Feature Pyramid and Hierarchical Boosting Network for Pavement Crack Detection

By Fan Yang, Lei Zhang, Sijia Yu, Danil V. Prokhorov, Xue Mei, Haibin Ling. IEEE transactions on intelligent transportation systems (Print), 2019

1,030 citations recorded by the source corpus.

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.

Subfields: Civil and Structural Engineering

View Paper: https://www.semanticscholar.org/paper/2b7c208c34dd4a186f5d6d327bc94ec7397cc766

How researchers see this paper

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

In Civil and Structural Engineering

1. D. Dais
2. Necati Catbas
3. Vasilis Sarhosis
4. E. Smyrou
5. İ. Bal
6. Chuan-Zhi Dong

Citations in the corpus

• A review of computer vision–based structural health monitoring at local and global levels (2020, background): “Yang et al.63 developed the FCN architecture to achieve crack segmentation of pavement structures at pixel level.”
• Automated pavement crack detection and segmentation based on two‐step convolutional neural network (2020, methodology): “Zhang et al. (2017) applied an efficient CNN-based architecture called CrackNet for automated pavement crack detection and achieved high detection accuracy. A recently developed technique called recurrent neural network (RNN) was utilized and found to perform faster and better than the previous Crac”
• RINDNet: Edge Detection for Discontinuity in Reflectance, Illumination, Normal and Depth (2021, background): “Recent studies [33, 40, 43, 46] have shown that the above types of edges are beneficial for downstream tasks.”
• PGA-Net: Pyramid Feature Fusion and Global Context Attention Network for Automated Surface Defect Detection (2020, methodology): “A novel CNN was proposed in [36], which integrated context information from top-to-down in a feature pyramid way for pavement crack detection.”
• Automatic crack classification and segmentation on masonry surfaces using convolutional neural networks and transfer learning (2021, methodology): “FPN was combined with an hierarchical boosting module to perform pavement crack segmentation obtaining high accuracy and generalizability [35].”