SCNet: A Generalized Attention-based Model for Crack Fault Segmentation

Abstract

Anomaly detection and localization is an important vision problem, having multiple applications. Effective and generic semantic segmentation of anomalous regions on various different surfaces, where most anomalous regions inherently do not have any obvious pattern, is still under active research. Periodic health monitoring and fault (anomaly) detection in vast infrastructures, which is an important safety-related task, is one such application area of vision-based anomaly segmentation. However, the task is quite challenging due to large variations in surface faults, texture-less construction material/background, lighting conditions etc. Cracks are critical and frequent surface faults that manifest as extreme zigzag-shaped thin, elongated regions. They are among the hardest faults to detect, even with deep learning. In this work, we address an open aspect of automatic crack segmentation problem, that of generalizing and improving the performance of segmentation across a variety of scenarios, by modeling the problem differently. We carefully study and abstract the sub-problems involved and solve them in a broader context, making our solution generic. On a variety of datasets related to surveillance of different infrastructures, under varying conditions, our model consistently outperforms the state-of-the-art algorithms by a significant margin, without any bells-and-whistles. This performance advantage easily carried over in two deployments of our model, tested against industryprovided datasets. Even further, we could establish our model's performance for two manufacturing quality inspection scenarios as well, where the defect types are not just crack equivalents, but much more and different. Hence we hope that our model is indeed a truly generic defect segmentation model.

A Multi-Stage Feature Aggregation and Structure Awareness Network for Concrete Bridge Crack Detection

“…To make the network focus more on the semantic features of cracks while suppressing non-semantic features, [ 21 , 34 , 37 ] introduced attention mechanisms into the network to pay more attention to the semantic information of cracks. Due to the excellent performance of transformers [ 38 ] in modeling long-range dependencies, Zhang et al [ 24 ] proposed the UTCD-Net model for dam crack detection, which utilizes a dual-branch structure to fuse the global features extracted by the transformer branch and the local features extracted by CNN via the fusion module.…”