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.
1,025
datasets available to search
ShareScore release 0.9.0
Dataset results
1,025 results for “Vision”
High spatiotemporal resolution free surface detection using cost-effective video equipment and computer vision techniques in nearly stationary flow along a transparent wall in the laboratory
<p>The identification of the air-water interface in free surface flows traditionally involves intrusive techniques or costly equipment. Non-intrusive alternatives, such as computer vision, are emerging as highly effective substitutes or supplements for more invasive techniques in laboratory measurements, thanks to their straightforward implementation and cost efficiency. This research specifically delves in the conjunction of various naive techniques, exploring their collective precision in detecting the air-water interface along transparent walls in laboratory. A detection technique based on the double gradient of the image is applied and thoroughly examined. The study progresses through multiple refinement stages, culminating in a method that is both cost effective and easy to implement. This methodology allows for large-scale, high resolution measurements (200 mm × 1800 frames per video at a 0.25 mm, 50 Hz resolution), offering both spatial and temporal measurements by adeptly detecting the free surface along transparent walls.</p>
EOL computer vision pipelines: Object Detection for Image Cropping: Aves
<p>Produced by an detection model pretrained on MS COCO 2017. Automatically crops images of birds (Aves) to square dimensions centered around animal(s). </p> <p>388,166 rows </p>
EOL computer vision pipelines: Object Detection for Image Cropping: Multi-taxon
<p>Produced by EOL Multitaxon Object Detection Model. Automatically crops images of snakes & lizards (Squamata), beetles (Coleoptera), frogs (Anura), and carnivores (Carnivora) to square dimensions centered around animal(s). Model available in the <a href="https://www.kaggle.com/models/eolorg/multitaxa-crops-thumbnails" target="_blank" rel="noopener">EOL Model Zoo on Kaggle</a>.</p> <ul> <li>Anura = 42646 rows</li> <li>Coleoptera = 115276 rows</li> <li>Squamata = 132680 rows</li> <li>Carnivora = 31132 rows</li> </ul>
EOL computer vision pipelines: Object Detection for Image Cropping: Chiroptera
<p>Produced by EOL Chiroptera Object Detection Model. Automatically crops images of bats (Chiroptera) to square dimensions centered around animal(s). Model available in the <a href="https://www.kaggle.com/models/eolorg/chiroptera-crops-thumbnails" target="_blank" rel="noopener">EOL Model Zoo on Kaggle</a>.</p> <p> </p> <p>17,401 rows</p>
EOL computer vision pipelines: Object Detection for Image Cropping: Lepidoptera
<p>Produced by EOL Lepidoptera Object Detection Model. Automatically crops images of butterflies and moths (Lepidoptera) to square dimensions centered around animal(s). Model available in the <a href="https://www.kaggle.com/models/eolorg/lepidoptera-crops-thumbnails" target="_blank" rel="noopener">EOL Model Zoo on Kaggle</a>.</p> <p> </p> <p>608,163 rows</p> <p> </p>
GTSRB - German Traffic Sign Recognition Benchmark by Real-Time Computer Vision at Ruhr-Universität Bochum
<div> <div>The German Traffic Sign Benchmark is a multi-class, single-image classification challenge held at the International Joint Conference on Neural Networks (IJCNN) 2011. <br>Our benchmark has the following properties: <br>- Single-image, multi-class classification problem <br>- More than 40 classes<br>- More than 50,000 images in total <br>- Large, lifelike database<br><br>Acknowledgements: [INI Benchmark Website][1]<br>[1]: http://benchmark.ini.rub.de/</div> </div>
ARIVVD: Aberystwyth Robot Infant Vision Video Dataset
<p>This is the Aberystwyth Robot Infant Vision Video Dataset, created for developmental robotics research at Aberystwyth University. This dataset was created for an internally funded research pilot project (“Babyvision: a robotic investigation into early development of colour constancy”). </p>
VISION Invited lecture - Bariatric surgery and non-alcoholic fatty liver disease
<p>Recording and presentation of the invited lecture that took place online on 16 June 2021 - <strong>Pantelis Antonakis, MD, PhD - Bariatric surgery and non-alcoholic fatty liver disease.</strong></p> <p>Bariatric surgery is a documented solution for morbid obesity. Additionally to excess weight loss, significant improvement in comorbidities is an established benefit after bariatric operations. In recent years, non-alcoholic fatty liver disease (NAFLD) has emerged as one of these comorbidities. Herein we will review the data supporting the positive effect of bariatric surgery in patients with NAFLD.</p>
VISION Invited lecture - Microfluidic technologies and their applications in cell biology
<p>Recording and presentation of the invited lecture that took place online on 27 April 2021 - <strong>Thorsten Knoll - Microfluidic technologies and their applications in cell biology.</strong></p> <p>In the past twenty years, microfluidic devices and systems have gained in importance in the field of bioanalytics and biomedicine, not only in research but also in the market. Lab-on-chip systems with microfluidic structures serve for medical tests with body fluids or extractions from fluids. Besides, microfluidic systems are also used for cell handling and culturing, for the mixing of liquids and for measuring quantitative amounts of components in liquid samples.</p> <p>Fraunhofer IBMT develops microfluidic systems for various applications in the field of life sciences. Different miniaturized approaches and solutions exist e.g. for transport studies or toxicological assays with single cells, 2D cell layers or 3D cell aggregates.</p> <p>The online lecture will cover some basic considerations regarding microfluidics and IBMT’s technological solutions for the fabrication of microfluidic devices and their use in different application scenarios. Furthermore, the presentation describes solutions for the integration of the microfluidic devices in a complete set-up comprising of peripheral fluidic components and optical or electrical measurement systems.</p>
VISION Invited lecture - Molecular and Cellular mechanisms/biomarkers in PDAC
<p>Recording and presentation of the invited lecture that took place online on 11 November 2020 - <strong>Dr Laura Garcia Bermejo - Molecular and Cellular mechanisms/biomarkers in PDAC.</strong></p> <p>Pancreatic ductal adenocarcinoma is a fatal disease that presents metastases at diagnosis in most of the cases leading to cancer-associated death. Mutations in drivers’ genes including KRas, CDKN2, Tp53 and SMAD4 and DNA repair genes have been already linked to pancreas cancer development. Pancreatic cancer cells possess properties of plasticity highlighting the epithelial mesenchymal transition and pluripotency genes as critical mediators in pancreas cancer development and progression. Both, EMT and plasticity could be responsible of the limited efficacy of current treatments. Additionally, microRNAs (miRNAs) small non-coding RNAs that regulate the expression of multiple messengers in the post-translation process emerge as promising biomarkers for prognosis, patient stratification and response to advanced pancreatic therapies. Profiling of deregulated miRNAs in pancreatic cancer can contribute to accurate diagnosis and molecular subtype characterization as well as indicate optimal treatment and predict response to therapy. Furthermore, understanding the main effector genes upon miRNAs regulation can also identify miRNAs as potential therapeutic candidates. However, obstacles to the translation of miRNAs into the clinical practice should be also considered, therefore validation of the profiles and the specific role of miRNAs in pancreas cancer development and progression are required for real clinical application.</p>
VISION Invited lecture - Future approaches of pancreatic ductal adenocarcinoma
<p>Recording and presentation of the invited lecture that took place online on 14 October 2020 - <strong>Prof Alfredo Carrato - Future approaches of pancreatic ductal adenocarcinoma.</strong></p> <p>Although pancreatic ductal adenocarcinoma (PDAC) is not so frequent, it is the third leading cause of cancer death. As it shows non-specific symptoms it is diagnosed late and only 20% of patients are surgery candidates. Tumor recurrs locally or distantly after surgery in two thirds of them. Only 5% of PDAC patients survive 10 years. Targeted therapies have not yet proven their efficacy and treatment prescribed consists of chemotherapy combinations.</p> <p>PDAC has a dense stroma that reaches an 80% of the tumor, helping PDAC epithelial tumor cells to evade the immune system and growth, invade and metastasize through a crosstalk among PDAC cells and fibroblasts, macrophages, pericytes, stroma, etc. Targeting the stromal constituents may result in a step forward a better treatment efficacy.</p> <p>PDAC microbiome is unique and has been identified into the cancer cells and the local immune cells. Wisely management of the different resident microbial species could also result in prevention and another alternative for treatment.</p> <p>The identification of the PDAC high-risk population and the development of a convenient screening program is an objective to be reached for an earlier diagnosis and a potential advantage as more patients will be candidates for surgery, but to know in depth and detail the biology of the tumor and its interaction with the host will lead to a better treatment design and a real benefit of our patients.</p>
VISION Invited lecture - Advances in familial pancreatic cancer
<p>Recording and presentation of the invited lecture that took place online on 28 October 2020 - <strong>Dr Julie Earl - Advances in familial pancreatic cancer.</strong></p> <p>The prognosis of patients diagnosed with pancreatic cancer (PC) is dismal with a 5 year survival rate of around 5% as the majority of patients present with advanced disease. Very few risk factors have been identified, although there is good evidence to suggest that smoking, obesity, a family history of pancreatic cancer, pancreatitis and diabetes increase pancreatic cancer risk. Sporadic PC occurs worldwide at an approximate frequency of 1 in 10,000 people. However, the risk of developing PC increases according to the number of affected family members, the standard incidence ratio is 4.6 with one affected family member to 32 with three affected family members. Familial pancreatic cancer (FPC) is defined as a family with at least one pair of affected first degree relatives and an estimated 4-10% of pancreatic cancers diagnosed have a familial background. Approximately 10–13% of FPC families carry germline mutations in BRCA2, PALB2, ATM, CHEK2, CDKN2A, Lynch syndrome mismatch repair genes, Fanconi anaemia related genes and PRSS1 and SPINK2 (hereditary pancreatitis), among others. The understanding of genetic basis of hereditary pancreatic cancer has important implications for the identification of true high-risk individuals in order to optimise secondary screening strategies.</p>
Fig. 7 in A new vision of the origin and the oocyte development in the ostariophysi applied to Gymnotus sylvius (Teleostei, Gymnotiformes)
Fig. 7. Schema comparing oocyte development in a saltwater perciform, Sciaenops ocellatus and in a freshwater gymnotiform, Gymnotus sylvius.
Fig. 1 in A new vision of the origin and the oocyte development in the ostariophysi applied to Gymnotus sylvius (Teleostei, Gymnotiformes)
Fig. 1. Folliculogenesis in Gymnotus sylvius. Light Microscopy. A: Scattered in the germinal epithelium, the quiescent oogonium (g) is wrapped by the epithelial cells (arrow). Ovarian lumen: ol; Primary growth oocyte: po. B: Oogonia (g) proliferate and are surrounded by cells derived from the epithelium, the prefollicle cells (pf). Epithelium: arrow; Ovarian lumen: ol; Primary growth oocyte: po. C: Proliferation of the oogonium give rise to cell clusters, the germ cell nests (n), upon the magenta, PAS-positive basement membrane (bm) which in cross section is seen surrounding the nest. Epithelium: arrow; Ovarian lumen: ol; Secondary growth oocyte: so. D, E: In the nests (n), with the beginning and progress of meiosis, the prophase oocytes differentiate. In leptotene (lo) and in pachytene (po), they can be distinguished by the pattern of chromatin condensation. Proliferating oogonia (g) and prophase oocytes co-occur in a same nest (n). Epithelium: arrow; Ovarian lumen: ol. F, G: Prefollicle cells increasingly surround the oocytes, separating them one from another. As basement membranes form around individual oocytes and the prefollicle cells surrounding them, they are separated from the cell cluster. Completely surrounded by and individualized by
Oblique profile of a Tyrannosaurus torosus head. Note the good degree of binocular vision, and the bulgingjaw-closing muscles on what is in effect a little frill at the back-top of the head. in Predatory Dinosaurs of the World
Oblique profile of a Tyrannosaurus torosus head. Note the good degree of binocular vision, and the bulgingjaw-closing muscles on what is in effect a little frill at the back-top of the head.
REMODEL. WP4. Vision-Based Perception. T4-2. Dynamic environment reconstruction. Data related to a paper presented at 2021 IEEE/RSJ International Conference on Intelligent Robots and Systems (IROS) (2021)
<p>Dataset with evaluation results of the paper "New Metrics for Industrial Depth Sensors Evaluation for Precise Robotic Applications", DOI <a href="https://doi.org/10.1109/IROS51168.2021.9636322">10.1109/IROS51168.2021.9636322</a></p>
REMODEL. WP4. Vision-Based Perception. T4-4. Functional component detection. Data related to a paper presented at 27th International Conference on Automation and Computing (ICAC) (2022)
<p>Dataset with evaluation parameters of the paper "Real-Time Instance Segmentation of Pedestrians using Transfer Learning", DOI: <a href="https://doi.org/10.1109/ICAC55051.2022.9911121">10.1109/ICAC55051.2022.9911121</a></p>
REMODEL. WP4. Vision-Based Perception. T4-2. Dynamic environment reconstruction. Data related to a paper published on IEEE Access (2022)
<p>Dataset with evaluation results of the paper "Point Cloud Registration With Object-Centric Alignment"; DOI: 10.1109/access.2022.3191352</p>
REMODEL. WP4. Vision-Based Perception. T4-2. Dynamic environment reconstruction. Data related to a paper published on RA-L (2020)
<p>Dataset with evaluation results of the paper "Extrinsic Calibration of an Eye-In-Hand 2D LiDAR Sensor in Unstructured Environments Using ICP" 10.1109/LRA.2020.2965878</p>
EyeFi: Fast Human Identification Through Vision and WiFi-based Trajectory Matching
<p><strong>EyeFi Dataset</strong></p> <p>This dataset is collected as a part of the EyeFi project at Bosch Research and Technology Center, Pittsburgh, PA, USA. The dataset contains WiFi CSI values of human motion trajectories along with ground truth location information captured through a camera. This dataset is used in the following paper "<em>EyeFi: Fast Human Identification Through Vision and WiFi-based Trajectory Matching</em>" that is published in the IEEE International Conference on Distributed Computing in Sensor Systems 2020 (DCOSS '20). We also published a dataset paper titled as "<em>Dataset: Person Tracking and Identification using Cameras and Wi-Fi Channel State Information (CSI) from Smartphones</em>" in Data: Acquisition to Analysis 2020 (DATA '20) workshop describing details of data collection. Please check it out for more information on the dataset.</p> <p><strong>Data Collection Setup</strong><br> <br> In our experiments, we used Intel 5300 WiFi Network Interface Card (NIC) installed in an Intel NUC and Linux CSI tools [1] to extract the WiFi CSI packets. The (x,y) coordinates of the subjects are collected from Bosch Flexidome IP Panoramic 7000 panoramic camera mounted on the ceiling and Angle of Arrivals (AoAs) are derived from the (x,y) coordinates. Both the WiFi card and camera are located at the same origin coordinates but at different height, the camera is location around 2.85m from the ground and WiFi antennas are around 1.12m above the ground.</p> <p>The data collection environment consists of two areas, first one is a rectangular space measured 11.8m x 8.74m, and the second space is an irregularly shaped kitchen area with maximum distances of 19.74m and 14.24m between two walls. The kitchen also has numerous obstacles and different materials that pose different RF reflection characteristics including strong reflectors such as metal refrigerators and dishwashers. </p> <p>To collect the WiFi data, we used a Google Pixel 2 XL smartphone as an access point and connect the Intel 5300 NIC to it for WiFi communication. The transmission rate is about 20-25 packets per second. The same WiFi card and phone are used in both lab and kitchen area.</p> <p><strong>List of Files</strong><br> Here is a list of files included in the dataset:</p> <pre><code>|- 1_person |- 1_person_1.h5 |- 1_person_2.h5 |- 2_people |- 2_people_1.h5 |- 2_people_2.h5 |- 2_people_3.h5 |- 3_people |- 3_people_1.h5 |- 3_people_2.h5 |- 3_people_3.h5 |- 5_people |- 5_people_1.h5 |- 5_people_2.h5 |- 5_people_3.h5 |- 5_people_4.h5 |- 10_people |- 10_people_1.h5 |- 10_people_2.h5 |- 10_people_3.h5 |- Kitchen |- 1_person |- kitchen_1_person_1.h5 |- kitchen_1_person_2.h5 |- kitchen_1_person_3.h5 |- 3_people |- kitchen_3_people_1.h5 |- training |- shuffuled_train.h5 |- shuffuled_valid.h5 |- shuffuled_test.h5 View-Dataset-Example.ipynb README.md </code></pre> <p>In this dataset, folder `1_person/` , `2_people/` , `3_people/` , `5_people/`, and `10_people/` contains data collected from the lab area whereas `Kitchen/` folder contains data collected from the kitchen area. To see how the each file is structured, please see below in section <em>Access the data</em><strong>.</strong> </p> <p>The training folder contains the training dataset we used to train the neural network discussed in our paper. They are generated by shuffling all the data from `1_person/` folder collected in the lab area (`1_person_1.h5` and `1_person_2.h5`). </p> <p><strong>Why multiple files in one folder?</strong></p> <p>Each folder contains multiple files. For example, `1_person` folder has two files: `1_person_1.h5` and `1_person_2.h5`. Files in the same folder always have the same number of human subjects present simultaneously in the scene. However, the person who is holding the phone can be different. Also, the data could be collected through different days and/or the data collection system needs to be rebooted due to stability issue. As result, we provided different files (like `1_person_1.h5`, `1_person_2.h5`) to distinguish different person who is holding the phone and possible system reboot that introduces different phase offsets (see below) in the system. </p> <p><strong>Special note:</strong></p> <p>For `1_person_1.h5`, this file is generated by the same person who is holding the phone, and `1_person_2.h5` contains different people holding the phone but only one person is present in the area at a time. Boths files are collected in different days as well.</p> <p><br> <strong>Access the data</strong><br> To access the data, hdf5 library is needed to open the dataset. There are free HDF5 viewer available on the official website: <a href="https://www.hdfgroup.org/downloads/hdfview/">https://www.hdfgroup.org/downloads/hdfview/</a>. We also provide an example Python code <em>View-Dataset-Example.ipynb</em> to demonstrate how to access the data.</p> <p>Each file is structured as (except the files under *"training/"* folder):<br> </p> <pre><code>|- csi_imag |- csi_real |- nPaths_1 |- offset_00 |- spotfi_aoa |- offset_11 |- spotfi_aoa |- offset_12 |- spotfi_aoa |- offset_21 |- spotfi_aoa |- offset_22 |- spotfi_aoa |- nPaths_2 |- offset_00 |- spotfi_aoa |- offset_11 |- spotfi_aoa |- offset_12 |- spotfi_aoa |- offset_21 |- spotfi_aoa |- offset_22 |- spotfi_aoa |- nPaths_3 |- offset_00 |- spotfi_aoa |- offset_11 |- spotfi_aoa |- offset_12 |- spotfi_aoa |- offset_21 |- spotfi_aoa |- offset_22 |- spotfi_aoa |- nPaths_4 |- offset_00 |- spotfi_aoa |- offset_11 |- spotfi_aoa |- offset_12 |- spotfi_aoa |- offset_21 |- spotfi_aoa |- offset_22 |- spotfi_aoa |- num_obj |- obj_0 |- cam_aoa |- coordinates |- obj_1 |- cam_aoa |- coordinates ... |- timestamp </code></pre> <p>The `csi_real` and `csi_imag` are the real and imagenary part of the CSI measurements. <strong>The order of antennas and subcarriers are as follows for the 90 `csi_real` and `csi_imag` values : [subcarrier1-antenna1, subcarrier1-antenna2, subcarrier1-antenna3, subcarrier2-antenna1, subcarrier2-antenna2, subcarrier2-antenna3,… subcarrier30-antenna1, subcarrier30-antenna2, subcarrier30-antenna3]</strong>. `nPaths_x` group are SpotFi [2] calculated WiFi Angle of Arrival (AoA) with `x` number of multiple paths specified during calculation. Under the `nPath_x` group are `offset_xx` subgroup where `xx` stands for the offset combination used to correct the phase offset during the SpotFi calculation. We measured the offsets as:</p> <pre><code>|Antennas | Offset 1 (rad) | Offset 2 (rad) | |:-------:|:---------------:|:-------------:| | 1 & 2 | 1.1899 | -2.0071 | 1 & 3 | 1.3883 | -1.8129 </code></pre> <p>The measurement is based on the work [3], where the authors state there are two possible offsets between two antennas which we measured by booting the device multiple times. The combination of the offset are used for the `offset_xx` naming. For example, `offset_12` is offset 1 between antenna 1 & 2 and offset 2 between antenna 1 & 3 are used in the SpotFi calculation.</p> <p>The `num_obj` field is used to store the number of human subjects present in the scene. The `obj_0` is always the subject who is holding the phone. In each file, there are `num_obj` of `obj_x`. For each `obj_x1`, we have the `coordinates` reported from the camera and `cam_aoa`, which is estimated AoA from the camera reported coordinates. The (x,y) coordinates and AoA listed here are chronologically ordered (except the files in the `training` folder) . It reflects the way the person carried the phone moved in the space (for `obj_0`) and everyone else walked (for other `obj_y`, where `y` > 0). </p> <p>The `timestamp` is provided here for time reference for each WiFi packets.</p> <p>To access the data (Python):</p> <pre><code class="language-python">import h5py data = h5py.File('3_people_3.h5','r') csi_real = data['csi_real'][()] csi_imag = data['csi_imag'][()] cam_aoa = data['obj_0/cam_aoa'][()] cam_loc = data['obj_0/coordinates'][()] </code></pre> <p><strong>For file inside `training/` folder:</strong></p> <p>Files inside training folder has a different data structure:</p> <pre><code> |- nPath-1 |- aoa |- csi_imag |- csi_real |- spotfi |- nPath-2 |- aoa |- csi_imag |- csi_real |- spotfi |- nPath-3 |- aoa |- csi_imag |- csi_real |- spotfi |- nPath-4 |- aoa |- csi_imag |- csi_real |- spotfi </code></pre> <p><br> The group `nPath-x` is the number of multiple path specified during the SpotFi calculation. `aoa` is the camera generated angle of arrival (AoA) (can be considered as ground truth), `csi_image` and `csi_real` is the imaginary and real component of the CSI value. `spotfi` is the SpotFi calculated AoA values. The SpotFi values are chosen based on the lowest median and mean error from across `1_person_1.h5` and `1_person_2.h5`. All the rows under the same `nPath-x` group are aligned (i.e., first row of `aoa` corresponds to the first row of `csi_imag`, `csi_real`, and `spotfi`. There is no timestamp recorded and the sequence of the data is not chronological as they are randomly shuffled from the `1_person_1.h5` and `1_person_2.h5` files. </p> <p><strong>Citation</strong><br> If you use the dataset, please cite our paper:</p> <pre><code>@inproceedings{eyefi2020, title={EyeFi: Fast Human Identification Through Vision and WiFi-based Trajectory Matching}, author={Fang, Shiwei and Islam, Tamzeed and Munir, Sirajum and Nirjon, Shahriar}, booktitle={2020 IEEE International Conference on Distributed Computing in Sensor Systems (DCOSS)}, year={2020}, organization={IEEE} } </code></pre> <p>Thanks!</p> <p><strong>References</strong></p> <p>1. Halperin, Daniel, et al. "Tool release: Gathering 802.11 n traces with channel state information." ACM SIGCOMM Computer Communication Review 41.1 (2011): 53-53.</p> <p>2. Kotaru, Manikanta, et al. "Spotfi: Decimeter level localization using wifi." Proceedings of the 2015 ACM Conference on Special Interest Group on Data Communication. 2015.</p> <p>3. Zhang, Dongheng, et al. "Calibrating Phase Offsets for Commodity WiFi." IEEE Systems Journal (2019).<br> </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.