Abstract
An exponential increase in population has created a high demand for housing. It is of paramount importance for stakeholders to maintain buildings and other mega-structures, to ensure their longevity. Building fault detection is a crucial step to address problems which might develop during construction or post completion. Detecting these faults early allows for corrective action to be taken immediately. However, this process is still being done manually, which is time-consuming, expensive, hazardous and provides room for human error. Deep learning is an efficient way to replace manual overseeing. The proposed solution involves using a deep learning model to accurately classify faults according to their types, and localize them. For this purpose, a web-scraped dataset of three categories, namely clean, crack and mould walls has been created. A comparison between three convolutional neural networks, including ResNet-50, Inception-v3 and VGG-16 is made, with ResNet-50 having the highest accuracy of 90.68%. Class Activation Mapping is used to identify and localize regions of faults. The metrics used also validate the robustness of the model, which would act as a prototype for a large-scale solution of building fault detection in the long run.
Access this chapter
Tax calculation will be finalised at checkout
Purchases are for personal use only
Similar content being viewed by others
References
Bakri NNO, Mydin MAO (2014) General building defects: causes, symptoms and remedial work. Eur J Technol Des 1:4–17
Hinks J, Cook G (2002) The technology of building defects. Routledge
Chong WK, Low SP (2006) Latent building defects: causes and design strategies to prevent them. J Perform Constr Facil 20(3):213–221
Bakri NNO, Mydin MAO (2014) General building defects: causes, symptoms and remedial work. Eur J Technol Des 1:4–17
Pheng LS, Wee D (2001) Improving maintenance and reducing building defects through ISO 9000. J Qual Maint Eng
Suffian A (2013) Some common maintenance problems and building defects: our experiences. Procedia Eng 54:101–108
Othman NL, Jaafar M, Harun WMW, Ibrahim F (2015) A case study on moisture problems and building defects. Procedia Soc Behav Sci 170:27–36
Ahzahar N, Karim NA, Hassan SH, Eman J (2011) A study of contribution factors to building failures and defects in construction industry. Procedia Eng 20:249–255
Das S, Chew MY (2011) Generic method of grading building defects using FMECA to improve maintainability decisions. J Perform Constr Facil 25(6):522–533
Georgiou J (2010) Verification of a building defect classification system for housing. Struct Surv
Mohseni H, Setunge S, Zhang GM, Wakefield R (2013) In Condition monitoring and condition aggregation for optimised decision making in management of buildings. Appl Mech Mater 438:1719–1725. https://doi.org/10.4028/www.scientific.net/AMM.438-439.1719
Agdas D, Rice JA, Martinez JR, Lasa IR (2015) Comparison of visual inspection and structural-health monitoring as bridge condition assessment methods. J Perform Constr Facil 30:04015049. https://doi.org/10.1061/(ASCE)CF.1943-5509.0000802
Shamshirband S, Mosavi A, Rabczuk T (2020) Particle swarm optimization model to predict scour depth around bridge pier. arXiv. 2019.19060
Zhang Y, Anderson N, Bland S, Nutt S, Jursich G, Joshi S (2017) All-printed strain sensors: building blocks of the aircraft structural health monitoring system. Sens Actuators A Phys 253:165–172. https://doi.org/10.1016/j.sna.2016.10.007
Wahab S, Hamid M (2011) A review factors affecting building defects of structural steel construction. Case study: student accommodation in UiTM Perak. Procedia Eng 20. https://doi.org/10.1016/j.proeng.2011.11.153
Szegedy C, Liu W, Jia Y, Sermanet P, Reed S, Anguelov D, Rabinovich A et al (2015) Going deeper with convolutions. In: Proceedings of the IEEE conference on computer vision and pattern recognition, pp 1–9
Simonyan K, Zisserman A (2014) Very deep convolutional networks for large-scale image recognition. arXiv preprint. arXiv:1409.1556
He K, Zhang X, Ren S, Sun J (2016) Deep residual learning for image recognition. In: Proceedings of the IEEE conference on computer vision and pattern recognition, pp 770–778
Pan H, Pi L (2018) Study on cracks in concrete structures and the database. IOP Conf Ser Earth Environ Sci 189(2):022078. IOP Publishing
Nie M, Wang C (2019) Pavement crack detection based on yolo v3. In: 2019 2nd international conference on safety produce informatization (IICSPI). IEEE, pp 327–330
Redmon J, Farhadi A (2018) Yolov3: an incremental improvement. arXiv preprint. arXiv:1804.02767
Kuchi A, Hoque MT, Abdelguerfi M, Flanagin MC (2020) Levee-crack detection from satellite or drone imagery using machine learning approaches. In: IGARSS 2020-2020 IEEE international geoscience and remote sensing symposium. IEEE, pp 976–979
Thendral R, Ranjeeth A (2021) Computer vision system for railway track crack detection using deep learning neural network. In: 2021 3rd international conference on signal processing and communication (ICPSC). IEEE, pp 193–196
Chen FC, Jahanshahi MR (2017) NB-CNN: deep learning-based crack detection using convolutional neural network and Naïve Bayes data fusion. IEEE Trans Ind Electron 65(5):4392–4400
Kumar P, Batchu S, Kota SR (2021) Real-time concrete damage detection using deep learning for high rise structures. IEEE Access 9:112312–112331
Mandal V, Uong L, Adu-Gyamfi Y (2018) Automated road crack detection using deep convolutional neural networks. In: 2018 IEEE international conference on big data (Big Data). IEEE, pp 5212–5215
Nong CR, Liu ZY, Zhang J, Zeng QS (2020) Research on crack edge detection of aircraft skin based on traditional inspired network. In: 2020 2nd international conference on information technology and computer application (ITCA). IEEE, pp 751–754
Wibisono JK, Hang H-M (2020) Traditional method inspired deep neural network for edge detection. In: 2020 IEEE international conference on image processing (ICIP)
Qu Z, Chen YX, Liu L, Xie Y, Zhou Q (2019) The algorithm of concrete surface crack detection based on the genetic programming and percolation model. IEEE Access 7:57592–57603
Chen Q, Zhang XX, Chen Y, Jiang W, Gui G, Sari H (2020) Deep learning-based automatic safety detection system for crack detection. In: 2020 7th international conference on dependable systems and their applications (DSA). IEEE, pp 190–194
Ren S, He K, Girshick R, Sun J (2015) Faster R-CNN: towards real-time object detection with region proposal networks. Advances in neural information processing systems, p 28
Lee K, Hong G, Sael L, Lee S, Kim HY (2020) MultiDefectNet: multi-class defect detection of building façade based on deep convolutional neural network. Sustainability 12(22):9785
Semwal A, Mohan RE, Melvin LMJ, Palanisamy P, Baskar C, Yi L, Ramalingam B (2021) False ceiling deterioration detection and mapping using a deep learning framework and the teleoperated reconfigurable ‘Falcon’ Robot. Sensors 22(1):262
Jubayer F, Soeb JA, Mojumder AN, Paul MK, Barua P, Kayshar S, Islam A (2021) Detection of mold on the food surface using YOLOv5. Curr Res Food Sci 4:724–728
Tahir MW (2019) Fungus detection using computer vision and machine learning techniques. Doctoral dissertation, Universität Bremen
Tahir MW, Zaidi NA, Rao AA, Blank R, Vellekoop MJ, Lang W (2018) A fungus spores dataset and a convolutional neural network based approach for fungus detection. IEEE Trans Nanobioscience 17(3):281–290
Manhando E, Zhou Y, Wang F (2021) Early detection of mold-contaminated peanuts using machine learning and deep features based on optical coherence tomography. AgriEngineering 3(3):703–715
Shruthi U, Nagaveni V, Raghavendra BK (2019) A review on machine learning classification techniques for plant disease detection. In: 2019 5th international conference on advanced computing & communication systems (ICACCS). IEEE, pp 281–284
Natarajan VA, Babitha MM, Kumar MS (2020) Detection of disease in tomato plant using deep learning techniques. Int J Mod Agric 9(4):525–540
Sharma P, Berwal YPS, Ghai W (2020) Performance analysis of deep learning CNN models for disease detection in plants using image segmentation. Inf Process Agric 7(4):566–574
Fuentes A, Yoon S, Kim SC, Park DS (2017) A robust deep-learning-based detector for real-time tomato plant diseases and pests recognition. Sensors 17(9):2022
Bhujel A, Khan F, Basak JK, Jaihuni M, Sihalath T, Moon BE, Kim HT et al (2022) Detection of gray mold disease and its severity on strawberry using deep learning networks. J Plant Dis Prot 1–14
Perez H, Tah JH (2021) Deep learning smartphone application for real-time detection of defects in buildings. Struct Control Health Monit 28(7):e2751
Liu W, Anguelov D, Erhan D, Szegedy C, Reed S, Fu CY, Berg AC (2016) SSD: single shot multibox detector. In: European conference on computer vision. Springer, Cham, pp 21–37
Howard AG, Zhu M, Chen B, Kalenichenko D, Wang W, Weyand T, Adam H et al (2017) Mobilenets: efficient convolutional neural networks for mobile vision applications. arXiv preprint. arXiv:1704.04861
Bhavani DSS, Adhikari A, Sumathi D (2022) Detection of building defects using convolutional neural networks. In: Proceedings of second doctoral symposium on computational intelligence. Springer, Singapore, pp 839–855
Perez H, Tah JH, Mosavi A (2019) Deep learning for detecting building defects using convolutional neural networks. Sensors 19(16):3556
Ruder S (2016) An overview of gradient descent optimization algorithms. arXiv preprint. arXiv:1609.04747
Ioffe S, Szegedy C (2015) Batch normalization: accelerating deep network training by reducing internal covariate shift. In: International conference on machine learning. PMLR, pp 448–456
Li W, Dasarathy G, Berisha V (2020) Regularization via structural label smoothing. In: International conference on artificial intelligence and statistics. PMLR, pp 1453–1463
He K, Zhang X, Ren S, Sun J (2015) Delving deep into rectifiers: surpassing human-level performance on imagenet classification. In: Proceedings of the IEEE international conference on computer vision, pp 1026–1034
Bengio Y, Simard P, Frasconi P (1994) Learning long-term dependencies with gradient descent is difficult. IEEE Trans Neural Netw 5(2):157–166
Basodi S, Ji C, Zhang H, Pan Y (2020) Gradient amplification: an efficient way to train deep neural networks. Big Data Min Anal 3(3):196–207
Zhou B, Khosla A, Lapedriza A, Oliva A, Torralba A (2016) Learning deep features for discriminative localization. In: Proceedings of the IEEE conference on computer vision and pattern recognition, pp 2921–2929
Author information
Authors and Affiliations
Corresponding author
Editor information
Editors and Affiliations
Rights and permissions
Copyright information
© 2023 The Author(s), under exclusive license to Springer Nature Singapore Pte Ltd.
About this paper
Cite this paper
Maheysh, V., Kirthica, S. (2023). CNN-Based Detection of Cracks and Moulds in Buildings. In: Shakya, S., Papakostas, G., Kamel, K.A. (eds) Mobile Computing and Sustainable Informatics. Lecture Notes on Data Engineering and Communications Technologies, vol 166. Springer, Singapore. https://doi.org/10.1007/978-981-99-0835-6_52
Download citation
DOI: https://doi.org/10.1007/978-981-99-0835-6_52
Published:
Publisher Name: Springer, Singapore
Print ISBN: 978-981-99-0834-9
Online ISBN: 978-981-99-0835-6
eBook Packages: Intelligent Technologies and RoboticsIntelligent Technologies and Robotics (R0)