Automatic Road Crack Detection and Characterization

By Henrique Oliveira, P. Correia. IEEE transactions on intelligent transportation systems (Print), 2013

486 citations recorded by the source corpus.

A fully integrated system for the automatic detection and characterization of cracks in road flexible pavement surfaces, which does not require manually labeled samples, is proposed to minimize the human subjectivity resulting from traditional visual surveys. The first task addressed, i.e., crack detection, is based on a learning from samples paradigm, where a subset of the available image database is automatically selected and used for unsupervised training of the system. The system classifies nonoverlapping image blocks as either containing crack pixels or not. The second task deals with crack type characterization, for which another classification system is constructed, to characterize the detected cracks' connect components. Cracks are labeled according to the types defined in the Portuguese Distress Catalog, with each different crack present in a given image receiving the appropriate label. Moreover, a novel methodology for the assignment of crack severity levels is introduced, computing an estimate for the width of each detected crack. Experimental crack detection and characterization results are presented based on images captured during a visual road pavement surface survey over Portuguese roads, with promising results. This is shown by the quantitative evaluation methodology introduced for the evaluation of this type of system, including a comparison with human experts' manual labeling results.

Subfields: Civil and Structural Engineering, Industrial and Manufacturing Engineering

View Paper: https://www.semanticscholar.org/paper/ef72a6af035ab299c8fda182c1a547866ceb7b7f

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 Industrial and Manufacturing Engineering

Citations in the corpus

Road crack detection using deep convolutional neural network (2016, methodology): “A fully integrated system for crack detection and characterization is proposed in [9] and a comprehensive set of image processing algorithms for detection and characterization of road pavement surface crack distresses is introduced in [5].”
DeepCrack: Learning Hierarchical Convolutional Features for Crack Detection (2019, methodology): “As the crack is thin and displays as an edge, many methods stemmed from edge detection and wavelet transformation have been developed for crack detection [37]–[40].”
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 Minimal Path Selection (MPS) [14].”
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.”
Automatic Crack Detection on Two-Dimensional Pavement Images: An Algorithm Based on Minimal Path Selection (2016, methodology): “only few of the existing methods are fully unsupervised [3].”
Ensemble of Deep Convolutional Neural Networks for Automatic Pavement Crack Detection and Measurement (2020, methodology): “ing: Recently, many algorithms have been proposed to detect cracks based on machine learning. A support vector machine (SVM) was employed to detect aircraft skin cracks [21]. Oliveira and Correia, in [22], proposed an unsupervised learning algorithm named CrackIT to detect cracks. After that, they d”
Road Crack Detection Using Deep Convolutional Neural Network and Adaptive Thresholding (2019, methodology): “[7], [28] utilized several image analysis algorithms to detect and characterize cracks from road pavements.”