Automatic Pavement Crack Detection Based on Structured Prediction with the Convolutional Neural Network

TL;DR

This paper introduces a deep learning-based supervised method using CNNs for automated pavement crack detection, capable of handling various pavement conditions without preprocessing, and demonstrates superior performance over existing methods.

Contribution

The paper presents a novel CNN-based approach for pavement crack detection that addresses data imbalance and is effective across different pavement conditions.

Findings

Outperforms five existing crack detection methods

Effective on two public databases

Handles data imbalance with a novel sampling strategy

Abstract

Automated pavement crack detection is a challenging task that has been researched for decades due to the complicated pavement conditions in real world. In this paper, a supervised method based on deep learning is proposed, which has the capability of dealing with different pavement conditions. Specifically, a convolutional neural network (CNN) is used to learn the structure of the cracks from raw images, without any preprocessing. Small patches are extracted from crack images as inputs to generate a large training database, a CNN is trained and crack detection is modeled as a multi-label classification problem. Typically, crack pixels are much fewer than non-crack pixels. To deal with the problem with severely imbalanced data, a strategy with modifying the ratio of positive to negative samples is proposed. The method is tested on two public databases and compared with five existing methods. Experimental results show that it outperforms the other methods.