Multi-class Road Defect Detection and Segmentation using Spatial and Channel-wise Attention for Autonomous Road Repairing

Fuente: arXiv
Gespeichert in:
Bibliographische Detailangaben
Hauptverfasser: Yu, Jongmin, Chi, Chen Bene, Fichera, Sebastiano, Paoletti, Paolo, Mehta, Devansh, Luo, Shan
Format: Preprint
Veröffentlicht: 2024
Schlagworte:
Online-Zugang:
Tags: Tag hinzufügen
Keine Tags, Fügen Sie den ersten Tag hinzu!
_version_ 1866917583496675328
author Yu, Jongmin
Chi, Chen Bene
Fichera, Sebastiano
Paoletti, Paolo
Mehta, Devansh
Luo, Shan
author_facet Yu, Jongmin
Chi, Chen Bene
Fichera, Sebastiano
Paoletti, Paolo
Mehta, Devansh
Luo, Shan
contents Road pavement detection and segmentation are critical for developing autonomous road repair systems. However, developing an instance segmentation method that simultaneously performs multi-class defect detection and segmentation is challenging due to the textural simplicity of road pavement image, the diversity of defect geometries, and the morphological ambiguity between classes. We propose a novel end-to-end method for multi-class road defect detection and segmentation. The proposed method comprises multiple spatial and channel-wise attention blocks available to learn global representations across spatial and channel-wise dimensions. Through these attention blocks, more globally generalised representations of morphological information (spatial characteristics) of road defects and colour and depth information of images can be learned. To demonstrate the effectiveness of our framework, we conducted various ablation studies and comparisons with prior methods on a newly collected dataset annotated with nine road defect classes. The experiments show that our proposed method outperforms existing state-of-the-art methods for multi-class road defect detection and segmentation methods.
format Preprint
id arxiv_https___arxiv_org_abs_2402_04064
institution arXiv
publishDate 2024
record_format arxiv
spellingShingle Multi-class Road Defect Detection and Segmentation using Spatial and Channel-wise Attention for Autonomous Road Repairing
Yu, Jongmin
Chi, Chen Bene
Fichera, Sebastiano
Paoletti, Paolo
Mehta, Devansh
Luo, Shan
Computer Vision and Pattern Recognition
Artificial Intelligence
Road pavement detection and segmentation are critical for developing autonomous road repair systems. However, developing an instance segmentation method that simultaneously performs multi-class defect detection and segmentation is challenging due to the textural simplicity of road pavement image, the diversity of defect geometries, and the morphological ambiguity between classes. We propose a novel end-to-end method for multi-class road defect detection and segmentation. The proposed method comprises multiple spatial and channel-wise attention blocks available to learn global representations across spatial and channel-wise dimensions. Through these attention blocks, more globally generalised representations of morphological information (spatial characteristics) of road defects and colour and depth information of images can be learned. To demonstrate the effectiveness of our framework, we conducted various ablation studies and comparisons with prior methods on a newly collected dataset annotated with nine road defect classes. The experiments show that our proposed method outperforms existing state-of-the-art methods for multi-class road defect detection and segmentation methods.
title Multi-class Road Defect Detection and Segmentation using Spatial and Channel-wise Attention for Autonomous Road Repairing
topic Computer Vision and Pattern Recognition
Artificial Intelligence
url https://arxiv.org/abs/2402.04064