{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,1,18]],"date-time":"2026-01-18T04:38:37Z","timestamp":1768711117203,"version":"3.49.0"},"reference-count":47,"publisher":"MDPI AG","issue":"12","license":[{"start":{"date-parts":[[2021,6,16]],"date-time":"2021-06-16T00:00:00Z","timestamp":1623801600000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/creativecommons.org\/licenses\/by\/4.0\/"}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["Sensors"],"abstract":"<jats:p>Fatigue cracks are critical types of damage in steel structures due to repeated loads and distortion effects. Fatigue crack growth may lead to further structural failure and even induce collapse. Efficient and timely fatigue crack detection and segmentation can support condition assessment, asset maintenance, and management of existing structures and prevent the early permit post and improve life cycles. In current research and engineering practices, visual inspection is the most widely implemented approach for fatigue crack inspection. However, the inspection accuracy of this method highly relies on the subjective judgment of the inspectors. Furthermore, it needs large amounts of cost, time, and labor force. Non-destructive testing methods can provide accurate detection results, but the cost is very high. To overcome the limitations of current fatigue crack detection methods, this study presents a pixel-level fatigue crack segmentation framework for large-scale images with complicated backgrounds taken from steel structures by using an encoder-decoder network, which is modified from the U-net structure. To effectively train and test the images with large resolutions such as 4928 \u00d7 3264 pixels or larger, the large images were cropped into small images for training and testing. The final segmentation results of the original images are obtained by assembling the segment results in the small images. Additionally, image post-processing including opening and closing operations were implemented to reduce the noises in the segmentation maps. The proposed method achieved an acceptable accuracy of automatic fatigue crack segmentation in terms of average intersection over union (mIOU). A comparative study with an FCN model that implements ResNet34 as backbone indicates that the proposed method using U-net could give better fatigue crack segmentation performance with fewer training epochs and simpler model structure. Furthermore, this study also provides helpful considerations and recommendations for researchers and practitioners in civil infrastructure engineering to apply image-based fatigue crack detection.<\/jats:p>","DOI":"10.3390\/s21124135","type":"journal-article","created":{"date-parts":[[2021,6,16]],"date-time":"2021-06-16T21:58:32Z","timestamp":1623880712000},"page":"4135","update-policy":"https:\/\/doi.org\/10.3390\/mdpi_crossmark_policy","source":"Crossref","is-referenced-by-count":38,"title":["Pixel-Level Fatigue Crack Segmentation in Large-Scale Images of Steel Structures Using an Encoder\u2013Decoder Network"],"prefix":"10.3390","volume":"21","author":[{"ORCID":"https:\/\/orcid.org\/0000-0001-6010-2859","authenticated-orcid":false,"given":"Chuanzhi","family":"Dong","sequence":"first","affiliation":[{"name":"Department of Civil, Environmental, and Construction Engineering, University of Central Florida, Orlando, FL 32816, USA"}]},{"given":"Liangding","family":"Li","sequence":"additional","affiliation":[{"name":"Department of Computer Science, University of Central Florida, Orlando, FL 32816, USA"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-2288-8114","authenticated-orcid":false,"given":"Jin","family":"Yan","sequence":"additional","affiliation":[{"name":"Palo Alto Research Center, Palo Alto, CA 94304, USA"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-7678-605X","authenticated-orcid":false,"given":"Zhiming","family":"Zhang","sequence":"additional","affiliation":[{"name":"School for Engineering of Matter, Transport and Energy, Arizona State University, Tempe, AZ 85281, USA"}]},{"given":"Hong","family":"Pan","sequence":"additional","affiliation":[{"name":"Department of Civil and Environmental Engineering, North Dakota State University, Fargo, ND 58105, USA"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-9255-9976","authenticated-orcid":false,"given":"Fikret Necati","family":"Catbas","sequence":"additional","affiliation":[{"name":"Department of Civil, Environmental, and Construction Engineering, University of Central Florida, Orlando, FL 32816, USA"}]}],"member":"1968","published-online":{"date-parts":[[2021,6,16]]},"reference":[{"key":"ref_1","doi-asserted-by":"crossref","unstructured":"Barker, R.M., and Puckett, J.A. (2013). Design of Highway Bridges An LRFD Approach, John Wiley & Sons. [3rd ed.].","DOI":"10.1002\/9781118411124"},{"key":"ref_2","doi-asserted-by":"crossref","unstructured":"Chen, Y., Zhang, B., Zhang, N., and Zheng, M. (2015). A condensation method for the dynamic analysis of vertical vehicle\u2013track interaction considering vehicle flexibility. J. Vib. Acoust., 137.","DOI":"10.1115\/1.4029947"},{"key":"ref_3","doi-asserted-by":"crossref","unstructured":"Zhu, Z., Luo, S., Feng, Q., Chen, Y., Wang, F., and Jiang, L. (2020). A hybrid DIC\u2013EFG method for strain field characterization and stress intensity factor evaluation of a fatigue crack. Meas. J. Int. Meas. Confed., 154.","DOI":"10.1016\/j.measurement.2020.107498"},{"key":"ref_4","unstructured":"Russo, F.M., Mertz, D.R., Frank, K.H., and Wilson, K.E. (2016). Design and Evaluation of Steel Bridges for Fatigue and Fracture\u2014Reference Manual, National Highway Institute. FHWA-NHI-16-016."},{"key":"ref_5","doi-asserted-by":"crossref","first-page":"1001","DOI":"10.1007\/s13349-020-00431-2","article-title":"A portable monitoring approach using cameras and computer vision for bridge load rating in smart cities","volume":"10","author":"Dong","year":"2020","journal-title":"J. Civ. Struct. Health Monit."},{"key":"ref_6","doi-asserted-by":"crossref","first-page":"1","DOI":"10.1061\/(ASCE)BE.1943-5592.0001507","article-title":"Benchmark for evaluating performance in visual inspection of fatigue cracking in steel bridges","volume":"25","author":"Campbell","year":"2020","journal-title":"J. Bridg. Eng."},{"key":"ref_7","doi-asserted-by":"crossref","first-page":"198","DOI":"10.1016\/j.engfracmech.2019.02.022","article-title":"Monitoring fatigue cracks on eyebars of steel bridges using acoustic emission: A case study","volume":"211","author":"Megid","year":"2019","journal-title":"Eng. Fract. Mech."},{"key":"ref_8","doi-asserted-by":"crossref","unstructured":"Yan, J., Downey, A., Cancelli, A., Laflamme, S., Chen, A., Li, J., and Ubertini, F. (2019). Concrete crack detection and monitoring using a capacitive dense sensor array. Sensors, 19.","DOI":"10.3390\/s19081843"},{"key":"ref_9","doi-asserted-by":"crossref","unstructured":"Zhang, Z., Pan, H., Wang, X., and Lin, Z. (2020). Machine learning-enriched lamb wave approaches for automated damage detection. Sensors, 20.","DOI":"10.3390\/s20061790"},{"key":"ref_10","doi-asserted-by":"crossref","first-page":"653","DOI":"10.1177\/1475921718764873","article-title":"Surface fatigue crack identification in steel box girder of bridges by a deep fusion convolutional neural network based on consumer-grade camera images","volume":"18","author":"Xu","year":"2019","journal-title":"Struct. Health Monit."},{"key":"ref_11","doi-asserted-by":"crossref","first-page":"199","DOI":"10.1016\/j.eng.2018.11.030","article-title":"Advances in computer vision-based civil infrastructure inspection and monitoring","volume":"5","author":"Spencer","year":"2019","journal-title":"Engineering"},{"key":"ref_12","doi-asserted-by":"crossref","unstructured":"Dong, C.Z., and Catbas, F.N. (2020). A review of computer vision\u2013based structural health monitoring at local and global levels. Struct. Health Monit., 1475921720935585.","DOI":"10.1177\/1475921720935585"},{"key":"ref_13","doi-asserted-by":"crossref","first-page":"783","DOI":"10.1111\/mice.12353","article-title":"Vision-based fatigue crack detection of steel structures using video feature tracking","volume":"33","author":"Kong","year":"2018","journal-title":"Comput. Civ. Infrastruct. Eng."},{"key":"ref_14","doi-asserted-by":"crossref","first-page":"234","DOI":"10.1016\/j.eng.2018.11.027","article-title":"The State of the Art of Data Science and Engineering in Structural Health Monitoring","volume":"5","author":"Bao","year":"2019","journal-title":"Engineering"},{"key":"ref_15","doi-asserted-by":"crossref","unstructured":"Bao, Y., and Li, H. (2020). Machine learning paradigm for structural health monitoring. Struct. Health Monit.","DOI":"10.1177\/1475921720972416"},{"key":"ref_16","doi-asserted-by":"crossref","unstructured":"Dong, C.Z., Celik, O., Catbas, F.N., OBrien, E., and Taylor, S. (2019). A robust vision-based method for displacement measurement under adverse environmental factors using Spatio-Temporal context learning and Taylor approximation. Sensors, 19.","DOI":"10.20944\/preprints201906.0023.v1"},{"key":"ref_17","doi-asserted-by":"crossref","first-page":"040190621","DOI":"10.1061\/(ASCE)ST.1943-541X.0002321","article-title":"Vision-based modal survey of civil infrastructure using unmanned aerial vehicles","volume":"145","author":"Hoskere","year":"2019","journal-title":"J. Struct. Eng."},{"key":"ref_18","first-page":"617","article-title":"A completely non-contact recognition system for bridge unit influence line using portable cameras and computer vision","volume":"24","author":"Dong","year":"2019","journal-title":"Smart Struct. Syst."},{"key":"ref_19","doi-asserted-by":"crossref","first-page":"1491","DOI":"10.1177\/1475921718806895","article-title":"Marker free monitoring of the grandstand structures and modal identification using computer vision methods","volume":"18","author":"Dong","year":"2019","journal-title":"Struct. Health Monit."},{"key":"ref_20","doi-asserted-by":"crossref","first-page":"51","DOI":"10.1080\/15732479.2019.1650078","article-title":"Structural displacement monitoring using deep learning-based full field optical flow methods","volume":"16","author":"Dong","year":"2020","journal-title":"Struct. Infrastruct. Eng."},{"key":"ref_21","doi-asserted-by":"crossref","first-page":"111224","DOI":"10.1016\/j.engstruct.2020.111224","article-title":"Investigation of vibration serviceability of a footbridge using computer vision-based methods","volume":"224","author":"Dong","year":"2020","journal-title":"Eng. Struct."},{"key":"ref_22","doi-asserted-by":"crossref","first-page":"1","DOI":"10.1002\/stc.2075","article-title":"Identification framework for cracks on a steel structure surface by a restricted Boltzmann machines algorithm based on consumer-grade camera images","volume":"25","author":"Xu","year":"2018","journal-title":"Struct. Control Health Monit."},{"key":"ref_23","doi-asserted-by":"crossref","first-page":"1","DOI":"10.1061\/(ASCE)BE.1943-5592.0001598","article-title":"Development of a distortion-induced fatigue crack characterization methodology using digital image correlation","volume":"25","author":"Dellenbaugh","year":"2020","journal-title":"J. Bridg. Eng."},{"key":"ref_24","doi-asserted-by":"crossref","first-page":"106688","DOI":"10.1016\/j.ymssp.2020.106688","article-title":"Data Consistency Assessment Function (DCAF)","volume":"141","author":"Chen","year":"2020","journal-title":"Mech. Syst. Signal Process."},{"key":"ref_25","doi-asserted-by":"crossref","first-page":"271","DOI":"10.1111\/mice.12256","article-title":"A texture-based video processing methodology using Bayesian data fusion for autonomous crack detection on metallic surfaces","volume":"32","author":"Chen","year":"2017","journal-title":"Comput. Civ. Infrastruct. Eng."},{"key":"ref_26","doi-asserted-by":"crossref","unstructured":"Zhang, L., Wang, Z., Wang, L., Zhang, Z., Chen, X., and Meng, L. (2021). Machine learning based real-time visible fatigue crack growth detection. Digit. Commun. Netw.","DOI":"10.1016\/j.dcan.2021.03.003"},{"key":"ref_27","doi-asserted-by":"crossref","first-page":"94204","DOI":"10.1109\/ACCESS.2020.2995276","article-title":"Machine vision-based monitoring methodology for the fatigue cracks in U-Rib-to-deck weld seams","volume":"8","author":"Wang","year":"2020","journal-title":"IEEE Access"},{"key":"ref_28","doi-asserted-by":"crossref","unstructured":"Karaaslan, E., Bagci, U., and Catbas, F.N. (2019). Artificial Intelligence Assisted Infrastructure Assessment using Mixed Reality Systems. J. Transp. Res. Board.","DOI":"10.1177\/0361198119839988"},{"key":"ref_29","doi-asserted-by":"crossref","first-page":"52","DOI":"10.1016\/j.autcon.2018.11.028","article-title":"Autonomous concrete crack detection using deep fully convolutional neural network","volume":"99","author":"Dung","year":"2019","journal-title":"Autom. Constr."},{"key":"ref_30","doi-asserted-by":"crossref","first-page":"640","DOI":"10.1109\/TPAMI.2016.2572683","article-title":"Fully Convolutional Networks for Semantic Segmentation","volume":"39","author":"Long","year":"2017","journal-title":"IEEE Trans. Pattern Anal. Mach. Intell."},{"key":"ref_31","unstructured":"Simonyan, K., and Zisserman, A. (2014). Very Deep Convolutional Networks for Large-Scale Image Recognition. arXiv."},{"key":"ref_32","doi-asserted-by":"crossref","unstructured":"Szegedy, C., Vanhoucke, V., Ioffe, S., Shlens, J., and Wojna, Z. (2016, January 27\u201330). Rethinking the Inception Architecture for Computer Vision. Proceedings of the 2016 IEEE Conference on Computer Vision and Pattern Recognition (CVPR) 2016, Las Vegas, NV, USA.","DOI":"10.1109\/CVPR.2016.308"},{"key":"ref_33","doi-asserted-by":"crossref","unstructured":"He, K., Zhang, X., Ren, S., and Sun, J. (2016, January 27\u201330). Deep residual learning for image recognition. Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, Las Vegas, NV, USA.","DOI":"10.1109\/CVPR.2016.90"},{"key":"ref_34","doi-asserted-by":"crossref","first-page":"1090","DOI":"10.1111\/mice.12412","article-title":"Automatic pixel-level crack detection and measurement using fully convolutional network","volume":"33","author":"Yang","year":"2018","journal-title":"Comput. Civ. Infrastruct. Eng."},{"key":"ref_35","doi-asserted-by":"crossref","first-page":"713","DOI":"10.1111\/mice.12440","article-title":"Encoder\u2013decoder network for pixel-level road crack detection in black-box images","volume":"34","author":"Bang","year":"2019","journal-title":"Comput. Civ. Infrastruct. Eng."},{"key":"ref_36","doi-asserted-by":"crossref","unstructured":"Ronneberger, O., Fischer, P., and Brox, T. (2015). U-net: Convolutional networks for biomedical image segmentation. arXiv.","DOI":"10.1007\/978-3-319-24574-4_28"},{"key":"ref_37","doi-asserted-by":"crossref","first-page":"129","DOI":"10.1016\/j.autcon.2019.04.005","article-title":"Computer vision-based concrete crack detection using U-net fully convolutional networks","volume":"104","author":"Liu","year":"2019","journal-title":"Autom. Constr."},{"key":"ref_38","doi-asserted-by":"crossref","unstructured":"Shi, J., Dang, J., Cui, M., Zuo, R., Shimizu, K., Tsunoda, A., and Suzuki, Y. (2021). Improvement of damage segmentation based on pixel-level data balance using vgg-unet. Appl. Sci., 11.","DOI":"10.3390\/app11020518"},{"key":"ref_39","doi-asserted-by":"crossref","unstructured":"Zhang, L., Shen, J., and Zhu, B. (2020). A research on an improved Unet-based concrete crack detection algorithm. Struct. Health Monit.","DOI":"10.1177\/1475921720940068"},{"key":"ref_40","doi-asserted-by":"crossref","unstructured":"Cui, X., Wang, Q., Dai, J., Xue, Y., and Duan, Y. (2021). Intelligent crack detection based on attention mechanism in convolution neural network. Adv. Struct. Eng.","DOI":"10.1177\/1369433220986638"},{"key":"ref_41","doi-asserted-by":"crossref","first-page":"4205","DOI":"10.1007\/s12652-020-01803-8","article-title":"Localization and segmentation of metal cracks using deep learning","volume":"12","author":"Aslam","year":"2020","journal-title":"J. Ambient Intell. Humaniz. Comput."},{"key":"ref_42","doi-asserted-by":"crossref","first-page":"119397","DOI":"10.1016\/j.conbuildmat.2020.119397","article-title":"A cost effective solution for pavement crack inspection using cameras and deep neural networks","volume":"256","author":"Mei","year":"2020","journal-title":"Constr. Build. Mater."},{"key":"ref_43","doi-asserted-by":"crossref","unstructured":"Huang, G., Liu, Z., Van Der Maaten, L., and Weinberger, K.Q. (2017, January 21\u201326). Densely Connected Convolutional Networks. Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition (CVPR), Honolulu, HI, USA.","DOI":"10.1109\/CVPR.2017.243"},{"key":"ref_44","doi-asserted-by":"crossref","first-page":"8016","DOI":"10.1109\/TIE.2019.2945265","article-title":"SDDNet: Real-Time Crack Segmentation","volume":"67","author":"Choi","year":"2020","journal-title":"IEEE Trans. Ind. Electron."},{"key":"ref_45","unstructured":"Ferrari, V., Hebert, M., Sminchisescu, C., and Weiss, Y. (2018, January 8\u201314). Encoder-Decoder with Atrous Separable Convolution for Semantic Image Segmentation. Proceedings of the European Conference on Computer Vision (Computer Vision\u2014ECCV 2018), Munich, Germany."},{"key":"ref_46","unstructured":"(2020, August 30). IPC-SHM The 1st International Project Competition for Structural Health Monitoring (IPC-SHM 2020). Available online: http:\/\/www.schm.org.cn\/#\/IPC-SHM."},{"key":"ref_47","doi-asserted-by":"crossref","unstructured":"Bao, Y., Li, J., Nagayama, T., Xu, Y., Spencer, B.F., and Li, H. (2021). The 1st International Project Competition for Structural Health Monitoring (IPC-SHM, 2020): A summary and benchmark problem. Struct. Health Monit.","DOI":"10.1177\/14759217211006485"}],"container-title":["Sensors"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/www.mdpi.com\/1424-8220\/21\/12\/4135\/pdf","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,10,11]],"date-time":"2025-10-11T06:17:04Z","timestamp":1760163424000},"score":1,"resource":{"primary":{"URL":"https:\/\/www.mdpi.com\/1424-8220\/21\/12\/4135"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2021,6,16]]},"references-count":47,"journal-issue":{"issue":"12","published-online":{"date-parts":[[2021,6]]}},"alternative-id":["s21124135"],"URL":"https:\/\/doi.org\/10.3390\/s21124135","relation":{},"ISSN":["1424-8220"],"issn-type":[{"value":"1424-8220","type":"electronic"}],"subject":[],"published":{"date-parts":[[2021,6,16]]}}}