Feature Pyramid and Hierarchical Boosting Network for Pavement Crack Detection

TLDR

Pavement crack detection is critical for road safety but remains difficult due to intensity inhomogeneity, low contrast, and shadows. The study proposes an automatic crack detection method to overcome these challenges. We introduce the Feature Pyramid and Hierarchical Boosting Network (FPHBN), which fuses context into low‑level features via a feature pyramid and reweights easy and hard samples hierarchically, and we define a new average intersection over union metric. Experiments on five datasets show the method outperforms state‑of‑the‑art crack, edge, and segmentation approaches in accuracy and generalizability. Code and data are available at https://github.com/fyangneil/pavement-crack-detection.

Abstract

Pavement crack detection is a critical task for insuring road safety. Manual crack detection is extremely time-consuming. Therefore, an automatic road crack detection method is required to boost this progress. However, it remains a challenging task due to the intensity inhomogeneity of cracks and complexity of the background, e.g., the low contrast with surrounding pavements and possible shadows with a similar intensity. Inspired by recent advances of deep learning in computer vision, we propose a novel network architecture, named feature pyramid and hierarchical boosting network (FPHBN), for pavement crack detection. The proposed network integrates context information to low-level features for crack detection in a feature pyramid way, and it balances the contributions of both easy and hard samples to loss by nested sample reweighting in a hierarchical way during training. In addition, we propose a novel measurement for crack detection named average intersection over union (AIU). To demonstrate the superiority and generalizability of the proposed method, we evaluate it on five crack datasets and compare it with the state-of-the-art crack detection, edge detection, and semantic segmentation methods. The extensive experiments show that the proposed method outperforms these methods in terms of accuracy and generalizability. Code and data can be found in https://github.com/fyangneil/pavement-crack-detection.