UP-CrackNet: Unsupervised Pixel-Wise Road Crack Detection via Adversarial Image Restoration

TL;DR

UP-CrackNet introduces an unsupervised pixel-wise road crack detection method that uses adversarial image restoration, eliminating the need for extensive pixel-level annotations and improving generalizability over supervised approaches.

Contribution

The paper presents UP-CrackNet, a novel unsupervised network that detects road cracks by restoring corrupted images, reducing annotation efforts and enhancing cross-dataset performance.

Findings

Outperforms unsupervised anomaly detection algorithms

Shows satisfactory performance compared to supervised methods

Exhibits strong generalizability across datasets

Abstract

Over the past decade, automated methods have been developed to detect cracks more efficiently, accurately, and objectively, with the ultimate goal of replacing conventional manual visual inspection techniques. Among these methods, semantic segmentation algorithms have demonstrated promising results in pixel-wise crack detection tasks. However, training such networks requires a large amount of human-annotated datasets with pixel-level annotations, which is a highly labor-intensive and time-consuming process. Moreover, supervised learning-based methods often struggle with poor generalizability in unseen datasets. Therefore, we propose an unsupervised pixel-wise road crack detection network, known as UP-CrackNet. Our approach first generates multi-scale square masks and randomly selects them to corrupt undamaged road images by removing certain regions. Subsequently, a generative adversarial network is trained to restore the corrupted regions by leveraging the semantic context learned from surrounding uncorrupted regions. During the testing phase, an error map is generated by calculating the difference between the input and restored images, which allows for pixel-wise crack detection. Our comprehensive experimental results demonstrate that UP-CrackNet outperforms other general-purpose unsupervised anomaly detection algorithms, and exhibits satisfactory performance and superior generalizability when compared with state-of-the-art supervised crack segmentation algorithms. Our source code is publicly available at mias.group/UP-CrackNet.