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.
328
datasets available to search
ShareScore release 0.9.0
Dataset results
328 results for “segmentation dataset”
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
<p>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.<br> <br> 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.<br> <br> The structure of the data is as follows:<br> 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.<br> 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.<br> <br> 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.<br> <br> 1-Panels-Ortho<br> |----Train<br> |----Test<br> -----Validation<br> <br> 1-Panels-Mask<br> |----Train<br> |----Test<br> -----Validation<br> <br> 2-NoPanels-Ortho<br> |----Train<br> |----Test<br> -----Validation</p>
CBRA: The first multi-annual (2016-2021) and high-resolution (2.5 m) building rooftop area dataset in China derived with Super-resolution Segmentation from Sentinel-2 imagery
<p>Large-scale and up-to-date maps of building rooftop area (BRA) are crucial for addressing policy decisions and sustainable development. In addition, as a fine-grained indicator of human activities, BRA could contribute to urban planning and energy modeling to provide benefits to human well-being. However, existing large-scale BRA datasets, such as those from Microsoft and Google, do not include China, hence there are no full-coverage maps of BRA in China. To this end, we produce the multi-annual China building rooftop area dataset (CBRA) with 2.5 m resolution from 2016-2021 Sentinel-2 images. The CBRA is the first full-coverage and multi-annual BRA data in China. The CBRA achieves good performance with the F1 score of 62.55% (+10.61% compared with the previous BRA data in China) based on 250,000 testing samples in urban areas, and the recall of 78.94% based on 30,000 testing samples in rural areas. </p> <p>The CBRA is organized as GeoTIFF (.tif) raster file format with a single band and GCS_WGS_1984 coordinate system. The pixel values are 0 and 255, with 0 representing the background and 255 representing the building rooftop area. Furthermore, to facilitate the use of the data, the CBRA is split into 215 tiles of spatial grid, named “CBRA_year_E/W**N/S**.tif”, where “year” is the sampling year, the “E/W**N/S**” is the latitude and longitude coordinates found in the upper left corner of the tile data.</p> <p> </p> <p>Version 2.0: In version 1.0, there were empty raster images (because they didn't contain buildings). In version 2.0, these raster images were removed.</p>
Dataset for "Synchronous multi-segmental activity between metachronal waves controls locomotion speed in Drosophila larvae"
<p>Dataset for publication "Synchronous multi-segmental activity between metachronal waves controls locomotion speed in Drosophila larvae". </p>
EPIC Aff: A multi-label segmentation visual affordances dataset.
<p>This is the EPIC-Aff dataset introduced on the ICCV 2023 paper "Multi-label affordance mapping from egocentric vision".</p>
LiverHccSeg: A Publicly Available Multiphasic MRI Dataset with Liver and HCC Tumor Segmentations and Inter-Rater Agreement Analysis
<p>Please <strong>cite our data paper </strong>published in "Data in Brief": https://www.sciencedirect.com/science/article/pii/S2352340923007473</p><p> </p><p><strong>Background</strong><br>Liver cancer ranks as the third leading cause of cancer-related mortality worldwide [1] and alarmingly, both the incidence and mortality rates of liver cancer are increasing [2; 3]. Among the various types of primary liver cancer, hepatocellular carcinoma (HCC) stands out as the most prevalent, accounting for approximately 70-85% of liver cancer cases [4]. Leveraging the advantages of magnetic resonance (MR) imaging, HCC can be reliably detected and diagnosed without the requirement of an invasive biopsy [5]. MR imaging offers high tissue contrast, which can be further enhanced through contrast-enhanced multiphasic magnetic resonance imaging (mpMRI) techniques. This enables accurate identification and non-invasive diagnosis of HCC [6].</p><p> </p><p><strong>Objective</strong><br>Precise segmentation of the liver plays a crucial role in volumetry assessment and serves as a vital pre-processing step for subsequent tumor detection algorithms [7]. However, accurate liver segmentation can be particularly challenging in patients with cancer-related tissue alterations and deformations in shape [8]. Accurate HCC tumor segmentation is essential for the extraction of quantitative imaging biomarkers such as radiomics and can be used for studies on treatment response assessment and prognosis evaluation and provides critical information about the tumor biology. In order to enhance the reproducibility of liver and tumor segmentation, automated methods utilizing image analysis techniques and machine learning have been developed. These methods have demonstrated promising results [7; 8]; however, most algorithms were tested only on small internal test sets and therefore do not guarantee generalizable and consistent performance on external data.</p><p>Publicly available datasets allow for fair and objective comparisons between different algorithms, techniques, or approaches. Researchers can evaluate the strengths and weaknesses of their methods in relation to existing solutions and establish benchmarks for performance evaluation. In addition to providing a benchmark with this dataset, we also assess the inter-rater variability between two different sets of tumor segmentations. This analysis serves as a measure of reproducibility for human segmentations, highlighting the consistency or variability that may exist among different human raters. Understanding the reproducibility of human segmentations is essential in assessing the reliability of manual annotations and establishing a baseline for algorithm performance comparison. By introducing LiverHccSeg, we aim to fill the gap of lacking publicly available mpMRI HCC datasets and offer researchers and developers a valuable resource for algorithmic evaluation on external data and imaging biomarker analyzes.</p><p> </p><p><strong>Materials and Methods</strong></p><p><i><strong>Inclusion of Patients</strong></i><br>All available scans from The Cancer Genome Atlas Liver Hepatocellular Carcinoma Collection (TCGA-LIHC) (<a href="https://wiki.cancerimagingarchive.net/pages/viewpage.action?pageId=6885436">https://wiki.cancerimagingarchive.net/pages/viewpage.action?pageId=6885436</a>) were downloaded [9]. One multiphasic MRI scan (pre and triphasic post contrast) per patient was included. Patients who did not exhibit a tumor or residual tumor were excluded from the tumor segmentation dataset; however, they were included in the liver segmentation dataset.</p><p> </p><p><i><strong>MR Imaging Data</strong></i><br>Subsequently, all imaging data was converted to the Neuroimaging Informatics Technology Initiative (NIfTI) format with the dcm2nii (v2.1.53) package [10] and available header information was extracted using the pydicom (v.2.1.2) package [11]. Multiparametric MR sequences were labeled with a consistent syntax ('pre', 'art', 'pv', 'del', for the pre-contrast, arterial, portal-venous and delayed contrast phases, respectively). All images were already de-identified by the TCIA website. Images were acquired between the years 1993 and 2007 on Philips and Siemens scanners with field strengths of 1.5 and 3 Tesla. Full details of the imaging parameters can be found in Table 5. Briefly, the median repetition time (TR) and median echo time (TE) were 365.8 ms and 26.4 ms, respectively. The median slice thickness was 9.5 mm, the median bandwidth 536.9 Hz.</p><p> </p><p><i><strong>Scientific Reading</strong></i><br>After conversion, all images were read in a scientific reading by two board-certified abdominal radiologists (S.A. and S.H with 9 and 10 years of experience, respectively). Any disagreement between the two raters was discussed in a consensus meeting. All HCC lesions were classified according to LI-RADS criteria [6].</p><p> </p><p><i><strong>Image Registration</strong></i><br>The co-registration of pre-contrast, portal-venous, and delayed-phase images with arterial phase images was performed using the software BioImage Suite (v3.5) [12]. A non-rigid intensity-based registration approach was applied, employing a parameterized free-form deformation (FFD) with 3D B-splines [13]. The optimal FFD transformation was estimated by maximizing the normalized mutual information similarity metric [14] through gradient descent optimization. To enhance the optimization process, a multi-resolution image pyramid with three levels was utilized. The final B-spline control point spacing was set to 80 mm. The estimated transformation was then employed to warp the moving images (pre-contrast, portal-venous, and delayed-phase) into the reference image space, specifically the arterial phase image.</p><p> </p><p><i><strong>Liver and Tumor Segmentation and Statistical Analysis</strong></i><br>All livers and tumors were manually segmented under the supervision of two board-certified abdominal radiologists using the software 3D Slicer (v4.10.2) [15]. To compare the segmentation agreement between the two sets of liver and tumor segmentations, we calculated segmentation metrics using the Python package seg-metrics (v1.0.0) [16]. All segmentation metrics and statistics were calculated in Python (v3.7).</p><p> </p><p><strong>Data description</strong><br>The data that appears in this article include:</p><ol><li>dicoms.zip: This zip file contains all the raw MR images from The Cancer Genome Atlas Liver Hepatocellular Carcinoma Collection (TCGA-LIHC) [1] in the Digital Imaging and Communications in Medicine (DICOM) format used for the curation of this dataset. The data is structured as Patient-ID/DATE/SEQUENCE where Patient-ID is the unique unidentified patient ID, DATE is the date of the image acquisition, and SEQUENCE is the name of the MR sequence.<br> </li><li>LiverHccSeg_MetaData.xlsx: This spreadsheet contains all the metadata from the DICOM headers along with the data from the scientific image readings.<br> </li><li>nifti_and_segms.zip: This zip file contains all MR images along with the liver and tumor segmentations in the Neuroimaging Informatics Technology Initiative (NIfTI) format.<br>The data is structured as Patient-ID/DATE/SEQUENCE where Patient-ID is the unique anonymized patient identifier, DATE is the date of the image acquisition, and SEQUENCE is the name of the MRI sequence or segmentation image.<br><br>The NIfTI files are named as follows:<br><strong>pre.nii.gz</strong> : Pre-contrast T1-weighted MRI<br><strong>art.nii.gz</strong>: Arterial-phase T1-weighted MRI<br><strong>pv.nii.gz</strong>: Portal-venous-phase T1-weighted MRI<br><strong>del.nii.gz</strong>: Delayed-phase T1-weighted MRI<br><strong>art_pre.nii.gz</strong>: Pre-contrast T1-weighted MRI registered to the corresponding arterial-phase T1-weighted image<br><strong>art_pv.nii.gz</strong>: Portal-venous-phase T1-weighted MRI registered to the corresponding arterial-phase T1-weighted MRI<br><strong>art_del.nii.gz</strong>: Delayed-phase T1-weighted MRI registered to the corresponding arterial-phase T1-weighted MRI<br><br>The corresponding manual segmentations are named after the rater and the type of segmentation and follow the format 'RATER_ROI.nii.gz' where RATER denotes the human rater and ROI denotes the region of interest that was segmented, for example, '<strong>rater1_liver.nii.gz</strong>', '<strong>rater2_liver.nii.gz</strong>', '<strong>rater1_tumor1.nii.gz</strong>', and '<strong>rater2_tumor1.nii.gz</strong>'. For tumor segmentations, an integer indicates the tumor identification number for different tumor ROIs, for example, 'rater1_tumor1.nii.gz' and 'rater2_tumor1.nii.gz'. The segmentations can be used for the arterial phase NIfTI file as well as the corresponding co-registered pre-contrast (art_pre.nii.gz), portal-venous (art_pv.nii.gz), and delayed-phase (art_del.nii.gz) images.<br> </li><li>segm_metrics.xlsx: This spreadsheet summarizes the segmentation agreement between the two sets of liver and tumor segmentations by the two board-certified abdominal radiologists.</li></ol><p> </p><p><strong>References</strong></p><p>1 Sung H, Ferlay J, Siegel RL et al (2021) Global Cancer Statistics 2020: GLOBOCAN Estimates of Incidence and Mortality Worldwide for 36 Cancers in 185 Countries. CA Cancer J Clin 71:209-249</p><p>2 Siegel RL, Miller KD, Jemal A (2019) Cancer statistics, 2019. CA Cancer J Clin 69:7-34</p><p>3 White DL, Thrift AP, Kanwal F, Davila J, El-Serag HB (2017) Incidence of Hepatocellular Carcinoma in All 50 United States, From 2000 Through 2012. Gastroenterology 152:812-820.e815</p><p>4 Perz JF, Armstrong GL, Farrington LA, Hutin YJ, Bell BP (2006) The contributions of hepatitis B virus and hepatitis C virus infections to cirrhosis and primary liver cancer worldwide. J Hepatol 45:529-538</p><p>5 Hamer OW, Schlottmann K, Sirlin CB, Feuerbach S (2007) Technology insight: advances in liver imaging. Nat Clin Pract Gastroenterol Hepatol 4:215-228</p><p>6 Chernyak V, Fowler KJ, Kamaya A et al (2018) Liver Imaging Reporting and Data System (LI-RADS) Version 2018: Imaging of Hepatocellular Carcinoma in At-Risk Patients. Radiology 289:816-830</p><p>7 Bousabarah K, Letzen B, Tefera J et al (2020) Automated detection and delineation of hepatocellular carcinoma on multiphasic contrast-enhanced MRI using deep learning. Abdom Radiol. 10.1007/s00261-020-02604-5</p><p>8 Gross M, Spektor M, Jaffe A et al (2021) Improved performance and consistency of deep learning 3D liver segmentation with heterogeneous cancer stages in magnetic resonance imaging. PLoS One 16:e0260630</p><p>9 Erickson BJ, Kirk S, Lee Y et al (2016) Radiology Data from The Cancer Genome Atlas Liver Hepatocellular Carcinoma [TCGA-LIHC] collection. The Cancer Imaging Archive. 10.7937/K9/TCIA.2016.IMMQW8UQ</p><p>10 dcm2nii DICOM to NIfTI converter. <a href="https://github.com/rordenlab/dcm2niix">https://github.com/rordenlab/dcm2niix</a> Accessed: 2021-12-07.</p><p>11 Mason D, scaramallion;, rhaxton; et al (2020) pydicom/pydicom: pydicom 2.1.2, v2.1.2. Zenodo</p><p>12 X. Papademetris MJ, N. Rajeevan, H. Okuda, R.T. Constable, L.H Staib BioImage Suite: An integrated medical image analysis suite, Section of Bioimaging Sciences, Dept. of Diagnostic Radiology, Yale School of Medicine. <a href="http://www.bioimagesuite.org">http://www.bioimagesuite.org</a>.</p><p>13 Rueckert D, Sonoda LI, Hayes C, Hill DLG, Leach MO, Hawkes DJ (1999) Nonrigid Registration Using Free-Form Deformations: Application to Breast MR Images. IEEE Trans Med Imaging 18:712–721</p><p>14 Studholme C, Hill DL, Hawkes DJ (1999) An overlap invariant entropy measure of 3D medical image alignment. Pattern Recognition 32:71-86</p><p>15 Fedorov A., Beichel R., Kalpathy-Cramer J. et al (2012) 3D Slicer as an Image Computing Platform for the Quantitative Imaging Network. Magn Reson Imaging 30:1323-1341</p><p>16 Ordgod (2020) Ordgod/segmentation_metrics: seg-metrics, v1.0.0. Zenodo</p><p> </p><p>- - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - -</p><p><strong>ChangeLog</strong></p><p><strong>Version 1.1:</strong> Fixed incorrect liver segmentation mask.</p><p> </p><p> </p><p> </p><p> </p>
Volumetric segmentation of biological cells and subcellular structures for optical diffraction tomography images - dataset
<p>This dataset includes 4 files with segmentation results for 4 different ODT reconstructions of SH-SY5Y neuroblastoma cell. The segmentation results contain:</p> <ol> <li>3D binary masks of biological cells obtained through Cellpose [1] and <a href="https://github.com/biopto/ODT-SAS.git">ODT-SAS</a>;</li> <li>3D binary masks of organelles: nucleoli and lipid structures (LS) obtained through slice-by-slice manual segmentation and ODT-SAS.</li> </ol> <p>All files are .*mat files.</p> <p>The files <em>REC_SH-SY5Y_1.mat, REC_SH-SY5Y_2.mat</em> and<em> REC_SH-SY5Y_3.mat</em> consist of 7 variables:</p> <p>RECON – tomographic reconstruction of SH-SY5Y neuroblastoma cell;<br> n_imm – refractive index of object immersion medium;<br> dx – object space sample size in XY [<span class="math-tex">\(\mu m\)</span>];<br> rayXY – xy-coordinates of illumination vectors;</p> <p>maskManual – table with manually determined 3D binary masks of organelles;<br> maskCellpose – 3D binary mask of biological cell obtained through Cellpose;<br> maskODTSAS – table with 3D binary masks of biological cell and their organelles obtained through ODT-SAS.</p> <p>File <em>REC_SH-SY5Y_4.mat</em> includes masks for the ODT-SAS and Cellpose segmentation of three closely packed cells and consists of 5 variables: RECON, n_imm, dx, maskCellpose and maskODTSAS.<br> <br> Access a particular 3D binary mask from 'maskManual' and 'maskODTSAS' tables, using the following names: 'Cell', 'Nucleoli', 'LS'.<br> For example:</p> <pre><code>cellMask = maskODTSAS.Cell{1};</code></pre> <p><br> [1] Stringer, C., Wang, T., Michaelos, M., & Pachitariu, M. (2021). Cellpose: a generalist algorithm for cellular segmentation. Nature methods, 18(1), 100-106.</p> <p> </p>
Illuminating the Hierarchical Segmentation of Faults through an Unsupervised Learning Approach applied to clouds of earthquake hypocenters [Dataset]
<p>Data repository to the preprint “Illuminating the Hierarchical Segmentation of Faults through an Unsupersived Larning Approach applied to clouds of earthquake hypocenters” by Piegari et al. (2023), including the datasets for the three analyzed earthquake catalogs.</p>
NCCD-PF - A pre-failure narrow concrete cracks dataset for engineering structures damage classification and semantic segmentation
<p>The NCCD-PF dataset was developed for the classification and semantic segmentation of narrow concrete cracks in engineering structures elements at the pre-failure state. It only includes cracks whose width is narrower than 0.3 mm, i.e. the limit value specified in EC 1992-1-1 for typical elements of engineering structures and environmental conditions.</p> <p>This dataset is dedicated to the early crack detection at a stage when the serviceability limit state has not yet been exceeded and the failure of a structural element has not occurred. By implementing the early crack detection approach, it is possible to protect cracks in order to stop or slow down their propagation and thus to extend the structure's lifespan.</p> <p>This dataset contains images of cracks appearing on various elements of engineering structures (bridges, viaducts, tunnels) made of reinforced concrete (including abutments, tunnel walls, concrete barriers, pillars). The images were captured on construction sites and during inspections of engineering structures, at different stages of the reinforced concrete structure's working conditions - from the construction stage (when the elements are loaded only by their own weight) to the structure's use stage (when the elements are loaded by most of the design loads). The images are also differentiated by the cause of the cracking (ex., thermal and shrinkage stresses in young concrete, excessive stresses). The images were acquired using fixed-focus cameras without prior conditioning in order to represent the real working conditions of a bridge engineer during structural inspections. The images are characterised by a high degree of complexity due to the quality of the concrete surface finish (e.g. presence of formwork marks, concrete trowel marks), which could potentially be recognised as cracks.</p> <p>This dataset is dedicated to researchers working in the fields of computer vision, machine learning and deep learning. In particular, it contains domain knowledge in structural health monitoring, so that it can support the work of engineers in detecting cracks of concrete elements in a pre-failure state.</p> <p>A detailed description of the dataset is presented in <a href="https://www.nature.com/articles/s41597-023-02839-z" target="_blank" rel="noopener">A pre-failure narrow concrete cracks dataset for engineering structures damage classification and segmentation</a> (DOI: 10.1038/s41597-023-02839-z).</p>
iRodent: a keypoint and segmentation dataset of rodents in the wild
<p>Description: The "iRodent" dataset contains rodent species observations obtained using the iNaturalist API, with a focus on Suborder Myomorpha (Taxon ID: 16). The dataset features prominent rodent species like Muskrat, Brown Rat, House Mouse, Black Rat, Hispid Cotton Rat, Meadow Vole, Bank Vole, Deer Mouse, White-footed Mouse, and Striped Field Mouse. The dataset provides manually labeled keypoints for pose estimation and segmentation masks for a subset of images using a Mask R-CNN model.<br> Creator: Adaptive Motor Control Lab<br> Data Format: COCO format<br> Number of Images: 443<br> Species: Muskrat, Brown Rat, House Mouse, Black Rat, Hispid Cotton Rat, Meadow Vole, Bank Vole, Deer Mouse, White-footed Mouse, Striped Field Mouse<br> Image Resolution: Varied (800x600 to 5184x3456 pixels)<br> Annotations: Pose keypoints and generated segmentation masks by Tian Qiu and Mackenzie Mathis.<br> License: Apache 2.0<br> Keywords: animal pose estimation, behaviour analysis, keypoints, rodent<br> Contact: Mackenzie Mathis<br> Email: <a href="mailto:mackenzie.mathis@epfl.ch">mackenzie.mathis@epfl.ch</a><br> </p>
FOR-instance: a UAV laser scanning benchmark dataset for semantic and instance segmentation of individual trees
<p>The challenge of accurately segmenting individual trees from laser scanning data hinders the assessment of crucial tree parameters necessary for effective forest management, impacting many downstream applications. While dense laser scanning offers detailed 3D representations, automating the segmentation of trees and their structures from point clouds remains difficult. The lack of suitable benchmark datasets and reliance on small datasets have limited method development. The emergence of deep learning models exacerbates the need for standardized benchmarks. Addressing these gaps, the FOR-instance data represent a novel benchmarking dataset to enhance forest measurement using dense airborne laser scanning data, aiding researchers in advancing segmentation methods for forested 3D scenes.</p> <p>In this repository, users will find forest laser scanning point clouds from unamnned aerial vehicle (using Riegl sensors) that are manually segmented according to the individual trees (1130 trees) and semantic classes. The point clouds are subdivided into five data collections representing different forests in Norway, the Czech Republic, Austria, New Zealand, and Australia. </p> <p>These data are meant to be used either for developement of new methods (using the dev data) or for testing of exisitng methods (test data). The data splits are provided in the data_split_metadata.csv file.</p> <p>A full description of the FOR-instance data can be found at <a href="http://arxiv.org/abs/2309.01279">http://arxiv.org/abs/2309.01279</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>
Benthos Dataset; segmented photomosaics from three oceanic environments
Open the record for dataset details and reuse information.
Dataset to ACM MMSys'20 paper entitled "Comparing Fixed and Variable Segment Durations for Adaptive Video Streaming – A Holistic Analysis"
<p>Dataset for the ACM MMSys'20 paper entitled "Comparing Fixed and Variable Segment Durations for Adaptive<br> Video Streaming – A Holistic Analysis".<br> The dataset includes</p> <ul> <li>Results from video encoding (using variable and fixed segment durations)</li> <li>Video sequences used for streaming evaluations</li> </ul>
Hakea vegetation dataset for training and evaluating segmentation network
<p>This dataset is the version used for both training and evaluation of the models discussed the (in press) publication in Methods in Ecology and Evolution, "Detecting plant species in the field with deep learning and drone technology".</p> <p>Also included in this upload, results_inference_images.tar includes the output predictions for each of the trained models on the unseen test set.</p>
Clouds dataset for semantic segmentation
<p>This database contains images used for training a fully convolutional neural network for the semantic segmentation of clouds in images from the Sentinel-2 Level 2A Satellite.</p> <p>The images refer to the RGB composition (bands 4, 3, and 2).</p> <p>After that, 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 1.160 GeoTIFF images with 512x512 pixels and associated PNG masks (clouds indicated in white and background in black color).</li> <li><strong>Validation dataset</strong>: it contains 100 GeoTIFF images with 512x512 pixels and associated PNG masks used for validation step.</li> <li><strong>Test dataset: </strong>it contains 100 GeoTIFF images 512x512 pixels for testing.</li> </ol>
RibFrac Dataset: A Benchmark for Rib Fracture Detection, Segmentation and Classification (Test Set)
<p>RibFrac dataset is a benchmark for developping algorithms on rib fracture detection, segmentation and classification. We hope this large-scale dataset could facilitate both clinical research for automatic rib fracture detection and diagnoses, and engineering research for 3D detection, segmentation and classification.</p> <p>This is the Test Set of RibFrac dataset, including 160 CTs and the corresponding annotations. Files include:</p> <ol> <li>ribfrac-test-images.zip: 160 chest-abdomen CTs in NII format (nii.gz) </li> </ol> <p>Note that only the images are released; the corresponding ground truth labels are not available. Check the <a href="https://ribfrac.grand-challenge.org/">MICCAI 2020 RibFrac Challenge website</a> to evaluate your algorithm.</p> <p> </p> <p>If you find this work useful in your research, please acknowledge the RibFrac project teams in the paper and cite this project as:</p> <p><em>Liang Jin, Jiancheng Yang, Kaiming Kuang, Bingbing Ni, Yiyi Gao, Yingli Sun, Pan Gao, Weiling Ma, Mingyu Tan, Hui Kang, Jiajun Chen, Ming Li. Deep-</em><em>Learning-Assisted Detection and Segmentation of Rib Fractures from CT Scans: Development and Validation of FracNet. EBioMedicine (2020). (<a href="https://doi.org/10.1016/j.ebiom.2020.103106">DOI</a>)</em></p> <p>or using bibtex</p> <p><em>@article{ribfrac2020,<br> title={Deep-Learning-Assisted Detection and Segmentation of Rib Fractures from CT Scans: Development and Validation of FracNet},<br> author={Jin, Liang and Yang, Jiancheng and Kuang, Kaiming and Ni, Bingbing and Gao, Yiyi and Sun, Yingli and Gao, Pan and Ma, Weiling and Tan, Mingyu and Kang, Hui and Chen, Jiajun and Li, Ming},<br> journal={EBioMedicine},<br> year={2020},<br> publisher={Elsevier}<br> }</em></p> <p> </p> <p>The RibFrac dataset is a research effort of thousands of hours by experienced radiologists, computer scientists and engineers. We kindly ask you to respect our effort by appropriate citation and keeping data license.</p> <p> </p> <p>This work is licensed under a <a href="http://creativecommons.org/licenses/by-nc/4.0/">Creative Commons Attribution-NonCommercial 4.0 International License</a>.</p>
Brazil's South Region landslide dataset for semantic segmentation
<p>This database contains images used for the semantic segmentation of landslide scars from a fully convolutional neural network U-Net of the three States of Brazil's South Region: Rio Grande do Sul, Santa Catarina and Paraná. Each .rar file contains 3 folders:</p> <p><strong>Image: </strong>GeoTIFF 8 bits images of locations with landslide scars.</p> <p><strong>Masks: </strong>PNG masks (scars indicated in white and background in black color).</p> <p><strong>Slope: </strong>GeoTIFF float rasters of slope (in degrees).</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>
VTT-Coffee: A small dataset for instance segmentation and iterative learning
<p>VTT-Coffee is a small scale dataset containing microscopic images of coffee grinds and annotations of their contours (segmentation masks).</p> <p>The dataset is useful to benchmark instance segmentations methods, especially for use cases containing just one class with a lot of variability.</p>
The Mountain Habitats Segmentation and Change Detection Dataset
<p>This is the dataset presented in the paper <em>The Mountain Habitats Segmentation and Change Detection Dataset</em> accepted for publication in the <em>IEEE Winter Conference on Applications of Computer Vision </em>(WACV), Waikoloa Beach, HI, USA, January 6-9, 2015. The full-sized images and masks along with the accompanying files and results can be downloaded here. The size of the dataset is about 2.1 GB.</p> <p>The dataset is released under the <em>Creative Commons Attribution-Non Commercial 4.0 International License </em>(http://creativecommons.org/licenses/by-nc/4.0/legalcode).</p> <p>The dataset documentation is hosted on GitHub at the following address: http://github.com/fjean/mhscd-dataset-doc. Direct download links to the latest revision of the documentation are provided below:</p> <ul> <li><strong>PDF format</strong>: http://github.com/fjean/mhscd-dataset-doc/raw/master/mhscd-dataset-doc.pdf</li> <li><strong>Text format</strong>: http://github.com/fjean/mhscd-dataset-doc/raw/master/mhscd-dataset-doc.rst</li> </ul> <p> </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.