Hybrid-Segmentor: Hybrid approach for automated fine-grained crack segmentation in civil infrastructure

It is essential to detect and segment cracks in various infrastructures, such as roads and buildings, to ensure safety, longevity, and cost-effective maintenance. Despite deep learning advancements, precise crack detection across diverse conditions remains challenging. This paper introduces Hybrid-Segmentor, a deep learning model combining Convolutional Neural Networks-based and Transformer-based architectures to extract both fine-grained local features and global crack patterns, significantly enhancing crack detection for improved infrastructure maintenance. Hybrid-Segmentor, trained on a large custom dataset created by merging multiple open-source datasets, can accurately detect cracks on different types of surfaces, crack shapes, and sizes. The model demonstrates robustness and versatility by accurately detecting discontinuities, vague cracks, non-crack regions within crack areas, blurred images, and complex crack contours. Furthermore, when compared against other recent models for crack segmentation, the proposed model achieves state-of-the-art performance, significantly outperforming them across five key metrics: accuracy (0.971), precision (0.807), recall (0.756), F1-score (0.774), and IoU (0.631). • Introduced Hybrid-Segmentor, combining CNN and Transformer paths for enhanced crack segmentation. • Experiments on a refined dataset of 12,000 images • Achieved state-of-the-art performance on 5 metrics: Accuracy, Precision, Recall, F-1 Score and IoU. • Model generalizes well across diverse crack shapes and surfaces. • Outperforms benchmarks in handling discontinuities, small regions, and low-quality crack contours.