M2S-RoAD: Multi-Modal Semantic Segmentation for Road Damage Using Camera and LiDAR Data

Fuente: arXiv
Saved in:
Bibliographic Details
Main Authors: Tseng, Tzu-Yun, Lyu, Hongyu, Li, Josephine, Berrio, Julie Stephany, Shan, Mao, Worrall, Stewart
Format: Preprint
Published: 2025
Subjects:
Online Access:
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866916688521330688
author Tseng, Tzu-Yun
Lyu, Hongyu
Li, Josephine
Berrio, Julie Stephany
Shan, Mao
Worrall, Stewart
author_facet Tseng, Tzu-Yun
Lyu, Hongyu
Li, Josephine
Berrio, Julie Stephany
Shan, Mao
Worrall, Stewart
contents Road damage can create safety and comfort challenges for both human drivers and autonomous vehicles (AVs). This damage is particularly prevalent in rural areas due to less frequent surveying and maintenance of roads. Automated detection of pavement deterioration can be used as an input to AVs and driver assistance systems to improve road safety. Current research in this field has predominantly focused on urban environments driven largely by public datasets, while rural areas have received significantly less attention. This paper introduces M2S-RoAD, a dataset for the semantic segmentation of different classes of road damage. M2S-RoAD was collected in various towns across New South Wales, Australia, and labelled for semantic segmentation to identify nine distinct types of road damage. This dataset will be released upon the acceptance of the paper.
format Preprint
id arxiv_https___arxiv_org_abs_2504_10123
institution arXiv
publishDate 2025
record_format arxiv
spellingShingle M2S-RoAD: Multi-Modal Semantic Segmentation for Road Damage Using Camera and LiDAR Data
Tseng, Tzu-Yun
Lyu, Hongyu
Li, Josephine
Berrio, Julie Stephany
Shan, Mao
Worrall, Stewart
Computer Vision and Pattern Recognition
Road damage can create safety and comfort challenges for both human drivers and autonomous vehicles (AVs). This damage is particularly prevalent in rural areas due to less frequent surveying and maintenance of roads. Automated detection of pavement deterioration can be used as an input to AVs and driver assistance systems to improve road safety. Current research in this field has predominantly focused on urban environments driven largely by public datasets, while rural areas have received significantly less attention. This paper introduces M2S-RoAD, a dataset for the semantic segmentation of different classes of road damage. M2S-RoAD was collected in various towns across New South Wales, Australia, and labelled for semantic segmentation to identify nine distinct types of road damage. This dataset will be released upon the acceptance of the paper.
title M2S-RoAD: Multi-Modal Semantic Segmentation for Road Damage Using Camera and LiDAR Data
topic Computer Vision and Pattern Recognition
url https://arxiv.org/abs/2504.10123