{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,5,1]],"date-time":"2026-05-01T17:46:38Z","timestamp":1777657598773,"version":"3.51.4"},"reference-count":38,"publisher":"Springer Science and Business Media LLC","issue":"3-4","license":[{"start":{"date-parts":[[2022,9,28]],"date-time":"2022-09-28T00:00:00Z","timestamp":1664323200000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/creativecommons.org\/licenses\/by\/4.0"},{"start":{"date-parts":[[2022,9,28]],"date-time":"2022-09-28T00:00:00Z","timestamp":1664323200000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/creativecommons.org\/licenses\/by\/4.0"}],"content-domain":{"domain":["link.springer.com"],"crossmark-restriction":false},"short-container-title":["Hum-Cent Intell Syst"],"abstract":"<jats:title>Abstract<\/jats:title><jats:p>Manual investigation of damages incurred to infrastructure is a challenging process, in that it is not only labour-intensive and expensive but also inefficient and error-prone. To automate the process, a method that is based on computer vision for automatically detecting cracks from 2D images is a viable option. Amongst the different methods of deep learning that are commonly used, the convolutional neural network (CNNs) is one that provides the opportunity for end-to-end mapping\/learning of image features instead of using the manual suboptimal image feature extraction. Specifically, CNNs do not require human supervision and are more suitable to be used for indoor and outdoor applications requiring image feature extraction and are less influenced by internal and external noise. Additionally, the CNN\u2019s are also computationally efficient since they are based on special convolution layers and pooling operations that enable the full execution of CNN frameworks on several hardware devices. Keeping this in mind, we propose a deep CNN framework that is based on 10 different convolution layers along with a cycle GAN (Generative Adversarial Network) for predicting the crack segmentation pixel by pixel in an end-to-end manner. The methods proposed here include the Deeply Supervised Nets (DSN) and Fully Convolutional Networks (FCN). The use of DSN enables integrated feature supervision for each stage of convolution. Furthermore, the model has been designed intricately for learning and aggregating multi-level and multiscale features while moving from the lower to higher convolutional layers through training. Hence, the architecture in use here is unique from the ones in practice which just use the final convolution layer. In addition, to further refine the predicted results, we have used a guided filter and CRFs (Conditional Random Fields) based methods. The verification step for the proposed framework was carried out with a set of 537 images. The deep hierarchical CNN framework of 10 convolutional layers and the Guided filtering achieved high-tech and advanced performance on the acquired dataset, showing higher F-score, Recall and Precision values of 0.870, 0.861, and 0.881 respectively, as compared to the traditional methods such as SegNet, Crack-BN, and Crack-GF.<\/jats:p>","DOI":"10.1007\/s44230-022-00009-9","type":"journal-article","created":{"date-parts":[[2022,9,28]],"date-time":"2022-09-28T17:40:26Z","timestamp":1664386826000},"page":"95-112","update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":20,"title":["Modern Crack Detection for Bridge Infrastructure Maintenance Using Machine Learning"],"prefix":"10.1007","volume":"2","author":[{"given":"Hafiz Suliman","family":"Munawar","sequence":"first","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Ahmed W. A.","family":"Hammad","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"S. Travis","family":"Waller","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Md Rafiqul","family":"Islam","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"297","published-online":{"date-parts":[[2022,9,28]]},"reference":[{"key":"9_CR1","doi-asserted-by":"publisher","first-page":"255","DOI":"10.1061\/(ASCE)0887-3801(2003)17:4(255)","volume":"17","author":"I Abdel-Qader","year":"2003","unstructured":"Abdel-Qader I, Abudayyeh O, Kelly ME. Analysis of edge-detection techniques for crack identification in bridges. J Comput Civ Eng. 2003;17:255\u201363.","journal-title":"J Comput Civ Eng"},{"key":"9_CR2","doi-asserted-by":"crossref","unstructured":"Yang G, Liu K, Zhao Z, Zhang J, Chen X, Chen BM. Datasets and methods for boosting infrastructure inspection: a survey on defect classification. In: 2022 IEEE 17th international conference on control & automation (ICCA), 2022. IEEE; pp. 15\u201322","DOI":"10.1109\/ICCA54724.2022.9831922"},{"key":"9_CR3","doi-asserted-by":"publisher","DOI":"10.1177\/14759217221083649","author":"Y Bai","year":"2022","unstructured":"Bai Y, Zha B, Sezen H, Yilmaz A. Engineering deep learning methods on automatic detection of damage in infrastructure due to extreme events. Struct Health Monit. 2022. https:\/\/doi.org\/10.1177\/14759217221083649.","journal-title":"Struct Health Monit"},{"key":"9_CR4","unstructured":"Gal Y, Ghahramani Z, Bayesian convolutional neural networks with Bernoulli approximate variational inference. arXiv preprint arXiv:1506.02158, 2015."},{"key":"9_CR5","doi-asserted-by":"publisher","first-page":"137","DOI":"10.1007\/s10462-020-09854-1","volume":"54","author":"S Asgari Taghanaki","year":"2021","unstructured":"Asgari Taghanaki S, et al. Deep semantic segmentation of natural and medical images: a review. Artif Intell Rev. 2021;54:137\u201378.","journal-title":"Artif Intell Rev"},{"key":"9_CR6","doi-asserted-by":"crossref","unstructured":"Gibb S, La HM, Louis S. A genetic algorithm for convolutional network structure optimization for concrete crack detection. In: 2018 IEEE congress on evolutionary computation (CEC), 2018. IEEE; pp. 1\u20138.","DOI":"10.1109\/CEC.2018.8477790"},{"key":"9_CR7","first-page":"1","volume":"60","author":"L Han","year":"2021","unstructured":"Han L, et al. Convective precipitation nowcasting using U-Net model. IEEE Trans Geosci Remote Sens. 2021;60:1\u20138.","journal-title":"IEEE Trans Geosci Remote Sens"},{"key":"9_CR8","first-page":"1","volume":"2018","author":"ND Hoang","year":"2018","unstructured":"Hoang ND. Detection of surface crack in building structures using image processing technique with an improved Otsu method for image thresholding. Adv Civ Eng. 2018;2018:1\u201310.","journal-title":"Adv Civ Eng"},{"key":"9_CR9","doi-asserted-by":"publisher","DOI":"10.1016\/j.autcon.2022.104396","volume":"141","author":"IO Agyemang","year":"2022","unstructured":"Agyemang IO, Zhang X, Acheampong D, Adjei-Mensah I, Kusi GA, Mawuli BC, Agbley BLY. Autonomous health assessment of civil infrastructure using deep learning and smart devices. Autom Constr. 2022;141: 104396.","journal-title":"Autom Constr"},{"key":"9_CR10","doi-asserted-by":"publisher","first-page":"1440","DOI":"10.1177\/1475921719883202","volume":"19","author":"M Mohtasham Khani","year":"2020","unstructured":"Mohtasham Khani M, et al. Deep-learning-based crack detection with applications for the structural health monitoring of gas turbines. Struct Health Monit. 2020;19:1440\u201352.","journal-title":"Struct Health Monit"},{"issue":"4","key":"9_CR11","doi-asserted-by":"publisher","first-page":"432","DOI":"10.3390\/buildings12040432","volume":"12","author":"L Ali","year":"2022","unstructured":"Ali L, Alnajjar F, Khan W, Serhani MA, Al Jassmi H. Bibliometric analysis and review of deep learning-based crack detection literature published between 2010 and 2022. Buildings. 2022;12(4):432.","journal-title":"Buildings"},{"key":"9_CR12","doi-asserted-by":"publisher","first-page":"54564","DOI":"10.1109\/ACCESS.2020.2981561","volume":"8","author":"Z Qu","year":"2020","unstructured":"Qu Z, et al. Crack detection of concrete pavement with cross-entropy loss function and improved VGG16 network model. IEEE Access. 2020;8:54564\u201373.","journal-title":"IEEE Access"},{"key":"9_CR13","doi-asserted-by":"publisher","first-page":"640","DOI":"10.1109\/TPAMI.2016.2572683","volume":"39","author":"E Shelhamer","year":"2017","unstructured":"Shelhamer E, Long J, Darrell T. Fully convolutional networks for semantic segmentation. IEEE Trans Pattern Anal Mach Intell. 2017;39:640\u201351.","journal-title":"IEEE Trans Pattern Anal Mach Intell"},{"key":"9_CR14","first-page":"6056","volume":"13","author":"SN Sitara","year":"2018","unstructured":"Sitara SN. Review and analysis of crack detection and classification techniques based on crack types. Int J Appl Eng Res. 2018;13:6056\u201362.","journal-title":"Int J Appl Eng Res"},{"key":"9_CR15","doi-asserted-by":"publisher","first-page":"506","DOI":"10.1080\/2150704X.2019.1574990","volume":"10","author":"M Yuan","year":"2019","unstructured":"Yuan M, Liu Z, Wang F. Using the wide-range attention U-Net for road segmentation. Remote Sens Lett. 2019;10:506\u201315.","journal-title":"Remote Sens Lett"},{"key":"9_CR16","doi-asserted-by":"publisher","first-page":"139","DOI":"10.1016\/j.neucom.2019.01.036","volume":"338","author":"Y Liu","year":"2019","unstructured":"Liu Y, et al. DeepCrack: a deep hierarchical feature learning architecture for crack segmentation. Neurocomputing. 2019;338:139\u201353.","journal-title":"Neurocomputing"},{"key":"9_CR17","unstructured":"Simonyan K, Zisserman A. Very deep convolutional networks for large-scale image recognition. In: 3rd International conference on learning representations. In: ICLR 2015\u2014conference track proceedings, 2015."},{"key":"9_CR18","doi-asserted-by":"publisher","first-page":"669","DOI":"10.1016\/j.autcon.2011.04.013","volume":"20","author":"Y-H Yu","year":"2011","unstructured":"Yu Y-H, Kwok NM, Ha QP. Color tracking for multiple robot control using a system-on-programmable-chip. Autom Constr. 2011;20:669\u201376.","journal-title":"Autom Constr"},{"key":"9_CR19","doi-asserted-by":"publisher","first-page":"669","DOI":"10.1109\/TGRS.1990.572977","volume":"28","author":"R Samadani","year":"1990","unstructured":"Samadani R, Vesecky JF. Finding Curvilinear Features In Speckled Images. IEEE Trans Geosci Remote Sens. 1990;28:669\u201373.","journal-title":"IEEE Trans Geosci Remote Sens"},{"key":"9_CR20","doi-asserted-by":"publisher","DOI":"10.1016\/j.engstruct.2019.110157","volume":"206","author":"M Alipour","year":"2020","unstructured":"Alipour M, Harris DK. Increasing the robustness of material-specific deep learning models for crack detection across different materials. Eng Struct. 2020;206: 110157.","journal-title":"Eng Struct"},{"key":"9_CR21","doi-asserted-by":"publisher","first-page":"361","DOI":"10.1111\/mice.12263","volume":"32","author":"YJ Cha","year":"2017","unstructured":"Cha YJ, Choi W, B\u00fcy\u00fck\u00f6zt\u00fcrk O. Deep learning-based crack damage detection using convolutional neural networks. Comput Aided Civ Infrastruct Eng. 2017;32:361\u201378.","journal-title":"Comput Aided Civ Infrastruct Eng"},{"key":"9_CR22","doi-asserted-by":"publisher","DOI":"10.1016\/j.conbuildmat.2019.117367","volume":"234","author":"Y Ren","year":"2020","unstructured":"Ren Y, et al. Image-based concrete crack detection in tunnels using deep fully convolutional networks. Constr Build Mater. 2020;234: 117367.","journal-title":"Constr Build Mater"},{"key":"9_CR23","doi-asserted-by":"publisher","first-page":"787","DOI":"10.1016\/j.aej.2017.01.020","volume":"57","author":"A Mohan","year":"2018","unstructured":"Mohan A, Poobal S. Crack detection using image processing: a critical review and analysis. Alex Eng J. 2018;57:787\u201398.","journal-title":"Alex Eng J"},{"key":"9_CR24","doi-asserted-by":"crossref","unstructured":"Mou L, Zhu XX. Spatiotemporal scene interpretation of space videos via deep neural network and tracklet analysis. In: 2016 IEEE international geoscience and remote sensing symposium (IGARSS), 2016. IEEE; pp. 1823\u20131826.","DOI":"10.1109\/IGARSS.2016.7729468"},{"key":"9_CR25","doi-asserted-by":"publisher","first-page":"1730","DOI":"10.3390\/app8101730","volume":"8","author":"M Safiuddin","year":"2018","unstructured":"Safiuddin M, et al. Early-age cracking in concrete: causes, consequences, remedial measures, and recommendations. Appl Sci. 2018;8:1730.","journal-title":"Appl Sci"},{"key":"9_CR26","doi-asserted-by":"crossref","unstructured":"Shi W, et al. Real-time single image and video super-resolution using an efficient sub-pixel convolutional neural network. In: 2016 IEEE conference on computer vision and pattern recognition (CVPR), 2016. IEEE; pp. 1874\u20131883.","DOI":"10.1109\/CVPR.2016.207"},{"key":"9_CR27","doi-asserted-by":"publisher","first-page":"1939","DOI":"10.1109\/TPAMI.2018.2878849","volume":"41","author":"Y Liu","year":"2019","unstructured":"Liu Y, et al. Richer convolutional features for edge detection. IEEE Trans Pattern Anal Mach Intell. 2019;41:1939\u201346.","journal-title":"IEEE Trans Pattern Anal Mach Intell"},{"key":"9_CR28","doi-asserted-by":"crossref","unstructured":"\u00d6zgenel \u00c7F, Sorgu\u00e7 AG, Performance comparison of pretrained convolutional neural networks on crack detection in buildings. In: ISARC 2018\u201435th international symposium on automation and robotics in construction and international AEC\/FM hackathon: the future of building things, 2018. IAARC Publications; pp. 1\u20138.","DOI":"10.22260\/ISARC2018\/0094"},{"key":"9_CR29","doi-asserted-by":"publisher","first-page":"709","DOI":"10.1109\/LGRS.2017.2672734","volume":"14","author":"Y Wei","year":"2017","unstructured":"Wei Y, Wang Z, Xu M. Road structure refined CNN for road extraction in aerial image. IEEE Geosci Remote Sens Lett. 2017;14:709\u201313.","journal-title":"IEEE Geosci Remote Sens Lett"},{"key":"9_CR30","doi-asserted-by":"publisher","first-page":"04020004","DOI":"10.1061\/(ASCE)CP.1943-5487.0000883","volume":"34","author":"K Zhang","year":"2020","unstructured":"Zhang K, Zhang Y, Cheng HD. Self-supervised structure learning for crack detection based on cycle-consistent generative adversarial networks. J Comput Civ Eng. 2020;34:04020004.","journal-title":"J Comput Civ Eng"},{"key":"9_CR31","doi-asserted-by":"publisher","first-page":"457","DOI":"10.7763\/IJET.2014.V5.596","volume":"5","author":"T-C Su","year":"2013","unstructured":"Su T-C. Application of computer vision to crack detection of concrete structure. Int J Eng Technol. 2013;5:457\u201361.","journal-title":"Int J Eng Technol"},{"key":"9_CR32","doi-asserted-by":"publisher","first-page":"591","DOI":"10.1109\/TASE.2014.2354314","volume":"13","author":"P Prasanna","year":"2016","unstructured":"Prasanna P, et al. Automated crack detection on concrete bridges. IEEE Trans Autom Sci Eng. 2016;13:591\u20139.","journal-title":"IEEE Trans Autom Sci Eng"},{"key":"9_CR33","doi-asserted-by":"publisher","first-page":"1285","DOI":"10.1109\/TIP.2019.2936649","volume":"29","author":"A Rana","year":"2019","unstructured":"Rana A, et al. Deep tone mapping operator for high dynamic range images. IEEE Trans Image Process. 2019;29:1285\u201398.","journal-title":"IEEE Trans Image Process"},{"key":"9_CR34","doi-asserted-by":"publisher","first-page":"131","DOI":"10.5194\/isprs-archives-XLI-B5-131-2016","volume":"XLI-B5","author":"C Stentoumis","year":"2016","unstructured":"Stentoumis C, et al. A holistic approach for inspection of civil infrastructures based on computer vision techniques. ISPRS Int Arch Photogramm Remote Sens Spat Inf Sci. 2016;XLI-B5:131\u20138.","journal-title":"ISPRS Int Arch Photogramm Remote Sens Spat Inf Sci"},{"key":"9_CR35","doi-asserted-by":"crossref","unstructured":"Zhu J-Y, et al. Unpaired image-to-image translation using cycle-consistent adversarial networks. In: 2017 IEEE international conference on computer vision (ICCV), 2017. IEEE; pp. 2242\u20132251.","DOI":"10.1109\/ICCV.2017.244"},{"key":"9_CR36","doi-asserted-by":"crossref","unstructured":"Zheng S et al. Conditional random fields as recurrent neural networks. In: 2015 IEEE international conference on computer vision (ICCV), 2015. IEEE; pp. 1529\u20131537.","DOI":"10.1109\/ICCV.2015.179"},{"key":"9_CR37","doi-asserted-by":"crossref","unstructured":"Redmon J et al. You only look once: unified, real-time object detection In: 2016 IEEE conference on computer vision and pattern recognition (CVPR). IEEE; 2016. pp. 779\u2013788.","DOI":"10.1109\/CVPR.2016.91"},{"issue":"6","key":"9_CR38","doi-asserted-by":"publisher","first-page":"1789","DOI":"10.1007\/s11263-021-01453-z","volume":"129","author":"J Gou","year":"2021","unstructured":"Gou J, et al. Knowledge distillation: a survey. Int J Comput Vision. 2021;129(6):1789\u2013819.","journal-title":"Int J Comput Vision"}],"container-title":["Human-Centric Intelligent Systems"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/s44230-022-00009-9.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/link.springer.com\/article\/10.1007\/s44230-022-00009-9\/fulltext.html","content-type":"text\/html","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/s44230-022-00009-9.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2022,12,7]],"date-time":"2022-12-07T13:11:14Z","timestamp":1670418674000},"score":1,"resource":{"primary":{"URL":"https:\/\/link.springer.com\/10.1007\/s44230-022-00009-9"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2022,9,28]]},"references-count":38,"journal-issue":{"issue":"3-4","published-online":{"date-parts":[[2022,12]]}},"alternative-id":["9"],"URL":"https:\/\/doi.org\/10.1007\/s44230-022-00009-9","relation":{},"ISSN":["2667-1336"],"issn-type":[{"value":"2667-1336","type":"electronic"}],"subject":[],"published":{"date-parts":[[2022,9,28]]},"assertion":[{"value":"8 July 2022","order":1,"name":"received","label":"Received","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"11 September 2022","order":2,"name":"accepted","label":"Accepted","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"28 September 2022","order":3,"name":"first_online","label":"First Online","group":{"name":"ArticleHistory","label":"Article History"}},{"order":1,"name":"Ethics","group":{"name":"EthicsHeading","label":"Declarations"}},{"value":"The authors declare no conflicts of interest.","order":2,"name":"Ethics","group":{"name":"EthicsHeading","label":"Conflicts of interest"}},{"value":"Not applicable.","order":3,"name":"Ethics","group":{"name":"EthicsHeading","label":"Institutional review board statement"}},{"value":"Not applicable.","order":4,"name":"Ethics","group":{"name":"EthicsHeading","label":"Informed consent"}}]}}