Automatic Crack Detection on Two-Dimensional Pavement Images: An Algorithm Based on Minimal Path Selection

By Rabih Amhaz, Sylvie Chambon, Jérôme Idier, Vincent Baltazart. IEEE transactions on intelligent transportation systems (Print), 2016

425 citations recorded by the source corpus.

How researchers see this paper

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

Ensemble of Deep Convolutional Neural Networks for Automatic Pavement Crack Detection and Measurement (2020, methodology): “the metric for TP, FP, and FN, we consider the transitional areas between non-crack and crack pixels. Therefore, a two-pixels distance between the prediction image and the ground truth is accepted in [20,29,45,46]. In this project, we accepted a two-pixel distance. 3.2. Ensemble Network In this sub-”
Feature Pyramid and Hierarchical Boosting Network for Pavement Crack Detection (2019, methodology): “To conduct crack detection from a global view, some works [4], [14], [15] carry out crack detection by taking into account photometric and geometric characteristics of pavement crack images.”
DeepCrack: Learning Hierarchical Convolutional Features for Crack Detection (2019, methodology): “In [35] and [41], seed-growing methods built on minimal path searching were proposed for pavement crack detection.”
A review of computer vision–based structural health monitoring at local and global levels (2020, background): “Amhaz et al.62 proposed a crack detection approach based on minimal path selection (MPS) and with the skeleton refinement, the artifacts could be eliminated.”