Deep Learning‐Based Crack Damage Detection Using Convolutional Neural Networks

By Young-Jin Cha, Wooram Choi, Oral Büyüköztürk. 2017

2,960 citations recorded by the source corpus.

Subfields: Civil and Structural Engineering, Ocean Engineering

How researchers see this paper

The researchers whose trusted networks rank it highest, strongest advocate first. Every researcher gets a different order.

In Civil and Structural Engineering

In Ocean Engineering

Citations in the corpus

Deep learning for financial time series forecasting in A-Trader system (2017, neutral): “[30,31].”
Advances in Computer Vision-Based Civil Infrastructure Inspection and Monitoring (2019, methodology): “Object detection methods have recently been applied for damage detection [112,119].”
Research on a Surface Defect Detection Algorithm Based on MobileNet-SSD (2018, methodology): “Cha et al. employ a deep convolution neural network (CNN) to identify concrete cracks in complex situations, e.g. strong spots, shadows and ultra-thin cracks, and proves that the deep CNN outperformed the traditional tools like Canny edge detector and Sobel edge detector [24].”
Road Damage Detection and Classification Using Deep Neural Networks with Smartphone Images (2018, background): “, 2010) for 5,888 × 3,584 pixel images in order to detect cracks on the concrete surface (Cha et al., 2017).”
NB-CNN: Deep Learning-Based Crack Detection Using Convolutional Neural Network and Naïve Bayes Data Fusion (2018, background): “Due to CNN’s outstanding performance, several recent studies applied it for defect detection including railroad defects on steel surfaces [26], road cracks [27], concrete cracks [28], and cracks on nuclear power plant components [29].”
Automatic pixel‐level multiple damage detection of concrete structure using fully convolutional network (2019, methodology): “A deep learning-based method was developed to detect railway defects (Soukup & Huber-Mörk, 2014), road cracks (Zhang et al., 2017; Zhang, Yang, Zhang, & Zhu, 2016b), concrete cracks (Cha, Choi, & Büyüköztürk, 2017a; Zhao & Li, 2017), and other damages (Lin, Nie, & Ma, 2017).”
FEMa: a finite element machine for fast learning (2019, background): “In recent years, machine learning has been a subject of signiﬁcant research in a variety of ﬁelds such as diagnosis of neurological disorders [13, 26, 29], damage detection and health monitoring of structures [8, 24, 30].”
SDDNet: Real-Time Crack Segmentation (2020, background): “The authors in [1], [10], and [11] explored the potential of DL in structural health monitoring (SHM).”
Autonomous Structural Visual Inspection Using Region‐Based Deep Learning for Detecting Multiple Damage Types (2018, methodology): “However, the traditional CNN-based method applies “sliding window” to the original image many times implementing the processing of the entire network for each sliding window, and the sliding windows are overlapped 50% for the detection of crack in edges (Cha et al., 2017).”