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.
130
datasets available to search
ShareScore release 0.9.0
Dataset results
130 results for “image reconstruction”
Data for "Image-based Backbone Reconstruction for Non-Slender Soft Robots"
<p>This dataset provides the data for the forthcoming paper "Image-based Backbone Reconstruction for Non-Slender Soft Robots". The backbone reconstruction method used is based on the method described in Hoffmann et al. [1]. The modifications to this method to support the non-slender soft robot in this dataset are described in the forthcoming paper mentioned above. This dataset holds raw images of pressurized and elongated soft robots and the corresponding reconstructed backbones.</p> <h2>Dataset</h2> <p>The dataset is split into two subsets with similar structure. The first subset is contained in `dataset_01`. The second dataset is contained in `dataset_02`.</p> <p>Each subset consists of five folders and one schedule file. The schedule file `schedule.csv` contains the index of the schedule entry, the angle <span>α</span> in degree, the pressure of each chamber p_1 to p_3 in bar and if the pressurization is active. Furthermore, the five folders of the subset can be described as follows</p> <p>- `raw`: Contains the raw cropped images. The filenames are formatted as `CROPPED_C{CAMERA_INDEX}_E{SCHEDULE_ENTRY}.png` with the camera index `CAMERA_INDEX` and the schedule entry `SCHEDULE_ENTRY`.</p> <p>-`constant_curvature_slender`, `constant_curvature_volumetric`, `cubic_curvature_slender` and `cubic_curvature_volumetric`. These folders contain the actual reconstructed backbones based on the raw data from the `raw` folder. A different reconstruction approach was used in each of these folders<br> - `constant_curvature_slender` - A constant curvature backbone kinematic based on the slender model,<br> - `constant_curvature_volumetric` - A constant curvature backbone kinematic based on the volumetric model,<br> - `cubic_curvature_slender` - A cubic curvature backbone kinematic based on the slender model,<br> - `cubic_curvature_volumetric` - A cubic curvature backbone kinematic based on the volumetric model.<br>Each of these folders contain a `data` and `figures` folder. The data folder consists of `PARAMETER_E{SCHEDULE_ENTRY}.json` files listing the optimization parameters for each schedule entry `SCHEDULE_ENTRY` in the JSON format. The `figures` folder contains annotated images of the reconstructed backbone on the cropped raw images. The filenames are structured `ANNOTATED_E{SCHEDULE_ENTRY}_C{CAMERA_INDEX}_EPOCH{EPOCH}.png` with the schedule entry `SCHEDULE_ENTRY`, the camera index `CAMERA_INDEX` and the epoch `EPOCH` of the optimization algorithm.</p> <p>The optimization parameters include the base position `base_position` of the reconstructed backbone in world coordinates, the coefficients for the curvature polynomials `ux` and `uy`, and the constant coefficient for the elongation polynomial `la`.</p> <h2>Calibration Data</h2> <p>The calibration data is located in the `calibration` folder and consists of multiple `.npy` files in the numpy format. The corresponding camera index for the calibrated camera is abbreviated with `CAMERA_INDEX` in the following:</p> <ul> <li>`C{CAMERA_INDEX}.npy` - Stores the reprojection error, camera matrix, distortion coefficients, rotation, and translation vectors as returned by the `cv2.calibrateCamera` [2] method. </li> <li>`C{CAMERA_INDEX}_camera_matrix.npy` - Stores the camera_matrix as returned by the `cv2.calibrateCamera` [2] method. </li> <li>`C{CAMERA_INDEX}_distortion_coefficients.npy` - Stores the distortion coefficients as returned by the `cv2.calibrateCamera` [2] method. </li> <li> `C{CAMERA_INDEX}_projection_matrix.npy` - Stores the projection matrix from world space to pixel space based on the stereo camera calibration.</li> <li> `STEREO.npy` - Stores the reprojection error, R, T, E, F as returned by the `cv2.stereoCalibrate` [2] method as an object datatype.</li> </ul> <h2>Acknowledgement</h2> <p>Funded by the Deutsche Forschungsgemeinschaft (DFG, German Research Foundation) – 501861263 – SPP2353</p> <h2>References</h2> <p>[1] M. K. Hoffmann, J. Mühlenhoff, Z. Ding, T. Sattel and K. Flaßkamp. An iterative closest point algorithm for marker-free 3D shape registration of continuum robots. arXiv.<br>https://arxiv.org/abs/2405.15336</p> <p>[2] OpenCV. Camera Calibration and 3D Reconstruction. OpenCV Documentation. https://docs.opencv.org/4.x/d9/d0c/group__calib3d.html, accessed May 27, 2024.</p>
Unmixing Autoencoder for Image Reconstruction from Hyperspectral Data
<p>The NIR handwriting imaging data and the noise simulated data of five <span>hydroxyl compounds: methanol, ethanol, 2-phenylethanol, 1-propanol, and 2-chloroethanol.</span></p>
Extrait de la chronologie reconstruite - Proposition d'une méthodologie de reconstruction d'évènement à partir d'images
<p>Le fichier doit être téléchargé et visionné à l'aide d'un lecteur multimédia.</p> <p>Figure 3b. Extrait de la chronologie reconstruite à l’aide de plusieurs séries d’images qui constituent des points de vue différents de l’événement.</p> <p>La vidéo est séparée en quatre quadrants. Les temps indiqués correspondent au temps de chaque clip. L'heure indiquée dans le quadrant inférieur gauche correspond aux indications du système de vidéosurveillance.</p> <p>Les vidéosurveillances fournissent une ligne de temps continue entre 20h et 22h. La 1<sup>ère</sup> série de vidéos (quadrant supérieur droit) et les clips du caméraman (quadrant inférieur droit) sont liés dans une chronologie et situés à partir de leurs métadonnées corrigées. Ces indications sont utilisées pour chercher les explosions dans le contenu des vidéosurveillances (quadrants gauches). La caméra fixe qui se trouve au Sud de la rue Dinso filme une portion de trottoir en plongée avec un mur sur la gauche, un arbre au centre et quatre cabines téléphoniques alignées le long du côté droit de l’image (quadrant inférieur gauche). Le reflet de la lueur de la première explosion sur les soldats et les vitres des cabines situe la trace de la première explosion à 20h44m57s, selon les indications du système de surveillance.</p> <p>La chronologie reconstruite a été publiée à la page 104 du rapport suivant : </p> <p>Truth for Reconciliation Commission of Thailand (2012), Final report july 2010 – july 2012, Bangkok, Thailand, pp. 1-378.</p>
Configuration de la rue Dinso - Proposition d'une méthodologie de reconstruction d'évènement à partir d'images
<p>Le fichier doit être téléchargé et visionné à l'aide d'un lecteur multimédia.</p> <p>Figure 3a. Présentation de la configuration de la rue Dinso avec les véhicules, les protagonistes et les points de vue des caméras : en rouge les caméras de vidéosurveillance, en cyan la dernière image du caméraman et en jaune l'image de la personne muni d'un drapeau.</p> <p>Cette animation est générée à partir d'un modèle 3D de la scène. Il s’agit d’un agrégat d’actions qui se sont déroulées à des moments différents. Ils sont ajoutés à une même représentation, qui donne une vue d’ensemble des situations reconstruites</p>
Représentation de la méthodologie développée avec une découpe animée des trois niveaux successifs - Proposition d'une méthodologie de reconstruction d'évènement à partir d'images
<p>Le fichier doit être téléchargé et visionné à l'aide d'un lecteur multimédia.</p> <p>Figure 1. Représentation de la méthodologie développée avec une découpe animée des trois niveaux successifs</p> <p>L'évènement marque le point de départ de la méthodologie. Celle-ci est constituée d'un cycle de trois étapes : Organisation, Analyse et Évaluation. Ces étapes assurent une systématique de construction des connaissances à partir des données images et des informations d’enquête. Ces connaissances progressent à chaque itération du cycle de trois étapes. Chaque itération intègre des nouvelles données et produit des informations qui nourrissent un potentiel de communication.</p> <p>L'animation présente les trois niveaux successifs de la méthodologie.</p> <p>Le niveau 1 est caractérisé par la pré-analyse, avec la réception du cas et des images. Les étapes font progresser les connaissances de l’évènement : le temps, les lieux, les objets et les personnes. Ces connaissances permettent (I) de communiquer les premiers indices aux mandants (flèche sortante <strong>a</strong>), (II) d’affiner l’organisation, l’analyse et l’évaluation. La communication avec les parties prenantes de l’enquête est entrante et sortante. Elle peut influencer l’orientation de l’enquête, et élargir le champ d’investigation (flèche <strong>b</strong>), notamment à ce qui précède l’évènement. En conséquence, de nouvelles données sous la forme d’images témoins et d’informations d’enquête sont à leur tour intégrées dans la spirale (flèche entrante <strong>c</strong>).</p> <p>Le niveau 2 se concentre sur l’exploitation de ces nouvelles données. Elles rentrent dans la spirale par l’intérieur et amorcent un autre cycle des trois étapes. Ce cycle génère des hypothèses sur l’évènement et produit des indices (flèche <strong>d</strong>) qui ouvrent de nouvelles pistes d’enquête.</p> <p>Le niveau 3 intègre des données de référence sur les éléments pertinents et des nouvelles images témoins. Ces entrées peuvent concerner des actes préparatoires, antérieurs à l’évènement d’intérêt (flèche <strong>e</strong> venant de la partie située en dessous de l’évènement). Les échanges avec d’autres spécialistes font avancer les connaissances jusqu’à la présentation de l’évènement reconstruit aux mandants, qui marque la fin du processus.</p>
Reconstructed Aneto glacier surfaces from historic aerial image photogrammetry (1981) and remote sensing techniques (2020, 2021, 2022)
<p>The Aneto Glacier, is the largest glacier in the Pyrenees. Its shrinkage and wastage have been continuous in recent decades, and there are signs of accelerated melting in recent years. In this study, changes in the surface and ice thickness of the Aneto Glacier from 1981 to 2022 are investigated using historical aerial imagery, airborne LiDAR point clouds, and UAV imagery. A GPR survey conducted in 2020, combined with data from photogrammetric analyses, allowed us to reconstruct the current ice thickness and also the existing ice distribution in 1981 and 2011. Over the last 41 years, the total glaciated area has shrunk by 64.7% and the ice thickness has decreased, on average, by 30.5 m. The mean remaining ice thickness in autumn 2022 was 11.9 m, as against the mean thicknesses of 32.9 m, 19.2 m reconstructed for 1981 and 2011 and 15.0 m observed in 2020 respectively. The results demonstrate the critical situation of the glacier, with an imminent segmentation into two smaller ice bodies and no evidence of an accumulation zone. We also found that the occurrence of an extremely hot and dry year, as observed in the 2021–2022 season, leads to a drastic degradation of the glacier, posing a high risk to the persistence of the Aneto Glacier, a situation that could extend to the rest of the Pyrenean glaciers in a relatively short time. </p>
Reconstructing the Image Scanning Microscopy Dataset: an Inverse Problem
<p>It contains the simulation scripts and the data acquired and analyzed to produce the manuscript "Reconstructing the Image Scanning Microscopy Dataset: an Inverse Problem" (DOI: <a href="https://doi.org/10.1088/1361-6420/accdc5"> 10.1088/1361-6420/accdc5</a>).</p>
Software Architecture Reconstruction for Microservice Systems Using GraalVM Native Image
<p>This Dataset contains the System Architecture Reconstruction for Train-Ticket microservice benchmark.</p> <p>It includes: Manual Analysis, GraalVM Analysis, and Source code Analysis.</p> <p>It's described in a paper with title: Software Architecture Reconstruction for Microservice Systems Using GraalVM Native Image</p> <p> </p>
3D Breast Imaging for Cosmetic and Reconstructive Breast Surgery
ClinicalTrials.gov study NCT01964105. IPD Sharing: Not stated. Countries: 1. Publications: 3.
Deep-Learning Image Reconstruction in CCTA
ClinicalTrials.gov study NCT03980470. IPD Sharing: NO. Countries: 1. Publications: 5.
4D light sheet imaging, computational reconstruction, and cell tracking in mouse embryos -- example data (raw .czi and fused .klb light sheet images of mouse E7.5)
Open the record for dataset details and reuse information.
Evaluation of Image Filters for their integration with LSQR Computerized Tomography Reconstruction Method
<p>Projection data used for the results, including the A matrix and b projections vector for resolution 512x512 and different number of views. Reference image included. Format for Matlab (.mat files). </p>
Fast and Regularized Reconstruction of Building Facades from Street-View Images using Binary Integer Programming
<p>Video demonstrations of the paper "Fast and Regularized Reconstruction of Building Facades from Street-View Images using Binary Integer Programming".</p>
Catalhoyuk reconstructed houses images
<p>Standard images taken to be used as close-ups in the Virtual Museum created with 360-degrees panoramas of the Catalhoyuk reconstructed and experimental houses. Part of these images has been used in the EMOTIVE project (https://emotiveproject.eu/) Çatalhöyük Digital education kit, a virtual collaborative experience. Catalhoyuk is a neolithic archaeological site located in Konya, Turkey.</p>
CT images reconstructed using level-set-reconstruction (published in PTRSA)
<p>A new CT reconstruction algorithm based on the level-set-method has been proposed and evaluated. The results are published in Philosophical Transactions of the Royal Society A. The data set includes all examples described in the paper.</p>
Patch-based image reconstruction for PET using prior-image derived dictionaries
<p>This collection contains figures and reconstructed images in .mat format associated with the manuscript tiled "<strong>Patch-based image reconstruction for PET using prior-image derived dictionaries</strong>" . The file, Data_Fig9-10.zip contains the reconstructed images associated with Fig 9 and 10 as a function of iteration for different methods. Data_Fig10-12.zip contains reconstructed images of the real data for different methods.</p>
Supporting data of the PET image reconstruction using multi-parametric anato-functional priors
<p>Abolfazl Mehranian, Martin A. Belzunce, Flavia Niccolini, Marios Politis, Claudia Prieto, Federico Turkheimer, Alexander Hammers and Andrew J. Reader, "PET image reconstruction using multi-parametric anato-functional priors", Physics in Medicine and Biology, 2017, in press</p> <p>This work is supported by Engineering and Physical Sciences Research Council (EPSRC) under grant EP/M020142/1. T According to EPSRC’s policy framework on research data, all simulation and clinical results supporting this study will be openly available at http://dx.doi.org/10.5281/zenodo.580304</p>
Effects of individualized Electrical Impedance Tomography and image reconstruction settings upon the assessment of regional ventilation distribution: Comparison to 4-dimensional Computed Tomography in a porcine model
<p>Reconstruction Models used for identification of optimal settings for comparison to CT images. Forward models are available in the supplement of the article but were removed form the inverse models due to redundance storage within each model.</p> <p>Prior reconstruction in EIDORS, forward models have to be added again to<em> imdl.fwd_model</em> and <em>imdl.jacobian_background.fwd_model</em>.</p>
Comparative analysis of autofocus criteria in reconstructed images of individual plankton for digital in line holography - Supplementary Material
<p>Supplementary Material belonging to the manuscript entitled "Comparative analysis of autofocus criteria in reconstructed images of individual plankton for digital in line holography", by Moreno et al., submitted to the journal OPTIK.</p>
AEROBLADE: Training-Free Detection of Latent Diffusion Images Using Autoencoder Reconstruction Error (Dataset)
<p>This upload contains the dataset used in <a href="https://arxiv.org/abs/2401.17879" target="_blank" rel="noopener">AEROBLADE: Training-Free Detection of Latent Diffusion Images Using Autoencoder Reconstruction Error</a>.</p> <p>Further details and instructions are provided in the <a href="https://github.com/jonasricker/aeroblade" target="_blank" rel="noopener">project's Github repository</a>.</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.