Saved in:
Bibliographic Details
Main Authors: Li, Yongshang, Ma, Ronggui, Liu, Han, Cheng, Gaoli
Format: Preprint
Published: 2023
Subjects:
Online Access:https://arxiv.org/abs/2307.00270
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866913222626377728
author Li, Yongshang
Ma, Ronggui
Liu, Han
Cheng, Gaoli
author_facet Li, Yongshang
Ma, Ronggui
Liu, Han
Cheng, Gaoli
contents 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.
format Preprint
id arxiv_https___arxiv_org_abs_2307_00270
institution arXiv
publishDate 2023
record_format arxiv
spellingShingle Real-time High-Resolution Neural Network with Semantic Guidance for Crack Segmentation
Li, Yongshang
Ma, Ronggui
Liu, Han
Cheng, Gaoli
Computer Vision and Pattern Recognition
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.
title Real-time High-Resolution Neural Network with Semantic Guidance for Crack Segmentation
topic Computer Vision and Pattern Recognition
url https://arxiv.org/abs/2307.00270