Automated Pixel‐Level Pavement Crack Detection on 3D Asphalt Surfaces Using a Deep‐Learning Network

By Allen A. Zhang, Kelvin C. P. Wang, Baoxian Li, Enhui Yang, Xianxing Dai, Yi Peng, Yue Fei, Yang Liu, Joshua Qiang Li, Cheng Chen. Comput. Aided Civ. Infrastructure Eng., 2017

900 citations recorded by the source corpus.

Subfields: Civil and Structural Engineering, Mechanical Engineering

View Paper: https://www.semanticscholar.org/paper/e4d9a7fc44e4888deaf9ee08be7e06de5ef3bf24

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 Mechanical Engineering

Citations in the corpus

Ensemble of Deep Convolutional Neural Networks for Automatic Pavement Crack Detection and Measurement (2020, methodology): “In CrackNet [27], the proposed CNN without pooling layers was used to inspect cracks and improve accuracy.”
Advances in Computer Vision-Based Civil Infrastructure Inspection and Monitoring (2019, background): “Zhang et al. [126] proposed CrackNet, an efﬁcient architecture for the semantic segmentation of pavement cracks.”
Automatic Pixel‐Level Crack Detection and Measurement Using Fully Convolutional Network (2018, methodology): “To compare FCN with existing state-of-the-art DNN for crack recognition, authors collected gray images to examine the performances of Pixel-SVM (Marques and Correia, 2012), CrackNet (Zhang et al. 2017), and the framework proposed in this article.”
Encoder–decoder network for pixel‐level road crack detection in black‐box images (2019, background): “Zhang et al. (2017) proposed a CNN (CrackNet) for detecting pixel-level pavement cracks in 3D asphalt surfaces.”
Automated pavement crack detection and segmentation based on two‐step convolutional neural network (2020, methodology): “…2012, convolutional neural network (CNN) has been broadly applied in object recognition and segmentation, such as classification of cancer (Esteva et al., 2017), imagenet classification (Krizhevsky, Sutskever, & Hinton, 2012), and pixel-level crack segmentation (A. Zhang et al., 2017) Sun, 2016).”
Image‐based post‐disaster inspection of reinforced concrete bridge systems using deep learning with Bayesian optimization (2018, background): “…a one-dimensional CNN (Abdeljaber, Avci, Kiranyaz, Gabbouj, & Inman, 2017), pavement crack detection (Vetrivel, Gerke, Kerle, Nex, & Vossel-man, 2018; Zhang et al., 2017), structural damage recognition through transfer learning (Gao & Mosalam, 2018), and structural damage detection with feature…”
Automatic crack classification and segmentation on masonry surfaces using convolutional neural networks and transfer learning (2021, background): “As Zhang et al. [75] pointed out, precision and recall frequently conflict with each other and a compromise between recall and precision is made to select the best model.”
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).”
A Fast Detection Method via Region‐Based Fully Convolutional Neural Networks for Shield Tunnel Lining Defects (2018, methodology): “An ef-ﬁcient architecture of CNN (CrackNet) was proposed for 3D asphalt pavement surface pixel-wise classiﬁcation (Zhang et al., 2017).”
Deep Transfer Learning for Image‐Based Structural Damage Recognition (2018, methodology): “…veriﬁed experimentally by monitoring a steel frame demonstrating a high performance level for real-time SHM and structural damage detection processes; Zhang et al. (2017) designed a new CNN architecture, namely CrackNet, for pavement crack detection in pixel-level; and Vetrivel et al. (2017)…”
Comparison of deep convolutional neural networks and edge detectors for image-based crack detection in concrete (2018, methodology): “DCNNs have been used in vision-based structural health monitoring in recent years for crack detection 197 [42], road pavement cracks [55, 56], corrosion detection [57, 58], multi-damage detection [41, 59] structural 198 health monitoring [62].”