Evaluation and Comparison of Deep Learning Methods for Pavement Crack Identification with Visual Images

TL;DR

This paper reviews deep learning frameworks for pavement crack detection using visual images, compares their performance on public datasets, and introduces a weakly supervised learning approach to reduce labeling effort.

Contribution

It provides a comprehensive comparison of CNN, GAN, and transfer learning models for crack detection and proposes a novel weakly supervised framework to improve efficiency.

Findings

Transfer learning models achieve accuracy comparable to encoder-decoder models with faster prediction.

Both encoder-decoder and GAN models can perform pixel-level crack segmentation in real time.

The proposed weakly supervised framework reduces labeled data requirements while maintaining performance.

Abstract

Compared with contact detection techniques, pavement crack identification with visual images via deep learning algorithms has the advantages of not being limited by the material of object to be detected, fast speed and low cost. The fundamental frameworks and typical model architectures of transfer learning (TL), encoder-decoder (ED), generative adversarial networks (GAN), and their common modules were first reviewed, and then the evolution of convolutional neural network (CNN) backbone models and GAN models were summarized. The crack classification, segmentation performance, and effect were tested on the SDNET2018 and CFD public data sets. In the aspect of patch sample classification, the fine-tuned TL models can be equivalent to or even slightly better than the ED models in accuracy, and the predicting time is faster; In the aspect of accurate crack location, both ED and GAN algorithms can achieve pixel-level segmentation and is expected to be detected in real time on low computing power platform. Furthermore, a weakly supervised learning framework of combined TL-SSGAN and its performance enhancement measures are proposed, which can maintain comparable crack identification performance with that of the supervised learning, while greatly reducing the number of labeled samples required.