TB-Net: A Three-Stream Boundary-Aware Network for Fine-Grained Pavement Disease Segmentation

TL;DR

This paper introduces TB-Net, a three-stream boundary-aware neural network designed for comprehensive pavement disease segmentation, effectively handling various disease types and landmarks in a single model.

Contribution

The paper presents a novel three-stream architecture that fuses spatial, contextual, and boundary information for fine-grained pavement disease segmentation.

Findings

Outperforms existing methods on a new pavement disease dataset.

Effectively segments diverse pavement diseases and landmarks.

Improves boundary accuracy with global-gated convolution.

Abstract

Regular pavement inspection plays a significant role in road maintenance for safety assurance. Existing methods mainly address the tasks of crack detection and segmentation that are only tailored for long-thin crack disease. However, there are many other types of diseases with a wider variety of sizes and patterns that are also essential to segment in practice, bringing more challenges towards fine-grained pavement inspection. In this paper, our goal is not only to automatically segment cracks, but also to segment other complex pavement diseases as well as typical landmarks (markings, runway lights, etc.) and commonly seen water/oil stains in a single model. To this end, we propose a three-stream boundary-aware network (TB-Net). It consists of three streams fusing the low-level spatial and the high-level contextual representations as well as the detailed boundary information. Specifically, the spatial stream captures rich spatial features. The context stream, where an attention mechanism is utilized, models the contextual relationships over local features. The boundary stream learns detailed boundaries using a global-gated convolution to further refine the segmentation outputs. The network is trained using a dual-task loss in an end-to-end manner, and experiments on a newly collected fine-grained pavement disease dataset show the effectiveness of our TB-Net.