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.
22
datasets available to search
ShareScore release 0.7.1
Dataset results
22 results for “Crack detection”
Results of the 3D detection of cracks in tested disc-shaped specimens
<p> </p> <p>3D images of fatigue crack obtained by laboratory tomography and synchrotron tomography within bi-disc specimens.</p>
CRACK-CH: A Crack detection and classification dataset on complex stone masonry surfaces
<p><strong>Description</strong></p> <p>This dataset includes various images with cracks from the test sites of HYPERION H2020 project (Grant Agreement No. 821054). Specifically, square image patches of 224x224 pixels from the test sites of Naillac and St. Nikolaos Fort are included.</p> <p>The Saint Nikolaos Fort is an important part of the great fortifications of the Medieval City of Rhodes located at the entrance of the Mantraki port. At this location, there was just a chapel dedicated to Saint Nikolaos until 1464, when it was turned to a fortification. Since then it has undergone reinforcements and expansions in order to defend the city. The outer walls were built in 1480 AD and in 1863 AD it was finally transformed to a lighthouse. The second study area is the Naillac at Saint Paul’s rampart where a monumental tower was located as part of the fortification of the Commercial Harbour of Rhodes. It was constructed around 1400 AD on the Hellenistic Pier, but it was destroyed in 1863 after a severe earthquake. In 2017, the Naillac Tower was graphically reconstructed and presented as it stood until 1863, during the Ottoman rule. The Rodini Roman Bridge is one of the few ancient bridges surviving in Greece and part of the Hellenistic fortification of the city, making it a monument of great importance. It was built across the stream of Rhodini, situated outside the Medieval City and has two arched openings. The Roman Bridge is in continuous use until today and its static efficiency has deteriorated, while the scaffoldings which now support the arches are gradually rusting and losing their efficiency. Those images were split into two separate categories, facilitating the later training and evaluation of the model: “Cracks” and “No cracks”.</p> <p>The dataset is used to train and evaluate the CNN models for crack detection on complex stone masonry surfaces.</p> <p><strong>Publication</strong></p> <p>The paper is availbale here: https://arxiv.org/abs/2303.17989</p> <p><strong>If you use this dataset please cite it as CRACK-CH [reference]</strong>.<br> [Reference] Agrafiotis, Panagiotis, Doulamis, Anastasios, and Georgopoulos, Andreas. (2023) "Unsupervised crack detection on complex stone masonry surfaces", <em>arXiv preprint arXiv:2303.17989</em><br> <br> Bibtex entry:</p> <p>@misc{agrafiotis2023unsupervised,<br> title={Unsupervised crack detection on complex stone masonry surfaces}, <br> author={Panagiotis Agrafiotis and Anastastios Doulamis and Andreas Georgopoulos},<br> year={2023},<br> eprint={2303.17989},<br> archivePrefix={arXiv},<br> primaryClass={cs.CV}<br> }</p>
Convolutional neural network for automated surface crack detection using inductive thermography
<p>Two phase images of the samples AIT_01 and AIT_08, analysed in the publication "Convolutional neural network for automated surface crack detection using inductive thermography", submitted to the Journal of Electronic Imaging.</p>
Cracks in the mirror hypothesis: high specularity does not reduce detection or predation risk
<p>Some animals, including certain fish, beetles, spiders and Lepidoptera chrysalises, have such shiny or glossy surfaces that they appear almost mirror-like. A compelling but unsubstantiated hypothesis is that a highly specular or mirror-like appearance enhances survival by reflecting the surrounding environment and reducing detectability.</p> <p>We tested this hypothesis by asking human participants to wear a mobile eye-tracking device and locate highly realistic mirror-green and diffuse-green replica beetles against a variety of backgrounds in a natural forest environment. We also tested whether a mirror-like appearance enhances survival to wild predators by monitoring survival of mirror-green and diffuse-green replica beetles in a forested habitat and an open habitat.</p> <p>Human participants showed no difference in the detection probability or detection latency of mirror versus diffuse replica beetles, indicating that mirror-like appearance does not impair prey capture. The field predation experiment found no difference in survival between the mirror and diffuse replica beetles in forested environments. Similarly, there was no difference in survival when beetles were deployed in open habitat where there is no background to reflect, indicating that predators detect and do not actively avoid mirror-like beetles.</p> <p>Our results suggest that a mirror-like appearance does not reduce attack by predators. Instead, highly specular, mirror-like surfaces may have evolved for an alternate visual function or as a secondary consequence of selection for a non-visual function, such as thermoregulation.</p>
Dataset for Crack Detection in Images of Bricks and Masonry Using CNNs
<p><strong>Dataset for training CNN built from aerial drone images of buildings in Hamburg</strong></p> <p>This dataset contains images extracted from aerial surveillance photos of the <a href="https://www.bing.com/ck/a?!&&p=b45d6a7b67c7b3c6JmltdHM9MTY1ODMzOTc0MCZpZ3VpZD04NTU2MjdiYS1kYjljLTQyOTMtOTFlOC0xYmM0NmE1ZWViOGMmaW5zaWQ9NTIyMQ&ptn=3&hsh=3&fclid=2a810abc-0855-11ed-8af8-d88619cb2403&u=a1aHR0cHM6Ly9kZS53aWtpcGVkaWEub3JnL3dpa2kvU3BlaWNoZXJzdGFkdA&ntb=1">Speicherstadt</a> and <a href="https://www.bing.com/ck/a?!&&p=750d82f6afc564d9JmltdHM9MTY1ODMzOTg0OSZpZ3VpZD1mOWMwYzE5OC01NjU3LTQ1NzMtOGE0YS1mNzYxN2VlOTlmMmEmaW5zaWQ9NTIxNA&ptn=3&hsh=3&fclid=6b854f27-0855-11ed-9794-60e2f5efc96c&u=a1aHR0cHM6Ly93d3cuaGFmZW5jaXR5LmNvbS9pbmZvY2VudGVyL2tlc3NlbGhhdXM&ntb=1">Kesselhaus</a> buildings in Hamburg, provided by the City of Hamburg. Original 834 high resolution images (5472 x 3648 pixels) have been separated into smaller images (227 x 227 pixels) of the size that could be processed using SqueezeNet, a deep Convolutional Neural Network (CNN). This resulted in more than 350 thousand images that had to be subsequently processed automatically to retain images containing solely bricks and mortar and concrete. The final stage contained tedious manual/visual verification of images and their separation into positive (containing cracks) and negative (clear bricks and mortars) sets of images. The final set contains nearly 40 thousand images.</p> <p>Since images extracted from Hamburg buildings contained only specific type of bricks and our intention was to extend the CNN to be able to deal with wider range of brick types as well as concrete surfaces, we added to our training set also images from the following Open Access databases (note that such images required resizing to 227 x 227 pixel size before use):</p> <ul> <li><a href="https://data.mendeley.com/datasets/5y9wdsg2zt/1">Concrete Crack Images for Classification (Mendeley Data)</a></li> <li><a href="https://zenodo.org/record/5108846#.YthGSLbP0bB">Dataset for Crack Detection in Images of Masonry Using CNNs</a></li> </ul> <p>Such a combined data set resulted in over 80 thousand of images.</p> <p><strong>Matlab WebApp Server application based on trained SqueezeNet CNN </strong></p> <p>The integrated database of images has been used to train the SqueezeNet CNN using a method proposed by <a href="https://www.linkedin.com/in/kenta-itakura-b88129202/">Kenta Itakura</a> in his article published on Matlab Central: <a href="https://www.mathworks.com/matlabcentral/fileexchange/75418-classify-crack-image-using-deep-learning-and-explain-why?s_tid=srchtitle">Classify crack image using deep learning and explain "WHY"</a>, which in turn is based on the work of <a href="https://ieeexplore.ieee.org/author/37280177000">Lei Zhang</a> reported in his IEEE article: <a href="https://ieeexplore.ieee.org/abstract/document/7533052">Road crack detection using deep convolutional neural network</a> published at <a href="https://ieeexplore.ieee.org/xpl/conhome/7527113/proceeding">2016 IEEE International Conference on Image Processing (ICIP)</a>.</p> <p>The "Matlab" subfolder contains the complete software to allow building the application to run under Matlab WebApps Server. The provided version of the "<em>netTransfer.mat</em>" file has been compiled for Matlab revision 2020b, but it should also work when compiled for other revisions from 2019a onwards. BTW, the original location of the files was "D:\Cracks (2-class)\". For instructions how to use the provided Matlab files, refer to Matlab instructions at <a href="https://www.mathworks.com/products/matlab-web-app-server.html">MATLAB Web App Server</a> and <a href="https://www.mathworks.com/help/webappserver/getting-started-with-matlab-web-app-server.html?s_tid=CRUX_lftnav">Get Started with MATLAB Web App Server</a>.</p> <p>After producing and uploading the application to the Matlab WebApps Server, the application can be found at http://localhost:9988/webapps/home/ if deployed locally. It can be also deployed on a WEB server, subject to installation of the compliant Matlab Runtime package on the custom server, whcih can be found at <a href="https://www.mathworks.com/products/compiler/matlab-runtime.html">MATLAB Runtimes (mathworks.com)</a>.</p> <p>The important function included in the package is "unscramble.m", which <strong>corrects the error that exists in all known revisions of Matlab</strong> in uploading images selected by open file function in the Matlab App Designer. The effect is that image is "scrambled beyond recognition" after uploading to the Matlab WebApps Server. Our function de-scrambles such images, converting them into their original form.</p>
Text-fig. 2. CT slices on Block 2. Details of other skeletal parts (a). The familiar shape of an ammonite (a, c). Holes, cracks and empty cavities in both the limestone matrix and within the vertebrate fossil (b, c). Heterogeneity of the 'tuffeau' limestone, the more porous areas of the matrix clearly distinguishable from the more compact ones (c). Ferric nodules (c). in Hidden Treasures Uncovered: Successful Detection Of Fossils Below The Surface In Large Limestone Blocks Using A Standard Medical X-Ray Ct Scanner
Text-fig. 2. CT slices on Block 2. Details of other skeletal parts (a). The familiar shape of an ammonite (a, c). Holes, cracks and empty cavities in both the limestone matrix and within the vertebrate fossil (b, c). Heterogeneity of the 'tuffeau' limestone, the more porous areas of the matrix clearly distinguishable from the more compact ones (c). Ferric nodules (c).
Text-fig. 1. CT slices on Block 1. Details of the internal bone structure (a, b), teeth (b, c). Invertebrate imprints (a, c). Holes, cracks and empty cavities in both the limestone matrix and within the vertebrate fossil (b). in Hidden Treasures Uncovered: Successful Detection Of Fossils Below The Surface In Large Limestone Blocks Using A Standard Medical X-Ray Ct Scanner
Text-fig. 1. CT slices on Block 1. Details of the internal bone structure (a, b), teeth (b, c). Invertebrate imprints (a, c). Holes, cracks and empty cavities in both the limestone matrix and within the vertebrate fossil (b).
Cracks in the mirror hypothesis: high specularity does not reduce detection or predation risk
Open the record for dataset details and reuse information.
Weakly-Supervised Crack Detection Dataset
<p>This repo contains two files: crack detection dataset (weakly_sup_crackdet_dataset.zip), and pretrained TensorFlow model for Xception65 (pascal_voc_seg.zip).</p> <p>The dataset consists of rough annotations used in weakly-supervised crack detection. It contains roughly annotated ground truths for the following datasets:</p> <ul> <li> <p><a href="https://www.irit.fr/~Sylvie.Chambon/AigleRN_GT.html">Aigle</a></p> </li> <li> <p><a href="https://github.com/cuilimeng/CrackForest-dataset">Crack Forest Dataset</a></p> </li> <li> <p><a href="https://github.com/yhlleo/DeepCrack">DeepCrack</a></p> </li> </ul> <p>Annotations of different "roughness" are stored. Directories suffixed "*_dil*" are synthetically-generated annotations, while directories suffixed "*_rough" and "*_rougher" are manually-generated annotations. The detail of the dataset is described in [1]. Please also refer to our GitHub repo <a href="https://github.com/hitachi-rd-cv/weakly-sup-crackdet">https://github.com/hitachi-rd-cv/weakly-sup-crackdet</a> for more details.</p> <p>This dataset is made available by Hitachi, Ltd.</p> <p>The pretrained model is used by [1]. Please use it for comparison experiments. Please refer to our GitHub repor for more details.</p> <p>[1] Inoue, Y., Nagayoshi, H.: Crack detection as a weakly-supervised problem: Towards achieving less annotation-intensive crack detectors. In: International Conference on Pattern Recognition (ICPR) (2020)</p>
Fused Image dataset for convolutional neural Network-based crack Detection (FIND)
<p>The “<strong>F</strong>used <strong>I</strong>mage dataset for convolutional neural <strong>N</strong>etwork-based crack <strong>D</strong>etection” (<strong>FIND</strong>) is a large-scale image dataset with pixel-level ground truth crack data for deep learning-based crack segmentation analysis. It features four types of image data including raw intensity image, raw range (i.e., elevation) image, filtered range image, and fused raw image. The FIND dataset consists of 2500 image patches (dimension: 256x256 pixels) and their ground truth crack maps for each of the four data types.</p> <p>The images contained in this dataset were collected from multiple bridge decks and roadways under real-world conditions. A laser scanning device was adopted for data acquisition such that the captured raw intensity and raw range images have pixel-to-pixel location correspondence (i.e., spatial co-registration feature). The filtered range data were generated by applying frequency domain filtering to eliminate image disturbances (e.g., surface variations, and grooved patterns) from the raw range data [1]. The fused image data were obtained by combining the raw range and raw intensity data to achieve cross-domain feature correlation [2,3]. Please refer to [4] for a comprehensive benchmark study performed using the FIND dataset to investigate the impact from different types of image data on deep convolutional neural network (DCNN) performance.</p> <p>If you share or use this dataset, please cite [4] and [5] in any relevant documentation. </p> <p>In addition, an image dataset for crack classification has also been published at [6].</p> <p>References:</p> <p>[1] Shanglian Zhou, & Wei Song. (2020). Robust Image-Based Surface Crack Detection Using Range Data. Journal of Computing in Civil Engineering, 34(2), 04019054. <a href="https://doi.org/10.1061/(asce)cp.1943-5487.0000873">https://doi.org/10.1061/(asce)cp.1943-5487.0000873</a></p> <p>[2] Shanglian Zhou, & Wei Song. (2021). Crack segmentation through deep convolutional neural networks and heterogeneous image fusion. Automation in Construction, 125. <a href="https://doi.org/10.1016/j.autcon.2021.103605">https://doi.org/10.1016/j.autcon.2021.103605</a></p> <p>[3] Shanglian Zhou, & Wei Song. (2020). Deep learning–based roadway crack classification with heterogeneous image data fusion. Structural Health Monitoring, 20(3), 1274-1293. <a href="https://doi.org/10.1177/1475921720948434">https://doi.org/10.1177/1475921720948434</a> </p> <p>[4] Shanglian Zhou, Carlos Canchila, & Wei Song. (2023). Deep learning-based crack segmentation for civil infrastructure: data types, architectures, and benchmarked performance. Automation in Construction, 146. <a href="https://doi.org/10.1016/j.autcon.2022.104678">https://doi.org/10.1016/j.autcon.2022.104678</a></p> <p>[5] (<strong>This dataset</strong>) Shanglian Zhou, Carlos Canchila, & Wei Song. (2022). Fused Image dataset for convolutional neural Network-based crack Detection (FIND) [Data set]. Zenodo. <a href="https://doi.org/10.5281/zenodo.6383044">https://doi.org/10.5281/zenodo.6383044</a></p> <p>[6] Wei Song, & Shanglian Zhou. (2020). Laser-scanned roadway range image dataset (LRRD). Laser-scanned Range Image Dataset from Asphalt and Concrete Roadways for DCNN-based Crack Classification, DesignSafe-CI. <a href="https://doi.org/10.17603/ds2-bzv3-nc78">https://doi.org/10.17603/ds2-bzv3-nc78</a></p>
Bridge Cracks Monitoring: Detection, Measurement, and Comparison using Augmented Reality
<p>Crack occurrence and propagation are among critical factors that affect the performance and lifespan of civil infrastructures such as bridges. Consequently, numerous crack detection and measurement methods have been proposed and developed in the recent decades in the areas of Structural Health Monitoring and non-destructive testing. Many novel technologies have emerged with the potential to overcome the limitations of the presented techniques of crack detection and characterization. Crack detection and characterization method used in this research lies in supplementing human visual inspection capabilities in a systematic manner through an appropriate level of automation. The Augmented Reality (AR) tool developed in this project allows a user to perform tasks in a real-world environment while visually receiving supplementary 3D computer-generated information to support the tasks. More specifically, we developed a crack detection/characterization tool in this research and deployed it in Microsoft HoloLens smart glasses. This AR tool provides the user with automatic data collection capability through AR headset camera and is a means of hands-free data sharing for inspectors while conducting their normal inspection. We conducted several laboratory and field experiments by which we evaluated the effectiveness of the developed crack detection and measurement system. The result confirm that the AR tool devised in this project has the potential to help the inspection process in terms of time, comfort and accuracy.</p>
Dataset for TOPO-Loss for continuity-preserving crack detection using deep learning
<p>This is the dataset used to assess the performance of the crack detection algorithm proposed by Pantoja-Rosero et, al (2022) in the article "TOPO-Loss for continuity-preserving crack detection using deep learning" (https://doi.org/10.1016/j.conbuildmat.2022.128264)</p>
Dataset for: Asphalt pavement crack detection based on convolutional neural network and infrared thermography
<p>This is the dataset for the following paper: </p> <p>Fangyu Liu, Jian Liu, and Linbing Wang. "Asphalt pavement crack detection based on convolutional neural network and infrared thermography." IEEE Transactions on Intelligent Transportation Systems 23, no. 11 (2022): 22145-22155. https://doi.org/10.1109/TITS.2022.3142393. </p> <p>Data component:</p> <ul> <li>01-Visible images: this folder includes fully visible images</li> <li>02-Infrared images: this folder includes fully infrared images</li> <li>03-Fusion(50IRT) images: this folder includes fusion images (50% infrared + 50% visible)</li> <li>04-Ground truth: this folder includes ground truth (binary images)</li> </ul>
Dataset for Label-free and Sensitive Detection of Citrus Bark Cracking Viroid in Hop Using Ti3C2Tx MXene-modified Genosensor
<p>This is a dataset for a paper "Label-free and Sensitive Detection of Citrus Bark Cracking Viroid in Hop Using Ti3C2Tx MXene-modified Genosensor". All details about the data are included in the readme file.</p>
Data to accompany manuscript: Detection and tracking of cracks based on thermoelastic stress analysis
<p>Thermoelastic stress analysis datasets were collected during tensile loading of hole-in-plate aluminium alloy specimens, at both constant amplitude and frequency conditions, and at variable amplitude and frequency conditions - based on an idealised flight cycle. Data were collected during initiation and propagation of a fatigue crack and monitored using three types of infra-red detector at different price points.</p> <p> </p> <p>--------------------------</p> <p>This dataset accompanies the manuscript:</p> <p>Detection and tracking of cracks based on thermoelastic stress analysis</p> <p>Middleton C. A.1, Weihrauch, M.1, Christian, W. J. R.1, Greene, R. J.2, and Patterson, E. A.1</p> <p>1School of Engineering, University of Liverpool, The Quadrangle, Brownlow Hill, Liverpool, L69 3GH, U.K.<br> 2Strain Solutions Ltd, Dunston Innovation Centre, Dunston Road, Chesterfield, Derbyshire S41 8NG, U.K.</p> <p>Royal Society Open Science, Accepted: 26 November 2020</p> <p> </p> <p> </p>
Data for: Condition monitoring system for in situ crack detection based on thermal emissions
<p>The advent of packaged infra-red (IR) bolometer detectors has led to thermography-based techniques becoming popular for non-destructive evaluation of aerospace structures. These packaged bolometers are relatively compact and cost about 10% the price of high-resolution IR photovoltaic effect detectors. In this work, a condition monitoring system for in situ crack detection has been presented which utilises an original equipment manufacturer (OEM) microbolometer detector. The proposed system cost approximately 1% the price of a state-of-the-art photovoltaic effect detector system and has the potential to transform the use of IR imaging for condition monitoring in the aerospace industry and elsewhere. The proposed system performs crack detection based on the principles of thermoelastic stress analysis (TSA), which is a well-established non-destructive thermography technique. Proof-of-concept lab tests were performed on open-hole aluminium specimens to compare the performance of the proposed system against an IR photovoltaic effect detector system and demonstrate its potential application for in situ crack detection in industrial environments. It was demonstrated that crack detection is possible from loading waveform signals with frequencies as low as 0.3 Hz. This represents a significant advance in the viability of TSA-based crack detection in large-scale structural tests where loading frequencies are usually lower than 1 Hz.</p> <p> </p>
Dataset for Crack Detection in Images of Masonry Using CNNs
<p>We trained a convolutional neural network (CNN) on images of brick walls built in a laboratory environment and test its ability to detect cracks in images of brick-and-mortar structures both in the laboratory and on real-world images taken from the internet. We also compared the performance of the CNN to a variety of simple classifiers operating on handcrafted features. This is the dataset used in that work.</p>
Data for: Condition monitoring system for in situ crack detection based on thermal emissions
Open the record for dataset details and reuse information.
Data to accompany manuscript: Detection and tracking of cracks based on thermoelastic stress analysis
Open the record for dataset details and reuse information.
Efficient, Low-cost Bridge Cracking Detection and Quantification Using Deep-learning and UAV Images
<p>Many bridges in the State of Louisiana and the United States are working under serious degradation conditions where cracks on bridges threaten structural integrity and public security. To ensure structural integrity and public security, it is required that bridges in the US be inspected and rated every two years. Currently, this biannual assessment is largely implemented using manual visual inspection methods, which is slow and costly. In addition, it is challenging for workers to detect cracks in regions that are hard to reach, e.g., the top part of the bridge tower, cables, mid-span of the bridge girders, and decks. This research develops an efficient low-cost deep learning-based methodology to identify cracks on bridges using computer vision-based techniques and deep learning. The Convolutional Neural Networks (CNN) deep learning method is used to identify cracks from images. In this research, a programmable drone is developed that can fly along a pre-defined trajectory. A large volume of images was collected from local bridges and pavements using drones. The collected images were preprocessed and divided into around forty thousand 256 by 256-pixel sub-images and fed into the CNN model. Data augmentation techniques are applied to increase the number of images in some cases. Parameters of the selected CNN model were optimized to obtain the best configuration. To evaluate the performance of the method, images from a different local bridge were used for testing. Research results show that with the optimized CNN model, cracks in the images can be identified efficiently and accurately. The developed methodology can also category the cracked image as slight, moderate, or severe cracking based on a pre-defined quantification index. The research outcome of this project has the potential to automate crack damage identification of bridge key components in a cost-effective manner. Also, the developed methodology is expected to facilitate crack damage identification for other transportation infrastructures, e.g., pavement and traffic sign structures.</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.