Concrete crack classification using deep feature fusion and XGBoost for structural health monitoring
Kavita Bodke1, S. G. Bhirud2 and K. K. Sangle3
Vice-Chancellor,COEP Tech. University,Pune, 411005,India2
Department of Structural Engineering,Veermata Jijabai Technological Institute,Mumbai, 400019,India3
Corresponding Author : Kavita Bodke
Recieved : 04-August-2025; Revised : 23-April-2026; Accepted : 24-April-2026
Abstract
Automated crack detection is a vital component of structural health monitoring (SHM) for civil infrastructure. Conventional methods and standalone deep learning (DL) systems often struggle to handle the wide variability in concrete crack formations, resulting in unreliable performance. This study presents a robust and scalable solution by integrating the strengths of multiple models. A novel methodology for concrete crack classification is proposed, which combines an ensemble of 14 pre-trained convolutional neural networks (CNNs), including residual network models (ResNet50V2, ResNet101V2), MobileNet variants (MobileNetV2, MobileNetV3Large, MobileNetV3Small), EfficientNet models (EfficientNetB0, EfficientNetB1, EfficientNetB2), visual geometry group models (VGG16, VGG19), InceptionV3, DenseNet121, DenseNet169, and Xception. These models are employed to extract a diverse set of structural features from concrete crack images. The extracted features are then fused into a comprehensive high-dimensional feature vector, which is used as input to an optimized extreme gradient boosting (XGBoost) classifier. The classifier is trained and validated using a 3-fold stratified cross-validation strategy. The proposed methodology achieves an average cross-validation accuracy of 94.38% and a final testing accuracy of 96.25%. The results demonstrate the effectiveness of the multi-model feature fusion approach. The proposed framework offers a promising solution for automated crack assessment, contributing to more efficient and accurate management of civil infrastructure.
Keywords
Structural health monitoring (SHM), Concrete crack detection, Convolutional neural networks (CNNs), Feature fusion, Extreme gradient boosting (XGBoost), Deep learning ensemble.
Cite this article
Bodke K, Bhirud SG, Sangle KK. Concrete crack classification using deep feature fusion and XGBoost for structural health monitoring. International Journal of Advanced Technology and Engineering Exploration. 2026;13(137):461-473. DOI : 10.19101/IJATEE.2025.121221084
[1] Khan MZ, Shahzadi M, Khan A, Ali U, Hassan MA, Hussain M. Review on crack detection in civil infrastructure using structural health monitoring and machine learning techniques. Innovative Infrastructure Solutions. 2025; 10(8):348.
[2] Azimi M, Eslamlou AD, Pekcan G. Data-driven structural health monitoring and damage detection through deep learning: state-of-the-art review. Sensors. 2020; 20(10):1-34.
[3] Flah M, Nunez I, Ben CW, Nehdi ML. Machine learning algorithms in civil structural health monitoring: a systematic review. Archives of Computational Methods in Engineering. 2021; 28(4):2621-43.
[4] Chakurkar PS, Vora D, Patil S, Mishra S, Kotecha K. Data-driven approach for AI-based crack detection: techniques, challenges, and future scope. Frontiers in Sustainable Cities. 2023; 5:1-28.
[5] Yuan Q, Shi Y, Li M. A review of computer vision-based crack detection methods in civil infrastructure: progress and challenges. Remote Sensing. 2024; 16(16):1-34.
[6] Mohan A, Poobal S. Crack detection using image processing: a critical review and analysis. Alexandria Engineering Journal. 2018; 57(2):787-98.
[7] Liu YF, Fan JS, Nie JG, Kong SY, Qi Y. Review and prospect of digital-image-based crack detection of structure surface. China Civil Engineering Journal. 2021; 54(6):79-98.
[8] Canny J. A computational approach to edge detection. IEEE Transactions on Pattern Analysis and Machine Intelligence. 2009; 27(6):679-98.
[9] Otsu N. A threshold selection method from gray-level histograms. Automatica. 1975; 11:285-96.
[10] Sezgin M, Sankur BL. Survey over image thresholding techniques and quantitative performance evaluation. Journal of Electronic Imaging. 2004; 13(1):146-68.
[11] Pal M, Palevičius P, Landauskas M, Orinaitė U, Timofejeva I, Ragulskis M. An overview of challenges associated with automatic detection of concrete cracks in the presence of shadows. Applied Sciences. 2021; 11(23):1-14.
[12] LeCun Y, Bengio Y, Hinton G. Deep learning. Nature. 2015; 521(7553):436-44.
[13] Li G, Ma B, He S, Ren X, Liu Q. Automatic tunnel crack detection based on u-net and a convolutional neural network with alternately updated clique. Sensors. 2020; 20(3):1-23.
[14] Liu Z, Cao Y, Wang Y, Wang W. Computer vision-based concrete crack detection using U-net fully convolutional networks. Automation in Construction. 2019; 104:129-39.
[15] Dorafshan S, Thomas RJ, Maguire M. Comparison of deep convolutional neural networks and edge detectors for image-based crack detection in concrete. Construction and Building Materials. 2018; 186:1031-45.
[16] Hamishebahar Y, Guan H, So S, Jo J. A comprehensive review of deep learning-based crack detection approaches. Applied Sciences. 2022; 12(3):1-24.
[17] Ali R, Chuah JH, Talip MS, Mokhtar N, Shoaib MA. Structural crack detection using deep convolutional neural networks. Automation in Construction. 2022; 133:103989.
[18] Fan CL. Detection of multidamage to reinforced concrete using support vector machine‐based clustering from digital images. Structural Control and Health Monitoring. 2021; 28(12):e2841.
[19] Mazni M, Husain AR, Shapiai MI, Ibrahim IS, Anggara DW, Zulkifli R. An investigation into real-time surface crack classification and measurement for structural health monitoring using transfer learning convolutional neural networks and Otsu method. Alexandria Engineering Journal. 2024; 92:310-20.
[20] Meng S, Gao Z, Zhou Y, He B, Djerrad A. Real‐time automatic crack detection method based on drone. Computer‐Aided Civil and Infrastructure Engineering. 2023; 38(7):849-72.
[21] Humpe A. Bridge inspection with an off-the-shelf 360 camera drone. Drones. 2020; 4(4):1-23.
[22] Numan M. Advancements in structural health monitoring: a review of machine learning approaches for damage detection and assessment. International Journal for Computational Civil and Structural Engineering. 2024; 20(1):124-42.
[23] Birgani SA, Zadeh SS, Davari DD, Ostovar A. Deep learning applications for analysing concrete surface cracks. International Journal of Applied Data Science in Engineering and Health. 2024; 1(2):69-84.
[24] He K, Zhang X, Ren S, Sun J. Deep residual learning for image recognition. In proceedings of the IEEE conference on computer vision and pattern recognition 2016 (pp. 770-8). IEEE.
[25] Yan Z, Zhang H, Piramuthu R, Jagadeesh V, Decoste D, Di W, et al. HD-CNN: hierarchical deep convolutional neural networks for large scale visual recognition. In proceedings of the international conference on computer vision 2015 (pp. 2740-8). IEEE.
[26] Zhang X, Zhou X, Lin M, Sun J. Shufflenet: an extremely efficient convolutional neural network for mobile devices. In proceedings of the conference on computer vision and pattern recognition 2018 (pp. 6848-56). IEEE
[27] Tan M, Le Q. Efficientnet: rethinking model scaling for convolutional neural networks. In international conference on machine learning 2019 (pp. 6105-14). PMLR.
[28] Sohaib M, Jamil S, Kim JM. An ensemble approach for robust automated crack detection and segmentation in concrete structures. Sensors. 2024; 24(1):1-18.
[29] Krishnan SS, Karuppan MN, Khadidos AO, Khadidos AO, Selvarajan S, Tandon S, et al. Comparative analysis of deep learning models for crack detection in buildings. Scientific Reports. 2025; 15(1):1-33.
[30] Alshawabkeh S, Wu L, Dong D, Cheng Y, Li L. A hybrid approach for pavement crack detection using mask R-CNN and vision transformer model. Computers, Materials, & Continua. 2025; 82(1):561-77.
[31] Fan CL. Evaluation model for crack detection with deep learning: improved confusion matrix based on linear features. Journal of Construction Engineering and Management. 2025; 151(3):04024210.
[32] Pham MV, Ha YS, Kim YT. Automatic detection and measurement of ground crack propagation using deep learning networks and an image processing technique. Measurement. 2023; 215:112832.
[33] Laxman KC, Tabassum N, Ai L, Cole C, Ziehl P. Automated crack detection and crack depth prediction for reinforced concrete structures using deep learning. Construction and Building Materials. 2023; 370:130709.
[34] Flah M, Suleiman AR, Nehdi ML. Classification and quantification of cracks in concrete structures using deep learning image-based techniques. Cement and Concrete Composites. 2020; 114:103781.
[35] Liang S, Jianchun X, Xun Z. An extraction and classification algorithm for concrete cracks based on machine vision. IEEE Access. 2018; 6:45051-61.
[36] Ashraf A, Sophian A, Bawono AA. Crack detection, classification, and segmentation on road pavement material using multi-scale feature aggregation and transformer-based attention mechanisms. Construction Materials. 2024; 4(4):655-75.
[37] Jahanshahi MR, Masri SF, Padgett CW, Sukhatme GS. An innovative methodology for detection and quantification of cracks through incorporation of depth perception. Machine Vision and Applications. 2013; 24(2):227-41.
[38] Golding VP, Gharineiat Z, Munawar HS, Ullah F. Crack detection in concrete structures using deep learning. Sustainability. 2022; 14(13):1-25.
[39] Qayyum W, Ehtisham R, Bahrami A, Mir J, Khan QU, Ahmad A, et al. Predicting characteristics of cracks in concrete structure using convolutional neural network and image processing. Frontiers in Materials. 2023; 10:1210543.
[40] Özgenel ÇF. Concrete crack images for classification. Mendeley Data. 2019.