Real-time High-Resolution Neural Network with Semantic Guidance for Crack Segmentation

TL;DR

This paper introduces HrSegNet, a high-resolution neural network with semantic guidance tailored for crack segmentation, achieving state-of-the-art accuracy and real-time performance on multiple datasets, suitable for edge device deployment.

Contribution

The paper presents a novel high-resolution network specifically designed for crack segmentation that balances detailed accuracy with real-time inference capabilities.

Findings

HrSegNet achieves superior segmentation accuracy.

It maintains real-time inference speed.

The approach is effective on multiple datasets.

Abstract

Deep learning plays an important role in crack segmentation, but most work utilize off-the-shelf or improved models that have not been specifically developed for this task. High-resolution convolution neural networks that are sensitive to objects' location and detail help improve the performance of crack segmentation, yet conflict with real-time detection. This paper describes HrSegNet, a high-resolution network with semantic guidance specifically designed for crack segmentation, which guarantees real-time inference speed while preserving crack details. After evaluation on the composite dataset CrackSeg9k and the scenario-specific datasets Asphalt3k and Concrete3k, HrSegNet obtains state-of-the-art segmentation performance and efficiencies that far exceed those of the compared models. This approach demonstrates that there is a trade-off between high-resolution modeling and real-time detection, which fosters the use of edge devices to analyze cracks in real-world applications.