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.
107
datasets available to search
ShareScore release 0.7.1
Dataset results
107 results for “Computer Vision”
A computer vision pipeline for predicting zoonotic reservoir distribution
<p>Shared here is the complete project repository of code and data supporting the manuscript, "Predicting the fine-scale spatial distribution of zoonotic reservoirs using computer vision."</p> <p>Note that all project subdirectories (with the exception of the "Data" subdirectory) were compressed into single .zip files and thus need to be decompressed upon download. The "Data" subdirectory, which contains numerous large data files, was stored as a split zip archive to facilitate upload to Zenodo and consists of the files "Data.z01", "Data.z02", "Data.z03", and "Data.zip". These files may need to be decompressed using dedicated archiver software (such as The Unarchiver [https://theunarchiver.com/] on macOS). The "Data" subdirectory should be ~17 GB upon decompression. Note that the entire project repository is ~40 GB when uncompressed.</p>
Tassie BRUV: A benchmark data set for computer vision and movement quantification algorithms
Open the record for dataset details and reuse information.
2 Datasets of forests for Computer Vision and Deep Learning techniques
<p>Datasets:</p> <p>1) Coastal forest in Shonai area; contains an orthomosaic (processed by Metashape) of the coastal forest and annotated layers (processed in Gimp)</p> <p>Annotated layers: 0 = annotations of black locust; 1 = annotations of soil; 2 = annotations of man-made; 3 = annotations of other trees and the orthomosaic as JPEG file</p> <p>2) Mixed forest images of the Yamagata University Research Forest taken in the winter season; contains 7 orthomosaics (TIFF file), annotated layers (named wM1 to wM7; processed in Gimp)</p> <p>Orthomosaics: 7 orthomosaics of 5 different sites; for one of the sites we provide 3 orthomosaics of different days and illumination conditions</p> <p>Annotated layers: 0 = annotations of river class; 1 = annotations of deciduous class; 2 = annotations of uncovered class; 3 = annotations of evergreen class; 4 = annotations of man-made class and the orthomosaic as JPEG file</p> <p> </p> <p>The dataset was used for our transfer learning study in the field of forest applications. We used in one experiment the winter images to run deep learning algorithms. In a second experiment we used the coastal forest data for a similar approach.</p>
Shadow Detection/Texture Segmentation Computer Vision Dataset
<p>A simple computer vision dataset for shadow detection and texture analysis, specifically created to help test shadow detection algorithms (and texture segmentation algorithms) for mobile robots - that is, shadow detection with an <em>active (moving) camera</em>.</p> <p>The dataset is focused around texture analysis, so each image sequence contains shadows moving in front of a number of various textured surfaces. The dataset contains four main subfolders: "active", "artificial", "kondo", and "static". The "static" folder contains ground-truthed image sequences of textured surfaces with shadows moving over them, and the "active" folder contains ground-truthed image sequences of a camera travelling over textured surfaces. The "artificial" folder contains a computer-generated 3D scene with computer-generated ground truth, but note that texture is absent from all images within. Finally, the "kondo" folder contains a series of extremely challenging images captured from a webcam mounted to a Kondo bipedal robot. This final dataset is challenging because it contains a high level of noise, flicker and interference from electrical lighting, and the poor lighting conditions make for complex shadows with large penumbrae.</p>
Reconstructing illusory camouflage patterns on moth wings using computer vision - Datas and codes
<p>This repository contains the data, codes and pre-trained weights for the experiments in our paper "Reconstructing illusory camouflage patterns on moth wings using computer vision", accepted for publication in the Journal of The Royal Society Interface.</p> <p>The images, in photos.zip, are available under CC-BY-SA 4.0 International license.</p> <p>The c++ codes, available in codes_closed_forms.zip, are available under a GPL 3.0 license.</p> <p>The monocular depth reconstruction toolbox we used to test different deep learning models for monocular reconstruction is available under the Apache 2.0 software license.</p>
Images of Public Streetlights with Operational Monitoring using Computer Vision Techniques
<p>This dataset consists of ~350k JPEG images of streetlight columns installed on a public road infrastructure located in the city of Bristol, UK.</p> <p>Each streetlight is photographed by a Raspberry Pi Camera Module v1, installed on each lamppost, providing a unique camera placement, photographic angle, and distance from the streetlight. Several streetlights are partially obstructed by vegetation or are outside the Field of View (FoV) of the Raspberry Pi camera. Finally, the cameras facing the sky are susceptible to weather conditions (e.g., rain, snow, direct sunlight, etc.) that can partially or entirely alter the quality of the images taken.</p> <p>The above provides a unique and diverse dataset of images that can be used for training tools and machine learning models for inspection, monitoring and maintenance use-cases within Smart Cities applications.</p>
Target-focused library design by pocket-applied computer vision and fragment deep generative linking
<p>Data inputs and outputs used in</p> <pre>Target-focused library design by pocket-applied computer vision and fragment deep generative linking</pre> <p>Code: https://github.com/kimeguida/POEM</p> <p> </p>
Dataset, Model Statistics, and 3D designs for "From Eyes to Cameras: Computer Vision for High-Throughput Liquid-Liquid Separation"
<p>Dataset, model statistics, and 3D design of high throughput platform associated with HeinSight3.0. </p> <p> </p> <p>Pre-print: https://chemrxiv.org/engage/chemrxiv/article-details/65e5481f9138d231619c1879</p> <p> </p> <p>The code and model of HeinSight3.0 can be found at (https://doi.org/10.5281/zenodo.11053915)</p>
Adaptive Computer Vision-Based 2D Tracking of Workers in Complex Environments
<p>Data set used for testing the efficiency of a vision-based tracking method on tracking construction workers. </p>
Computer Vision-Based Image Analysis
<p>Computer Vision-Based Image Analysis Tool is an innovative tool analysing the colour change of the foods in the fridge to correlate this information to the food loss and waste at household level. This tool deals with colour measurement from the 2D image of 3D fresh fruit and vegetable. The system takes the pictures of the selected fruit or vegetable, analyses the image and detects the colour-based deterioration, if any. The deterioration is calculated as area percentage. Finally, this information is correlated to the weight of these fruits or vegetables. This technology will also be adapted to the meat supply chain to evaluate the meat quality according to their colour for further processing.</p>
High-throughput robotic determination of hydrogen peroxide using computer vision
<p>A fully automated process of high-throughput determination of hydrogen peroxide integrating a liquid handling robot (Opentrons, OT-2) with a webcam based on chemical titration.</p>
Dataset for article: Gait Speed Assessment in the 10-meter Walk Test for Older Adults Using a Computer Vision-based System: A Cross-sectional Study on Validity, Reliability, and Usability
<p>This dataset provides the Validity, Reliability, and Usability for an assessment of gait speed detection system in the 10-meter Walk Test for Older Adults.</p> <p>The dataset is formatted for easy import into microsoft excel software consist of:<br>Supplementary1.xlsx - Validity <br>Supplementary2.xlsx - Reliability<br>Supplementary3.xlsx - Usability test</p>
Figures from the paper "The diversity of canonical and ubiquitous progress in computer vision: A dynamic topic modeling approach"(v2))
<p>Figures from the paper "The diversity of canonical and ubiquitous progress in computer vision: A dynamic topic modeling approach".</p> <p><strong>The second version:</strong> Corrections to Figure 1. (fig1-> fig_v2).</p>
Combining graph neural networks and computer vision methods for cell nuclei classification in lung tissue
<p>Database of the article "Combining graph neural networks and computer vision methods for cell nuclei classification in lung tissue ".</p>
Development and Validation of Delirium Recognition Using Computer Vision in Neuro-critical Patients
ClinicalTrials.gov study NCT07136207. IPD Sharing: NO. Countries: 1. Publications: 10.
Evaluation of the Accuracy of a Computer Vision-based Tool for Assessment of Total Body Fat Percentage
ClinicalTrials.gov study NCT04854421. IPD Sharing: NO. Countries: 1. Publications: 1.
Videos of computer vision based recognition/segmentation/classification of materials inside vessels in chemistry lab and other setting
<p>These videos contain materials in vessels in various settings related to the chemistry lab, medical samples and handling liquids in everyday life settings. The region and type of each vessel and material phase found by the computer vision (neural net) are marked in purple, the class of each phase appears above each panel in green (each panel corresponds to a different class). The work is part of the computer vision for the chemistry lab project.</p> <p>For details on the project see:</p> <p><a href="https://chemrxiv.org/articles/Computer_Vision_for_Recognition_of_Materials_and_Vessels_in_Chemistry_Lab_Settings_and_the_Vector-LabPics_Dataset/11930004">https://chemrxiv.org/articles/Computer_Vision_for_Recognition_of_Materials_and_Vessels_in_Chemistry_Lab_Settings_and_the_Vector-LabPics_Dataset/11930004</a></p> <p>For Details on the videos See:</p> <p><a href="https://www.youtube.com/watch?v=K7I2QJcIyBQ&list=PLRiTwBVzSM3B6MirlFl6fW0YQR4TtQmtJ">https://www.youtube.com/watch?v=K7I2QJcIyBQ&list=PLRiTwBVzSM3B6MirlFl6fW0YQR4TtQmtJ</a></p> <p>Basically, the videos contain process such as pouring, mixing, foam formation precipitation, phase separation, melting freezing, dissolving, etc.., where the region of each vessel and material phase and their type (liquid, solid, powder, suspension, foam) is found by the neural net and marked purple.</p> <p>For code see:</p> <p><a href="https://github.com/aspuru-guzik-group/Computer-vision-for-the-chemistry-lab">https://github.com/aspuru-guzik-group/Computer-vision-for-the-chemistry-lab</a></p> <p> </p> <p> </p> <p> </p>
Dataset for "Predicting the growth trajectory and yield of greenhouse strawberries based on knowledge-guided computer vision"
<h2>Overall</h2> <p>A strawberry dataset for the paper "Qi Yang, Licheng Liu, Junxiong Zhou, Mary Rogers, Zhenong Jin, 2024. Predicting the growth trajectory and yield of greenhouse strawberries based on knowledge-guided computer vision, Computers and Electronics in Agriculture, 220, 108911. <a title="Persistent link using digital object identifier" href="https://doi.org/10.1016/j.compag.2024.108911" target="_blank" rel="noreferrer noopener">https://doi.org/10.1016/j.compag.2024.108911</a>"</p> <h2>Plant traits measurements</h2> <p>The folder "measurement.zip" includes treatment-level and fruit-level ground truth data. </p> <h3>Treatment-level</h3> <pre><code>data_dryMatter_2022.csv data_dryMatter_2023.csv data_freshMatter_2022.csv data_freshMatter_2023.csv data_fruitNumber_2022.csv data_fruitNumber_2023.csv data_plantBiomass_2022.csv data_plantBiomass_2023.csv</code></pre> <h3>Fruit-level</h3> <p>Fruit conditions with five classes, 1-5 represent Normal, Wizened, Malformed, Wizened & Malformed, and Overripe, respectively.</p> <pre><code>data_size_freshWeight_condition_2022_0N.csv data_size_freshWeight_condition_2022_50N.csv data_size_freshWeight_condition_2022_100N.csv data_size_freshWeight_condition_2022_150N.csv</code></pre> <p>Fruit size for tagged fruits</p> <pre><code>data_taggedFruit_diameter_2022.csv data_taggedFruit_diameter_2023.csv data_taggedFruit_length_2022.csv data_taggedFruit_length_2023.csv</code></pre> <p>Fresh yield and lifespan for tagged fruits (only available in experiment 2023)</p> <pre><code>data_taggedFruit_freshMatter_2023.csv data_taggedFruit_lifespan_2023.csv</code></pre> <h3>Weather data</h3> <pre><code>weather_daily_2022.csv weather_daily_2023.csv</code></pre> <h2>Image data with label</h2> <h3>Object and phenology detection</h3> <p>The folder "strawberry_img_random.zip" contains images and the corresponding JSON labels for object and phenological stages detection.</p> <h3>Fruit size and decimal phenological stage</h3> <p>The folder "strawberry_img_tagged.zip" contains images and the corresponding JSON labels for fruit size and decimal phenological stages detection.</p> <pre><code>For example, "label": "small g, 8.84, 7.62, 0.4", This label means the fruit has an 8.84mm diameter and 7.62mm length, with the main stage being small green and the decimal stage being DS-4 </code></pre> <h3>Merge and split Data</h3> <p>A Python script, "datasetProcessing.py", can be used to merge and split the image data into training and testing set.</p> <h3>Pre-trained models</h3> <p>models.zip</p> <p> </p> <p><em>Data collector: Dr. Qi Yang, University of Minnesota, USA. Email: qiyang577@gmail.com</em></p> <p><em>All the files belong to Prof. Zhenong Jin, University of Minnesota, USA. Email: jinzn@umn.edu</em></p>
Dataset for "Predicting the Strength of Composites with Computer Vision Using Small Experimental Datasets"
<p>Composite_Strength_Prediction_by_CNN_v1.0</p>
Dataset from "A Hybrid 3D Printed Hand Prosthesis Prototype Based on sEMG and a Fully Embedded Computer Vision System"
<p>Open access dataset containing objects images to be used in training computer vision systems for hand gestures recognition. There are 4 zip files with 6900 images for tripod pinch, 8345 images for palmar grasp with neutral wrist position, 8280 images for palmar grasp with pronated wrist, and 2188 images for key grasp pattern. These are images from the Newcastle Grasp Library (NGL) and the Amsterdam Object Image Library (ALOI). There are other 3 zip files with musical and computer keyboards and tablets images.</p> <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.