A vision-based active learning convolutional neural network model for concrete surface crack detection

Abstract

Concrete surface crack detection based on computer vision, specifically via a convolutional neural network, has drawn increasing attention for replacing manual visual inspection of bridges and buildings. This article proposes a new framework for this task and a sampling and training method based on active learning to treat class imbalances. In particular, the new framework includes a clear definition of two categories of samples, a relevant sliding window technique, data augmentation and annotation methods. The advantages of this framework are that data integrity can be ensured and a very large amount of annotation work can be saved. Training datasets generated with the proposed sampling and training method not only are representative of the original dataset but also highlight samples that are highly complex, yet informative. Based on the proposed framework and sampling and training strategy, AlexNet is re-tuned, validated, tested and compared with an existing network. The investigation revealed outstanding performances of the proposed framework in terms of the detection accuracy, precision and F1 measure due to its nonlinear learning ability, training dataset integrity and active learning strategy.

Assessment of Convolutional Neural Network Pre-Trained Models for Detection and Orientation of Cracks

“…They found an improvement in the local detection with linear modeling compared with global detection. Wang et al [ 33 ] utilized the three AlexNet models, compared them with ChaNet to detect concrete cracks, and found the ChaNet more reliable with an accuracy of 87.91%. Cha and Choi [ 34 ] obtained a 98% accuracy when they applied a CNN architecture to predict cracks using a data set of 40,000 images for training and validation.…”

Bibliometric Analysis and Review of Deep Learning-Based Crack Detection Literature Published between 2010 and 2022

“…Additionally, the importance of training dataset integrity in DL crack classification architecture was shown in [62]. The authors used sampling and training methods based on cross-entropy ranking to address the training class imbalance issue.…”

“…Custom Concrete [2,[20][21][22]32,33,[36][37][38][39][43][44][45]48,49,60,62,63,67,69,71,73,75,84,85,87,[89][90][91]93,97,105,107,108,110,112,[117][118][119]121,126,127,130,133,141,142,146, Pavement [20,[40][41][42]47,…”

Performance-based post-earthquake building evaluations using computer vision-derived damage observations

“…Such systems typically rely on unmanned aerial vehicles (UAVs) to collect images of a structure, and then use computer vision, including image processing and machine learning, to identify damage in photographs (Koch et al, 2014;Morgenthal and Hallermann, 2014;Spencer et al, 2019). Recently, convolutional neural networks have been employed to automatically detect various types of structural damage, including cracking, concrete spalling, exposed rebar, and steel corrosion, and to identify structural components like beams and columns (Hoskere et al, 2017(Hoskere et al, , 2020(Hoskere et al, , 2022Hüthwohl et al, 2019;Narazaki et al, 2020Narazaki et al, , 2021Yeum et al, 2018;Wang et al, 2020Wang et al, , 2022Xu et al, 2019). Researchers have correlated visual damage with expected component damage progressions to automatically estimate maximum column drift demands (Paal et al, 2015) and classify columns into fragility-consistent damage states (Pan and Yang, 2020) based on photographs of columns.…”