Road crack detection using deep convolutional neural network

By Lei Zhang, Fan Yang, Yimin Daniel Zhang, Ying Julie Zhu. International Conference on Information Photonics, 2016

989 citations recorded by the source corpus.

Subfields: Civil and Structural Engineering, Mechanical Engineering

View Paper: https://www.semanticscholar.org/paper/6043fa75051571b3260e72827d0d189805611a3c

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

Automatic pixel‐level multiple damage detection of concrete structure using fully convolutional network (2019, methodology): “…Abudayyeh, & Kelly, 2003; Fujita, Mitani, & Hamamoto, 2006; Nishikawa, Yoshida, Sugiyama, & Fujino, 2012), concrete spalling (German, Brilakis, & DesRoches, 2012), and potholes and cracks in asphalt pavement (Koch & Brilakis, 2011; Wang, Zhang, Wang, Braham, & Qiu, 2018; Zhang et al., 2016a).”
Automatic Classification of Defective Photovoltaic Module Cells in Electroluminescence Images (2018, methodology): “Although their dataset consists of only 2,281 training and 646 test images, the CNN architecture classiﬁes steel defects at least twice as accurately as the SVMs. Zhang et al. [15] proposed a CNN architecture for detection of cracks on roads.”
Advances in Computer Vision-Based Civil Infrastructure Inspection and Monitoring (2019, methodology): “CNNs have been employed for the application of crack detection in steel decks [110], asphalt pave-ments [111], and concrete surfaces [112], with very high accuracy being achieved in all cases.”
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].”
DeepCrack: Learning Hierarchical Convolutional Features for Crack Detection (2019, background): “In [2], deep convolutional neural network”
Automated Pixel‐Level Pavement Crack Detection on 3D Asphalt Surfaces Using a Deep‐Learning Network (2017, methodology): “Precision and Recall are two commonly used indicators for evaluating crack detecting algorithms (Fawcett, 2006; Zhang et al., 2016a, 2017).”
DeepCrack: A deep hierarchical feature learning architecture for crack segmentation (2019, methodology): “…convincing, we compared our method with other four typical meth-ods: (1) AutoCrack [22] , a traditional artiﬁcial designed detector; (2) RoadCNNs [37] , a latest CNNs-based classiﬁer for patch clas-siﬁcation; (3) HED [3] , an edge detection network achieving the state-of-the-art performances;…”
Road Crack Detection Using Deep Convolutional Neural Network and Adaptive Thresholding (2019, background): “A CNN is generally considered as a hierarchical feature extractor [36].”
A Fast Detection Method via Region‐Based Fully Convolutional Neural Networks for Shield Tunnel Lining Defects (2018, methodology): “A deep CNN was used for detecting road cracks (Zhang et al., 2016).”
Road Damage Detection and Classification Using Deep Neural Networks with Smartphone Images (2018, methodology): “…according to the Road Maintenance and Repair Guidebook 2013 (JRA, 2013)), many studies have been limited to the detection or classiﬁcation of damage in only the longitudinal and lateral directions (Chun et al., 2015; Zalama et al., 2014; Zhang et al., 2016; Akarsu et al., 2016; Maeda et al., 2016).”
Automatic Pixel‐Level Crack Detection and Measurement Using Fully Convolutional Network (2018, background): “…both gray and colorful images, even Red-Green-Blue (RGB)-depth images could be mixed as the input of DNNs (Jahanshahi et al., 2012; Jahanshahi and Masri, 2012; Ouyang and Xu, 2013; Huang et al., 2014; Jiang and Tsai, 2015; Zhang et al., 2016a; Guldur Erkal and Hajjar, 2017; Zhang and Wang, 2017).”