Advancing Textile Damage Segmentation: A Novel RGBT Dataset and Thermal Frequency Normalization

RGB-Thermal (RGBT) semantic segmentation is an emerging technology for identifying objects and materials in high dynamic range scenes. Thermal imaging particularly enhances feature extraction at close range for applications such as textile damage detection. In this paper, we present RGBT-Textile, a...

Full description

Saved in:
Bibliographic Details
Main Authors: Farshid Rayhan, Jitesh Joshi, Guangyu Ren, Lucie Hernandez, Bruna Petreca, Sharon Baurley, Nadia Berthouze, Youngjun Cho
Format: Article
Language:English
Published: MDPI AG 2025-04-01
Series:Sensors
Subjects:
Online Access:https://www.mdpi.com/1424-8220/25/7/2306
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1850188342568681472
author Farshid Rayhan
Jitesh Joshi
Guangyu Ren
Lucie Hernandez
Bruna Petreca
Sharon Baurley
Nadia Berthouze
Youngjun Cho
author_facet Farshid Rayhan
Jitesh Joshi
Guangyu Ren
Lucie Hernandez
Bruna Petreca
Sharon Baurley
Nadia Berthouze
Youngjun Cho
author_sort Farshid Rayhan
collection DOAJ
description RGB-Thermal (RGBT) semantic segmentation is an emerging technology for identifying objects and materials in high dynamic range scenes. Thermal imaging particularly enhances feature extraction at close range for applications such as textile damage detection. In this paper, we present RGBT-Textile, a novel dataset specifically developed for close-range textile and damage segmentation. We meticulously designed the data collection protocol, software tools, and labeling process in collaboration with textile scientists. Additionally, we introduce ThermoFreq, a novel thermal frequency normalization method that reduces temperature noise effects in segmentation tasks. We evaluate our dataset alongside six existing RGBT datasets using state-of-the-art (SOTA) models. Experimental results demonstrate the superior performance of the SOTA models with ThermoFreq, highlighting its effectiveness in addressing noise challenges inherent in RGBT semantic segmentation across diverse environmental conditions. We make our dataset publicly accessible to foster further research and collaborations.
format Article
id doaj-art-40c298c9a5a249588dc98ba4d0c3e2a2
institution OA Journals
issn 1424-8220
language English
publishDate 2025-04-01
publisher MDPI AG
record_format Article
series Sensors
spelling doaj-art-40c298c9a5a249588dc98ba4d0c3e2a22025-08-20T02:15:54ZengMDPI AGSensors1424-82202025-04-01257230610.3390/s25072306Advancing Textile Damage Segmentation: A Novel RGBT Dataset and Thermal Frequency NormalizationFarshid Rayhan0Jitesh Joshi1Guangyu Ren2Lucie Hernandez3Bruna Petreca4Sharon Baurley5Nadia Berthouze6Youngjun Cho7Department of Computer Science, University College London, London NW1 2AE, UKDepartment of Computer Science, University College London, London NW1 2AE, UKDepartment of Computer Science, University College London, London NW1 2AE, UKMaterials Science Research Centre, Royal College of Art, London SW7 2EU, UKMaterials Science Research Centre, Royal College of Art, London SW7 2EU, UKMaterials Science Research Centre, Royal College of Art, London SW7 2EU, UKDepartment of Computer Science, University College London, London NW1 2AE, UKDepartment of Computer Science, University College London, London NW1 2AE, UKRGB-Thermal (RGBT) semantic segmentation is an emerging technology for identifying objects and materials in high dynamic range scenes. Thermal imaging particularly enhances feature extraction at close range for applications such as textile damage detection. In this paper, we present RGBT-Textile, a novel dataset specifically developed for close-range textile and damage segmentation. We meticulously designed the data collection protocol, software tools, and labeling process in collaboration with textile scientists. Additionally, we introduce ThermoFreq, a novel thermal frequency normalization method that reduces temperature noise effects in segmentation tasks. We evaluate our dataset alongside six existing RGBT datasets using state-of-the-art (SOTA) models. Experimental results demonstrate the superior performance of the SOTA models with ThermoFreq, highlighting its effectiveness in addressing noise challenges inherent in RGBT semantic segmentation across diverse environmental conditions. We make our dataset publicly accessible to foster further research and collaborations.https://www.mdpi.com/1424-8220/25/7/2306RGB-Thermal datasettextile damage detectionsemantic segmentation
spellingShingle Farshid Rayhan
Jitesh Joshi
Guangyu Ren
Lucie Hernandez
Bruna Petreca
Sharon Baurley
Nadia Berthouze
Youngjun Cho
Advancing Textile Damage Segmentation: A Novel RGBT Dataset and Thermal Frequency Normalization
Sensors
RGB-Thermal dataset
textile damage detection
semantic segmentation
title Advancing Textile Damage Segmentation: A Novel RGBT Dataset and Thermal Frequency Normalization
title_full Advancing Textile Damage Segmentation: A Novel RGBT Dataset and Thermal Frequency Normalization
title_fullStr Advancing Textile Damage Segmentation: A Novel RGBT Dataset and Thermal Frequency Normalization
title_full_unstemmed Advancing Textile Damage Segmentation: A Novel RGBT Dataset and Thermal Frequency Normalization
title_short Advancing Textile Damage Segmentation: A Novel RGBT Dataset and Thermal Frequency Normalization
title_sort advancing textile damage segmentation a novel rgbt dataset and thermal frequency normalization
topic RGB-Thermal dataset
textile damage detection
semantic segmentation
url https://www.mdpi.com/1424-8220/25/7/2306
work_keys_str_mv AT farshidrayhan advancingtextiledamagesegmentationanovelrgbtdatasetandthermalfrequencynormalization
AT jiteshjoshi advancingtextiledamagesegmentationanovelrgbtdatasetandthermalfrequencynormalization
AT guangyuren advancingtextiledamagesegmentationanovelrgbtdatasetandthermalfrequencynormalization
AT luciehernandez advancingtextiledamagesegmentationanovelrgbtdatasetandthermalfrequencynormalization
AT brunapetreca advancingtextiledamagesegmentationanovelrgbtdatasetandthermalfrequencynormalization
AT sharonbaurley advancingtextiledamagesegmentationanovelrgbtdatasetandthermalfrequencynormalization
AT nadiaberthouze advancingtextiledamagesegmentationanovelrgbtdatasetandthermalfrequencynormalization
AT youngjuncho advancingtextiledamagesegmentationanovelrgbtdatasetandthermalfrequencynormalization