CrackTree: Automatic crack detection from pavement images

By Qin Zou, Yu Cao, Qingquan Li, Qingzhou Mao, Song Wang. Pattern Recognition Letters, 2012

1,073 citations recorded by the source corpus.

Subfields: Civil and Structural Engineering, Computer Vision and Pattern Recognition

View Paper: https://www.semanticscholar.org/paper/36df22f68f2e8b106b0be03f61b8ce2abfa92de3

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 Computer Vision and Pattern Recognition

Citations in the corpus

Automated Pixel‐Level Pavement Crack Detection on 3D Asphalt Surfaces Using a Deep‐Learning Network (2017, background): “The CrackTree demonstrated a strong capability of detecting discontinued cracks (Zou et al., 2012), however without considering the actual crack width.”
A review of computer vision–based structural health monitoring at local and global levels (2020, methodology): “Probability map: Zou et al.(61) Minimal path selection: Amhaz et al.”
Feature Pyramid and Hierarchical Boosting Network for Pavement Crack Detection (2019, methodology): “This method is shown to outperform state-of-the-art crack detection methods like CrackTree [4], CrackIT [17], Free-Form Anisotropy (FFA) [18], and”
Automatic Pixel‐Level Crack Detection and Measurement Using Fully Convolutional Network (2018, methodology): “…model, extending the crack detection from linear to nonlinear domain; Cha et al. (2016) stated a mixed method for specific loosed bolt, combining linear SVM and Hough transforms; Zou et al. (2012) built a three-step CrackTree to generate a probability map for crack localization and identification.”
Road Crack Detection Using Deep Convolutional Neural Network and Adaptive Thresholding (2019, methodology): “Although the above-mentioned algorithms are commonly used in crack detection and they perform well on high-quality datasets [22], [28], [29], they are however not accurate enough to distinguish cracks from the complex background in low-quality images.”
DeepCrack: A deep hierarchical feature learning architecture for crack segmentation (2019, methodology): “The “FoSA” approach [1] was proposed to extend the NDHM with a stronger anti-noise capability and the “CrackTree” method [17] was designed to remove the pavement shadows.”
Automatic Road Crack Detection Using Random Structured Forests (2016, methodology): “These methods use a local binary pattern operator to determine whether each pixel belongs to a crack and the local neighbor information is not taken into consideration.”
Road crack detection using deep convolutional neural network (2016, methodology): “Although hand-crafted features are widely used and support top-ranking algorithms on the well acquired data set [4, 5, 10], it is important to note that they are not discriminative enough to differentiate the crack and complex background in low level image cues.”
DeepCrack: Learning Hierarchical Convolutional Features for Crack Detection (2019, background): “the minimal spanning tree [45] and the random structure forest [46].”
Encoder–decoder network for pixel‐level road crack detection in black‐box images (2019, methodology): “…eﬃcient and safe for monitoring the road pavement conditions compared with manual inspections or those involving specialized vehicles (Haas, 1996; Radopoulou & Brilakis, 2016; Sun, Kamaliardakani, & Zhang, 2015; Zalama, Gómez-García-Bermejo, Medina, & Llamas, 2014; Zou, Cao, Li, Mao, & Wang, 2012).”