabv3+ model that reached mean values of 91.43% and 93.13% for overall accuracy and F1 score, respectively, for 5 rounds of experiments (training and testing), each with a different, random initialization of network weights. For further questions and suggestions, please do not hesitate to contact us.   Contact email: ogomes@gmail.com   If you use this dataset in your own work, please cite this DOI: 10.5281/zenodo.5014700   Please also cite this paper, which provides additional details about the dataset: Michel Pedro Filippo, Otávio da Fonseca Martins Gomes, Gilson Alexandre Ostwald Pedro da Costa, Guilherme Lucio Abelha Mota. Deep learning semantic segmentation of opaque and non-opaque minerals from epoxy resin in reflected light microscopy images. Minerals Engineering, Volume 170, 2021, 107007, https://doi.org/10.1016/j.mineng.2021.107007.

Segmentation Labels for Emergency Response Imagery from Hurricane Barry, Delta, Dorian, Florence, Isaias, Laura, Michael, Sally, Zeta, and Tropical Storm Gordon

The zip file here contains 1,179 pairs of human-generated segmentation labels and images from Emergency Response Imagery collected by US National Oceanic and Atmospheric Administration (NOAA) after Hurricane Barry, Delta, Dorian, Florence, Ida, Laura, Michael, Sally, Zeta, and Tropical Storm Gordon. A total of 1,054 unique images were labeled. 946 images were annotated by a single labeler. 95 images were annotated by two labelers. 11 images were annotated by three labelers. 2 images were annotated by five labelers. All authors contributed to labeling, and all labeling was done with an open-source labeling tool (Buscombe et al., 2022). All pixels in each image are labeled with one of four classes: 0 (water), 1 (bare sand), 2 (vegetation - both sparse and dense), 4 (the built environment - buildings, roads, parking lots, boats, etc.) The csv file provided here is a list of each image file name (which includes the anonymized labeler ID), the name of the image without the labeler ID, the name of the corresponding NOAA jpg, the NOAA flight name, the storm name, the latitude and longitude of the image, and a column stating if the image has been labeled multiple times.  Images labeled here correspond to multiple NOAA flights — all listed in the csv file for each jpeg image. These jpeg images can be downloaded directly from NOAA (https://storms.ngs.noaa.gov/) or using Moretz et al. (2020a, 2020b). The images included in this data release correspond to original NOAA images that have been resized and then split into quadrants (using ImageMagick). The naming convention corresponds to the image quarter — the *-0.jpg is upper left, *-1.jpg is upper right, *-2.jpg is lower left, and *-3.jpg is the lower right. The resize command used was: #to resize and then quarter #Dir structure is: # --Desktop #    |- originals #    |- resized #    |- quarters `cd originals` `mogrify -resize 2000x2000 -path ../resized *.jpg` #then quarter them `cd ..` `cd resized` `mogrify -crop 2x2@ +repage -path ../quarters *.jpg` For full size images, please download the jpegs directly from NOAA.

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)

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) Description 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 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**. 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. 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> Imagery comes from the following 10 sand beach sites: <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> 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 File descriptions <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> References *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> **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> ***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 **** 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>

Images and 4-class labels for semantic segmentation of Sentinel-2 and Landsat RGB satellite images of coasts (water, whitewater, sediment, other)

Description 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 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**. 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. Imagery comes from the following 10 sand beach sites: <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> 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 File descriptions <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> References *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> **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> ***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

Images and 2-class labels for semantic segmentation of Sentinel-2 and Landsat RGB satellite images of coasts (water, other)

Images and 2-class labels for semantic segmentation of Sentinel-2 and Landsat RGB satellite images of coasts (water, other) Images and 2-class labels for semantic segmentation of Sentinel-2 and Landsat RGB satellite images of coasts (water, other) Description 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 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**. Two data sources have been combined Dataset 1 <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> Dataset 2 <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> File descriptions <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> References *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. **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 ***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 ****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 *****Seale, C., Redfern, T., Chatfield, P. 2022. Sentinel-2 Water Edges Dataset (SWED) https://openmldata.ukho.gov.uk/ ******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.

opencc-by-4.0Jun 2023View details →

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)

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) Description Supplementary dataset to: 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 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 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**. 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 File descriptions <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> References 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 *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> **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>

opencc-by-4.0Jul 2023View details →

NPM3D dataset with instance labels used in paper "Toward Accurate Instance Segmentation in Large-scale LiDAR Point Clouds"

NPM3D (https://npm3d.fr/paris-carla-3d) consists of mobile laser scanning (MLS) point clouds collected in four different regions in the French cities of Paris and Lille, where each point has been annotated with two labels: one that assigns it to one out of 10 semantic categories and another one that assigns it to an object instance. When inspecting the data, we found 9 cases where multiple tree instances had not been separated correctly (i.e., they had the same ground truth instance label). These cases were manually corrected using the CloudCompare software (https://www.cloudcompare.org), and 35 individual tree instances were obtained. Our variant of the dataset with 10 semantic categories and enhanced instance labels is publicly available.

opencc-by-4.0Oct 2023View details →

A multi-scale labeled dataset for boulder segmentation and navigation on small bodies

The capability to detect boulders on the surface of small bodies is beneficial for vision-based applications such as hazard detection during critical operations, safety quantification, autonomous planning of scientific operations, and autonomous navigation. This task, however, is challenging due to the wide assortment of irregular shapes, the characteristics of the boulders population, and the rapid variability in the illumination conditions. Moreover, the lack of publicly available labeled datasets damps the research about data-driven algorithms. The following dataset has been designed and made publicly available to tackle these challenges. Its purpose is twofold. First, from the lessons learned from previous datasets, to develop a multi-purpose, high-fidelity dataset with boulders scattered across the surface of a small body. Second, to exploit domain randomization, artificial noise addition, scaling, and post-processing, enabling the design of data-driven pipelines.  The methodology used to generate the dataset is illustrated in the work "A multi-scale labeled dataset for boulder segmentation and navigation on small bodies" by Mattia Pugliatti and Michele Maestrini, presented at the 74th IAC (International Astronautical Congress), 2024, Baku, Azerbaijan. The dataset contains the image-label pairs of 47502 samples, organized with the following structure:  Dataset_PugliattiMaestrini_2023IAC     --img     --labels     --masks The dataset is comprised of 47502 samples. The "img" folder contains the input, 512x 512 grayscale images. The "labels" folder includes the .txt segmentation labels of the 15 most prominent boulders for each image detected with the methodology illustrated in the IAC paper. The "masks" dataset contains the segmentation masks for all image layers, with the values being encoded between 0 and 17 as uint8. The samples are named as XXXXXX_YYY. XXXXXX stands for the image's original ID during rendering. YYY corresponds to the sub-splits of the original image obtained at rendering:      001 - Top-Left crop     002 - Top-Right crop     003 - Bottom-Left crop     004 - Bottom-right crop     005 - Whole, resized The file "10000_ub_2023-01-18 00.09.43.txt" contains all the values of the rendering inputs detailed in the IAC paper.

opencc-by-4.0Apr 2024View details →

Pockmark Bounding Box Detection and Segmentation Labels

This dataset contains 256x256 pixel jpeg images of gridded depth values as well as binary masks for pixels containing pockmarks (these jpegs are merged together with the depth image on the left and the mask on the right, making a 512x256 image). These are contained within the subdirectory 'PockmarkMaskAnnotations'. Additionally, this dataset contains a csv containing bounding box annotations (label, bounding box coordinates in terms of image pixels, and a unique integer for the label) of pockmarks in each image. These are contained within the subdirectory 'PockmarkBoxAnnotations'. Together, these annotations can be used to construct either a bounding box object detector, a bounding box and mask object detector, or a semantic segmentation model. These were the labels used for the experiments described in Lundine et al., 2023. See this reference to find original data sources to the collected bathymetry data. Lundine, M., Brothers, L., Trembanis, A., Deep learning-based pockmark detection: implications for quantitative seafloor characterization, Geomorphology, 2023, Volume 421, 108524, <a href="https://doi.org/10.1016/j.geomorph.2022.108524">https://doi.org/10.1016/j.geomorph.2022.108524</a>.

opencc-by-4.0Apr 2023View details →

SPVPANELEX: Dataset containing aerial orthoimages (covering 257.93 km2 of the Spanish territory, with a spatial resolution of 0.5 m) labelled with photovoltaic panel information for binary recognition and semantic segmentation

The data have been generated using scripts developed in Python with Open-Source libraries (GDAL/OGR and MapScript) to rasterize of vector cartography representing the photovoltaic (PV) panels instalations in urban, industrial, and rural areas. This PV panels cartography has been generated by manual digitalizing the PV panels found latest aerial orthofotographs available on June 1, 2021 from Plano Nacional de Ortofotografía Aérea (PNOA), produced by the National Geographic Institute of Spain, using the Web Map Service PNOA-MA. The dataset consists of 239,680 images of 256 × 256 pixels in size, in png format, labelled with Class_1: “Contains PV panel” and Class_2: “Does not contain PV panel”, that were pre-divided with a split criterion of 70:10:20%. in train, validation and test folders, respectively. The structure of the data is as follows: 1-Panels-Ortho and 1-Panels-Mask contain the images featuring PV panels and their corresponding ground truth mask for training the semantic segmentation networks. 1-Panels-Ortho and 2-NoPanels-Ortho contain images containing and not containing PV panels, for the training of binary recognition models of PV panels. Moreover, in each folder the structure is the same: train, test, validation containing 70%, 10% and 20% of the total images and masks of each type. 1-Panels-Ortho     |----Train     |----Test     -----Validation 1-Panels-Mask     |----Train     |----Test     -----Validation 2-NoPanels-Ortho     |----Train     |----Test     -----Validation

opencc-by-4.0Jul 2023View details →

EPIC Aff: A multi-label segmentation visual affordances dataset.

This is the EPIC-Aff dataset introduced on the ICCV 2023 paper "Multi-label affordance mapping from egocentric vision".

opencc-by-4.0Jan 2022View details →

Cape Hatteras Landsat8 RGB Images and Labels for Image Segmentation using the program, Segmentation Zoo

# Cape Hatteras Landsat8 RGB Images and Labels for Image Segmentation using the program, Segmentation Gym ## Overview * Test datasets and files for testing the [segmentation gym](https://github.com/Doodleverse/segmentation_gym) program for image segmentation * Data set made by Daniel Buscombe, Marda Science LLC. This is version 5.0 * Dataset consists of a time-series of Landsat-8 images of Cape Hatteras National Seashore, courtesy of the U.S. Geological Survey. * Imagery spans the period February 2015 to September 2021. * Labels were created by Daniel Buscombe, Marda Science, using the labeling program [Doodler](https://github.com/Doodleverse/dash_doodler). Download this file and unzip to somewhere on your machine (although *not* inside the `segmentation_gym` folder), then see the relevant page on the [segmentation gym wiki](https://github.com/Doodleverse/segmentation_gym/wiki) for further explanation. This dataset and associated models were made by Dr Daniel Buscombe, Marda Science LLC, for the purposes of demonstrating the functionality of Segmentation Gym. The labels were created using [Doodler](https://github.com/Doodleverse/dash_doodler/). Previous versions: 1.0. https://zenodo.org/record/5895128#.Y1G5s3bMIuU original release, Oct 2021, conforming to Segmentation Gym functionality on Oct 2021 2.0 https://zenodo.org/record/7036025#.Y1G57XbMIuU, Jan 23 2022, conforming to Segmentation Gym functionality on Jan 23 2022 This is version 5.0, created 7/20/23, and has been tested with Segmentation Gym using doodleverse-utils 0.0.33 https://pypi.org/project/doodleverse-utils/0.0.33/   ## file structure ```{sh} /Users/Someone/my_segmentation_zoo_datasets                     │   ├── config                     │   |    └── *.json                     │   ├── capehatteras_data                     |   |   ├── fromDoodler                     |   |   |     ├──images                     │   |   |     └──labels                     |   |   ├──npzForModel                     │   |   └──toPredict                     │   └── modelOut                     │       └── *.png                     │   └── weights                     │       └── *.h5 ``` ## config There are 4 config files: 1. `/config/hatteras_l8_resunet.json` 2. `/config/hatteras_l8_vanilla_unet.json` 3. `/config/hatteras_l8_resunet_model2.json` 4. `/config/hatteras_l8_segformer.json`     The first two are for res-unet and unet models respectively. The third one differs from the first only with specification of kernel size. It is provided as an example of how to conduct model training experiments, modifying one hyperparameter at a time in the effort to create an optimal model. The last one is based on the new Segformer model architecture. They all contain the same essential information and differ as indicated below ``` {   "TARGET_SIZE": [768,768], # the size of the imagery you wish the model to train on. This may not be the original size   "MODEL": "resunet", # model name. Otherwise, "unet" or "segformer"   "NCLASSES": 4, # number of classes   "KERNEL":9, # horizontal size of convolution kernel in pixels   "STRIDE":2, # stride in convolution kernel   "BATCH_SIZE": 7, # number of images/labels per batch   "FILTERS":6, # number of filters   "N_DATA_BANDS": 3, # number of image bands   "DROPOUT":0.1, # amount of dropout   "DROPOUT_CHANGE_PER_LAYER":0.0, # change in dropout per layer   "DROPOUT_TYPE":"standard", # type of dropout. Otherwise "spatial"   "USE_DROPOUT_ON_UPSAMPLING":false, # if true, dropout is used on upsampling as well as downsampling   "DO_TRAIN": false, # if false, the model will not train, but you will select this config file, data directory, and the program will load the model weights and test the model on the validation subset   if true, the model will train from scratch (warning! this will overwrite the existing weights file in h5 format)   "LOSS":"dice", # model training loss function, otherwise "cat" for categorical cross-entropy   "PATIENCE": 10, # number of epochs of no model improvement before training is aborted   "MAX_EPOCHS": 100, # maximum number of training epochs   "VALIDATION_SPLIT": 0.6, #proportion to use for validation   "RAMPUP_EPOCHS": 20, # [LR-scheduler] rampup to maximim   "SUSTAIN_EPOCHS": 0.0, # [LR-scheduler] sustain at maximum   "EXP_DECAY": 0.9, # [LR-scheduler] decay rate   "START_LR":  1e-7, # [LR-scheduler] start lr   "MIN_LR": 1e-7, # [LR-scheduler] min lr   "MAX_LR": 1e-4, # [LR-scheduler] max lr   "FILTER_VALUE": 0, #if >0, the size of a median filter to apply on outputs (not recommended unless you have noisy outputs)   "DOPLOT": true, #make plots   "ROOT_STRING": "hatteras_l8_aug_768", #data file (npz) prefix string   "USEMASK": false, # use the convention 'mask' in label image file names, instead of the preferred 'label'   "AUG_ROT": 5, # [augmentation] amount of rotation in degrees   "AUG_ZOOM": 0.05, # [augmentation] amount of zoom as a proportion   "AUG_WIDTHSHIFT": 0.05, # [augmentation] amount of random width shift as a proportion   "AUG_HEIGHTSHIFT": 0.05,# [augmentation] amount of random width shift as a proportion   "AUG_HFLIP": true, #  [augmentation] if true, randomly apply horizontal flips   "AUG_VFLIP": false, #  [augmentation] if true, randomly apply vertical flips   "AUG_LOOPS": 10, #[augmentation] number of portions to split the data into (recommended > 2 to save memory)   "AUG_COPIES": 5  #[augmentation] number iof augmented copies to make   "SET_GPU": "0" #which GPU to use. If multiple, list separated by a comma, e.g. '0,1,2'. If CPU is requested, use "-1"   "WRITE_MODELMETADATA": false, #if true, the prompts `seg_images_in_folder.py` to write detailed metadata for each sample file   "LOSS_WEIGHTS": false, #if true, apply per-class weights to loss function   "SET_PCI_BUS_ID": true, #if true, make keras aware of the PCI BUS ID (advanced or nonstandard GPU usage)   "TESTTIMEAUG": true, #if true, apply test-time augmentation when model in inference mode   "WRITE_MODELMETADATA": true,# if true, write model metadata per image when model in inference mode   "OTSU_THRESHOLD": true# if true, and NCLASSES=2 only, use per-image Otsu threshold rather than decision boundary of 0.5 on softmax scores } ``` ## capehatteras_data Folder containing all the model input data ```{sh}                     │   ├── capehatteras_data: folder containing all the model input data                     |   |   ├── fromDoodler: folder containing images and labels exported from Doodler using [this program](https://github.com/dbuscombe-usgs/dash_doodler/blob/main/utils/gen_images_and_labels_4_zoo.py)                     |   |   |     ├──images: jpg format files, one per label image                     │   |   |     └──labels: jpg format files, one per image                     |   |   ├──npz4gym npz format files for model training using [this program](https://github.com/dbuscombe-usgs/segmentation_zoo/blob/main/train_model.py) that have been created following the workflow [documented here](https://github.com/dbuscombe-usgs/segmentation_zoo/wiki/Create-a-model-ready-dataset) using [this program](https://github.com/dbuscombe-usgs/segmentation_zoo/blob/main/make_nd_dataset.py)                     │   |   └──toPredict: a folder of images to test model prediction using [this program](https://github.com/dbuscombe-usgs/segmentation_zoo/blob/main/seg_images_in_folder.py) ``` ## modelOut PNG format files containing example model outputs from the train ('_train_' in filename) and validation ('_val_' in filename) subsets as well as an image showing training loss and accuracy curves with `trainhist` in the filename. There are two sets of these files, those associated with the residual unet trained with dice loss contain `resunet` in their name, and those from the UNet are named with `vanilla_unet`. ## weights There are model weights files associated with each config files.

opencc-by-4.0Oct 2023View details →

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

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 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).   The dataset has been created in the framework of the SROADEX project to train a multiclass semantic segmentation process based on Deep Learning. 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 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). 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 Set              Nº images   Class_1 (continuous line)   Class_2 (discontinuous line) Class_3 (line defining highway entrance or exit)  Class_4 (background)Train                 21,622      27,633,537                         4,543,552                               3,284,380                                                           1,381,557,923Validation           2,702        3,433,103                            570,741                                  395,646                                                               172,678,782Test                    2,701        3,435,072                            536,838                                  429,527                                                               172,611,299Total                 27,025      34,501,712                         5,651,131                               4,109,553                                                            1,726,848,004

dryad36/100

The structural determinants of PH domain-mediated regulation of Akt revealed by segmental labeling

Akt is a critical protein kinase that governs cancer cell growth and metabolism. Akt appears to be autoinhibited by an intramolecular interaction between its N-terminal pleckstrin homology (PH) domain and kinase domain, which is relieved by C-tail phosphorylation, but the precise molecular mechanisms remain elusive. Here we use a combination of protein semisynthesis, NMR, and enzymological analysis to characterize structural features of the PH domain in its autoinhibited and activated states. We find that Akt autoinhibition depends on the length/tension of the PH-kinase linker. We identify a role for a dynamic short segment in the PH domain that appears to regulate autoinhibition and PDK1-catalyzed phosphorylation of Thr308 in the activation loop. We determine that Akt allosteric inhibitor MK2206 drives distinct PH domain structural changes compared to baseline autoinhibited Akt. These results highlight how the conformational plasticity of Akt governs the delicate control of its catalytic properties.

opencc-zeroAug 2020View details →

opencc-by-4.0Dec 2022View details →

Super Resolved and Multi-Label Segmented PEMFC

Super Resolved and Multi-Label Segmented PEMFC with Configuration Files for; Large-scale Physically Accurate Modelling of Real Proton Exchange Membrane Fuel Cell with Deep Learning, Nature Communications. <table> <tbody> <tr> <td><a href="https://zenodo.org/api/files/19f99ad1-b88b-45aa-8731-a88d2753fe3c/ffov_crop_origsize.tiff">ffov_crop_origsize.tiff </a>- LOW RESOLUTION REGISTERED TRAINING BLOCK md5:0b8293b1bf6ded48df1cdd6a36b22e61</td> <td>8.8 MB</td> <td> </td> <td> </td> </tr> <tr> <td><a href="https://zenodo.org/api/files/19f99ad1-b88b-45aa-8731-a88d2753fe3c/inputFile.db">inputFile.db </a>- LBPM INPUT FILE md5:542d244a9552d6b4b1b7ecfa8fd1c153</td> <td>1 kB</td> <td> </td> <td> </td> </tr> <tr> <td><a href="https://zenodo.org/api/files/19f99ad1-b88b-45aa-8731-a88d2753fe3c/LRTest.tif">LRTest.tif </a>- LOW RESOLUTION FULL FOV DOMAIN md5:85f2ccaff7b96188062efd6ab241630b</td> <td>1.3 GB</td> <td> </td> <td> </td> </tr> <tr> <td><a href="https://zenodo.org/api/files/19f99ad1-b88b-45aa-8731-a88d2753fe3c/PEFC_hres_0p7um.tiff">PEFC_hres_0p7um.tiff </a>- HIGH RESOLUTION REGISTERED TRAINING BLOCK md5:ec918d150a6bb6ee5af576cb0bc55c03</td> <td>1.7 GB</td> <td> </td> <td> </td> </tr> <tr> <td><a href="https://zenodo.org/api/files/19f99ad1-b88b-45aa-8731-a88d2753fe3c/SRSegFinal_Processed_oneWeave_Opened.tif">SRSegFinal_Processed_oneWeave_Opened.tif </a>- SUPER RESOLVED AND MULTI-LABEL SEGMENTED FULL FOV DOMAIN md5:20c7aea8c3b832b400811958b8ea243a</td> <td>2.2 GB</td> <td> </td> <td> </td> </tr> <tr> <td><a href="https://zenodo.org/api/files/19f99ad1-b88b-45aa-8731-a88d2753fe3c/SRSegWithGC.tif">SRSegWithGC.tif </a>- SUPER RESOLVED AND MULTI-LABEL SEGMENTED FULL FOV DOMAIN WITH GAS CHANNELS md5:8a6cdd51d7b1b55f1ce9e0beaaa0aaed</td> <td>2.5 GB</td> <td> </td> <td> </td> </tr> <tr> <td><a href="https://zenodo.org/api/files/19f99ad1-b88b-45aa-8731-a88d2753fe3c/SRVis_1100_4000_8000.raw">SRVis_1100_4000_8000.raw </a>- SUPER RESOLVED FULL FOV DOMAIN md5:3ba78b624e60845c09f1d34820eb68e5</td> <td>35.2 GB</td> <td> </td> <td> </td> </tr> </tbody> </table> <table> <tbody> <tr> <th> </th> <th> </th> <th> </th> <th> </th> </tr> <tr> <td> </td> <td> </td> <td> </td> <td> </td> </tr> <tr> <td> </td> <td> </td> <td> </td> <td> </td> </tr> <tr> <td> </td> <td> </td> <td> </td> <td> </td> </tr> <tr> <td> </td> <td> </td> <td> </td> <td> </td> </tr> <tr> <td> </td> <td> </td> <td> </td> <td> </td> </tr> <tr> <td> </td> <td> </td> <td> </td> <td> </td> </tr> <tr> <td> </td> </tr> </tbody> </table>

opencc-by-4.0May 2021View details →

Background-Foreground-Segmentation Labels for "Self-improving Semantic Perception on a Construction Robot"

Background-foreground-segmentation labels the paper "Self-improving Semantic Perception on a Construction Robot" of CoRL 2021

opencc-by-4.0Jun 2023View details →

Structure preserving adversarial generation of labeled training samples for single cell segmentation

Supplementary package (dataset, generated data and code) for the article: "Structure preserving adversarial generation of labeled training samples for single cell segmentation". (Cell Reports Methods, 2023 - under submission) Content of the package: <ul> <li>datasets.zip: the images and annotations for the fallopian tube and salivary gland dataset.</li> <li>mask_quality_experiment.zip: the generated masks using SIMCEP and the generated microscopy images using pix2pix using the SIMCEP masks.</li> <li>pix2pix_models.zip: the models for fold 0 for both datasets. It can be used to synthesize new images.</li> <li>StyleGAN2-ada_models.zip: the models for synthesizing new masks.</li> <li>code.zip: a github repository (named .git) for executing the pipeline.</li> </ul>